diff options
1319 files changed, 27543 insertions, 11448 deletions
diff --git a/.gitignore b/.gitignore index 8f5422cba6e2..2030c7a4d2f8 100644 --- a/.gitignore +++ b/.gitignore @@ -142,3 +142,6 @@ x509.genkey # Kdevelop4 *.kdev4 + +# Clang's compilation database file +/compile_commands.json @@ -98,6 +98,7 @@ Jason Gunthorpe <[email protected]> <[email protected]> Javi Merino <[email protected]> <[email protected]> Jean Tourrilhes <[email protected]> Jeff Garzik <[email protected]> Jeff Layton <[email protected]> <[email protected]> Jeff Layton <[email protected]> <[email protected]> @@ -116,6 +117,7 @@ John Stultz <[email protected]> Juha Yrjola <at solidboot.com> Juha Yrjola <[email protected]> Juha Yrjola <[email protected]> +Julien Thierry <[email protected]> <[email protected]> Kay Sievers <[email protected]> Kenneth W Chen <[email protected]> Konstantin Khlebnikov <[email protected]> <[email protected]> @@ -132,6 +134,7 @@ Linus Lüssing <[email protected]> <[email protected]> Li Yang <[email protected]> <[email protected]> Li Yang <[email protected]> <[email protected]> Maciej W. Rozycki <[email protected]> <[email protected]> +Marc Zyngier <[email protected]> <[email protected]> Marcin Nowakowski <[email protected]> <[email protected]> Mark Brown <[email protected]> Mark Yao <[email protected]> <[email protected]> diff --git a/Documentation/ABI/testing/sysfs-kernel-btf b/Documentation/ABI/testing/sysfs-kernel-btf new file mode 100644 index 000000000000..2c9744b2cd59 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-btf @@ -0,0 +1,17 @@ +What: /sys/kernel/btf +Date: Aug 2019 +KernelVersion: 5.5 +Contact: [email protected] +Description: + Contains BTF type information and related data for kernel and + kernel modules. + +What: /sys/kernel/btf/vmlinux +Date: Aug 2019 +KernelVersion: 5.5 +Contact: [email protected] +Description: + Read-only binary attribute exposing kernel's own BTF type + information with description of all internal kernel types. See + Documentation/bpf/btf.rst for detailed description of format + itself. diff --git a/Documentation/PCI/pci-error-recovery.rst b/Documentation/PCI/pci-error-recovery.rst index 7e30f43a9659..13beee23cb04 100644 --- a/Documentation/PCI/pci-error-recovery.rst +++ b/Documentation/PCI/pci-error-recovery.rst @@ -403,7 +403,7 @@ That is, the recovery API only requires that: .. note:: Implementation details for the powerpc platform are discussed in - the file Documentation/powerpc/eeh-pci-error-recovery.txt + the file Documentation/powerpc/eeh-pci-error-recovery.rst As of this writing, there is a growing list of device drivers with patches implementing error recovery. Not all of these patches are in @@ -421,3 +421,6 @@ That is, the recovery API only requires that: - drivers/net/ixgbe - drivers/net/cxgb3 - drivers/net/s2io.c + +The End +------- diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt index 8151f0195f76..23f115dc87cf 100644 --- a/Documentation/RCU/rculist_nulls.txt +++ b/Documentation/RCU/rculist_nulls.txt @@ -1,7 +1,7 @@ Using hlist_nulls to protect read-mostly linked lists and objects using SLAB_TYPESAFE_BY_RCU allocations. -Please read the basics in Documentation/RCU/listRCU.txt +Please read the basics in Documentation/RCU/listRCU.rst Using special makers (called 'nulls') is a convenient way to solve following problem : diff --git a/Documentation/admin-guide/conf.py b/Documentation/admin-guide/conf.py deleted file mode 100644 index 86f738953799..000000000000 --- a/Documentation/admin-guide/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel User Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'linux-user.tex', 'Linux Kernel User Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 25f3b2532198..e05e581af5cf 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -41,10 +41,11 @@ Related CVEs The following CVE entries describe Spectre variants: - ============= ======================= ================= + ============= ======================= ========================== CVE-2017-5753 Bounds check bypass Spectre variant 1 CVE-2017-5715 Branch target injection Spectre variant 2 - ============= ======================= ================= + CVE-2019-1125 Spectre v1 swapgs Spectre variant 1 (swapgs) + ============= ======================= ========================== Problem ------- @@ -78,6 +79,13 @@ There are some extensions of Spectre variant 1 attacks for reading data over the network, see :ref:`[12] <spec_ref12>`. However such attacks are difficult, low bandwidth, fragile, and are considered low risk. +Note that, despite "Bounds Check Bypass" name, Spectre variant 1 is not +only about user-controlled array bounds checks. It can affect any +conditional checks. The kernel entry code interrupt, exception, and NMI +handlers all have conditional swapgs checks. Those may be problematic +in the context of Spectre v1, as kernel code can speculatively run with +a user GS. + Spectre variant 2 (Branch Target Injection) ------------------------------------------- @@ -132,6 +140,9 @@ not cover all possible attack vectors. 1. A user process attacking the kernel ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +Spectre variant 1 +~~~~~~~~~~~~~~~~~ + The attacker passes a parameter to the kernel via a register or via a known address in memory during a syscall. Such parameter may be used later by the kernel as an index to an array or to derive @@ -144,7 +155,40 @@ not cover all possible attack vectors. potentially be influenced for Spectre attacks, new "nospec" accessor macros are used to prevent speculative loading of data. - Spectre variant 2 attacker can :ref:`poison <poison_btb>` the branch +Spectre variant 1 (swapgs) +~~~~~~~~~~~~~~~~~~~~~~~~~~ + + An attacker can train the branch predictor to speculatively skip the + swapgs path for an interrupt or exception. If they initialize + the GS register to a user-space value, if the swapgs is speculatively + skipped, subsequent GS-related percpu accesses in the speculation + window will be done with the attacker-controlled GS value. This + could cause privileged memory to be accessed and leaked. + + For example: + + :: + + if (coming from user space) + swapgs + mov %gs:<percpu_offset>, %reg + mov (%reg), %reg1 + + When coming from user space, the CPU can speculatively skip the + swapgs, and then do a speculative percpu load using the user GS + value. So the user can speculatively force a read of any kernel + value. If a gadget exists which uses the percpu value as an address + in another load/store, then the contents of the kernel value may + become visible via an L1 side channel attack. + + A similar attack exists when coming from kernel space. The CPU can + speculatively do the swapgs, causing the user GS to get used for the + rest of the speculative window. + +Spectre variant 2 +~~~~~~~~~~~~~~~~~ + + A spectre variant 2 attacker can :ref:`poison <poison_btb>` the branch target buffer (BTB) before issuing syscall to launch an attack. After entering the kernel, the kernel could use the poisoned branch target buffer on indirect jump and jump to gadget code in speculative @@ -280,11 +324,18 @@ The sysfs file showing Spectre variant 1 mitigation status is: The possible values in this file are: - ======================================= ================================= - 'Mitigation: __user pointer sanitation' Protection in kernel on a case by - case base with explicit pointer - sanitation. - ======================================= ================================= + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable. + * - 'Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers' + - The swapgs protections are disabled; otherwise it has + protection in the kernel on a case by case base with explicit + pointer sanitation and usercopy LFENCE barriers. + * - 'Mitigation: usercopy/swapgs barriers and __user pointer sanitization' + - Protection in the kernel on a case by case base with explicit + pointer sanitation, usercopy LFENCE barriers, and swapgs LFENCE + barriers. However, the protections are put in place on a case by case basis, and there is no guarantee that all possible attack vectors for Spectre @@ -366,12 +417,27 @@ Turning on mitigation for Spectre variant 1 and Spectre variant 2 1. Kernel mitigation ^^^^^^^^^^^^^^^^^^^^ +Spectre variant 1 +~~~~~~~~~~~~~~~~~ + For the Spectre variant 1, vulnerable kernel code (as determined by code audit or scanning tools) is annotated on a case by case basis to use nospec accessor macros for bounds clipping :ref:`[2] <spec_ref2>` to avoid any usable disclosure gadgets. However, it may not cover all attack vectors for Spectre variant 1. + Copy-from-user code has an LFENCE barrier to prevent the access_ok() + check from being mis-speculated. The barrier is done by the + barrier_nospec() macro. + + For the swapgs variant of Spectre variant 1, LFENCE barriers are + added to interrupt, exception and NMI entry where needed. These + barriers are done by the FENCE_SWAPGS_KERNEL_ENTRY and + FENCE_SWAPGS_USER_ENTRY macros. + +Spectre variant 2 +~~~~~~~~~~~~~~~~~ + For Spectre variant 2 mitigation, the compiler turns indirect calls or jumps in the kernel into equivalent return trampolines (retpolines) :ref:`[3] <spec_ref3>` :ref:`[9] <spec_ref9>` to go to the target @@ -473,6 +539,12 @@ Mitigation control on the kernel command line Spectre variant 2 mitigation can be disabled or force enabled at the kernel command line. + nospectre_v1 + + [X86,PPC] Disable mitigations for Spectre Variant 1 + (bounds check bypass). With this option data leaks are + possible in the system. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 46b826fcb5ad..47d981a86e2f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2545,7 +2545,7 @@ mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME - Refer to Documentation/virtual/kvm/amd-memory-encryption.rst + Refer to Documentation/virt/kvm/amd-memory-encryption.rst for details on when memory encryption can be activated. mem_sleep_default= [SUSPEND] Default system suspend mode: @@ -2604,7 +2604,7 @@ expose users to several CPU vulnerabilities. Equivalent to: nopti [X86,PPC] kpti=0 [ARM64] - nospectre_v1 [PPC] + nospectre_v1 [X86,PPC] nobp=0 [S390] nospectre_v2 [X86,PPC,S390,ARM64] spectre_v2_user=off [X86] @@ -2965,9 +2965,9 @@ nosmt=force: Force disable SMT, cannot be undone via the sysfs control file. - nospectre_v1 [PPC] Disable mitigations for Spectre Variant 1 (bounds - check bypass). With this option data leaks are possible - in the system. + nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1 + (bounds check bypass). With this option data leaks are + possible in the system. nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for the Spectre variant 2 (indirect branch prediction) diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 7ab93a8404b9..bd5714547cee 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -53,7 +53,7 @@ disabled, there is ``khugepaged`` daemon that scans memory and collapses sequences of basic pages into huge pages. The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>` -interface and using madivse(2) and prctl(2) system calls. +interface and using madvise(2) and prctl(2) system calls. Transparent Hugepage Support maximizes the usefulness of free memory if compared to the reservation approach of hugetlbfs by allowing all diff --git a/Documentation/bpf/prog_flow_dissector.rst b/Documentation/bpf/prog_flow_dissector.rst index ed343abe541e..a78bf036cadd 100644 --- a/Documentation/bpf/prog_flow_dissector.rst +++ b/Documentation/bpf/prog_flow_dissector.rst @@ -26,6 +26,7 @@ The inputs are: * ``nhoff`` - initial offset of the networking header * ``thoff`` - initial offset of the transport header, initialized to nhoff * ``n_proto`` - L3 protocol type, parsed out of L2 header + * ``flags`` - optional flags Flow dissector BPF program should fill out the rest of the ``struct bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be @@ -101,6 +102,23 @@ can be called for both cases and would have to be written carefully to handle both cases. +Flags +===== + +``flow_keys->flags`` might contain optional input flags that work as follows: + +* ``BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG`` - tells BPF flow dissector to + continue parsing first fragment; the default expected behavior is that + flow dissector returns as soon as it finds out that the packet is fragmented; + used by ``eth_get_headlen`` to estimate length of all headers for GRO. +* ``BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL`` - tells BPF flow dissector to + stop parsing as soon as it reaches IPv6 flow label; used by + ``___skb_get_hash`` and ``__skb_get_hash_symmetric`` to get flow hash. +* ``BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP`` - tells BPF flow dissector to stop + parsing as soon as it reaches encapsulated headers; used by routing + infrastructure. + + Reference Implementation ======================== diff --git a/Documentation/conf.py b/Documentation/conf.py index 3b2397bcb565..a8fe845832bc 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -16,6 +16,8 @@ import sys import os import sphinx +from subprocess import check_output + # Get Sphinx version major, minor, patch = sphinx.version_info[:3] @@ -276,10 +278,21 @@ latex_elements = { \\setsansfont{DejaVu Sans} \\setromanfont{DejaVu Serif} \\setmonofont{DejaVu Sans Mono} - ''' } +# At least one book (translations) may have Asian characters +# with are only displayed if xeCJK is used + +cjk_cmd = check_output(['fc-list', '--format="%{family[0]}\n"']).decode('utf-8', 'ignore') +if cjk_cmd.find("Noto Sans CJK SC") >= 0: + print ("enabling CJK for LaTeX builder") + latex_elements['preamble'] += ''' + % This is needed for translations + \\usepackage{xeCJK} + \\setCJKmainfont{Noto Sans CJK SC} + ''' + # Fix reference escape troubles with Sphinx 1.4.x if major == 1 and minor > 3: latex_elements['preamble'] += '\\renewcommand*{\\DUrole}[2]{ #2 }\n' @@ -410,6 +423,21 @@ latex_documents = [ 'The kernel development community', 'manual'), ] +# Add all other index files from Documentation/ subdirectories +for fn in os.listdir('.'): + doc = os.path.join(fn, "index") + if os.path.exists(doc + ".rst"): + has = False + for l in latex_documents: + if l[0] == doc: + has = True + break + if not has: + latex_documents.append((doc, fn + '.tex', + 'Linux %s Documentation' % fn.capitalize(), + 'The kernel development community', + 'manual')) + # The name of an image file (relative to this directory) to place at the top of # the title page. #latex_logo = None diff --git a/Documentation/core-api/conf.py b/Documentation/core-api/conf.py deleted file mode 100644 index db1f7659f3da..000000000000 --- a/Documentation/core-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Core-API Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'core-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/crypto/conf.py b/Documentation/crypto/conf.py deleted file mode 100644 index 4335d251ddf3..000000000000 --- a/Documentation/crypto/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Crypto API' - -tags.add("subproject") - -latex_documents = [ - ('index', 'crypto-api.tex', 'Linux Kernel Crypto API manual', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/dev-tools/conf.py b/Documentation/dev-tools/conf.py deleted file mode 100644 index 7faafa3f7888..000000000000 --- a/Documentation/dev-tools/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Development tools for the kernel" - -tags.add("subproject") - -latex_documents = [ - ('index', 'dev-tools.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/devicetree/bindings/arm/idle-states.txt b/Documentation/devicetree/bindings/arm/idle-states.txt index 326f29b270ad..2d325bed37e5 100644 --- a/Documentation/devicetree/bindings/arm/idle-states.txt +++ b/Documentation/devicetree/bindings/arm/idle-states.txt @@ -703,4 +703,4 @@ cpus { https://www.devicetree.org/specifications/ [6] ARM Linux Kernel documentation - Booting AArch64 Linux - Documentation/arm64/booting.txt + Documentation/arm64/booting.rst diff --git a/Documentation/devicetree/bindings/arm/renesas.yaml b/Documentation/devicetree/bindings/arm/renesas.yaml index 08c923f8c257..28eb458f761a 100644 --- a/Documentation/devicetree/bindings/arm/renesas.yaml +++ b/Documentation/devicetree/bindings/arm/renesas.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/shmobile.yaml# +$id: http://devicetree.org/schemas/arm/renesas.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas SH-Mobile, R-Mobile, and R-Car Platform Device Tree Bindings diff --git a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml index aae53fc3cb1e..2bd519d2e855 100644 --- a/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml +++ b/Documentation/devicetree/bindings/arm/socionext/milbeaut.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/milbeaut.yaml# +$id: http://devicetree.org/schemas/arm/socionext/milbeaut.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Milbeaut platforms device tree bindings diff --git a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml index 4326d2cfa15d..a8765ba29476 100644 --- a/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml +++ b/Documentation/devicetree/bindings/arm/ti/ti,davinci.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/arm/ti/davinci.yaml# +$id: http://devicetree.org/schemas/arm/ti/ti,davinci.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments DaVinci Platforms Device Tree Bindings diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml index c935405458fe..fa4d143a73de 100644 --- a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml +++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ccu.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/phy/allwinner,sun4i-a10-ccu.yaml# +$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-ccu.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner Clock Control Unit Device Tree Bindings diff --git a/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml b/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml index 8cb136c376fb..4f0db8ee226a 100644 --- a/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml +++ b/Documentation/devicetree/bindings/firmware/intel,ixp4xx-network-processing-engine.yaml @@ -2,7 +2,7 @@ # Copyright 2019 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/firmware/intel-ixp4xx-network-processing-engine.yaml#" +$id: "http://devicetree.org/schemas/firmware/intel,ixp4xx-network-processing-engine.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx Network Processing Engine diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml index 7ba167e2e1ea..c602b6fe1c0c 100644 --- a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml +++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl345.yaml# +$id: http://devicetree.org/schemas/iio/accel/adi,adxl345.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices ADXL345/ADXL375 3-Axis Digital Accelerometers diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml index a7fafb9bf5c6..e7daffec88d3 100644 --- a/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml +++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl372.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl372.yaml# +$id: http://devicetree.org/schemas/iio/accel/adi,adxl372.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Analog Devices ADXL372 3-Axis, +/-(200g) Digital Accelerometer diff --git a/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt index 4e82fd575cec..c676b03c752e 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt @@ -5,21 +5,19 @@ Required properties: - compatible: should be "amazon,al-fic" - reg: physical base address and size of the registers - interrupt-controller: identifies the node as an interrupt controller -- #interrupt-cells: must be 2. - First cell defines the index of the interrupt within the controller. - Second cell is used to specify the trigger type and must be one of the - following: - - bits[3:0] trigger type and level flags - 1 = low-to-high edge triggered - 4 = active high level-sensitive -- interrupt-parent: specifies the parent interrupt controller. +- #interrupt-cells : must be 2. Specifies the number of cells needed to encode + an interrupt source. Supported trigger types are low-to-high edge + triggered and active high level-sensitive. - interrupts: describes which input line in the interrupt parent, this fic's output is connected to. This field property depends on the parent's binding +Please refer to interrupts.txt in this directory for details of the common +Interrupt Controllers bindings used by client devices. + Example: -amazon_fic: interrupt-controller@0xfd8a8500 { +amazon_fic: interrupt-controller@fd8a8500 { compatible = "amazon,al-fic"; interrupt-controller; #interrupt-cells = <2>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml b/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml index bae10e261fa9..507c141ea760 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml @@ -2,7 +2,7 @@ # Copyright 2018 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/interrupt/intel-ixp4xx-interrupt.yaml#" +$id: "http://devicetree.org/schemas/interrupt-controller/intel,ixp4xx-interrupt.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx XScale Networking Processors Interrupt Controller diff --git a/Documentation/devicetree/bindings/misc/intel,ixp4xx-queue-manager.yaml b/Documentation/devicetree/bindings/misc/intel,ixp4xx-ahb-queue-manager.yaml index d2313b1d9405..0ea21a6f70b4 100644 --- a/Documentation/devicetree/bindings/misc/intel,ixp4xx-queue-manager.yaml +++ b/Documentation/devicetree/bindings/misc/intel,ixp4xx-ahb-queue-manager.yaml @@ -2,7 +2,7 @@ # Copyright 2019 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/misc/intel-ixp4xx-ahb-queue-manager.yaml#" +$id: "http://devicetree.org/schemas/misc/intel,ixp4xx-ahb-queue-manager.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx AHB Queue Manager diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index d4084c149768..3fb0714e761e 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-gmac.yaml# +$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-emac.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A83t EMAC Device Tree Bindings diff --git a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml index c9efd6e2c134..1084e9d2917d 100644 --- a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml +++ b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml @@ -37,13 +37,13 @@ required: examples: - | - sid@1c23800 { + efuse@1c23800 { compatible = "allwinner,sun4i-a10-sid"; reg = <0x01c23800 0x10>; }; - | - sid@1c23800 { + efuse@1c23800 { compatible = "allwinner,sun7i-a20-sid"; reg = <0x01c23800 0x200>; }; diff --git a/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml b/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml new file mode 100644 index 000000000000..b7c00ed31085 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/nvmem-consumer.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/nvmem-consumer.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NVMEM (Non Volatile Memory) Consumer Device Tree Bindings + +maintainers: + - Srinivas Kandagatla <[email protected]> + +select: true + +properties: + nvmem: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + List of phandle to the nvmem providers. + + nvmem-cells: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + List of phandle to the nvmem data cells. + + nvmem-names: + $ref: /schemas/types.yaml#/definitions/string-array + description: + Names for the each nvmem provider. + + nvmem-cell-names: + $ref: /schemas/types.yaml#/definitions/string-array + description: + Names for each nvmem-cells specified. + +dependencies: + nvmem-names: [ nvmem ] + nvmem-cell-names: [ nvmem-cells ] + +examples: + - | + tsens { + /* ... */ + nvmem-cells = <&tsens_calibration>; + nvmem-cell-names = "calibration"; + }; diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.txt b/Documentation/devicetree/bindings/nvmem/nvmem.txt index fd06c09b822b..46a7ef485e24 100644 --- a/Documentation/devicetree/bindings/nvmem/nvmem.txt +++ b/Documentation/devicetree/bindings/nvmem/nvmem.txt @@ -1,80 +1 @@ -= NVMEM(Non Volatile Memory) Data Device Tree Bindings = - -This binding is intended to represent the location of hardware -configuration data stored in NVMEMs like eeprom, efuses and so on. - -On a significant proportion of boards, the manufacturer has stored -some data on NVMEM, for the OS to be able to retrieve these information -and act upon it. Obviously, the OS has to know about where to retrieve -these data from, and where they are stored on the storage device. - -This document is here to document this. - -= Data providers = -Contains bindings specific to provider drivers and data cells as children -of this node. - -Optional properties: - read-only: Mark the provider as read only. - -= Data cells = -These are the child nodes of the provider which contain data cell -information like offset and size in nvmem provider. - -Required properties: -reg: specifies the offset in byte within the storage device. - -Optional properties: - -bits: Is pair of bit location and number of bits, which specifies offset - in bit and number of bits within the address range specified by reg property. - Offset takes values from 0-7. - -For example: - - /* Provider */ - qfprom: qfprom@700000 { - ... - - /* Data cells */ - tsens_calibration: calib@404 { - reg = <0x404 0x10>; - }; - - tsens_calibration_bckp: calib_bckp@504 { - reg = <0x504 0x11>; - bits = <6 128> - }; - - pvs_version: pvs-version@6 { - reg = <0x6 0x2> - bits = <7 2> - }; - - speed_bin: speed-bin@c{ - reg = <0xc 0x1>; - bits = <2 3>; - - }; - ... - }; - -= Data consumers = -Are device nodes which consume nvmem data cells/providers. - -Required-properties: -nvmem-cells: list of phandle to the nvmem data cells. -nvmem-cell-names: names for the each nvmem-cells specified. Required if - nvmem-cells is used. - -Optional-properties: -nvmem : list of phandles to nvmem providers. -nvmem-names: names for the each nvmem provider. required if nvmem is used. - -For example: - - tsens { - ... - nvmem-cells = <&tsens_calibration>; - nvmem-cell-names = "calibration"; - }; +This file has been moved to nvmem.yaml and nvmem-consumer.yaml. diff --git a/Documentation/devicetree/bindings/nvmem/nvmem.yaml b/Documentation/devicetree/bindings/nvmem/nvmem.yaml new file mode 100644 index 000000000000..1c75a059206c --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/nvmem.yaml @@ -0,0 +1,93 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/nvmem.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NVMEM (Non Volatile Memory) Device Tree Bindings + +maintainers: + - Srinivas Kandagatla <[email protected]> + +description: | + This binding is intended to represent the location of hardware + configuration data stored in NVMEMs like eeprom, efuses and so on. + + On a significant proportion of boards, the manufacturer has stored + some data on NVMEM, for the OS to be able to retrieve these + information and act upon it. Obviously, the OS has to know about + where to retrieve these data from, and where they are stored on the + storage device. + +properties: + $nodename: + pattern: "^(eeprom|efuse|nvram)(@.*|-[0-9a-f])*$" + + "#address-cells": + const: 1 + + "#size-cells": + const: 1 + + read-only: + $ref: /schemas/types.yaml#/definitions/flag + description: + Mark the provider as read only. + +patternProperties: + "^.*@[0-9a-f]+$": + type: object + + properties: + reg: + maxItems: 1 + description: + Offset and size in bytes within the storage device. + + bits: + maxItems: 1 + items: + items: + - minimum: 0 + maximum: 7 + description: + Offset in bit within the address range specified by reg. + - minimum: 1 + description: + Size in bit within the address range specified by reg. + + required: + - reg + + additionalProperties: false + +examples: + - | + qfprom: eeprom@700000 { + #address-cells = <1>; + #size-cells = <1>; + + /* ... */ + + /* Data cells */ + tsens_calibration: calib@404 { + reg = <0x404 0x10>; + }; + + tsens_calibration_bckp: calib_bckp@504 { + reg = <0x504 0x11>; + bits = <6 128>; + }; + + pvs_version: pvs-version@6 { + reg = <0x6 0x2>; + bits = <7 2>; + }; + + speed_bin: speed-bin@c{ + reg = <0xc 0x1>; + bits = <2 3>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml index 250f9d5aabdf..fa46670de299 100644 --- a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml +++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: http://devicetree.org/schemas/display/allwinner,sun6i-a31-mipi-dphy.yaml# +$id: http://devicetree.org/schemas/phy/allwinner,sun6i-a31-mipi-dphy.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A31 MIPI D-PHY Controller Device Tree Bindings diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml index 876c0623f322..a02e2fe2bfb2 100644 --- a/Documentation/devicetree/bindings/spi/spi-controller.yaml +++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml @@ -73,7 +73,6 @@ patternProperties: Compatible of the SPI device. reg: - maxItems: 1 minimum: 0 maximum: 256 description: diff --git a/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml b/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml index a36a0746c056..2807225db902 100644 --- a/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml +++ b/Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml @@ -2,7 +2,7 @@ # Copyright 2018 Linaro Ltd. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/timer/intel-ixp4xx-timer.yaml#" +$id: "http://devicetree.org/schemas/timer/intel,ixp4xx-timer.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Intel IXP4xx XScale Networking Processors Timers diff --git a/Documentation/devicetree/bindings/usb/usb251xb.txt b/Documentation/devicetree/bindings/usb/usb251xb.txt index bc7945e9dbfe..17915f64b8ee 100644 --- a/Documentation/devicetree/bindings/usb/usb251xb.txt +++ b/Documentation/devicetree/bindings/usb/usb251xb.txt @@ -64,10 +64,8 @@ Optional properties : - power-on-time-ms : Specifies the time it takes from the time the host initiates the power-on sequence to a port until the port has adequate power. The value is given in ms in a 0 - 510 range (default is 100ms). - - swap-dx-lanes : Specifies the downstream ports which will swap the - differential-pair (D+/D-), default is not-swapped. - - swap-us-lanes : Selects the upstream port differential-pair (D+/D-) - swapping (boolean, default is not-swapped) + - swap-dx-lanes : Specifies the ports which will swap the differential-pair + (D+/D-), default is not-swapped. Examples: usb2512b@2c { diff --git a/Documentation/doc-guide/conf.py b/Documentation/doc-guide/conf.py deleted file mode 100644 index fd3731182d5a..000000000000 --- a/Documentation/doc-guide/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Documentation Guide' - -tags.add("subproject") - -latex_documents = [ - ('index', 'kernel-doc-guide.tex', 'Linux Kernel Documentation Guide', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/80211/conf.py b/Documentation/driver-api/80211/conf.py deleted file mode 100644 index 4424b4b0b9c3..000000000000 --- a/Documentation/driver-api/80211/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux 802.11 Driver Developer's Guide" - -tags.add("subproject") - -latex_documents = [ - ('index', '80211.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/conf.py b/Documentation/driver-api/conf.py deleted file mode 100644 index 202726d20088..000000000000 --- a/Documentation/driver-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux driver implementer's API guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'driver-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/driver-api/generic-counter.rst b/Documentation/driver-api/generic-counter.rst index 0c161b1a3be6..8382f01a53e3 100644 --- a/Documentation/driver-api/generic-counter.rst +++ b/Documentation/driver-api/generic-counter.rst @@ -233,7 +233,7 @@ Userspace Interface Several sysfs attributes are generated by the Generic Counter interface, and reside under the /sys/bus/counter/devices/counterX directory, where counterX refers to the respective counter device. Please see -Documentation/ABI/testing/sys-bus-counter-generic-sysfs for detailed +Documentation/ABI/testing/sysfs-bus-counter for detailed information on each Generic Counter interface sysfs attribute. Through these sysfs attributes, programs and scripts may interact with @@ -325,7 +325,7 @@ sysfs attributes, where Y is the unique ID of the respective Count: For a more detailed breakdown of the available Generic Counter interface sysfs attributes, please refer to the -Documentation/ABI/testing/sys-bus-counter file. +Documentation/ABI/testing/sysfs-bus-counter file. The Signals and Counts associated with the Counter device are registered to the system as well by the counter_register function. The diff --git a/Documentation/driver-api/phy/phy.rst b/Documentation/driver-api/phy/phy.rst index 457c3e0f86d6..8fc1ce0bb905 100644 --- a/Documentation/driver-api/phy/phy.rst +++ b/Documentation/driver-api/phy/phy.rst @@ -179,8 +179,8 @@ PHY Mappings In order to get reference to a PHY without help from DeviceTree, the framework offers lookups which can be compared to clkdev that allow clk structures to be -bound to devices. A lookup can be made be made during runtime when a handle to -the struct phy already exists. +bound to devices. A lookup can be made during runtime when a handle to the +struct phy already exists. The framework offers the following API for registering and unregistering the lookups:: diff --git a/Documentation/driver-api/pm/conf.py b/Documentation/driver-api/pm/conf.py deleted file mode 100644 index a89fac11272f..000000000000 --- a/Documentation/driver-api/pm/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Device Power Management" - -tags.add("subproject") - -latex_documents = [ - ('index', 'pm.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/filesystems/conf.py b/Documentation/filesystems/conf.py deleted file mode 100644 index ea44172af5c4..000000000000 --- a/Documentation/filesystems/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Filesystems API" - -tags.add("subproject") - -latex_documents = [ - ('index', 'filesystems.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/gpu/conf.py b/Documentation/gpu/conf.py deleted file mode 100644 index 1757b040fb32..000000000000 --- a/Documentation/gpu/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux GPU Driver Developer's Guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'gpu.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/hwmon/k8temp.rst b/Documentation/hwmon/k8temp.rst index 72da12aa17e5..fe9109521056 100644 --- a/Documentation/hwmon/k8temp.rst +++ b/Documentation/hwmon/k8temp.rst @@ -9,7 +9,7 @@ Supported chips: Addresses scanned: PCI space - Datasheet: http://support.amd.com/us/Processor_TechDocs/32559.pdf + Datasheet: http://www.amd.com/system/files/TechDocs/32559.pdf Author: Rudolf Marek diff --git a/Documentation/index.rst b/Documentation/index.rst index 70ae148ec980..2df5a3da563c 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -111,9 +111,11 @@ needed). netlabel/index networking/index pcmcia/index + power/index target/index timers/index watchdog/index + virtual/index input/index hwmon/index gpu/index @@ -143,6 +145,7 @@ implementation. arm64/index ia64/index m68k/index + powerpc/index riscv/index s390/index sh/index diff --git a/Documentation/input/conf.py b/Documentation/input/conf.py deleted file mode 100644 index d2352fdc92ed..000000000000 --- a/Documentation/input/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux input driver subsystem" - -tags.add("subproject") - -latex_documents = [ - ('index', 'linux-input.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/kernel-hacking/conf.py b/Documentation/kernel-hacking/conf.py deleted file mode 100644 index 3d8acf0f33ad..000000000000 --- a/Documentation/kernel-hacking/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Kernel Hacking Guides" - -tags.add("subproject") - -latex_documents = [ - ('index', 'kernel-hacking.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/locking/spinlocks.rst b/Documentation/locking/spinlocks.rst index 098107fb7d86..e93ec6645238 100644 --- a/Documentation/locking/spinlocks.rst +++ b/Documentation/locking/spinlocks.rst @@ -82,7 +82,7 @@ itself. The read lock allows many concurrent readers. Anything that **changes** the list will have to get the write lock. NOTE! RCU is better for list traversal, but requires careful - attention to design detail (see Documentation/RCU/listRCU.txt). + attention to design detail (see Documentation/RCU/listRCU.rst). Also, you cannot "upgrade" a read-lock to a write-lock, so if you at _any_ time need to do any changes (even if you don't do it every time), you have @@ -90,7 +90,7 @@ to get the write-lock at the very beginning. NOTE! We are working hard to remove reader-writer spinlocks in most cases, so please don't add a new one without consensus. (Instead, see - Documentation/RCU/rcu.txt for complete information.) + Documentation/RCU/rcu.rst for complete information.) ---- diff --git a/Documentation/maintainer/conf.py b/Documentation/maintainer/conf.py deleted file mode 100644 index 81e9eb7a7884..000000000000 --- a/Documentation/maintainer/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Development Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'maintainer.tex', 'Linux Kernel Development Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/media/conf.py b/Documentation/media/conf.py deleted file mode 100644 index 1f194fcd2cae..000000000000 --- a/Documentation/media/conf.py +++ /dev/null @@ -1,12 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -# SPDX-License-Identifier: GPL-2.0 - -project = 'Linux Media Subsystem Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'media.tex', 'Linux Media Subsystem Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 045bb8148fe9..1adbb8a371c7 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -548,7 +548,7 @@ There are certain things that the Linux kernel memory barriers do not guarantee: [*] For information on bus mastering DMA and coherency please read: - Documentation/PCI/pci.rst + Documentation/driver-api/pci/pci.rst Documentation/DMA-API-HOWTO.txt Documentation/DMA-API.txt diff --git a/Documentation/networking/conf.py b/Documentation/networking/conf.py deleted file mode 100644 index 40f69e67a883..000000000000 --- a/Documentation/networking/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Networking Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'networking.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index df33674799b5..49e95f438ed7 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -256,6 +256,12 @@ tcp_base_mss - INTEGER Path MTU discovery (MTU probing). If MTU probing is enabled, this is the initial MSS used by the connection. +tcp_mtu_probe_floor - INTEGER + If MTU probing is enabled this caps the minimum MSS used for search_low + for the connection. + + Default : 48 + tcp_min_snd_mss - INTEGER TCP SYN and SYNACK messages usually advertise an ADVMSS option, as described in RFC 1122 and RFC 6691. diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst index 048e5ca44824..b70b70dc4524 100644 --- a/Documentation/networking/tls-offload.rst +++ b/Documentation/networking/tls-offload.rst @@ -424,13 +424,24 @@ Statistics Following minimum set of TLS-related statistics should be reported by the driver: - * ``rx_tls_decrypted`` - number of successfully decrypted TLS segments - * ``tx_tls_encrypted`` - number of in-order TLS segments passed to device - for encryption + * ``rx_tls_decrypted_packets`` - number of successfully decrypted RX packets + which were part of a TLS stream. + * ``rx_tls_decrypted_bytes`` - number of TLS payload bytes in RX packets + which were successfully decrypted. + * ``tx_tls_encrypted_packets`` - number of TX packets passed to the device + for encryption of their TLS payload. + * ``tx_tls_encrypted_bytes`` - number of TLS payload bytes in TX packets + passed to the device for encryption. + * ``tx_tls_ctx`` - number of TLS TX HW offload contexts added to device for + encryption. * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream - but did not arrive in the expected order - * ``tx_tls_drop_no_sync_data`` - number of TX packets dropped because - they arrived out of order and associated record could not be found + but did not arrive in the expected order. + * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of + a TLS stream dropped, because they arrived out of order and associated + record could not be found. + * ``tx_tls_drop_bypass_req`` - number of TX packets which were part of a TLS + stream dropped, because they contain both data that has been encrypted by + software and data that expects hardware crypto offload. Notable corner cases, exceptions and additional requirements ============================================================ diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index 20415f21e48a..002e42745263 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -1,4 +1,4 @@ -:orphan: +.. SPDX-License-Identifier: GPL-2.0 ================ Power Management diff --git a/Documentation/powerpc/bootwrapper.txt b/Documentation/powerpc/bootwrapper.rst index d60fced5e1cc..a6292afba573 100644 --- a/Documentation/powerpc/bootwrapper.txt +++ b/Documentation/powerpc/bootwrapper.rst @@ -1,5 +1,7 @@ +======================== The PowerPC boot wrapper ------------------------- +======================== + Copyright (C) Secret Lab Technologies Ltd. PowerPC image targets compresses and wraps the kernel image (vmlinux) with @@ -21,6 +23,7 @@ it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target image. The details of the build system is discussed in the next section. Currently, the following image format targets exist: + ==================== ======================================================== cuImage.%: Backwards compatible uImage for older version of U-Boot (for versions that don't understand the device tree). This image embeds a device tree blob inside @@ -29,31 +32,36 @@ Currently, the following image format targets exist: with boot wrapper code that extracts data from the old bd_info structure and loads the data into the device tree before jumping into the kernel. - Because of the series of #ifdefs found in the + + Because of the series of #ifdefs found in the bd_info structure used in the old U-Boot interfaces, cuImages are platform specific. Each specific U-Boot platform has a different platform init file which populates the embedded device tree with data from the platform specific bd_info file. The platform specific cuImage platform init code can be found in - arch/powerpc/boot/cuboot.*.c. Selection of the correct + `arch/powerpc/boot/cuboot.*.c`. Selection of the correct cuImage init code for a specific board can be found in the wrapper structure. + dtbImage.%: Similar to zImage, except device tree blob is embedded inside the image instead of provided by firmware. The output image file can be either an elf file or a flat binary depending on the platform. - dtbImages are used on systems which do not have an + + dtbImages are used on systems which do not have an interface for passing a device tree directly. dtbImages are similar to simpleImages except that dtbImages have platform specific code for extracting data from the board firmware, but simpleImages do not talk to the firmware at all. - PlayStation 3 support uses dtbImage. So do Embedded + + PlayStation 3 support uses dtbImage. So do Embedded Planet boards using the PlanetCore firmware. Board specific initialization code is typically found in a file named arch/powerpc/boot/<platform>.c; but this can be overridden by the wrapper script. + simpleImage.%: Firmware independent compressed image that does not depend on any particular firmware interface and embeds a device tree blob. This image is a flat binary that @@ -61,14 +69,16 @@ Currently, the following image format targets exist: Firmware cannot pass any configuration data to the kernel with this image type and it depends entirely on the embedded device tree for all information. - The simpleImage is useful for booting systems with + + The simpleImage is useful for booting systems with an unknown firmware interface or for booting from a debugger when no firmware is present (such as on the Xilinx Virtex platform). The only assumption that simpleImage makes is that RAM is correctly initialized and that the MMU is either off or has RAM mapped to base address 0. - simpleImage also supports inserting special platform + + simpleImage also supports inserting special platform specific initialization code to the start of the bootup sequence. The virtex405 platform uses this feature to ensure that the cache is invalidated before caching @@ -81,9 +91,11 @@ Currently, the following image format targets exist: named (virtex405-<board>.dts). Search the wrapper script for 'virtex405' and see the file arch/powerpc/boot/virtex405-head.S for details. + treeImage.%; Image format for used with OpenBIOS firmware found on some ppc4xx hardware. This image embeds a device tree blob inside the image. + uImage: Native image format used by U-Boot. The uImage target does not add any boot code. It just wraps a compressed vmlinux in the uImage data structure. This image @@ -91,12 +103,14 @@ Currently, the following image format targets exist: a device tree to the kernel at boot. If using an older version of U-Boot, then you need to use a cuImage instead. + zImage.%: Image format which does not embed a device tree. Used by OpenFirmware and other firmware interfaces which are able to supply a device tree. This image expects firmware to provide the device tree at boot. Typically, if you have general purpose PowerPC hardware then you want this image format. + ==================== ======================================================== Image types which embed a device tree blob (simpleImage, dtbImage, treeImage, and cuImage) all generate the device tree blob from a file in the diff --git a/Documentation/powerpc/cpu_families.txt b/Documentation/powerpc/cpu_families.rst index fc08e22feb1a..1e063c5440c3 100644 --- a/Documentation/powerpc/cpu_families.txt +++ b/Documentation/powerpc/cpu_families.rst @@ -1,3 +1,4 @@ +============ CPU Families ============ @@ -8,8 +9,8 @@ and are supported by arch/powerpc. Book3S (aka sPAPR) ------------------ - - Hash MMU - - Mix of 32 & 64 bit +- Hash MMU +- Mix of 32 & 64 bit:: +--------------+ +----------------+ | Old POWER | --------------> | RS64 (threads) | @@ -108,8 +109,8 @@ Book3S (aka sPAPR) IBM BookE --------- - - Software loaded TLB. - - All 32 bit +- Software loaded TLB. +- All 32 bit:: +--------------+ | 401 | @@ -155,8 +156,8 @@ IBM BookE Motorola/Freescale 8xx ---------------------- - - Software loaded with hardware assist. - - All 32 bit +- Software loaded with hardware assist. +- All 32 bit:: +-------------+ | MPC8xx Core | @@ -166,9 +167,9 @@ Motorola/Freescale 8xx Freescale BookE --------------- - - Software loaded TLB. - - e6500 adds HW loaded indirect TLB entries. - - Mix of 32 & 64 bit +- Software loaded TLB. +- e6500 adds HW loaded indirect TLB entries. +- Mix of 32 & 64 bit:: +--------------+ | e200 | @@ -207,8 +208,8 @@ Freescale BookE IBM A2 core ----------- - - Book3E, software loaded TLB + HW loaded indirect TLB entries. - - 64 bit +- Book3E, software loaded TLB + HW loaded indirect TLB entries. +- 64 bit:: +--------------+ +----------------+ | A2 core | --> | WSP | diff --git a/Documentation/powerpc/cpu_features.txt b/Documentation/powerpc/cpu_features.rst index ae09df8722c8..b7bcdd2f41bb 100644 --- a/Documentation/powerpc/cpu_features.txt +++ b/Documentation/powerpc/cpu_features.rst @@ -1,3 +1,7 @@ +============ +CPU Features +============ + Hollis Blanchard <[email protected]> 5 Jun 2002 @@ -32,7 +36,7 @@ anyways). After detecting the processor type, the kernel patches out sections of code that shouldn't be used by writing nop's over it. Using cpufeatures requires just 2 macros (found in arch/powerpc/include/asm/cputable.h), as seen in head.S -transfer_to_handler: +transfer_to_handler:: #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.rst index c5e8d5098ed3..920546d81326 100644 --- a/Documentation/powerpc/cxl.txt +++ b/Documentation/powerpc/cxl.rst @@ -1,3 +1,4 @@ +==================================== Coherent Accelerator Interface (CXL) ==================================== @@ -21,6 +22,8 @@ Introduction Hardware overview ================= + :: + POWER8/9 FPGA +----------+ +---------+ | | | | @@ -59,14 +62,16 @@ Hardware overview the fault. The context to which this fault is serviced is based on who owns that acceleration function. - POWER8 <-----> PSL Version 8 is compliant to the CAIA Version 1.0. - POWER9 <-----> PSL Version 9 is compliant to the CAIA Version 2.0. + - POWER8 and PSL Version 8 are compliant to the CAIA Version 1.0. + - POWER9 and PSL Version 9 are compliant to the CAIA Version 2.0. + This PSL Version 9 provides new features such as: + * Interaction with the nest MMU on the P9 chip. * Native DMA support. * Supports sending ASB_Notify messages for host thread wakeup. * Supports Atomic operations. - * .... + * etc. Cards with a PSL9 won't work on a POWER8 system and cards with a PSL8 won't work on a POWER9 system. @@ -147,7 +152,9 @@ User API master devices. A userspace library libcxl is available here: + https://github.com/ibm-capi/libcxl + This provides a C interface to this kernel API. open @@ -165,7 +172,8 @@ open When all available contexts are allocated the open call will fail and return -ENOSPC. - Note: IRQs need to be allocated for each context, which may limit + Note: + IRQs need to be allocated for each context, which may limit the number of contexts that can be created, and therefore how many times the device can be opened. The POWER8 CAPP supports 2040 IRQs and 3 are used by the kernel, so 2037 are @@ -186,7 +194,9 @@ ioctl updated as userspace allocates and frees memory. This ioctl returns once the AFU context is started. - Takes a pointer to a struct cxl_ioctl_start_work: + Takes a pointer to a struct cxl_ioctl_start_work + + :: struct cxl_ioctl_start_work { __u64 flags; @@ -269,7 +279,7 @@ read The buffer passed to read() must be at least 4K bytes. The result of the read will be a buffer of one or more events, - each event is of type struct cxl_event, of varying size. + each event is of type struct cxl_event, of varying size:: struct cxl_event { struct cxl_event_header header; @@ -280,7 +290,9 @@ read }; }; - The struct cxl_event_header is defined as: + The struct cxl_event_header is defined as + + :: struct cxl_event_header { __u16 type; @@ -307,7 +319,9 @@ read For future extensions and padding. If the event type is CXL_EVENT_AFU_INTERRUPT then the event - structure is defined as: + structure is defined as + + :: struct cxl_event_afu_interrupt { __u16 flags; @@ -326,7 +340,9 @@ read For future extensions and padding. If the event type is CXL_EVENT_DATA_STORAGE then the event - structure is defined as: + structure is defined as + + :: struct cxl_event_data_storage { __u16 flags; @@ -356,7 +372,9 @@ read For future extensions If the event type is CXL_EVENT_AFU_ERROR then the event structure - is defined as: + is defined as + + :: struct cxl_event_afu_error { __u16 flags; @@ -393,15 +411,15 @@ open ioctl ----- -CXL_IOCTL_DOWNLOAD_IMAGE: -CXL_IOCTL_VALIDATE_IMAGE: +CXL_IOCTL_DOWNLOAD_IMAGE / CXL_IOCTL_VALIDATE_IMAGE: Starts and controls flashing a new FPGA image. Partial reconfiguration is not supported (yet), so the image must contain a copy of the PSL and AFU(s). Since an image can be quite large, the caller may have to iterate, splitting the image in smaller chunks. - Takes a pointer to a struct cxl_adapter_image: + Takes a pointer to a struct cxl_adapter_image:: + struct cxl_adapter_image { __u64 flags; __u64 data; @@ -442,7 +460,7 @@ Udev rules The following udev rules could be used to create a symlink to the most logical chardev to use in any programming mode (afuX.Yd for dedicated, afuX.Ys for afu directed), since the API is virtually - identical for each: + identical for each:: SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b" SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \ diff --git a/Documentation/powerpc/cxlflash.txt b/Documentation/powerpc/cxlflash.rst index a64bdaa0a1cf..cea67931b3b9 100644 --- a/Documentation/powerpc/cxlflash.txt +++ b/Documentation/powerpc/cxlflash.rst @@ -1,3 +1,7 @@ +================================ +Coherent Accelerator (CXL) Flash +================================ + Introduction ============ @@ -28,7 +32,7 @@ Introduction responsible for the initialization of the adapter, setting up the special path for user space access, and performing error recovery. It communicates directly the Flash Accelerator Functional Unit (AFU) - as described in Documentation/powerpc/cxl.txt. + as described in Documentation/powerpc/cxl.rst. The cxlflash driver supports two, mutually exclusive, modes of operation at the device (LUN) level: @@ -58,7 +62,7 @@ Overview The CXL Flash Adapter Driver establishes a master context with the AFU. It uses memory mapped I/O (MMIO) for this control and setup. The - Adapter Problem Space Memory Map looks like this: + Adapter Problem Space Memory Map looks like this:: +-------------------------------+ | 512 * 64 KB User MMIO | @@ -375,7 +379,7 @@ CXL Flash Driver Host IOCTLs Each host adapter instance that is supported by the cxlflash driver has a special character device associated with it to enable a set of host management function. These character devices are hosted in a - class dedicated for cxlflash and can be accessed via /dev/cxlflash/*. + class dedicated for cxlflash and can be accessed via `/dev/cxlflash/*`. Applications can be written to perform various functions using the host ioctl APIs below. diff --git a/Documentation/powerpc/DAWR-POWER9.txt b/Documentation/powerpc/dawr-power9.rst index ecdbb076438c..c96ab6befd9c 100644 --- a/Documentation/powerpc/DAWR-POWER9.txt +++ b/Documentation/powerpc/dawr-power9.rst @@ -1,10 +1,11 @@ +===================== DAWR issues on POWER9 -============================ +===================== On POWER9 the Data Address Watchpoint Register (DAWR) can cause a checkstop if it points to cache inhibited (CI) memory. Currently Linux has no way to disinguish CI memory when configuring the DAWR, so (for now) the DAWR is -disabled by this commit: +disabled by this commit:: commit 9654153158d3e0684a1bdb76dbababdb7111d5a0 Author: Michael Neuling <[email protected]> @@ -12,7 +13,7 @@ disabled by this commit: powerpc: Disable DAWR in the base POWER9 CPU features Technical Details: -============================ +================== DAWR has 6 different ways of being set. 1) ptrace @@ -37,7 +38,7 @@ DAWR on the migration. For xmon, the 'bd' command will return an error on P9. Consequences for users -============================ +====================== For GDB watchpoints (ie 'watch' command) on POWER9 bare metal , GDB will accept the command. Unfortunately since there is no hardware @@ -57,8 +58,8 @@ trapped in GDB. The watchpoint is remembered, so if the guest is migrated back to the POWER8 host, it will start working again. Force enabling the DAWR -============================= -Kernels (since ~v5.2) have an option to force enable the DAWR via: +======================= +Kernels (since ~v5.2) have an option to force enable the DAWR via:: echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous @@ -86,5 +87,7 @@ dawr_enable_dangerous file will fail if the hypervisor doesn't support writing the DAWR. To double check the DAWR is working, run this kernel selftest: + tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c + Any errors/failures/skips mean something is wrong. diff --git a/Documentation/powerpc/dscr.txt b/Documentation/powerpc/dscr.rst index ece300c64f76..2ab99006014c 100644 --- a/Documentation/powerpc/dscr.txt +++ b/Documentation/powerpc/dscr.rst @@ -1,5 +1,6 @@ - DSCR (Data Stream Control Register) - ================================================ +=================================== +DSCR (Data Stream Control Register) +=================================== DSCR register in powerpc allows user to have some control of prefetch of data stream in the processor. Please refer to the ISA documents or related manual @@ -10,14 +11,17 @@ user interface. (A) Data Structures: - (1) thread_struct: + (1) thread_struct:: + dscr /* Thread DSCR value */ dscr_inherit /* Thread has changed default DSCR */ - (2) PACA: + (2) PACA:: + dscr_default /* per-CPU DSCR default value */ - (3) sysfs.c: + (3) sysfs.c:: + dscr_default /* System DSCR default value */ (B) Scheduler Changes: @@ -35,8 +39,8 @@ user interface. (C) SYSFS Interface: - Global DSCR default: /sys/devices/system/cpu/dscr_default - CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr + - Global DSCR default: /sys/devices/system/cpu/dscr_default + - CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr Changing the global DSCR default in the sysfs will change all the CPU specific DSCR defaults immediately in their PACA structures. Again if diff --git a/Documentation/powerpc/eeh-pci-error-recovery.txt b/Documentation/powerpc/eeh-pci-error-recovery.rst index 678189280bb4..438a87ebc095 100644 --- a/Documentation/powerpc/eeh-pci-error-recovery.txt +++ b/Documentation/powerpc/eeh-pci-error-recovery.rst @@ -1,10 +1,10 @@ +========================== +PCI Bus EEH Error Recovery +========================== +Linas Vepstas <[email protected]> - PCI Bus EEH Error Recovery - -------------------------- - Linas Vepstas - 12 January 2005 +12 January 2005 Overview: @@ -143,17 +143,17 @@ seen in /proc/ppc64/eeh (subject to change). Normally, almost all of these occur during boot, when the PCI bus is scanned, where a large number of 0xff reads are part of the bus scan procedure. -If a frozen slot is detected, code in -arch/powerpc/platforms/pseries/eeh.c will print a stack trace to -syslog (/var/log/messages). This stack trace has proven to be very -useful to device-driver authors for finding out at what point the EEH -error was detected, as the error itself usually occurs slightly +If a frozen slot is detected, code in +arch/powerpc/platforms/pseries/eeh.c will print a stack trace to +syslog (/var/log/messages). This stack trace has proven to be very +useful to device-driver authors for finding out at what point the EEH +error was detected, as the error itself usually occurs slightly beforehand. Next, it uses the Linux kernel notifier chain/work queue mechanism to allow any interested parties to find out about the failure. Device drivers, or other parts of the kernel, can use -eeh_register_notifier(struct notifier_block *) to find out about EEH +`eeh_register_notifier(struct notifier_block *)` to find out about EEH events. The event will include a pointer to the pci device, the device node and some state info. Receivers of the event can "do as they wish"; the default handler will be described further in this @@ -162,10 +162,13 @@ section. To assist in the recovery of the device, eeh.c exports the following functions: -rtas_set_slot_reset() -- assert the PCI #RST line for 1/8th of a second -rtas_configure_bridge() -- ask firmware to configure any PCI bridges +rtas_set_slot_reset() + assert the PCI #RST line for 1/8th of a second +rtas_configure_bridge() + ask firmware to configure any PCI bridges located topologically under the pci slot. -eeh_save_bars() and eeh_restore_bars(): save and restore the PCI +eeh_save_bars() and eeh_restore_bars(): + save and restore the PCI config-space info for a device and any devices under it. @@ -191,7 +194,7 @@ events get delivered to user-space scripts. Following is an example sequence of events that cause a device driver close function to be called during the first phase of an EEH reset. -The following sequence is an example of the pcnet32 device driver. +The following sequence is an example of the pcnet32 device driver:: rpa_php_unconfig_pci_adapter (struct slot *) // in rpaphp_pci.c { @@ -241,53 +244,54 @@ The following sequence is an example of the pcnet32 device driver. }}}}}} - in drivers/pci/pci_driver.c, - struct device_driver->remove() is just pci_device_remove() - which calls struct pci_driver->remove() which is pcnet32_remove_one() - which calls unregister_netdev() (in net/core/dev.c) - which calls dev_close() (in net/core/dev.c) - which calls dev->stop() which is pcnet32_close() - which then does the appropriate shutdown. +in drivers/pci/pci_driver.c, +struct device_driver->remove() is just pci_device_remove() +which calls struct pci_driver->remove() which is pcnet32_remove_one() +which calls unregister_netdev() (in net/core/dev.c) +which calls dev_close() (in net/core/dev.c) +which calls dev->stop() which is pcnet32_close() +which then does the appropriate shutdown. --- + Following is the analogous stack trace for events sent to user-space -when the pci device is unconfigured. +when the pci device is unconfigured:: -rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c - calls - pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c + rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c calls - pci_destroy_dev (struct pci_dev *) { + pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c calls - device_unregister (&dev->dev) { // in /drivers/base/core.c + pci_destroy_dev (struct pci_dev *) { calls - device_del(struct device * dev) { // in /drivers/base/core.c + device_unregister (&dev->dev) { // in /drivers/base/core.c calls - kobject_del() { //in /libs/kobject.c + device_del(struct device * dev) { // in /drivers/base/core.c calls - kobject_uevent() { // in /libs/kobject.c + kobject_del() { //in /libs/kobject.c calls - kset_uevent() { // in /lib/kobject.c + kobject_uevent() { // in /libs/kobject.c calls - kset->uevent_ops->uevent() // which is really just - a call to - dev_uevent() { // in /drivers/base/core.c + kset_uevent() { // in /lib/kobject.c calls - dev->bus->uevent() which is really just a call to - pci_uevent () { // in drivers/pci/hotplug.c - which prints device name, etc.... + kset->uevent_ops->uevent() // which is really just + a call to + dev_uevent() { // in /drivers/base/core.c + calls + dev->bus->uevent() which is really just a call to + pci_uevent () { // in drivers/pci/hotplug.c + which prints device name, etc.... + } } - } - then kobject_uevent() sends a netlink uevent to userspace - --> userspace uevent - (during early boot, nobody listens to netlink events and - kobject_uevent() executes uevent_helper[], which runs the - event process /sbin/hotplug) + then kobject_uevent() sends a netlink uevent to userspace + --> userspace uevent + (during early boot, nobody listens to netlink events and + kobject_uevent() executes uevent_helper[], which runs the + event process /sbin/hotplug) + } } - } - kobject_del() then calls sysfs_remove_dir(), which would - trigger any user-space daemon that was watching /sysfs, - and notice the delete event. + kobject_del() then calls sysfs_remove_dir(), which would + trigger any user-space daemon that was watching /sysfs, + and notice the delete event. Pro's and Con's of the Current Design @@ -299,12 +303,12 @@ individual device drivers, so that the current design throws a wide net. The biggest negative of the design is that it potentially disturbs network daemons and file systems that didn't need to be disturbed. --- A minor complaint is that resetting the network card causes +- A minor complaint is that resetting the network card causes user-space back-to-back ifdown/ifup burps that potentially disturb network daemons, that didn't need to even know that the pci card was being rebooted. --- A more serious concern is that the same reset, for SCSI devices, +- A more serious concern is that the same reset, for SCSI devices, causes havoc to mounted file systems. Scripts cannot post-facto unmount a file system without flushing pending buffers, but this is impossible, because I/O has already been stopped. Thus, @@ -322,7 +326,7 @@ network daemons and file systems that didn't need to be disturbed. from the block layer. It would be very natural to add an EEH reset into this chain of events. --- If a SCSI error occurs for the root device, all is lost unless +- If a SCSI error occurs for the root device, all is lost unless the sysadmin had the foresight to run /bin, /sbin, /etc, /var and so on, out of ramdisk/tmpfs. @@ -330,5 +334,3 @@ network daemons and file systems that didn't need to be disturbed. Conclusions ----------- There's forward progress ... - - diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.rst index 10e7f4d16c14..9ca12830a48e 100644 --- a/Documentation/powerpc/firmware-assisted-dump.txt +++ b/Documentation/powerpc/firmware-assisted-dump.rst @@ -1,7 +1,8 @@ +====================== +Firmware-Assisted Dump +====================== - Firmware-Assisted Dump - ------------------------ - July 2011 +July 2011 The goal of firmware-assisted dump is to enable the dump of a crashed system, and to do so from a fully-reset system, and @@ -27,11 +28,11 @@ in production use. Comparing with kdump or other strategies, firmware-assisted dump offers several strong, practical advantages: --- Unlike kdump, the system has been reset, and loaded +- Unlike kdump, the system has been reset, and loaded with a fresh copy of the kernel. In particular, PCI and I/O devices have been reinitialized and are in a clean, consistent state. --- Once the dump is copied out, the memory that held the dump +- Once the dump is copied out, the memory that held the dump is immediately available to the running kernel. And therefore, unlike kdump, fadump doesn't need a 2nd reboot to get back the system to the production configuration. @@ -40,17 +41,18 @@ The above can only be accomplished by coordination with, and assistance from the Power firmware. The procedure is as follows: --- The first kernel registers the sections of memory with the +- The first kernel registers the sections of memory with the Power firmware for dump preservation during OS initialization. These registered sections of memory are reserved by the first kernel during early boot. --- When a system crashes, the Power firmware will save +- When a system crashes, the Power firmware will save the low memory (boot memory of size larger of 5% of system RAM or 256MB) of RAM to the previous registered region. It will also save system registers, and hardware PTE's. - NOTE: The term 'boot memory' means size of the low memory chunk + NOTE: + The term 'boot memory' means size of the low memory chunk that is required for a kernel to boot successfully when booted with restricted memory. By default, the boot memory size will be the larger of 5% of system RAM or 256MB. @@ -64,12 +66,12 @@ as follows: as fadump uses a predefined offset to reserve memory for boot memory dump preservation in case of a crash. --- After the low memory (boot memory) area has been saved, the +- After the low memory (boot memory) area has been saved, the firmware will reset PCI and other hardware state. It will *not* clear the RAM. It will then launch the bootloader, as normal. --- The freshly booted kernel will notice that there is a new +- The freshly booted kernel will notice that there is a new node (ibm,dump-kernel) in the device tree, indicating that there is crash data available from a previous boot. During the early boot OS will reserve rest of the memory above @@ -77,17 +79,18 @@ as follows: size. This will make sure that the second kernel will not touch any of the dump memory area. --- User-space tools will read /proc/vmcore to obtain the contents +- User-space tools will read /proc/vmcore to obtain the contents of memory, which holds the previous crashed kernel dump in ELF format. The userspace tools may copy this info to disk, or network, nas, san, iscsi, etc. as desired. --- Once the userspace tool is done saving dump, it will echo +- Once the userspace tool is done saving dump, it will echo '1' to /sys/kernel/fadump_release_mem to release the reserved memory back to general use, except the memory required for next firmware-assisted dump registration. - e.g. + e.g.:: + # echo 1 > /sys/kernel/fadump_release_mem Please note that the firmware-assisted dump feature @@ -95,7 +98,7 @@ is only available on Power6 and above systems with recent firmware versions. Implementation details: ----------------------- +----------------------- During boot, a check is made to see if firmware supports this feature on that particular machine. If it does, then @@ -121,7 +124,7 @@ Allocator (CMA) for memory reservation if CMA is configured for kernel. With CMA reservation this memory will be available for applications to use it, while kernel is prevented from using it. With this fadump will still be able to capture all of the kernel memory and most of the user -space memory except the user pages that were present in CMA region. +space memory except the user pages that were present in CMA region:: o Memory Reservation during first kernel @@ -166,7 +169,7 @@ The tools to examine the dump will be same as the ones used for kdump. How to enable firmware-assisted dump (fadump): -------------------------------------- +---------------------------------------------- 1. Set config option CONFIG_FA_DUMP=y and build kernel. 2. Boot into linux kernel with 'fadump=on' kernel cmdline option. @@ -177,19 +180,20 @@ How to enable firmware-assisted dump (fadump): to specify size of the memory to reserve for boot memory dump preservation. -NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead - use 'crashkernel=' to specify size of the memory to reserve - for boot memory dump preservation. - 2. If firmware-assisted dump fails to reserve memory then it - will fallback to existing kdump mechanism if 'crashkernel=' - option is set at kernel cmdline. - 3. if user wants to capture all of user space memory and ok with - reserved memory not available to production system, then - 'fadump=nocma' kernel parameter can be used to fallback to - old behaviour. +NOTE: + 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead + use 'crashkernel=' to specify size of the memory to reserve + for boot memory dump preservation. + 2. If firmware-assisted dump fails to reserve memory then it + will fallback to existing kdump mechanism if 'crashkernel=' + option is set at kernel cmdline. + 3. if user wants to capture all of user space memory and ok with + reserved memory not available to production system, then + 'fadump=nocma' kernel parameter can be used to fallback to + old behaviour. Sysfs/debugfs files: ------------- +-------------------- Firmware-assisted dump feature uses sysfs file system to hold the control files and debugfs file to display memory reserved region. @@ -197,20 +201,20 @@ the control files and debugfs file to display memory reserved region. Here is the list of files under kernel sysfs: /sys/kernel/fadump_enabled - This is used to display the fadump status. - 0 = fadump is disabled - 1 = fadump is enabled + + - 0 = fadump is disabled + - 1 = fadump is enabled This interface can be used by kdump init scripts to identify if fadump is enabled in the kernel and act accordingly. /sys/kernel/fadump_registered - This is used to display the fadump registration status as well as to control (start/stop) the fadump registration. - 0 = fadump is not registered. - 1 = fadump is registered and ready to handle system crash. + + - 0 = fadump is not registered. + - 1 = fadump is registered and ready to handle system crash. To register fadump echo 1 > /sys/kernel/fadump_registered and echo 0 > /sys/kernel/fadump_registered for un-register and stop the @@ -219,13 +223,12 @@ Here is the list of files under kernel sysfs: easily integrated with kdump service start/stop. /sys/kernel/fadump_release_mem - This file is available only when fadump is active during second kernel. This is used to release the reserved memory region that are held for saving crash dump. To release the - reserved memory echo 1 to it: + reserved memory echo 1 to it:: - echo 1 > /sys/kernel/fadump_release_mem + echo 1 > /sys/kernel/fadump_release_mem After echo 1, the content of the /sys/kernel/debug/powerpc/fadump_region file will change to reflect the new memory reservations. @@ -238,38 +241,39 @@ Here is the list of files under powerpc debugfs: (Assuming debugfs is mounted on /sys/kernel/debug directory.) /sys/kernel/debug/powerpc/fadump_region - This file shows the reserved memory regions if fadump is enabled otherwise this file is empty. The output format - is: - <region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size> + is:: + + <region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size> e.g. - Contents when fadump is registered during first kernel + Contents when fadump is registered during first kernel:: - # cat /sys/kernel/debug/powerpc/fadump_region - CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0 - HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0 - DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0 + # cat /sys/kernel/debug/powerpc/fadump_region + CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0 + HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0 + DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0 - Contents when fadump is active during second kernel + Contents when fadump is active during second kernel:: - # cat /sys/kernel/debug/powerpc/fadump_region - CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020 - HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000 - DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000 - : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000 + # cat /sys/kernel/debug/powerpc/fadump_region + CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020 + HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000 + DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000 + : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000 -NOTE: Please refer to Documentation/filesystems/debugfs.txt on +NOTE: + Please refer to Documentation/filesystems/debugfs.txt on how to mount the debugfs filesystem. TODO: ----- - o Need to come up with the better approach to find out more + - Need to come up with the better approach to find out more accurate boot memory size that is required for a kernel to boot successfully when booted with restricted memory. - o The fadump implementation introduces a fadump crash info structure + - The fadump implementation introduces a fadump crash info structure in the scratch area before the ELF core header. The idea of introducing this structure is to pass some important crash info data to the second kernel which will help second kernel to populate ELF core header with @@ -277,7 +281,9 @@ TODO: design implementation does not address a possibility of introducing additional fields (in future) to this structure without affecting compatibility. Need to come up with the better approach to address this. + The possible approaches are: + 1. Introduce version field for version tracking, bump up the version whenever a new field is added to the structure in future. The version field can be used to find out what fields are valid for the current @@ -285,8 +291,11 @@ TODO: 2. Reserve the area of predefined size (say PAGE_SIZE) for this structure and have unused area as reserved (initialized to zero) for future field additions. + The advantage of approach 1 over 2 is we don't need to reserve extra space. ---- + Author: Mahesh Salgaonkar <[email protected]> + This document is based on the original documentation written for phyp + assisted dump by Linas Vepstas and Manish Ahuja. diff --git a/Documentation/powerpc/hvcs.txt b/Documentation/powerpc/hvcs.rst index a730ca5a07f8..6808acde672f 100644 --- a/Documentation/powerpc/hvcs.txt +++ b/Documentation/powerpc/hvcs.rst @@ -1,19 +1,22 @@ -=========================================================================== - HVCS - IBM "Hypervisor Virtual Console Server" Installation Guide - for Linux Kernel 2.6.4+ - Copyright (C) 2004 IBM Corporation +=============================================================== +HVCS IBM "Hypervisor Virtual Console Server" Installation Guide +=============================================================== -=========================================================================== -NOTE:Eight space tabs are the optimum editor setting for reading this file. -=========================================================================== +for Linux Kernel 2.6.4+ - Author(s) : Ryan S. Arnold <[email protected]> - Date Created: March, 02, 2004 - Last Changed: August, 24, 2004 +Copyright (C) 2004 IBM Corporation ---------------------------------------------------------------------------- -Table of contents: +.. =========================================================================== +.. NOTE:Eight space tabs are the optimum editor setting for reading this file. +.. =========================================================================== + + +Author(s): Ryan S. Arnold <[email protected]> + +Date Created: March, 02, 2004 +Last Changed: August, 24, 2004 + +.. Table of contents: 1. Driver Introduction: 2. System Requirements @@ -27,8 +30,8 @@ Table of contents: 8. Questions & Answers: 9. Reporting Bugs: ---------------------------------------------------------------------------- 1. Driver Introduction: +======================= This is the device driver for the IBM Hypervisor Virtual Console Server, "hvcs". The IBM hvcs provides a tty driver interface to allow Linux user @@ -38,8 +41,8 @@ ppc64 system. Physical hardware consoles per partition are not practical on this hardware so system consoles are accessed by this driver using firmware interfaces to virtual terminal devices. ---------------------------------------------------------------------------- 2. System Requirements: +======================= This device driver was written using 2.6.4 Linux kernel APIs and will only build and run on kernels of this version or later. @@ -52,8 +55,8 @@ Sysfs must be mounted on the system so that the user can determine which major and minor numbers are associated with each vty-server. Directions for sysfs mounting are outside the scope of this document. ---------------------------------------------------------------------------- 3. Build Options: +================= The hvcs driver registers itself as a tty driver. The tty layer dynamically allocates a block of major and minor numbers in a quantity @@ -65,11 +68,11 @@ If the default number of device entries is adequate then this driver can be built into the kernel. If not, the default can be over-ridden by inserting the driver as a module with insmod parameters. ---------------------------------------------------------------------------- 3.1 Built-in: +------------- The following menuconfig example demonstrates selecting to build this -driver into the kernel. +driver into the kernel:: Device Drivers ---> Character devices ---> @@ -77,11 +80,11 @@ driver into the kernel. Begin the kernel make process. ---------------------------------------------------------------------------- 3.2 Module: +----------- The following menuconfig example demonstrates selecting to build this -driver as a kernel module. +driver as a kernel module:: Device Drivers ---> Character devices ---> @@ -89,11 +92,11 @@ driver as a kernel module. The make process will build the following kernel modules: - hvcs.ko - hvcserver.ko + - hvcs.ko + - hvcserver.ko To insert the module with the default allocation execute the following -commands in the order they appear: +commands in the order they appear:: insmod hvcserver.ko insmod hvcs.ko @@ -103,7 +106,7 @@ be inserted first, otherwise the hvcs module will not find some of the symbols it expects. To override the default use an insmod parameter as follows (requesting 4 -tty devices as an example): +tty devices as an example):: insmod hvcs.ko hvcs_parm_num_devs=4 @@ -115,31 +118,31 @@ source file before building. NOTE: The length of time it takes to insmod the driver seems to be related to the number of tty interfaces the registering driver requests. -In order to remove the driver module execute the following command: +In order to remove the driver module execute the following command:: rmmod hvcs.ko The recommended method for installing hvcs as a module is to use depmod to build a current modules.dep file in /lib/modules/`uname -r` and then -execute: +execute:: -modprobe hvcs hvcs_parm_num_devs=4 + modprobe hvcs hvcs_parm_num_devs=4 The modules.dep file indicates that hvcserver.ko needs to be inserted before hvcs.ko and modprobe uses this file to smartly insert the modules in the proper order. The following modprobe command is used to remove hvcs and hvcserver in the -proper order: +proper order:: -modprobe -r hvcs + modprobe -r hvcs ---------------------------------------------------------------------------- 4. Installation: +================ The tty layer creates sysfs entries which contain the major and minor numbers allocated for the hvcs driver. The following snippet of "tree" -output of the sysfs directory shows where these numbers are presented: +output of the sysfs directory shows where these numbers are presented:: sys/ |-- *other sysfs base dirs* @@ -164,7 +167,7 @@ output of the sysfs directory shows where these numbers are presented: |-- *other sysfs base dirs* For the above examples the following output is a result of cat'ing the -"dev" entry in the hvcs directory: +"dev" entry in the hvcs directory:: Pow5:/sys/class/tty/hvcs0/ # cat dev 254:0 @@ -184,7 +187,7 @@ systems running hvcs will already have the device entries created or udev will do it automatically. Given the example output above, to manually create a /dev/hvcs* node entry -mknod can be used as follows: +mknod can be used as follows:: mknod /dev/hvcs0 c 254 0 mknod /dev/hvcs1 c 254 1 @@ -195,15 +198,15 @@ Using mknod to manually create the device entries makes these device nodes persistent. Once created they will exist prior to the driver insmod. Attempting to connect an application to /dev/hvcs* prior to insertion of -the hvcs module will result in an error message similar to the following: +the hvcs module will result in an error message similar to the following:: "/dev/hvcs*: No such device". NOTE: Just because there is a device node present doesn't mean that there is a vty-server device configured for that node. ---------------------------------------------------------------------------- 5. Connection +============= Since this driver controls devices that provide a tty interface a user can interact with the device node entries using any standard tty-interactive @@ -249,7 +252,7 @@ vty-server adapter is associated with which /dev/hvcs* node a special sysfs attribute has been added to each vty-server sysfs entry. This entry is called "index" and showing it reveals an integer that refers to the /dev/hvcs* entry to use to connect to that device. For instance cating the -index attribute of vty-server adapter 30000004 shows the following. +index attribute of vty-server adapter 30000004 shows the following:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat index 2 @@ -262,8 +265,8 @@ system the /dev/hvcs* entry that interacts with a particular vty-server adapter is not guaranteed to remain the same across system reboots. Look in the Q & A section for more on this issue. ---------------------------------------------------------------------------- 6. Disconnection +================ As a security feature to prevent the delivery of stale data to an unintended target the Power5 system firmware disables the fetching of data @@ -305,7 +308,7 @@ connection between the vty-server and target vty ONLY if the vterm_state previously read '1'. The write directive is ignored if the vterm_state read '0' or if any value other than '0' was written to the vterm_state attribute. The following example will show the method used for verifying -the vty-server connection status and disconnecting a vty-server connection. +the vty-server connection status and disconnecting a vty-server connection:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state 1 @@ -318,12 +321,12 @@ the vty-server connection status and disconnecting a vty-server connection. All vty-server connections are automatically terminated when the device is hotplug removed and when the module is removed. ---------------------------------------------------------------------------- 7. Configuration +================ Each vty-server has a sysfs entry in the /sys/devices/vio directory, which is symlinked in several other sysfs tree directories, notably under the -hvcs driver entry, which looks like the following example: +hvcs driver entry, which looks like the following example:: Pow5:/sys/bus/vio/drivers/hvcs # ls . .. 30000003 30000004 rescan @@ -344,7 +347,7 @@ completed or was never executed. Vty-server entries in this directory are a 32 bit partition unique unit address that is created by firmware. An example vty-server sysfs entry -looks like the following: +looks like the following:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # ls . current_vty devspec name partner_vtys @@ -352,21 +355,21 @@ looks like the following: Each entry is provided, by default with a "name" attribute. Reading the "name" attribute will reveal the device type as shown in the following -example: +example:: Pow5:/sys/bus/vio/drivers/hvcs/30000003 # cat name vty-server Each entry is also provided, by default, with a "devspec" attribute which reveals the full device specification when read, as shown in the following -example: +example:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat devspec /vdevice/vty-server@30000004 Each vty-server sysfs dir is provided with two read-only attributes that provide lists of easily parsed partner vty data: "partner_vtys" and -"partner_clcs". +"partner_clcs":: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_vtys 30000000 @@ -396,7 +399,7 @@ A vty-server can only be connected to a single vty at a time. The entry, read. The current_vty can be changed by writing a valid partner clc to the entry -as in the following example: +as in the following example:: Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo U5112.428.10304 8A-V4-C0 > current_vty @@ -408,9 +411,9 @@ currently open connection is freed. Information on the "vterm_state" attribute was covered earlier on the chapter entitled "disconnection". ---------------------------------------------------------------------------- 8. Questions & Answers: -=========================================================================== +======================= + Q: What are the security concerns involving hvcs? A: There are three main security concerns: @@ -429,6 +432,7 @@ A: There are three main security concerns: partition) will experience the previously logged in session. --------------------------------------------------------------------------- + Q: How do I multiplex a console that I grab through hvcs so that other people can see it: @@ -440,6 +444,7 @@ term type "screen" to others. This means that curses based programs may not display properly in screen sessions. --------------------------------------------------------------------------- + Q: Why are the colors all messed up? Q: Why are the control characters acting strange or not working? Q: Why is the console output all strange and unintelligible? @@ -455,6 +460,7 @@ disconnect from the console. This will ensure that the next user gets their own TERM type set when they login. --------------------------------------------------------------------------- + Q: When I try to CONNECT kermit to an hvcs device I get: "Sorry, can't open connection: /dev/hvcs*"What is happening? @@ -490,6 +496,7 @@ A: There is not a corresponding vty-server device that maps to an existing /dev/hvcs* entry. --------------------------------------------------------------------------- + Q: When I try to CONNECT kermit to an hvcs device I get: "Sorry, write access to UUCP lockfile directory denied." @@ -497,6 +504,7 @@ A: The /dev/hvcs* entry you have specified doesn't exist where you said it does? Maybe you haven't inserted the module (on systems with udev). --------------------------------------------------------------------------- + Q: If I already have one Linux partition installed can I use hvcs on said partition to provide the console for the install of a second Linux partition? @@ -505,6 +513,7 @@ A: Yes granted that your are connected to the /dev/hvcs* device using kermit or cu or some other program that doesn't provide terminal emulation. --------------------------------------------------------------------------- + Q: Can I connect to more than one partition's console at a time using this driver? @@ -512,6 +521,7 @@ A: Yes. Of course this means that there must be more than one vty-server configured for this partition and each must point to a disconnected vty. --------------------------------------------------------------------------- + Q: Does the hvcs driver support dynamic (hotplug) addition of devices? A: Yes, if you have dlpar and hotplug enabled for your system and it has @@ -519,6 +529,7 @@ been built into the kernel the hvcs drivers is configured to dynamically handle additions of new devices and removals of unused devices. --------------------------------------------------------------------------- + Q: For some reason /dev/hvcs* doesn't map to the same vty-server adapter after a reboot. What happened? @@ -533,6 +544,7 @@ on how to determine which vty-server goes with which /dev/hvcs* node. Hint; look at the sysfs "index" attribute for the vty-server. --------------------------------------------------------------------------- + Q: Can I use /dev/hvcs* as a conduit to another partition and use a tty device on that partition as the other end of the pipe? @@ -554,7 +566,9 @@ read or write to /dev/hvcs*. Now you have a tty conduit between two partitions. --------------------------------------------------------------------------- + 9. Reporting Bugs: +================== The proper channel for reporting bugs is either through the Linux OS distribution company that provided your OS or by posting issues to the diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst new file mode 100644 index 000000000000..549b1cdd77ae --- /dev/null +++ b/Documentation/powerpc/index.rst @@ -0,0 +1,34 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======= +powerpc +======= + +.. toctree:: + :maxdepth: 1 + + bootwrapper + cpu_families + cpu_features + cxl + cxlflash + dawr-power9 + dscr + eeh-pci-error-recovery + firmware-assisted-dump + hvcs + isa-versions + mpc52xx + pci_iov_resource_on_powernv + pmu-ebb + ptrace + qe_firmware + syscall64-abi + transactional_memory + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/powerpc/isa-versions.rst b/Documentation/powerpc/isa-versions.rst index 66c24140ebf1..a363d8c1603c 100644 --- a/Documentation/powerpc/isa-versions.rst +++ b/Documentation/powerpc/isa-versions.rst @@ -1,13 +1,12 @@ -:orphan: - +========================== CPU to ISA Version Mapping ========================== Mapping of some CPU versions to relevant ISA versions. -========= ==================== +========= ==================================================================== CPU Architecture version -========= ==================== +========= ==================================================================== Power9 Power ISA v3.0B Power8 Power ISA v2.07 Power7 Power ISA v2.06 @@ -24,7 +23,7 @@ PPC970 - PowerPC User Instruction Set Architecture Book I v2.01 - PowerPC Virtual Environment Architecture Book II v2.01 - PowerPC Operating Environment Architecture Book III v2.01 - Plus Altivec/VMX ~= 2.03 -========= ==================== +========= ==================================================================== Key Features @@ -60,9 +59,9 @@ Power5 No PPC970 No ========== ==== -========== ==================== +========== ==================================== CPU Transactional Memory -========== ==================== +========== ==================================== Power9 Yes (* see transactional_memory.txt) Power8 Yes Power7 No @@ -73,4 +72,4 @@ Power5++ No Power5+ No Power5 No PPC970 No -========== ==================== +========== ==================================== diff --git a/Documentation/powerpc/mpc52xx.txt b/Documentation/powerpc/mpc52xx.rst index 0d540a31ea1a..8676ac63e077 100644 --- a/Documentation/powerpc/mpc52xx.txt +++ b/Documentation/powerpc/mpc52xx.rst @@ -1,11 +1,13 @@ +============================= Linux 2.6.x on MPC52xx family ------------------------------ +============================= For the latest info, go to http://www.246tNt.com/mpc52xx/ To compile/use : - - U-Boot: + - U-Boot:: + # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION if you wish to ). # make lite5200_defconfig @@ -16,7 +18,8 @@ To compile/use : => tftpboot 400000 pRamdisk => bootm 200000 400000 - - DBug: + - DBug:: + # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION if you wish to ). # make lite5200_defconfig @@ -28,7 +31,8 @@ To compile/use : DBug> dn -i zImage.initrd.lite5200 -Some remarks : +Some remarks: + - The port is named mpc52xxx, and config options are PPC_MPC52xx. The MGT5100 is not supported, and I'm not sure anyone is interesting in working on it so. I didn't took 5xxx because there's apparently a lot of 5xxx that have diff --git a/Documentation/powerpc/pci_iov_resource_on_powernv.txt b/Documentation/powerpc/pci_iov_resource_on_powernv.rst index b55c5cd83f8d..f5a5793e1613 100644 --- a/Documentation/powerpc/pci_iov_resource_on_powernv.txt +++ b/Documentation/powerpc/pci_iov_resource_on_powernv.rst @@ -1,6 +1,13 @@ +=================================================== +PCI Express I/O Virtualization Resource on Powerenv +=================================================== + Wei Yang <[email protected]> + Benjamin Herrenschmidt <[email protected]> + Bjorn Helgaas <[email protected]> + 26 Aug 2014 This document describes the requirement from hardware for PCI MMIO resource @@ -10,6 +17,7 @@ Endpoints and the implementation on P8 (IODA2). The next two sections talks about considerations on enabling SRIOV on IODA2. 1. Introduction to Partitionable Endpoints +========================================== A Partitionable Endpoint (PE) is a way to group the various resources associated with a device or a set of devices to provide isolation between @@ -35,6 +43,7 @@ is a completely separate HW entity that replicates the entire logic, so has its own set of PEs, etc. 2. Implementation of Partitionable Endpoints on P8 (IODA2) +========================================================== P8 supports up to 256 Partitionable Endpoints per PHB. @@ -149,6 +158,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. sense, but we haven't done it yet. 3. Considerations for SR-IOV on PowerKVM +======================================== * SR-IOV Background @@ -224,7 +234,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. IODA supports 256 PEs, so segmented windows contain 256 segments, so if total_VFs is less than 256, we have the situation in Figure 1.0, where segments [total_VFs, 255] of the M64 window may map to some MMIO range on - other devices: + other devices:: 0 1 total_VFs - 1 +------+------+- -+------+------+ @@ -243,7 +253,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. Figure 1.0 Direct map VF(n) BAR space Our current solution is to allocate 256 segments even if the VF(n) BAR - space doesn't need that much, as shown in Figure 1.1: + space doesn't need that much, as shown in Figure 1.1:: 0 1 total_VFs - 1 255 +------+------+- -+------+------+- -+------+------+ @@ -269,6 +279,7 @@ P8 supports up to 256 Partitionable Endpoints per PHB. responds to segments [total_VFs, 255]. 4. Implications for the Generic PCI Code +======================================== The PCIe SR-IOV spec requires that the base of the VF(n) BAR space be aligned to the size of an individual VF BAR. diff --git a/Documentation/powerpc/pmu-ebb.txt b/Documentation/powerpc/pmu-ebb.rst index 73cd163dbfb8..4f474758eb55 100644 --- a/Documentation/powerpc/pmu-ebb.txt +++ b/Documentation/powerpc/pmu-ebb.rst @@ -1,3 +1,4 @@ +======================== PMU Event Based Branches ======================== diff --git a/Documentation/powerpc/ptrace.rst b/Documentation/powerpc/ptrace.rst new file mode 100644 index 000000000000..864d4b6dddd1 --- /dev/null +++ b/Documentation/powerpc/ptrace.rst @@ -0,0 +1,156 @@ +====== +Ptrace +====== + +GDB intends to support the following hardware debug features of BookE +processors: + +4 hardware breakpoints (IAC) +2 hardware watchpoints (read, write and read-write) (DAC) +2 value conditions for the hardware watchpoints (DVC) + +For that, we need to extend ptrace so that GDB can query and set these +resources. Since we're extending, we're trying to create an interface +that's extendable and that covers both BookE and server processors, so +that GDB doesn't need to special-case each of them. We added the +following 3 new ptrace requests. + +1. PTRACE_PPC_GETHWDEBUGINFO +============================ + +Query for GDB to discover the hardware debug features. The main info to +be returned here is the minimum alignment for the hardware watchpoints. +BookE processors don't have restrictions here, but server processors have +an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid +adding special cases to GDB based on what it sees in AUXV. + +Since we're at it, we added other useful info that the kernel can return to +GDB: this query will return the number of hardware breakpoints, hardware +watchpoints and whether it supports a range of addresses and a condition. +The query will fill the following structure provided by the requesting process:: + + struct ppc_debug_info { + unit32_t version; + unit32_t num_instruction_bps; + unit32_t num_data_bps; + unit32_t num_condition_regs; + unit32_t data_bp_alignment; + unit32_t sizeof_condition; /* size of the DVC register */ + uint64_t features; /* bitmask of the individual flags */ + }; + +features will have bits indicating whether there is support for:: + + #define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1 + #define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2 + #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4 + #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8 + #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10 + +2. PTRACE_SETHWDEBUG + +Sets a hardware breakpoint or watchpoint, according to the provided structure:: + + struct ppc_hw_breakpoint { + uint32_t version; + #define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1 + #define PPC_BREAKPOINT_TRIGGER_READ 0x2 + #define PPC_BREAKPOINT_TRIGGER_WRITE 0x4 + uint32_t trigger_type; /* only some combinations allowed */ + #define PPC_BREAKPOINT_MODE_EXACT 0x0 + #define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1 + #define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2 + #define PPC_BREAKPOINT_MODE_MASK 0x3 + uint32_t addr_mode; /* address match mode */ + + #define PPC_BREAKPOINT_CONDITION_MODE 0x3 + #define PPC_BREAKPOINT_CONDITION_NONE 0x0 + #define PPC_BREAKPOINT_CONDITION_AND 0x1 + #define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */ + #define PPC_BREAKPOINT_CONDITION_OR 0x2 + #define PPC_BREAKPOINT_CONDITION_AND_OR 0x3 + #define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */ + #define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16)) + uint32_t condition_mode; /* break/watchpoint condition flags */ + + uint64_t addr; + uint64_t addr2; + uint64_t condition_value; + }; + +A request specifies one event, not necessarily just one register to be set. +For instance, if the request is for a watchpoint with a condition, both the +DAC and DVC registers will be set in the same request. + +With this GDB can ask for all kinds of hardware breakpoints and watchpoints +that the BookE supports. COMEFROM breakpoints available in server processors +are not contemplated, but that is out of the scope of this work. + +ptrace will return an integer (handle) uniquely identifying the breakpoint or +watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG +request to ask for its removal. Return -ENOSPC if the requested breakpoint +can't be allocated on the registers. + +Some examples of using the structure to: + +- set a breakpoint in the first breakpoint register:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = 0; + +- set a watchpoint which triggers on reads in the second watchpoint register:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = 0; + +- set a watchpoint which triggers only with a specific value:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL; + p.addr = (uint64_t) address; + p.addr2 = 0; + p.condition_value = (uint64_t) condition; + +- set a ranged hardware breakpoint:: + + p.version = PPC_DEBUG_CURRENT_VERSION; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; + p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) begin_range; + p.addr2 = (uint64_t) end_range; + p.condition_value = 0; + +- set a watchpoint in server processors (BookS):: + + p.version = 1; + p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; + p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; + or + p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; + + p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; + p.addr = (uint64_t) begin_range; + /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where + * addr2 - addr <= 8 Bytes. + */ + p.addr2 = (uint64_t) end_range; + p.condition_value = 0; + +3. PTRACE_DELHWDEBUG + +Takes an integer which identifies an existing breakpoint or watchpoint +(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the +corresponding breakpoint or watchpoint.. diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt deleted file mode 100644 index 99c5ce88d0fe..000000000000 --- a/Documentation/powerpc/ptrace.txt +++ /dev/null @@ -1,151 +0,0 @@ -GDB intends to support the following hardware debug features of BookE -processors: - -4 hardware breakpoints (IAC) -2 hardware watchpoints (read, write and read-write) (DAC) -2 value conditions for the hardware watchpoints (DVC) - -For that, we need to extend ptrace so that GDB can query and set these -resources. Since we're extending, we're trying to create an interface -that's extendable and that covers both BookE and server processors, so -that GDB doesn't need to special-case each of them. We added the -following 3 new ptrace requests. - -1. PTRACE_PPC_GETHWDEBUGINFO - -Query for GDB to discover the hardware debug features. The main info to -be returned here is the minimum alignment for the hardware watchpoints. -BookE processors don't have restrictions here, but server processors have -an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid -adding special cases to GDB based on what it sees in AUXV. - -Since we're at it, we added other useful info that the kernel can return to -GDB: this query will return the number of hardware breakpoints, hardware -watchpoints and whether it supports a range of addresses and a condition. -The query will fill the following structure provided by the requesting process: - -struct ppc_debug_info { - unit32_t version; - unit32_t num_instruction_bps; - unit32_t num_data_bps; - unit32_t num_condition_regs; - unit32_t data_bp_alignment; - unit32_t sizeof_condition; /* size of the DVC register */ - uint64_t features; /* bitmask of the individual flags */ -}; - -features will have bits indicating whether there is support for: - -#define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1 -#define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2 -#define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4 -#define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8 -#define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10 - -2. PTRACE_SETHWDEBUG - -Sets a hardware breakpoint or watchpoint, according to the provided structure: - -struct ppc_hw_breakpoint { - uint32_t version; -#define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1 -#define PPC_BREAKPOINT_TRIGGER_READ 0x2 -#define PPC_BREAKPOINT_TRIGGER_WRITE 0x4 - uint32_t trigger_type; /* only some combinations allowed */ -#define PPC_BREAKPOINT_MODE_EXACT 0x0 -#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1 -#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2 -#define PPC_BREAKPOINT_MODE_MASK 0x3 - uint32_t addr_mode; /* address match mode */ - -#define PPC_BREAKPOINT_CONDITION_MODE 0x3 -#define PPC_BREAKPOINT_CONDITION_NONE 0x0 -#define PPC_BREAKPOINT_CONDITION_AND 0x1 -#define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */ -#define PPC_BREAKPOINT_CONDITION_OR 0x2 -#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3 -#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */ -#define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16)) - uint32_t condition_mode; /* break/watchpoint condition flags */ - - uint64_t addr; - uint64_t addr2; - uint64_t condition_value; -}; - -A request specifies one event, not necessarily just one register to be set. -For instance, if the request is for a watchpoint with a condition, both the -DAC and DVC registers will be set in the same request. - -With this GDB can ask for all kinds of hardware breakpoints and watchpoints -that the BookE supports. COMEFROM breakpoints available in server processors -are not contemplated, but that is out of the scope of this work. - -ptrace will return an integer (handle) uniquely identifying the breakpoint or -watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG -request to ask for its removal. Return -ENOSPC if the requested breakpoint -can't be allocated on the registers. - -Some examples of using the structure to: - -- set a breakpoint in the first breakpoint register - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = 0; - -- set a watchpoint which triggers on reads in the second watchpoint register - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = 0; - -- set a watchpoint which triggers only with a specific value - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ; - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL; - p.addr = (uint64_t) address; - p.addr2 = 0; - p.condition_value = (uint64_t) condition; - -- set a ranged hardware breakpoint - - p.version = PPC_DEBUG_CURRENT_VERSION; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE; - p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) begin_range; - p.addr2 = (uint64_t) end_range; - p.condition_value = 0; - -- set a watchpoint in server processors (BookS) - - p.version = 1; - p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW; - p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE; - or - p.addr_mode = PPC_BREAKPOINT_MODE_EXACT; - - p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE; - p.addr = (uint64_t) begin_range; - /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where - * addr2 - addr <= 8 Bytes. - */ - p.addr2 = (uint64_t) end_range; - p.condition_value = 0; - -3. PTRACE_DELHWDEBUG - -Takes an integer which identifies an existing breakpoint or watchpoint -(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the -corresponding breakpoint or watchpoint.. diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.rst index e7ac24aec4ff..42f5103140c9 100644 --- a/Documentation/powerpc/qe_firmware.txt +++ b/Documentation/powerpc/qe_firmware.rst @@ -1,23 +1,23 @@ - Freescale QUICC Engine Firmware Uploading - ----------------------------------------- +========================================= +Freescale QUICC Engine Firmware Uploading +========================================= (c) 2007 Timur Tabi <timur at freescale.com>, Freescale Semiconductor -Table of Contents -================= +.. Table of Contents - I - Software License for Firmware + I - Software License for Firmware - II - Microcode Availability + II - Microcode Availability - III - Description and Terminology + III - Description and Terminology - IV - Microcode Programming Details + IV - Microcode Programming Details - V - Firmware Structure Layout + V - Firmware Structure Layout - VI - Sample Code for Creating Firmware Files + VI - Sample Code for Creating Firmware Files Revision Information ==================== @@ -39,7 +39,7 @@ http://opensource.freescale.com. For other firmware files, please contact your Freescale representative or your operating system vendor. III - Description and Terminology -================================ +================================= In this document, the term 'microcode' refers to the sequence of 32-bit integers that compose the actual QE microcode. @@ -89,7 +89,7 @@ being fixed in the RAM package utilizing they should be activated. This data structure signals the microcode which of these virtual traps is active. This structure contains 6 words that the application should copy to some -specific been defined. This table describes the structure. +specific been defined. This table describes the structure:: --------------------------------------------------------------- | Offset in | | Destination Offset | Size of | @@ -119,7 +119,7 @@ Extended Modes This is a double word bit array (64 bits) that defines special functionality which has an impact on the software drivers. Each bit has its own impact and has special instructions for the s/w associated with it. This structure is -described in this table: +described in this table:: ----------------------------------------------------------------------- | Bit # | Name | Description | @@ -220,7 +220,8 @@ The 'model' field is a 16-bit number that matches the actual SOC. The 'major' and 'minor' fields are the major and minor revision numbers, respectively, of the SOC. -For example, to match the 8323, revision 1.0: +For example, to match the 8323, revision 1.0:: + soc.model = 8323 soc.major = 1 soc.minor = 0 @@ -273,10 +274,10 @@ library and available to any driver that calles qe_get_firmware_info(). 'reserved'. After the last microcode is a 32-bit CRC. It can be calculated using -this algorithm: +this algorithm:: -u32 crc32(const u8 *p, unsigned int len) -{ + u32 crc32(const u8 *p, unsigned int len) + { unsigned int i; u32 crc = 0; @@ -286,7 +287,7 @@ u32 crc32(const u8 *p, unsigned int len) crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0); } return crc; -} + } VI - Sample Code for Creating Firmware Files ============================================ diff --git a/Documentation/powerpc/syscall64-abi.txt b/Documentation/powerpc/syscall64-abi.rst index fa716a0d88bd..e49f69f941b9 100644 --- a/Documentation/powerpc/syscall64-abi.txt +++ b/Documentation/powerpc/syscall64-abi.rst @@ -5,12 +5,12 @@ Power Architecture 64-bit Linux system call ABI syscall ======= -syscall calling sequence[*] matches the Power Architecture 64-bit ELF ABI +syscall calling sequence\ [1]_ matches the Power Architecture 64-bit ELF ABI specification C function calling sequence, including register preservation rules, with the following differences. -[*] Some syscalls (typically low-level management functions) may have - different calling sequences (e.g., rt_sigreturn). +.. [1] Some syscalls (typically low-level management functions) may have + different calling sequences (e.g., rt_sigreturn). Parameters and return value --------------------------- @@ -33,12 +33,14 @@ Register preservation rules Register preservation rules match the ELF ABI calling sequence with the following differences: -r0: Volatile. (System call number.) -r3: Volatile. (Parameter 1, and return value.) -r4-r8: Volatile. (Parameters 2-6.) -cr0: Volatile (cr0.SO is the return error condition) -cr1, cr5-7: Nonvolatile. -lr: Nonvolatile. +=========== ============= ======================================== +r0 Volatile (System call number.) +r3 Volatile (Parameter 1, and return value.) +r4-r8 Volatile (Parameters 2-6.) +cr0 Volatile (cr0.SO is the return error condition) +cr1, cr5-7 Nonvolatile +lr Nonvolatile +=========== ============= ======================================== All floating point and vector data registers as well as control and status registers are nonvolatile. @@ -90,9 +92,12 @@ The vsyscall may or may not use the caller's stack frame save areas. Register preservation rules --------------------------- -r0: Volatile. -cr1, cr5-7: Volatile. -lr: Volatile. + +=========== ======== +r0 Volatile +cr1, cr5-7 Volatile +lr Volatile +=========== ======== Invocation ---------- diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.rst index 52c023e14f26..09955103acb4 100644 --- a/Documentation/powerpc/transactional_memory.txt +++ b/Documentation/powerpc/transactional_memory.rst @@ -1,3 +1,4 @@ +============================ Transactional Memory support ============================ @@ -17,29 +18,29 @@ instructions are presented to delimit transactions; transactions are guaranteed to either complete atomically or roll back and undo any partial changes. -A simple transaction looks like this: +A simple transaction looks like this:: -begin_move_money: - tbegin - beq abort_handler + begin_move_money: + tbegin + beq abort_handler - ld r4, SAVINGS_ACCT(r3) - ld r5, CURRENT_ACCT(r3) - subi r5, r5, 1 - addi r4, r4, 1 - std r4, SAVINGS_ACCT(r3) - std r5, CURRENT_ACCT(r3) + ld r4, SAVINGS_ACCT(r3) + ld r5, CURRENT_ACCT(r3) + subi r5, r5, 1 + addi r4, r4, 1 + std r4, SAVINGS_ACCT(r3) + std r5, CURRENT_ACCT(r3) - tend + tend - b continue + b continue -abort_handler: - ... test for odd failures ... + abort_handler: + ... test for odd failures ... - /* Retry the transaction if it failed because it conflicted with - * someone else: */ - b begin_move_money + /* Retry the transaction if it failed because it conflicted with + * someone else: */ + b begin_move_money The 'tbegin' instruction denotes the start point, and 'tend' the end point. @@ -123,7 +124,7 @@ Transaction-aware signal handlers can read the transactional register state from the second ucontext. This will be necessary for crash handlers to determine, for example, the address of the instruction causing the SIGSEGV. -Example signal handler: +Example signal handler:: void crash_handler(int sig, siginfo_t *si, void *uc) { @@ -133,9 +134,9 @@ Example signal handler: if (ucp_link) { u64 msr = ucp->uc_mcontext.regs->msr; /* May have transactional ucontext! */ -#ifndef __powerpc64__ + #ifndef __powerpc64__ msr |= ((u64)transactional_ucp->uc_mcontext.regs->msr) << 32; -#endif + #endif if (MSR_TM_ACTIVE(msr)) { /* Yes, we crashed during a transaction. Oops. */ fprintf(stderr, "Transaction to be restarted at 0x%llx, but " @@ -176,6 +177,7 @@ Failure cause codes used by kernel These are defined in <asm/reg.h>, and distinguish different reasons why the kernel aborted a transaction: + ====================== ================================ TM_CAUSE_RESCHED Thread was rescheduled. TM_CAUSE_TLBI Software TLB invalid. TM_CAUSE_FAC_UNAV FP/VEC/VSX unavailable trap. @@ -184,6 +186,7 @@ kernel aborted a transaction: TM_CAUSE_MISC Currently unused. TM_CAUSE_ALIGNMENT Alignment fault. TM_CAUSE_EMULATE Emulation that touched memory. + ====================== ================================ These can be checked by the user program's abort handler as TEXASR[0:7]. If bit 7 is set, it indicates that the error is consider persistent. For example @@ -203,7 +206,7 @@ POWER9 ====== TM on POWER9 has issues with storing the complete register state. This -is described in this commit: +is described in this commit:: commit 4bb3c7a0208fc13ca70598efd109901a7cd45ae7 Author: Paul Mackerras <[email protected]> diff --git a/Documentation/process/conf.py b/Documentation/process/conf.py deleted file mode 100644 index 1b01a80ad9ce..000000000000 --- a/Documentation/process/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = 'Linux Kernel Development Documentation' - -tags.add("subproject") - -latex_documents = [ - ('index', 'process.tex', 'Linux Kernel Development Documentation', - 'The kernel development community', 'manual'), -] diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 49e0f64a3427..053b24a6dd38 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -119,3 +119,17 @@ array may exceed the remaining memory in the stack segment. This could lead to a crash, possible overwriting sensitive contents at the end of the stack (when built without `CONFIG_THREAD_INFO_IN_TASK=y`), or overwriting memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`) + +Implicit switch case fall-through +--------------------------------- +The C language allows switch cases to "fall through" when +a "break" statement is missing at the end of a case. This, +however, introduces ambiguity in the code, as it's not always +clear if the missing break is intentional or a bug. As there +have been a long list of flaws `due to missing "break" statements +<https://cwe.mitre.org/data/definitions/484.html>`_, we no longer allow +"implicit fall-through". In order to identify an intentional fall-through +case, we have adopted the marking used by static analyzers: a comment +saying `/* Fall through */`. Once the C++17 `__attribute__((fallthrough))` +is more widely handled by C compilers, static analyzers, and IDEs, we can +switch to using that instead. diff --git a/Documentation/s390/vfio-ccw.rst b/Documentation/s390/vfio-ccw.rst index 1e210c6afa88..fca9c4f5bd9c 100644 --- a/Documentation/s390/vfio-ccw.rst +++ b/Documentation/s390/vfio-ccw.rst @@ -180,6 +180,13 @@ The process of how these work together. add it to an iommu_group and a vfio_group. Then we could pass through the mdev to a guest. + +VFIO-CCW Regions +---------------- + +The vfio-ccw driver exposes MMIO regions to accept requests from and return +results to userspace. + vfio-ccw I/O region ------------------- @@ -205,6 +212,25 @@ irb_area stores the I/O result. ret_code stores a return code for each access of the region. +This region is always available. + +vfio-ccw cmd region +------------------- + +The vfio-ccw cmd region is used to accept asynchronous instructions +from userspace:: + + #define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0) + #define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1) + struct ccw_cmd_region { + __u32 command; + __u32 ret_code; + } __packed; + +This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD. + +Currently, CLEAR SUBCHANNEL and HALT SUBCHANNEL use this region. + vfio-ccw operation details -------------------------- @@ -306,9 +332,8 @@ Together with the corresponding work in QEMU, we can bring the passed through DASD/ECKD device online in a guest now and use it as a block device. -While the current code allows the guest to start channel programs via -START SUBCHANNEL, support for HALT SUBCHANNEL or CLEAR SUBCHANNEL is -not yet implemented. +The current code allows the guest to start channel programs via +START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL. vfio-ccw supports classic (command mode) channel I/O only. Transport mode (HPF) is not supported. diff --git a/Documentation/sh/conf.py b/Documentation/sh/conf.py deleted file mode 100644 index 1eb684a13ac8..000000000000 --- a/Documentation/sh/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "SuperH architecture implementation manual" - -tags.add("subproject") - -latex_documents = [ - ('index', 'sh.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/sound/conf.py b/Documentation/sound/conf.py deleted file mode 100644 index 3f1fc5e74e7b..000000000000 --- a/Documentation/sound/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Sound Subsystem Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'sound.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py index 301a21aa4f63..eeb394b39e2c 100644 --- a/Documentation/sphinx/load_config.py +++ b/Documentation/sphinx/load_config.py @@ -21,6 +21,29 @@ def loadConfig(namespace): and os.path.normpath(namespace["__file__"]) != os.path.normpath(config_file) ): config_file = os.path.abspath(config_file) + # Let's avoid one conf.py file just due to latex_documents + start = config_file.find('Documentation/') + if start >= 0: + start = config_file.find('/', start + 1) + + end = config_file.rfind('/') + if start >= 0 and end > 0: + dir = config_file[start + 1:end] + + print("source directory: %s" % dir) + new_latex_docs = [] + latex_documents = namespace['latex_documents'] + + for l in latex_documents: + if l[0].find(dir + '/') == 0: + has = True + fn = l[0][len(dir) + 1:] + new_latex_docs.append((fn, l[1], l[2], l[3], l[4])) + break + + namespace['latex_documents'] = new_latex_docs + + # If there is an extra conf.py file, load it if os.path.isfile(config_file): sys.stdout.write("load additional sphinx-config: %s\n" % config_file) config = namespace.copy() @@ -29,4 +52,6 @@ def loadConfig(namespace): del config['__file__'] namespace.update(config) else: - sys.stderr.write("WARNING: additional sphinx-config not found: %s\n" % config_file) + config = namespace.copy() + config['tags'].add("subproject") + namespace.update(config) diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst index 1739cba8863e..f1ad4504b734 100644 --- a/Documentation/translations/it_IT/doc-guide/sphinx.rst +++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst @@ -242,8 +242,9 @@ del kernel: * Per inserire blocchi di testo con caratteri a dimensione fissa (codici di esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario evidenziare la sintassi, specialmente per piccoli frammenti; invece, - utilizzate ``.. code-block:: <language>`` per blocchi di più lunghi che - potranno beneficiare dell'avere la sintassi evidenziata. + utilizzate ``.. code-block:: <language>`` per blocchi più lunghi che + beneficeranno della sintassi evidenziata. Per un breve pezzo di codice da + inserire nel testo, usate \`\`. Il dominio C @@ -267,12 +268,14 @@ molto comune come ``open`` o ``ioctl``: Il nome della funzione (per esempio ioctl) rimane nel testo ma il nome del suo riferimento cambia da ``ioctl`` a ``VIDIOC_LOG_STATUS``. Anche la voce -nell'indice cambia in ``VIDIOC_LOG_STATUS`` e si potrà quindi fare riferimento -a questa funzione scrivendo: - -.. code-block:: rst - - :c:func:`VIDIOC_LOG_STATUS` +nell'indice cambia in ``VIDIOC_LOG_STATUS``. + +Notate che per una funzione non c'è bisogno di usare ``c:func:`` per generarne +i riferimenti nella documentazione. Grazie a qualche magica estensione a +Sphinx, il sistema di generazione della documentazione trasformerà +automaticamente un riferimento ad una ``funzione()`` in un riferimento +incrociato quando questa ha una voce nell'indice. Se trovate degli usi di +``c:func:`` nella documentazione del kernel, sentitevi liberi di rimuoverli. Tabelle a liste diff --git a/Documentation/translations/it_IT/process/index.rst b/Documentation/translations/it_IT/process/index.rst index 2eda85d5cd1e..012de0f3154a 100644 --- a/Documentation/translations/it_IT/process/index.rst +++ b/Documentation/translations/it_IT/process/index.rst @@ -27,6 +27,7 @@ Di seguito le guide che ogni sviluppatore dovrebbe leggere. code-of-conduct development-process submitting-patches + programming-language coding-style maintainer-pgp-guide email-clients diff --git a/Documentation/translations/it_IT/process/kernel-docs.rst b/Documentation/translations/it_IT/process/kernel-docs.rst index 7bd70d661737..38e0a955121a 100644 --- a/Documentation/translations/it_IT/process/kernel-docs.rst +++ b/Documentation/translations/it_IT/process/kernel-docs.rst @@ -1,6 +1,7 @@ .. include:: ../disclaimer-ita.rst :Original: :ref:`Documentation/process/kernel-docs.rst <kernel_docs>` +:Translator: Federico Vaga <[email protected]> .. _it_kernel_docs: @@ -8,6 +9,10 @@ Indice di documenti per le persone interessate a capire e/o scrivere per il kernel Linux ======================================================================================== -.. warning:: - - TODO ancora da tradurre +.. note:: + Questo documento contiene riferimenti a documenti in lingua inglese; inoltre + utilizza dai campi *ReStructuredText* di supporto alla ricerca e che per + questo motivo è meglio non tradurre al fine di garantirne un corretto + utilizzo. + Per questi motivi il documento non verrà tradotto. Per favore fate + riferimento al documento originale in lingua inglese. diff --git a/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst b/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst index 276db0e37f43..118fb4153e8f 100644 --- a/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst +++ b/Documentation/translations/it_IT/process/maintainer-pgp-guide.rst @@ -248,7 +248,10 @@ possano ricevere la vostra nuova sottochiave:: kernel. Se per qualche ragione preferite rimanere con sottochiavi RSA, nel comando - precedente, sostituite "ed25519" con "rsa2048". + precedente, sostituite "ed25519" con "rsa2048". In aggiunta, se avete + intenzione di usare un dispositivo hardware che non supporta le chiavi + ED25519 ECC, come la Nitrokey Pro o la Yubikey, allora dovreste usare + "nistp256" al posto di "ed25519". Copia di riserva della chiave primaria per gestire il recupero da disastro -------------------------------------------------------------------------- @@ -449,23 +452,27 @@ implementi le funzionalità delle smartcard. Sul mercato ci sono diverse soluzioni disponibili: - `Nitrokey Start`_: è Open hardware e Free Software, è basata sul progetto - `GnuK`_ della FSIJ. Ha il supporto per chiavi ECC, ma meno funzionalità di - sicurezza (come la resistenza alla manomissione o alcuni attacchi ad un - canale laterale). + `GnuK`_ della FSIJ. Questo è uno dei pochi dispositivi a supportare le chiavi + ECC ED25519, ma offre meno funzionalità di sicurezza (come la resistenza + alla manomissione o alcuni attacchi ad un canale laterale). - `Nitrokey Pro`_: è simile alla Nitrokey Start, ma è più resistente alla - manomissione e offre più funzionalità di sicurezza, ma l'ECC. -- `Yubikey 4`_: l'hardware e il software sono proprietari, ma è più economica + manomissione e offre più funzionalità di sicurezza. La Pro 2 supporta la + crittografia ECC (NISTP). +- `Yubikey 5`_: l'hardware e il software sono proprietari, ma è più economica della Nitrokey Pro ed è venduta anche con porta USB-C il che è utile con i computer portatili più recenti. In aggiunta, offre altre funzionalità di - sicurezza come FIDO, U2F, ma non l'ECC + sicurezza come FIDO, U2F, e ora supporta anche le chiavi ECC (NISTP) `Su LWN c'è una buona recensione`_ dei modelli elencati qui sopra e altri. +La scelta dipenderà dal costo, dalla disponibilità nella vostra area +geografica e vostre considerazioni sull'hardware aperto/proprietario. + Se volete usare chiavi ECC, la vostra migliore scelta sul mercato è la Nitrokey Start. .. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6 -.. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3 -.. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/ +.. _`Nitrokey Pro 2`: https://shop.nitrokey.com/shop/product/nitrokey-pro-2-3 +.. _`Yubikey 5`: https://www.yubico.com/product/yubikey-5-overview/ .. _Gnuk: http://www.fsij.org/doc-gnuk/ .. _`Su LWN c'è una buona recensione`: https://lwn.net/Articles/736231/ diff --git a/Documentation/translations/it_IT/process/programming-language.rst b/Documentation/translations/it_IT/process/programming-language.rst new file mode 100644 index 000000000000..f4b006395849 --- /dev/null +++ b/Documentation/translations/it_IT/process/programming-language.rst @@ -0,0 +1,51 @@ +.. include:: ../disclaimer-ita.rst + +:Original: :ref:`Documentation/process/programming-language.rst <programming_language>` +:Translator: Federico Vaga <[email protected]> + +.. _it_programming_language: + +Linguaggio di programmazione +============================ + +Il kernel è scritto nel linguaggio di programmazione C [c-language]_. +Più precisamente, il kernel viene compilato con ``gcc`` [gcc]_ usando +l'opzione ``-std=gnu89`` [gcc-c-dialect-options]_: il dialetto GNU +dello standard ISO C90 (con l'aggiunta di alcune funzionalità da C99) + +Questo dialetto contiene diverse estensioni al linguaggio [gnu-extensions]_, +e molte di queste vengono usate sistematicamente dal kernel. + +Il kernel offre un certo livello di supporto per la compilazione con ``clang`` +[clang]_ e ``icc`` [icc]_ su diverse architetture, tuttavia in questo momento +il supporto non è completo e richiede delle patch aggiuntive. + +Attributi +--------- + +Una delle estensioni più comuni e usate nel kernel sono gli attributi +[gcc-attribute-syntax]_. Gli attributi permettono di aggiungere una semantica, +definita dell'implementazione, alle entità del linguaggio (come le variabili, +le funzioni o i tipi) senza dover fare importanti modifiche sintattiche al +linguaggio stesso (come l'aggiunta di nuove parole chiave) [n2049]_. + +In alcuni casi, gli attributi sono opzionali (ovvero un compilatore che non +dovesse supportarli dovrebbe produrre comunque codice corretto, anche se +più lento o che non esegue controlli aggiuntivi durante la compilazione). + +Il kernel definisce alcune pseudo parole chiave (per esempio ``__pure``) +in alternativa alla sintassi GNU per gli attributi (per esempio +``__attribute__((__pure__))``) allo scopo di mostrare quali funzionalità si +possono usare e/o per accorciare il codice. + +Per maggiori informazioni consultate il file d'intestazione +``include/linux/compiler_attributes.h``. + +.. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards +.. [gcc] https://gcc.gnu.org +.. [clang] https://clang.llvm.org +.. [icc] https://software.intel.com/en-us/c-compilers +.. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html +.. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html +.. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html +.. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index a33c2a536542..2774624ee843 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -569,7 +569,7 @@ ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE � [*] 버스 마스터링 DMA 와 일관성에 대해서는 다음을 참고하시기 바랍니다: - Documentation/PCI/pci.rst + Documentation/driver-api/pci/pci.rst Documentation/DMA-API-HOWTO.txt Documentation/DMA-API.txt diff --git a/Documentation/userspace-api/conf.py b/Documentation/userspace-api/conf.py deleted file mode 100644 index 2eaf59f844e5..000000000000 --- a/Documentation/userspace-api/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "The Linux kernel user-space API guide" - -tags.add("subproject") - -latex_documents = [ - ('index', 'userspace-api.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/virtual/index.rst b/Documentation/virt/index.rst index 062ffb527043..062ffb527043 100644 --- a/Documentation/virtual/index.rst +++ b/Documentation/virt/index.rst diff --git a/Documentation/virtual/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index d18c97b4e140..d18c97b4e140 100644 --- a/Documentation/virtual/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virt/kvm/api.txt index e54a3f51ddc5..2d067767b617 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virt/kvm/api.txt @@ -3781,7 +3781,7 @@ encrypted VMs. Currently, this ioctl is used for issuing Secure Encrypted Virtualization (SEV) commands on AMD Processors. The SEV commands are defined in -Documentation/virtual/kvm/amd-memory-encryption.rst. +Documentation/virt/kvm/amd-memory-encryption.rst. 4.111 KVM_MEMORY_ENCRYPT_REG_REGION diff --git a/Documentation/virtual/kvm/arm/hyp-abi.txt b/Documentation/virt/kvm/arm/hyp-abi.txt index a20a0bee268d..a20a0bee268d 100644 --- a/Documentation/virtual/kvm/arm/hyp-abi.txt +++ b/Documentation/virt/kvm/arm/hyp-abi.txt diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virt/kvm/arm/psci.txt index 559586fc9d37..559586fc9d37 100644 --- a/Documentation/virtual/kvm/arm/psci.txt +++ b/Documentation/virt/kvm/arm/psci.txt diff --git a/Documentation/virtual/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst index 01b081f6e7ea..01b081f6e7ea 100644 --- a/Documentation/virtual/kvm/cpuid.rst +++ b/Documentation/virt/kvm/cpuid.rst diff --git a/Documentation/virtual/kvm/devices/README b/Documentation/virt/kvm/devices/README index 34a69834124a..34a69834124a 100644 --- a/Documentation/virtual/kvm/devices/README +++ b/Documentation/virt/kvm/devices/README diff --git a/Documentation/virtual/kvm/devices/arm-vgic-its.txt b/Documentation/virt/kvm/devices/arm-vgic-its.txt index eeaa95b893a8..eeaa95b893a8 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic-its.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-its.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt b/Documentation/virt/kvm/devices/arm-vgic-v3.txt index ff290b43c8e5..ff290b43c8e5 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt +++ b/Documentation/virt/kvm/devices/arm-vgic-v3.txt diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virt/kvm/devices/arm-vgic.txt index 97b6518148f8..97b6518148f8 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic.txt +++ b/Documentation/virt/kvm/devices/arm-vgic.txt diff --git a/Documentation/virtual/kvm/devices/mpic.txt b/Documentation/virt/kvm/devices/mpic.txt index 8257397adc3c..8257397adc3c 100644 --- a/Documentation/virtual/kvm/devices/mpic.txt +++ b/Documentation/virt/kvm/devices/mpic.txt diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virt/kvm/devices/s390_flic.txt index a4e20a090174..a4e20a090174 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virt/kvm/devices/s390_flic.txt diff --git a/Documentation/virtual/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt index 2b5dab16c4f2..2b5dab16c4f2 100644 --- a/Documentation/virtual/kvm/devices/vcpu.txt +++ b/Documentation/virt/kvm/devices/vcpu.txt diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virt/kvm/devices/vfio.txt index 528c77c8022c..528c77c8022c 100644 --- a/Documentation/virtual/kvm/devices/vfio.txt +++ b/Documentation/virt/kvm/devices/vfio.txt diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virt/kvm/devices/vm.txt index 4ffb82b02468..4ffb82b02468 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virt/kvm/devices/vm.txt diff --git a/Documentation/virtual/kvm/devices/xics.txt b/Documentation/virt/kvm/devices/xics.txt index 42864935ac5d..42864935ac5d 100644 --- a/Documentation/virtual/kvm/devices/xics.txt +++ b/Documentation/virt/kvm/devices/xics.txt diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virt/kvm/devices/xive.txt index 9a24a4525253..9a24a4525253 100644 --- a/Documentation/virtual/kvm/devices/xive.txt +++ b/Documentation/virt/kvm/devices/xive.txt diff --git a/Documentation/virtual/kvm/halt-polling.txt b/Documentation/virt/kvm/halt-polling.txt index 4f791b128dd2..4f791b128dd2 100644 --- a/Documentation/virtual/kvm/halt-polling.txt +++ b/Documentation/virt/kvm/halt-polling.txt diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virt/kvm/hypercalls.txt index da210651f714..5f6d291bd004 100644 --- a/Documentation/virtual/kvm/hypercalls.txt +++ b/Documentation/virt/kvm/hypercalls.txt @@ -18,7 +18,7 @@ S390: number in R1. For further information on the S390 diagnose call as supported by KVM, - refer to Documentation/virtual/kvm/s390-diag.txt. + refer to Documentation/virt/kvm/s390-diag.txt. PowerPC: It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers. @@ -26,7 +26,7 @@ S390: KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions' property inside the device tree's /hypervisor node. - For more information refer to Documentation/virtual/kvm/ppc-pv.txt + For more information refer to Documentation/virt/kvm/ppc-pv.txt MIPS: KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall diff --git a/Documentation/virtual/kvm/index.rst b/Documentation/virt/kvm/index.rst index 0b206a06f5be..ada224a511fe 100644 --- a/Documentation/virtual/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -9,3 +9,4 @@ KVM amd-memory-encryption cpuid + vcpu-requests diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virt/kvm/locking.txt index 635cd6eaf714..635cd6eaf714 100644 --- a/Documentation/virtual/kvm/locking.txt +++ b/Documentation/virt/kvm/locking.txt diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virt/kvm/mmu.txt index 2efe0efc516e..1b9880dfba0a 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virt/kvm/mmu.txt @@ -298,7 +298,7 @@ Handling a page fault is performed as follows: vcpu->arch.mmio_gfn, and call the emulator - If both P bit and R/W bit of error code are set, this could possibly be handled as a "fast page fault" (fixed without taking the MMU lock). See - the description in Documentation/virtual/kvm/locking.txt. + the description in Documentation/virt/kvm/locking.txt. - if needed, walk the guest page tables to determine the guest translation (gva->gpa or ngpa->gpa) - if permissions are insufficient, reflect the fault back to the guest diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virt/kvm/msr.txt index df1f4338b3ca..df1f4338b3ca 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virt/kvm/msr.txt diff --git a/Documentation/virtual/kvm/nested-vmx.txt b/Documentation/virt/kvm/nested-vmx.txt index 97eb1353e962..97eb1353e962 100644 --- a/Documentation/virtual/kvm/nested-vmx.txt +++ b/Documentation/virt/kvm/nested-vmx.txt diff --git a/Documentation/virtual/kvm/ppc-pv.txt b/Documentation/virt/kvm/ppc-pv.txt index e26115ce4258..e26115ce4258 100644 --- a/Documentation/virtual/kvm/ppc-pv.txt +++ b/Documentation/virt/kvm/ppc-pv.txt diff --git a/Documentation/virtual/kvm/review-checklist.txt b/Documentation/virt/kvm/review-checklist.txt index a83b27635fdd..499af499e296 100644 --- a/Documentation/virtual/kvm/review-checklist.txt +++ b/Documentation/virt/kvm/review-checklist.txt @@ -7,7 +7,7 @@ Review checklist for kvm patches 2. Patches should be against kvm.git master branch. 3. If the patch introduces or modifies a new userspace API: - - the API must be documented in Documentation/virtual/kvm/api.txt + - the API must be documented in Documentation/virt/kvm/api.txt - the API must be discoverable using KVM_CHECK_EXTENSION 4. New state must include support for save/restore. diff --git a/Documentation/virtual/kvm/s390-diag.txt b/Documentation/virt/kvm/s390-diag.txt index 7c52e5f8b210..7c52e5f8b210 100644 --- a/Documentation/virtual/kvm/s390-diag.txt +++ b/Documentation/virt/kvm/s390-diag.txt diff --git a/Documentation/virtual/kvm/timekeeping.txt b/Documentation/virt/kvm/timekeeping.txt index 76808a17ad84..76808a17ad84 100644 --- a/Documentation/virtual/kvm/timekeeping.txt +++ b/Documentation/virt/kvm/timekeeping.txt diff --git a/Documentation/virtual/kvm/vcpu-requests.rst b/Documentation/virt/kvm/vcpu-requests.rst index 5feb3706a7ae..5feb3706a7ae 100644 --- a/Documentation/virtual/kvm/vcpu-requests.rst +++ b/Documentation/virt/kvm/vcpu-requests.rst diff --git a/Documentation/virtual/paravirt_ops.rst b/Documentation/virt/paravirt_ops.rst index 6b789d27cead..6b789d27cead 100644 --- a/Documentation/virtual/paravirt_ops.rst +++ b/Documentation/virt/paravirt_ops.rst diff --git a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt b/Documentation/virt/uml/UserModeLinux-HOWTO.txt index 87b80f589e1c..87b80f589e1c 100644 --- a/Documentation/virtual/uml/UserModeLinux-HOWTO.txt +++ b/Documentation/virt/uml/UserModeLinux-HOWTO.txt diff --git a/Documentation/vm/conf.py b/Documentation/vm/conf.py deleted file mode 100644 index 3b0b601af558..000000000000 --- a/Documentation/vm/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "Linux Memory Management Documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'memory-management.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 7d90964abbb0..710ce1c701bf 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -237,7 +237,7 @@ The usage pattern is:: ret = hmm_range_snapshot(&range); if (ret) { up_read(&mm->mmap_sem); - if (ret == -EAGAIN) { + if (ret == -EBUSY) { /* * No need to check hmm_range_wait_until_valid() return value * on retry we will get proper error with hmm_range_snapshot() diff --git a/Documentation/watchdog/hpwdt.rst b/Documentation/watchdog/hpwdt.rst index c165d92cfd12..c824cd7f6e32 100644 --- a/Documentation/watchdog/hpwdt.rst +++ b/Documentation/watchdog/hpwdt.rst @@ -63,7 +63,7 @@ Last reviewed: 08/20/2018 and loop forever. This is generally not what a watchdog user wants. For those wishing to learn more please see: - Documentation/kdump/kdump.rst + Documentation/admin-guide/kdump/kdump.rst Documentation/admin-guide/kernel-parameters.txt (panic=) Your Linux Distribution specific documentation. diff --git a/Documentation/x86/conf.py b/Documentation/x86/conf.py deleted file mode 100644 index 33c5c3142e20..000000000000 --- a/Documentation/x86/conf.py +++ /dev/null @@ -1,10 +0,0 @@ -# -*- coding: utf-8; mode: python -*- - -project = "X86 architecture specific documentation" - -tags.add("subproject") - -latex_documents = [ - ('index', 'x86.tex', project, - 'The kernel development community', 'manual'), -] diff --git a/MAINTAINERS b/MAINTAINERS index ee663e0e2f2e..e352550a6895 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -899,7 +899,7 @@ L: [email protected] W: http://ez.analog.com/community/linux-device-drivers S: Supported F: drivers/iio/adc/ad7124.c -F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.txt +F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml ANALOG DEVICES INC AD7606 DRIVER M: Stefan Popa <[email protected]> @@ -1194,7 +1194,7 @@ F: include/uapi/linux/if_arcnet.h ARM ARCHITECTED TIMER DRIVER M: Mark Rutland <[email protected]> -M: Marc Zyngier <[email protected]> +M: Marc Zyngier <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained F: arch/arm/include/asm/arch_timer.h @@ -2155,10 +2155,12 @@ F: Documentation/devicetree/bindings/arm/realtek.txt ARM/RENESAS ARM64 ARCHITECTURE M: Simon Horman <[email protected]> +M: Geert Uytterhoeven <[email protected]> M: Magnus Damm <[email protected]> Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm64/boot/dts/renesas/ F: Documentation/devicetree/bindings/arm/renesas.yaml @@ -2269,10 +2271,12 @@ F: drivers/media/platform/s5p-mfc/ ARM/SHMOBILE ARM ARCHITECTURE M: Simon Horman <[email protected]> +M: Geert Uytterhoeven <[email protected]> M: Magnus Damm <[email protected]> Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next S: Supported F: arch/arm/boot/dts/emev2* F: arch/arm/boot/dts/gr-peach* @@ -4195,7 +4199,7 @@ M: Jens Axboe <[email protected]> T: git git://git.kernel.dk/linux-block -F: Documentation/cgroup-v1/blkio-controller.rst +F: Documentation/admin-guide/cgroup-v1/blkio-controller.rst F: block/blk-cgroup.c F: include/linux/blk-cgroup.h F: block/blk-throttle.c @@ -4474,7 +4478,7 @@ F: arch/powerpc/platforms/powernv/pci-cxl.c F: drivers/misc/cxl/ F: include/misc/cxl* F: include/uapi/misc/cxl.h -F: Documentation/powerpc/cxl.txt +F: Documentation/powerpc/cxl.rst F: Documentation/ABI/testing/sysfs-class-cxl CXLFLASH (IBM Coherent Accelerator Processor Interface CAPI Flash) SCSI DRIVER @@ -4485,7 +4489,7 @@ L: [email protected] S: Supported F: drivers/scsi/cxlflash/ F: include/uapi/scsi/cxlflash_ioctl.h -F: Documentation/powerpc/cxlflash.txt +F: Documentation/powerpc/cxlflash.rst CYBERPRO FB DRIVER M: Russell King <[email protected]> @@ -6327,7 +6331,8 @@ F: Documentation/devicetree/bindings/counter/ftm-quaddec.txt F: drivers/counter/ftm-quaddec.c FLOPPY DRIVER -S: Orphan +M: Denis Efremov <[email protected]> +S: Odd Fixes F: drivers/block/floppy.c @@ -6827,13 +6832,6 @@ F: Documentation/filesystems/gfs2*.txt F: fs/gfs2/ F: include/uapi/linux/gfs2_ondisk.h -GIGASET ISDN DRIVERS -M: Paul Bolle <[email protected]> -W: http://gigaset307x.sourceforge.net/ -S: Odd Fixes -F: drivers/staging/isdn/gigaset/ - GNSS SUBSYSTEM M: Johan Hovold <[email protected]> T: git git://git.kernel.org/pub/scm/linux/kernel/git/johan/gnss.git @@ -6861,7 +6859,7 @@ R: Sagi Shahar <[email protected]> R: Jon Olson <[email protected]> S: Supported -F: Documentation/networking/device_drivers/google/gve.txt +F: Documentation/networking/device_drivers/google/gve.rst F: drivers/net/ethernet/google GPD POCKET FAN DRIVER @@ -8495,7 +8493,7 @@ S: Obsolete F: include/uapi/linux/ipx.h IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY) -M: Marc Zyngier <[email protected]> +M: Marc Zyngier <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: Documentation/IRQ-domain.txt @@ -8513,7 +8511,7 @@ F: kernel/irq/ IRQCHIP DRIVERS M: Thomas Gleixner <[email protected]> M: Jason Cooper <[email protected]> -M: Marc Zyngier <[email protected]> +M: Marc Zyngier <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core @@ -8813,7 +8811,7 @@ L: [email protected] W: http://www.linux-kvm.org T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git S: Supported -F: Documentation/virtual/kvm/ +F: Documentation/virt/kvm/ F: include/trace/events/kvm.h F: include/uapi/asm-generic/kvm* F: include/uapi/linux/kvm* @@ -8833,10 +8831,10 @@ F: arch/x86/include/asm/svm.h F: arch/x86/kvm/svm.c KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64) -M: Marc Zyngier <[email protected]> +M: Marc Zyngier <[email protected]> R: James Morse <[email protected]> -R: Julien Thierry <[email protected]> -R: Suzuki K Pouloze <[email protected]> +R: Julien Thierry <[email protected]> +R: Suzuki K Poulose <[email protected]> L: [email protected] (moderated for non-subscribers) T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git @@ -11149,6 +11147,7 @@ L: [email protected] S: Maintained W: https://fedorahosted.org/dropwatch/ F: net/core/drop_monitor.c +F: include/uapi/linux/net_dropmon.h NETWORKING DRIVERS M: "David S. Miller" <[email protected]> @@ -11287,6 +11286,7 @@ M: Aviad Yehezkel <[email protected]> M: Dave Watson <[email protected]> M: John Fastabend <[email protected]> M: Daniel Borkmann <[email protected]> +M: Jakub Kicinski <[email protected]> S: Maintained F: net/tls/* @@ -12141,7 +12141,7 @@ M: Thomas Hellstrom <[email protected]> M: "VMware, Inc." <[email protected]> S: Supported -F: Documentation/virtual/paravirt_ops.txt +F: Documentation/virt/paravirt_ops.rst F: arch/*/kernel/paravirt* F: arch/*/include/asm/paravirt*.h F: include/linux/hypervisor.h @@ -12398,7 +12398,7 @@ F: Documentation/PCI/pci-error-recovery.rst F: drivers/pci/pcie/aer.c F: drivers/pci/pcie/dpc.c F: drivers/pci/pcie/err.c -F: Documentation/powerpc/eeh-pci-error-recovery.txt +F: Documentation/powerpc/eeh-pci-error-recovery.rst F: arch/powerpc/kernel/eeh*.c F: arch/powerpc/platforms/*/eeh*.c F: arch/powerpc/include/*/eeh*.h @@ -13729,6 +13729,7 @@ F: drivers/mtd/nand/raw/r852.c F: drivers/mtd/nand/raw/r852.h RISC-V ARCHITECTURE +M: Paul Walmsley <[email protected]> M: Palmer Dabbelt <[email protected]> M: Albert Ou <[email protected]> @@ -13951,7 +13952,6 @@ F: drivers/pci/hotplug/s390_pci_hpc.c S390 VFIO-CCW DRIVER M: Cornelia Huck <[email protected]> -M: Farhan Ali <[email protected]> M: Eric Farman <[email protected]> R: Halil Pasic <[email protected]> @@ -14020,6 +14020,12 @@ F: drivers/media/common/saa7146/ F: drivers/media/pci/saa7146/ F: include/media/drv-intf/saa7146* +SAFESETID SECURITY MODULE +M: Micah Morton <[email protected]> +S: Supported +F: security/safesetid/ +F: Documentation/admin-guide/LSM/SafeSetID.rst + SAMSUNG AUDIO (ASoC) DRIVERS M: Krzysztof Kozlowski <[email protected]> M: Sangbeom Kim <[email protected]> @@ -16858,7 +16864,7 @@ W: http://user-mode-linux.sourceforge.net Q: https://patchwork.ozlabs.org/project/linux-um/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git S: Maintained -F: Documentation/virtual/uml/ +F: Documentation/virt/uml/ F: arch/um/ F: arch/x86/um/ F: fs/hostfs/ @@ -17127,7 +17133,7 @@ F: drivers/virtio/virtio_input.c F: include/uapi/linux/virtio_input.h VIRTIO IOMMU DRIVER -M: Jean-Philippe Brucker <[email protected]> +M: Jean-Philippe Brucker <[email protected]> S: Maintained F: drivers/iommu/virtio-iommu.c @@ -17176,7 +17182,6 @@ F: drivers/vme/ F: include/linux/vme* VMWARE BALLOON DRIVER -M: Julien Freche <[email protected]> M: Nadav Amit <[email protected]> M: "VMware, Inc." <[email protected]> @@ -17559,7 +17564,6 @@ M: Jakub Kicinski <[email protected]> M: Jesper Dangaard Brouer <[email protected]> M: John Fastabend <[email protected]> S: Supported F: net/core/xdp.c @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = Bobtail Squid # *DOCUMENTATION* @@ -472,6 +472,7 @@ KBUILD_CFLAGS_MODULE := -DMODULE KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds KBUILD_LDFLAGS := GCC_PLUGINS_CFLAGS := +CLANG_FLAGS := export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC export CPP AR NM STRIP OBJCOPY OBJDUMP PAHOLE KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS @@ -519,7 +520,7 @@ endif ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) -CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) +CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) @@ -843,6 +844,9 @@ NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) # warn about C99 declaration after statement KBUILD_CFLAGS += -Wdeclaration-after-statement +# Warn about unmarked fall-throughs in switch statement. +KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=3,) + # Variable Length Arrays (VLAs) should not be used anywhere in the kernel KBUILD_CFLAGS += -Wvla diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index c929bea9a9ff..85710e078afb 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1535,7 +1535,6 @@ config DEBUG_LL_INCLUDE DEBUG_IMX7D_UART default "debug/ks8695.S" if DEBUG_KS8695_UART default "debug/msm.S" if DEBUG_QCOM_UARTDM - default "debug/netx.S" if DEBUG_NETX_UART default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART default "debug/renesas-scif.S" if DEBUG_R7S72100_SCIF2 default "debug/renesas-scif.S" if DEBUG_RCAR_GEN1_SCIF0 @@ -1575,7 +1574,6 @@ config DEBUG_UART_8250 config DEBUG_UART_PHYS hex "Physical base address of debug UART" - default 0x00100a00 if DEBUG_NETX_UART default 0x01c20000 if DEBUG_DAVINCI_DMx_UART0 default 0x01c28000 if DEBUG_SUNXI_UART0 default 0x01c28400 if DEBUG_SUNXI_UART1 @@ -1700,7 +1698,6 @@ config DEBUG_UART_PHYS DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ DEBUG_LL_UART_EFM32 || \ DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ - DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_R7S72100_SCIF2 || \ DEBUG_RCAR_GEN1_SCIF0 || DEBUG_RCAR_GEN1_SCIF2 || \ DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF1 || \ @@ -1717,7 +1714,6 @@ config DEBUG_UART_VIRT default 0xc881f000 if DEBUG_RV1108_UART2 default 0xc8821000 if DEBUG_RV1108_UART1 default 0xc8912000 if DEBUG_RV1108_UART0 - default 0xe0000a00 if DEBUG_NETX_UART default 0xe0010fe0 if ARCH_RPC default 0xf0000be0 if ARCH_EBSA110 default 0xf0010000 if DEBUG_ASM9260_UART @@ -1822,7 +1818,6 @@ config DEBUG_UART_VIRT default DEBUG_UART_PHYS if !MMU depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ - DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \ DEBUG_S3C64XX_UART || \ DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ diff --git a/arch/arm/boot/dts/bcm47094-linksys-panamera.dts b/arch/arm/boot/dts/bcm47094-linksys-panamera.dts index 18d0ae46e76c..0faae8950375 100644 --- a/arch/arm/boot/dts/bcm47094-linksys-panamera.dts +++ b/arch/arm/boot/dts/bcm47094-linksys-panamera.dts @@ -124,6 +124,9 @@ }; mdio-bus-mux { + #address-cells = <1>; + #size-cells = <0>; + /* BIT(9) = 1 => external mdio */ mdio_ext: mdio@200 { reg = <0x200>; diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index cbe61b61a212..c2a9dd57e56a 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -112,7 +112,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-geam.dts b/arch/arm/boot/dts/imx6ul-geam.dts index 21ddd359d3ed..9f63706383a7 100644 --- a/arch/arm/boot/dts/imx6ul-geam.dts +++ b/arch/arm/boot/dts/imx6ul-geam.dts @@ -156,7 +156,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-isiot.dtsi b/arch/arm/boot/dts/imx6ul-isiot.dtsi index b26d4f57c655..cc9adce638f5 100644 --- a/arch/arm/boot/dts/imx6ul-isiot.dtsi +++ b/arch/arm/boot/dts/imx6ul-isiot.dtsi @@ -148,7 +148,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts index 39eeeddac39e..09f7ffa9ad8c 100644 --- a/arch/arm/boot/dts/imx6ul-pico-hobbit.dts +++ b/arch/arm/boot/dts/imx6ul-pico-hobbit.dts @@ -43,7 +43,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6ul-pico-pi.dts b/arch/arm/boot/dts/imx6ul-pico-pi.dts index de07357b27fc..6cd7d5877d20 100644 --- a/arch/arm/boot/dts/imx6ul-pico-pi.dts +++ b/arch/arm/boot/dts/imx6ul-pico-pi.dts @@ -43,7 +43,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; @@ -58,7 +58,7 @@ }; &i2c3 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi index 992747a57442..56907bb4b329 100644 --- a/arch/arm/boot/dts/imx7ulp.dtsi +++ b/arch/arm/boot/dts/imx7ulp.dtsi @@ -186,7 +186,7 @@ reg = <0x40330200 0x200>; }; - usbphy1: usb-phy@0x40350000 { + usbphy1: usb-phy@40350000 { compatible = "fsl,imx7ulp-usbphy", "fsl,imx6ul-usbphy"; reg = <0x40350000 0x1000>; interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index e6b98b6eb88d..822cddfbf1af 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -4,17 +4,9 @@ CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y CONFIG_ARCH_U8500=y -CONFIG_MACH_HREFV60=y -CONFIG_MACH_SNOWBALL=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_PREEMPT=y -CONFIG_AEABI=y CONFIG_HIGHMEM=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y @@ -25,6 +17,11 @@ CONFIG_CPU_IDLE=y CONFIG_ARM_U8500_CPUIDLE=y CONFIG_VFP=y CONFIG_NEON=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_CMA=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -47,7 +44,6 @@ CONFIG_SMSC911X=y CONFIG_SMSC_PHY=y CONFIG_CW1200=y CONFIG_CW1200_WLAN_SDIO=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set CONFIG_KEYBOARD_GPIO=y @@ -63,7 +59,6 @@ CONFIG_RMI4_CORE=y CONFIG_RMI4_I2C=y CONFIG_RMI4_F11=y # CONFIG_SERIO is not set -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y @@ -72,6 +67,7 @@ CONFIG_SPI=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_SENSORS_IIO_HWMON=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y @@ -79,6 +75,13 @@ CONFIG_MFD_STMPE=y CONFIG_MFD_TC3589X=y CONFIG_REGULATOR_AB8500=y CONFIG_REGULATOR_GPIO=y +CONFIG_DRM=y +CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_LIMA=y +CONFIG_DRM_MCDE=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y +CONFIG_BACKLIGHT_GENERIC=m +CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y CONFIG_SND_SOC=y @@ -87,6 +90,7 @@ CONFIG_SND_SOC_UX500_MACH_MOP500=y CONFIG_USB=y CONFIG_USB_MUSB_HDRC=y CONFIG_USB_MUSB_UX500=y +CONFIG_MUSB_PIO_ONLY=y CONFIG_AB8500_USB=y CONFIG_USB_GADGET=y CONFIG_USB_ETH=m @@ -103,6 +107,7 @@ CONFIG_RTC_DRV_AB8500=y CONFIG_RTC_DRV_PL031=y CONFIG_DMADEVICES=y CONFIG_STE_DMA40=y +CONFIG_HWSPINLOCK=y CONFIG_HSEM_U8500=y CONFIG_IIO=y CONFIG_IIO_SW_TRIGGER=y @@ -126,20 +131,19 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y +CONFIG_CRYPTO_DEV_UX500=y +CONFIG_CRYPTO_DEV_UX500_CRYP=y +CONFIG_CRYPTO_DEV_UX500_HASH=y +CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set -# CONFIG_DEBUG_PREEMPT is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y CONFIG_CORESIGHT=y CONFIG_CORESIGHT_SINK_TPIU=y CONFIG_CORESIGHT_SINK_ETBV10=y CONFIG_CORESIGHT_SOURCE_ETM3X=y -CONFIG_CRYPTO_DEV_UX500=y -CONFIG_CRYPTO_DEV_UX500_CRYP=y -CONFIG_CRYPTO_DEV_UX500_HASH=y -CONFIG_CRYPTO_DEV_UX500_DEBUG=y diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 7e0486ad1318..dba9355e2484 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -18,7 +18,9 @@ extern const struct dma_map_ops arm_coherent_dma_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL; + if (IS_ENABLED(CONFIG_MMU) && !IS_ENABLED(CONFIG_ARM_LPAE)) + return &arm_dma_ops; + return NULL; } #ifdef __arch_page_to_dma diff --git a/arch/arm/mach-davinci/sleep.S b/arch/arm/mach-davinci/sleep.S index 05d03f09ff54..71262dcdbca3 100644 --- a/arch/arm/mach-davinci/sleep.S +++ b/arch/arm/mach-davinci/sleep.S @@ -24,6 +24,7 @@ #define DEEPSLEEP_SLEEPENABLE_BIT BIT(31) .text + .arch armv5te /* * Move DaVinci into deep sleep state * diff --git a/arch/arm/mach-netx/Kconfig b/arch/arm/mach-netx/Kconfig deleted file mode 100644 index 1e5d9c870784..000000000000 --- a/arch/arm/mach-netx/Kconfig +++ /dev/null @@ -1,22 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -menu "NetX Implementations" - depends on ARCH_NETX - -config MACH_NXDKN - bool "Enable Hilscher nxdkn Eval Board support" - help - Board support for the Hilscher NetX Eval Board - -config MACH_NXDB500 - bool "Enable Hilscher nxdb500 Eval Board support" - select ARM_AMBA - help - Board support for the Hilscher nxdb500 Eval Board - -config MACH_NXEB500HMI - bool "Enable Hilscher nxeb500hmi Eval Board support" - select ARM_AMBA - help - Board support for the Hilscher nxeb500hmi Eval Board - -endmenu diff --git a/arch/arm/mach-netx/Makefile b/arch/arm/mach-netx/Makefile deleted file mode 100644 index 44ea83f7d9c2..000000000000 --- a/arch/arm/mach-netx/Makefile +++ /dev/null @@ -1,13 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for the linux kernel. -# - -# Object file lists. - -obj-y += time.o generic.o pfifo.o xc.o - -# Specific board support -obj-$(CONFIG_MACH_NXDKN) += nxdkn.o -obj-$(CONFIG_MACH_NXDB500) += nxdb500.o fb.o -obj-$(CONFIG_MACH_NXEB500HMI) += nxeb500hmi.o fb.o diff --git a/arch/arm/mach-netx/Makefile.boot b/arch/arm/mach-netx/Makefile.boot deleted file mode 100644 index 2eb23c0cb6b0..000000000000 --- a/arch/arm/mach-netx/Makefile.boot +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only - zreladdr-y += 0x80008000 - diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c deleted file mode 100644 index 2dc80db07390..000000000000 --- a/arch/arm/mach-netx/fb.c +++ /dev/null @@ -1,65 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/fb.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/device.h> -#include <linux/init.h> -#include <linux/dma-mapping.h> -#include <linux/amba/bus.h> -#include <linux/amba/clcd.h> -#include <linux/err.h> -#include <linux/gfp.h> - -#include <asm/irq.h> - -#include <mach/netx-regs.h> -#include <mach/hardware.h> - -static struct clcd_panel *netx_panel; - -void netx_clcd_enable(struct clcd_fb *fb) -{ -} - -int netx_clcd_setup(struct clcd_fb *fb) -{ - dma_addr_t dma; - - fb->panel = netx_panel; - - fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma, - GFP_KERNEL); - if (!fb->fb.screen_base) { - printk(KERN_ERR "CLCD: unable to map framebuffer\n"); - return -ENOMEM; - } - - fb->fb.fix.smem_start = dma; - fb->fb.fix.smem_len = 1024*1024; - - return 0; -} - -int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) -{ - return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, - fb->fb.fix.smem_start, fb->fb.fix.smem_len); -} - -void netx_clcd_remove(struct clcd_fb *fb) -{ - dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, - fb->fb.fix.smem_start); -} - -static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL); - -int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel) -{ - netx_panel = panel; - fb_device.dev.platform_data = board; - return amba_device_register(&fb_device, &iomem_resource); -} diff --git a/arch/arm/mach-netx/fb.h b/arch/arm/mach-netx/fb.h deleted file mode 100644 index 5cdc01fc3c86..000000000000 --- a/arch/arm/mach-netx/fb.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/fb.h - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -void netx_clcd_enable(struct clcd_fb *fb); -int netx_clcd_setup(struct clcd_fb *fb); -int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma); -void netx_clcd_remove(struct clcd_fb *fb); -int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel); diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c deleted file mode 100644 index 88881fd45e9f..000000000000 --- a/arch/arm/mach-netx/generic.c +++ /dev/null @@ -1,182 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/generic.c - * - * Copyright (C) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/device.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/platform_device.h> -#include <linux/io.h> -#include <linux/irqchip/arm-vic.h> -#include <linux/reboot.h> -#include <mach/hardware.h> -#include <asm/mach/map.h> -#include <mach/netx-regs.h> -#include <asm/mach/irq.h> - -static struct map_desc netx_io_desc[] __initdata = { - { - .virtual = NETX_IO_VIRT, - .pfn = __phys_to_pfn(NETX_IO_PHYS), - .length = NETX_IO_SIZE, - .type = MT_DEVICE - } -}; - -void __init netx_map_io(void) -{ - iotable_init(netx_io_desc, ARRAY_SIZE(netx_io_desc)); -} - -static struct resource netx_rtc_resources[] = { - [0] = { - .start = 0x00101200, - .end = 0x00101220, - .flags = IORESOURCE_MEM, - }, -}; - -static struct platform_device netx_rtc_device = { - .name = "netx-rtc", - .id = 0, - .num_resources = ARRAY_SIZE(netx_rtc_resources), - .resource = netx_rtc_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_rtc_device, -}; - -#if 0 -#define DEBUG_IRQ(fmt...) printk(fmt) -#else -#define DEBUG_IRQ(fmt...) while (0) {} -#endif - -static void netx_hif_demux_handler(struct irq_desc *desc) -{ - unsigned int irq = NETX_IRQ_HIF_CHAINED(0); - unsigned int stat; - - stat = ((readl(NETX_DPMAS_INT_EN) & - readl(NETX_DPMAS_INT_STAT)) >> 24) & 0x1f; - - while (stat) { - if (stat & 1) { - DEBUG_IRQ("handling irq %d\n", irq); - generic_handle_irq(irq); - } - irq++; - stat >>= 1; - } -} - -static int -netx_hif_irq_type(struct irq_data *d, unsigned int type) -{ - unsigned int val, irq; - - val = readl(NETX_DPMAS_IF_CONF1); - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - - if (type & IRQ_TYPE_EDGE_RISING) { - DEBUG_IRQ("rising edges\n"); - val |= (1 << 26) << irq; - } - if (type & IRQ_TYPE_EDGE_FALLING) { - DEBUG_IRQ("falling edges\n"); - val &= ~((1 << 26) << irq); - } - if (type & IRQ_TYPE_LEVEL_LOW) { - DEBUG_IRQ("low level\n"); - val &= ~((1 << 26) << irq); - } - if (type & IRQ_TYPE_LEVEL_HIGH) { - DEBUG_IRQ("high level\n"); - val |= (1 << 26) << irq; - } - - writel(val, NETX_DPMAS_IF_CONF1); - - return 0; -} - -static void -netx_hif_ack_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - writel((1 << 24) << irq, NETX_DPMAS_INT_STAT); - - val = readl(NETX_DPMAS_INT_EN); - val &= ~((1 << 24) << irq); - writel(val, NETX_DPMAS_INT_EN); - - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static void -netx_hif_mask_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - val = readl(NETX_DPMAS_INT_EN); - val &= ~((1 << 24) << irq); - writel(val, NETX_DPMAS_INT_EN); - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static void -netx_hif_unmask_irq(struct irq_data *d) -{ - unsigned int val, irq; - - irq = d->irq - NETX_IRQ_HIF_CHAINED(0); - val = readl(NETX_DPMAS_INT_EN); - val |= (1 << 24) << irq; - writel(val, NETX_DPMAS_INT_EN); - DEBUG_IRQ("%s: irq %d\n", __func__, d->irq); -} - -static struct irq_chip netx_hif_chip = { - .irq_ack = netx_hif_ack_irq, - .irq_mask = netx_hif_mask_irq, - .irq_unmask = netx_hif_unmask_irq, - .irq_set_type = netx_hif_irq_type, -}; - -void __init netx_init_irq(void) -{ - int irq; - - vic_init(io_p2v(NETX_PA_VIC), NETX_IRQ_VIC_START, ~0, 0); - - for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) { - irq_set_chip_and_handler(irq, &netx_hif_chip, - handle_level_irq); - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } - - writel(NETX_DPMAS_INT_EN_GLB_EN, NETX_DPMAS_INT_EN); - irq_set_chained_handler(NETX_IRQ_HIF, netx_hif_demux_handler); -} - -static int __init netx_init(void) -{ - return platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -subsys_initcall(netx_init); - -void netx_restart(enum reboot_mode mode, const char *cmd) -{ - writel(NETX_SYSTEM_RES_CR_FIRMW_RES_EN | NETX_SYSTEM_RES_CR_FIRMW_RES, - NETX_SYSTEM_RES_CR); -} diff --git a/arch/arm/mach-netx/generic.h b/arch/arm/mach-netx/generic.h deleted file mode 100644 index 223e304574a5..000000000000 --- a/arch/arm/mach-netx/generic.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/generic.h - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/reboot.h> - -extern void __init netx_map_io(void); -extern void __init netx_init_irq(void); -extern void netx_restart(enum reboot_mode, const char *); - -extern void netx_timer_init(void); diff --git a/arch/arm/mach-netx/include/mach/hardware.h b/arch/arm/mach-netx/include/mach/hardware.h deleted file mode 100644 index 84253993d1e0..000000000000 --- a/arch/arm/mach-netx/include/mach/hardware.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/hardware.h - * - * Copyright (C) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ -#ifndef __ASM_ARCH_HARDWARE_H -#define __ASM_ARCH_HARDWARE_H - -#define NETX_IO_PHYS 0x00100000 -#define NETX_IO_VIRT 0xe0000000 -#define NETX_IO_SIZE 0x00100000 - -#define SRAM_INTERNAL_PHYS_0 0x00000 -#define SRAM_INTERNAL_PHYS_1 0x08000 -#define SRAM_INTERNAL_PHYS_2 0x10000 -#define SRAM_INTERNAL_PHYS_3 0x18000 -#define SRAM_INTERNAL_PHYS(no) ((no) * 0x8000) - -#define XPEC_MEM_SIZE 0x4000 -#define XMAC_MEM_SIZE 0x1000 -#define SRAM_MEM_SIZE 0x8000 - -#define io_p2v(x) IOMEM((x) - NETX_IO_PHYS + NETX_IO_VIRT) -#define io_v2p(x) ((x) - NETX_IO_VIRT + NETX_IO_PHYS) - -#endif diff --git a/arch/arm/mach-netx/include/mach/irqs.h b/arch/arm/mach-netx/include/mach/irqs.h deleted file mode 100644 index 540c92104fe8..000000000000 --- a/arch/arm/mach-netx/include/mach/irqs.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/irqs.h - * - * Copyright (C) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#define NETX_IRQ_VIC_START 64 -#define NETX_IRQ_SOFTINT (NETX_IRQ_VIC_START + 0) -#define NETX_IRQ_TIMER0 (NETX_IRQ_VIC_START + 1) -#define NETX_IRQ_TIMER1 (NETX_IRQ_VIC_START + 2) -#define NETX_IRQ_TIMER2 (NETX_IRQ_VIC_START + 3) -#define NETX_IRQ_SYSTIME_NS (NETX_IRQ_VIC_START + 4) -#define NETX_IRQ_SYSTIME_S (NETX_IRQ_VIC_START + 5) -#define NETX_IRQ_GPIO_15 (NETX_IRQ_VIC_START + 6) -#define NETX_IRQ_WATCHDOG (NETX_IRQ_VIC_START + 7) -#define NETX_IRQ_UART0 (NETX_IRQ_VIC_START + 8) -#define NETX_IRQ_UART1 (NETX_IRQ_VIC_START + 9) -#define NETX_IRQ_UART2 (NETX_IRQ_VIC_START + 10) -#define NETX_IRQ_USB (NETX_IRQ_VIC_START + 11) -#define NETX_IRQ_SPI (NETX_IRQ_VIC_START + 12) -#define NETX_IRQ_I2C (NETX_IRQ_VIC_START + 13) -#define NETX_IRQ_LCD (NETX_IRQ_VIC_START + 14) -#define NETX_IRQ_HIF (NETX_IRQ_VIC_START + 15) -#define NETX_IRQ_GPIO_0_14 (NETX_IRQ_VIC_START + 16) -#define NETX_IRQ_XPEC0 (NETX_IRQ_VIC_START + 17) -#define NETX_IRQ_XPEC1 (NETX_IRQ_VIC_START + 18) -#define NETX_IRQ_XPEC2 (NETX_IRQ_VIC_START + 19) -#define NETX_IRQ_XPEC3 (NETX_IRQ_VIC_START + 20) -#define NETX_IRQ_XPEC(no) (NETX_IRQ_VIC_START + 17 + (no)) -#define NETX_IRQ_MSYNC0 (NETX_IRQ_VIC_START + 21) -#define NETX_IRQ_MSYNC1 (NETX_IRQ_VIC_START + 22) -#define NETX_IRQ_MSYNC2 (NETX_IRQ_VIC_START + 23) -#define NETX_IRQ_MSYNC3 (NETX_IRQ_VIC_START + 24) -#define NETX_IRQ_IRQ_PHY (NETX_IRQ_VIC_START + 25) -#define NETX_IRQ_ISO_AREA (NETX_IRQ_VIC_START + 26) -/* int 27 is reserved */ -/* int 28 is reserved */ -#define NETX_IRQ_TIMER3 (NETX_IRQ_VIC_START + 29) -#define NETX_IRQ_TIMER4 (NETX_IRQ_VIC_START + 30) -/* int 31 is reserved */ - -#define NETX_IRQS (NETX_IRQ_VIC_START + 32) - -/* for multiplexed irqs on gpio 0..14 */ -#define NETX_IRQ_GPIO(x) (NETX_IRQS + (x)) -#define NETX_IRQ_GPIO_LAST NETX_IRQ_GPIO(14) - -/* Host interface interrupts */ -#define NETX_IRQ_HIF_CHAINED(x) (NETX_IRQ_GPIO_LAST + 1 + (x)) -#define NETX_IRQ_HIF_PIO35 NETX_IRQ_HIF_CHAINED(0) -#define NETX_IRQ_HIF_PIO36 NETX_IRQ_HIF_CHAINED(1) -#define NETX_IRQ_HIF_PIO40 NETX_IRQ_HIF_CHAINED(2) -#define NETX_IRQ_HIF_PIO47 NETX_IRQ_HIF_CHAINED(3) -#define NETX_IRQ_HIF_PIO72 NETX_IRQ_HIF_CHAINED(4) -#define NETX_IRQ_HIF_LAST NETX_IRQ_HIF_CHAINED(4) - -#define NR_IRQS (NETX_IRQ_HIF_LAST + 1) diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h deleted file mode 100644 index 7c356a6ab80b..000000000000 --- a/arch/arm/mach-netx/include/mach/netx-regs.h +++ /dev/null @@ -1,420 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/netx-regs.h - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#ifndef __ASM_ARCH_NETX_REGS_H -#define __ASM_ARCH_NETX_REGS_H - -/* offsets relative to the beginning of the io space */ -#define NETX_OFS_SYSTEM 0x00000 -#define NETX_OFS_MEMCR 0x00100 -#define NETX_OFS_DPMAS 0x03000 -#define NETX_OFS_GPIO 0x00800 -#define NETX_OFS_PIO 0x00900 -#define NETX_OFS_UART0 0x00a00 -#define NETX_OFS_UART1 0x00a40 -#define NETX_OFS_UART2 0x00a80 -#define NETX_OF_MIIMU 0x00b00 -#define NETX_OFS_SPI 0x00c00 -#define NETX_OFS_I2C 0x00d00 -#define NETX_OFS_SYSTIME 0x01100 -#define NETX_OFS_RTC 0x01200 -#define NETX_OFS_EXTBUS 0x03600 -#define NETX_OFS_LCD 0x04000 -#define NETX_OFS_USB 0x20000 -#define NETX_OFS_XMAC0 0x60000 -#define NETX_OFS_XMAC1 0x61000 -#define NETX_OFS_XMAC2 0x62000 -#define NETX_OFS_XMAC3 0x63000 -#define NETX_OFS_XMAC(no) (0x60000 + (no) * 0x1000) -#define NETX_OFS_PFIFO 0x64000 -#define NETX_OFS_XPEC0 0x70000 -#define NETX_OFS_XPEC1 0x74000 -#define NETX_OFS_XPEC2 0x78000 -#define NETX_OFS_XPEC3 0x7c000 -#define NETX_OFS_XPEC(no) (0x70000 + (no) * 0x4000) -#define NETX_OFS_VIC 0xff000 - -/* physical addresses */ -#define NETX_PA_SYSTEM (NETX_IO_PHYS + NETX_OFS_SYSTEM) -#define NETX_PA_MEMCR (NETX_IO_PHYS + NETX_OFS_MEMCR) -#define NETX_PA_DPMAS (NETX_IO_PHYS + NETX_OFS_DPMAS) -#define NETX_PA_GPIO (NETX_IO_PHYS + NETX_OFS_GPIO) -#define NETX_PA_PIO (NETX_IO_PHYS + NETX_OFS_PIO) -#define NETX_PA_UART0 (NETX_IO_PHYS + NETX_OFS_UART0) -#define NETX_PA_UART1 (NETX_IO_PHYS + NETX_OFS_UART1) -#define NETX_PA_UART2 (NETX_IO_PHYS + NETX_OFS_UART2) -#define NETX_PA_MIIMU (NETX_IO_PHYS + NETX_OF_MIIMU) -#define NETX_PA_SPI (NETX_IO_PHYS + NETX_OFS_SPI) -#define NETX_PA_I2C (NETX_IO_PHYS + NETX_OFS_I2C) -#define NETX_PA_SYSTIME (NETX_IO_PHYS + NETX_OFS_SYSTIME) -#define NETX_PA_RTC (NETX_IO_PHYS + NETX_OFS_RTC) -#define NETX_PA_EXTBUS (NETX_IO_PHYS + NETX_OFS_EXTBUS) -#define NETX_PA_LCD (NETX_IO_PHYS + NETX_OFS_LCD) -#define NETX_PA_USB (NETX_IO_PHYS + NETX_OFS_USB) -#define NETX_PA_XMAC0 (NETX_IO_PHYS + NETX_OFS_XMAC0) -#define NETX_PA_XMAC1 (NETX_IO_PHYS + NETX_OFS_XMAC1) -#define NETX_PA_XMAC2 (NETX_IO_PHYS + NETX_OFS_XMAC2) -#define NETX_PA_XMAC3 (NETX_IO_PHYS + NETX_OFS_XMAC3) -#define NETX_PA_XMAC(no) (NETX_IO_PHYS + NETX_OFS_XMAC(no)) -#define NETX_PA_PFIFO (NETX_IO_PHYS + NETX_OFS_PFIFO) -#define NETX_PA_XPEC0 (NETX_IO_PHYS + NETX_OFS_XPEC0) -#define NETX_PA_XPEC1 (NETX_IO_PHYS + NETX_OFS_XPEC1) -#define NETX_PA_XPEC2 (NETX_IO_PHYS + NETX_OFS_XPEC2) -#define NETX_PA_XPEC3 (NETX_IO_PHYS + NETX_OFS_XPEC3) -#define NETX_PA_XPEC(no) (NETX_IO_PHYS + NETX_OFS_XPEC(no)) -#define NETX_PA_VIC (NETX_IO_PHYS + NETX_OFS_VIC) - -/* virtual addresses */ -#define NETX_VA_SYSTEM (NETX_IO_VIRT + NETX_OFS_SYSTEM) -#define NETX_VA_MEMCR (NETX_IO_VIRT + NETX_OFS_MEMCR) -#define NETX_VA_DPMAS (NETX_IO_VIRT + NETX_OFS_DPMAS) -#define NETX_VA_GPIO (NETX_IO_VIRT + NETX_OFS_GPIO) -#define NETX_VA_PIO (NETX_IO_VIRT + NETX_OFS_PIO) -#define NETX_VA_UART0 (NETX_IO_VIRT + NETX_OFS_UART0) -#define NETX_VA_UART1 (NETX_IO_VIRT + NETX_OFS_UART1) -#define NETX_VA_UART2 (NETX_IO_VIRT + NETX_OFS_UART2) -#define NETX_VA_MIIMU (NETX_IO_VIRT + NETX_OF_MIIMU) -#define NETX_VA_SPI (NETX_IO_VIRT + NETX_OFS_SPI) -#define NETX_VA_I2C (NETX_IO_VIRT + NETX_OFS_I2C) -#define NETX_VA_SYSTIME (NETX_IO_VIRT + NETX_OFS_SYSTIME) -#define NETX_VA_RTC (NETX_IO_VIRT + NETX_OFS_RTC) -#define NETX_VA_EXTBUS (NETX_IO_VIRT + NETX_OFS_EXTBUS) -#define NETX_VA_LCD (NETX_IO_VIRT + NETX_OFS_LCD) -#define NETX_VA_USB (NETX_IO_VIRT + NETX_OFS_USB) -#define NETX_VA_XMAC0 (NETX_IO_VIRT + NETX_OFS_XMAC0) -#define NETX_VA_XMAC1 (NETX_IO_VIRT + NETX_OFS_XMAC1) -#define NETX_VA_XMAC2 (NETX_IO_VIRT + NETX_OFS_XMAC2) -#define NETX_VA_XMAC3 (NETX_IO_VIRT + NETX_OFS_XMAC3) -#define NETX_VA_XMAC(no) (NETX_IO_VIRT + NETX_OFS_XMAC(no)) -#define NETX_VA_PFIFO (NETX_IO_VIRT + NETX_OFS_PFIFO) -#define NETX_VA_XPEC0 (NETX_IO_VIRT + NETX_OFS_XPEC0) -#define NETX_VA_XPEC1 (NETX_IO_VIRT + NETX_OFS_XPEC1) -#define NETX_VA_XPEC2 (NETX_IO_VIRT + NETX_OFS_XPEC2) -#define NETX_VA_XPEC3 (NETX_IO_VIRT + NETX_OFS_XPEC3) -#define NETX_VA_XPEC(no) (NETX_IO_VIRT + NETX_OFS_XPEC(no)) -#define NETX_VA_VIC (NETX_IO_VIRT + NETX_OFS_VIC) - -/********************************* - * System functions * - *********************************/ - -/* Registers */ -#define NETX_SYSTEM_REG(ofs) IOMEM(NETX_VA_SYSTEM + (ofs)) -#define NETX_SYSTEM_BOO_SR NETX_SYSTEM_REG(0x00) -#define NETX_SYSTEM_IOC_CR NETX_SYSTEM_REG(0x04) -#define NETX_SYSTEM_IOC_MR NETX_SYSTEM_REG(0x08) - -/* FIXME: Docs are not consistent */ -/* #define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x08) */ -#define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x0c) - -#define NETX_SYSTEM_PHY_CONTROL NETX_SYSTEM_REG(0x10) -#define NETX_SYSTEM_REV NETX_SYSTEM_REG(0x34) -#define NETX_SYSTEM_IOC_ACCESS_KEY NETX_SYSTEM_REG(0x70) -#define NETX_SYSTEM_WDG_TR NETX_SYSTEM_REG(0x200) -#define NETX_SYSTEM_WDG_CTR NETX_SYSTEM_REG(0x204) -#define NETX_SYSTEM_WDG_IRQ_TIMEOUT NETX_SYSTEM_REG(0x208) -#define NETX_SYSTEM_WDG_RES_TIMEOUT NETX_SYSTEM_REG(0x20c) - -/* Bits */ -#define NETX_SYSTEM_RES_CR_RSTIN (1<<0) -#define NETX_SYSTEM_RES_CR_WDG_RES (1<<1) -#define NETX_SYSTEM_RES_CR_HOST_RES (1<<2) -#define NETX_SYSTEM_RES_CR_FIRMW_RES (1<<3) -#define NETX_SYSTEM_RES_CR_XPEC0_RES (1<<4) -#define NETX_SYSTEM_RES_CR_XPEC1_RES (1<<5) -#define NETX_SYSTEM_RES_CR_XPEC2_RES (1<<6) -#define NETX_SYSTEM_RES_CR_XPEC3_RES (1<<7) -#define NETX_SYSTEM_RES_CR_DIS_XPEC0_RES (1<<16) -#define NETX_SYSTEM_RES_CR_DIS_XPEC1_RES (1<<17) -#define NETX_SYSTEM_RES_CR_DIS_XPEC2_RES (1<<18) -#define NETX_SYSTEM_RES_CR_DIS_XPEC3_RES (1<<19) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG0 (1<<20) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG1 (1<<21) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG2 (1<<22) -#define NETX_SYSTEM_RES_CR_FIRMW_FLG3 (1<<23) -#define NETX_SYSTEM_RES_CR_FIRMW_RES_EN (1<<24) -#define NETX_SYSTEM_RES_CR_RSTOUT (1<<25) -#define NETX_SYSTEM_RES_CR_EN_RSTOUT (1<<26) - -#define PHY_CONTROL_RESET (1<<31) -#define PHY_CONTROL_SIM_BYP (1<<30) -#define PHY_CONTROL_CLK_XLATIN (1<<29) -#define PHY_CONTROL_PHY1_EN (1<<21) -#define PHY_CONTROL_PHY1_NP_MSG_CODE -#define PHY_CONTROL_PHY1_AUTOMDIX (1<<17) -#define PHY_CONTROL_PHY1_FIXMODE (1<<16) -#define PHY_CONTROL_PHY1_MODE(mode) (((mode) & 0x7) << 13) -#define PHY_CONTROL_PHY0_EN (1<<12) -#define PHY_CONTROL_PHY0_NP_MSG_CODE -#define PHY_CONTROL_PHY0_AUTOMDIX (1<<8) -#define PHY_CONTROL_PHY0_FIXMODE (1<<7) -#define PHY_CONTROL_PHY0_MODE(mode) (((mode) & 0x7) << 4) -#define PHY_CONTROL_PHY_ADDRESS(adr) ((adr) & 0xf) - -#define PHY_MODE_10BASE_T_HALF 0 -#define PHY_MODE_10BASE_T_FULL 1 -#define PHY_MODE_100BASE_TX_FX_FULL 2 -#define PHY_MODE_100BASE_TX_FX_HALF 3 -#define PHY_MODE_100BASE_TX_HALF 4 -#define PHY_MODE_REPEATER 5 -#define PHY_MODE_POWER_DOWN 6 -#define PHY_MODE_ALL 7 - -/* Bits */ -#define VECT_CNTL_ENABLE (1 << 5) - -/******************************* - * GPIO and timer module * - *******************************/ - -/* Registers */ -#define NETX_GPIO_REG(ofs) IOMEM(NETX_VA_GPIO + (ofs)) -#define NETX_GPIO_CFG(gpio) NETX_GPIO_REG(0x0 + ((gpio)<<2)) -#define NETX_GPIO_THRESHOLD_CAPTURE(gpio) NETX_GPIO_REG(0x40 + ((gpio)<<2)) -#define NETX_GPIO_COUNTER_CTRL(counter) NETX_GPIO_REG(0x80 + ((counter)<<2)) -#define NETX_GPIO_COUNTER_MAX(counter) NETX_GPIO_REG(0x94 + ((counter)<<2)) -#define NETX_GPIO_COUNTER_CURRENT(counter) NETX_GPIO_REG(0xa8 + ((counter)<<2)) -#define NETX_GPIO_IRQ_ENABLE NETX_GPIO_REG(0xbc) -#define NETX_GPIO_IRQ_DISABLE NETX_GPIO_REG(0xc0) -#define NETX_GPIO_SYSTIME_NS_CMP NETX_GPIO_REG(0xc4) -#define NETX_GPIO_LINE NETX_GPIO_REG(0xc8) -#define NETX_GPIO_IRQ NETX_GPIO_REG(0xd0) - -/* Bits */ -#define NETX_GPIO_CFG_IOCFG_GP_INPUT (0x0) -#define NETX_GPIO_CFG_IOCFG_GP_OUTPUT (0x1) -#define NETX_GPIO_CFG_IOCFG_GP_UART (0x2) -#define NETX_GPIO_CFG_INV (1<<2) -#define NETX_GPIO_CFG_MODE_INPUT_READ (0<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_CONT_RISING (1<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_ONCE_RISING (2<<3) -#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_HIGH_LEVEL (3<<3) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER0 (0<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER1 (1<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER2 (2<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER3 (3<<5) -#define NETX_GPIO_CFG_COUNT_REF_COUNTER4 (4<<5) -#define NETX_GPIO_CFG_COUNT_REF_SYSTIME (7<<5) - -#define NETX_GPIO_COUNTER_CTRL_RUN (1<<0) -#define NETX_GPIO_COUNTER_CTRL_SYM (1<<1) -#define NETX_GPIO_COUNTER_CTRL_ONCE (1<<2) -#define NETX_GPIO_COUNTER_CTRL_IRQ_EN (1<<3) -#define NETX_GPIO_COUNTER_CTRL_CNT_EVENT (1<<4) -#define NETX_GPIO_COUNTER_CTRL_RST_EN (1<<5) -#define NETX_GPIO_COUNTER_CTRL_SEL_EVENT (1<<6) -#define NETX_GPIO_COUNTER_CTRL_GPIO_REF /* FIXME */ - -#define GPIO_BIT(gpio) (1<<(gpio)) -#define COUNTER_BIT(counter) ((1<<16)<<(counter)) - -/******************************* - * PIO * - *******************************/ - -/* Registers */ -#define NETX_PIO_REG(ofs) IOMEM(NETX_VA_PIO + (ofs)) -#define NETX_PIO_INPIO NETX_PIO_REG(0x0) -#define NETX_PIO_OUTPIO NETX_PIO_REG(0x4) -#define NETX_PIO_OEPIO NETX_PIO_REG(0x8) - -/******************************* - * MII Unit * - *******************************/ - -/* Registers */ -#define NETX_MIIMU IOMEM(NETX_VA_MIIMU) - -/* Bits */ -#define MIIMU_SNRDY (1<<0) -#define MIIMU_PREAMBLE (1<<1) -#define MIIMU_OPMODE_WRITE (1<<2) -#define MIIMU_MDC_PERIOD (1<<3) -#define MIIMU_PHY_NRES (1<<4) -#define MIIMU_RTA (1<<5) -#define MIIMU_REGADDR(adr) (((adr) & 0x1f) << 6) -#define MIIMU_PHYADDR(adr) (((adr) & 0x1f) << 11) -#define MIIMU_DATA(data) (((data) & 0xffff) << 16) - -/******************************* - * xmac / xpec * - *******************************/ - -/* XPEC register offsets relative to NETX_VA_XPEC(no) */ -#define NETX_XPEC_R0_OFS 0x00 -#define NETX_XPEC_R1_OFS 0x04 -#define NETX_XPEC_R2_OFS 0x08 -#define NETX_XPEC_R3_OFS 0x0c -#define NETX_XPEC_R4_OFS 0x10 -#define NETX_XPEC_R5_OFS 0x14 -#define NETX_XPEC_R6_OFS 0x18 -#define NETX_XPEC_R7_OFS 0x1c -#define NETX_XPEC_RANGE01_OFS 0x20 -#define NETX_XPEC_RANGE23_OFS 0x24 -#define NETX_XPEC_RANGE45_OFS 0x28 -#define NETX_XPEC_RANGE67_OFS 0x2c -#define NETX_XPEC_PC_OFS 0x48 -#define NETX_XPEC_TIMER_OFS(timer) (0x30 + ((timer)<<2)) -#define NETX_XPEC_IRQ_OFS 0x8c -#define NETX_XPEC_SYSTIME_NS_OFS 0x90 -#define NETX_XPEC_FIFO_DATA_OFS 0x94 -#define NETX_XPEC_SYSTIME_S_OFS 0x98 -#define NETX_XPEC_ADC_OFS 0x9c -#define NETX_XPEC_URX_COUNT_OFS 0x40 -#define NETX_XPEC_UTX_COUNT_OFS 0x44 -#define NETX_XPEC_PC_OFS 0x48 -#define NETX_XPEC_ZERO_OFS 0x4c -#define NETX_XPEC_STATCFG_OFS 0x50 -#define NETX_XPEC_EC_MASKA_OFS 0x54 -#define NETX_XPEC_EC_MASKB_OFS 0x58 -#define NETX_XPEC_EC_MASK0_OFS 0x5c -#define NETX_XPEC_EC_MASK8_OFS 0x7c -#define NETX_XPEC_EC_MASK9_OFS 0x80 -#define NETX_XPEC_XPU_HOLD_PC_OFS 0x100 -#define NETX_XPEC_RAM_START_OFS 0x2000 - -/* Bits */ -#define XPU_HOLD_PC (1<<0) - -/* XMAC register offsets relative to NETX_VA_XMAC(no) */ -#define NETX_XMAC_RPU_PROGRAM_START_OFS 0x000 -#define NETX_XMAC_RPU_PROGRAM_END_OFS 0x3ff -#define NETX_XMAC_TPU_PROGRAM_START_OFS 0x400 -#define NETX_XMAC_TPU_PROGRAM_END_OFS 0x7ff -#define NETX_XMAC_RPU_HOLD_PC_OFS 0xa00 -#define NETX_XMAC_TPU_HOLD_PC_OFS 0xa04 -#define NETX_XMAC_STATUS_SHARED0_OFS 0x840 -#define NETX_XMAC_CONFIG_SHARED0_OFS 0x844 -#define NETX_XMAC_STATUS_SHARED1_OFS 0x848 -#define NETX_XMAC_CONFIG_SHARED1_OFS 0x84c -#define NETX_XMAC_STATUS_SHARED2_OFS 0x850 -#define NETX_XMAC_CONFIG_SHARED2_OFS 0x854 -#define NETX_XMAC_STATUS_SHARED3_OFS 0x858 -#define NETX_XMAC_CONFIG_SHARED3_OFS 0x85c - -#define RPU_HOLD_PC (1<<15) -#define TPU_HOLD_PC (1<<15) - -/******************************* - * Pointer FIFO * - *******************************/ - -/* Registers */ -#define NETX_PFIFO_REG(ofs) IOMEM(NETX_VA_PFIFO + (ofs)) -#define NETX_PFIFO_BASE(pfifo) NETX_PFIFO_REG(0x00 + ((pfifo)<<2)) -#define NETX_PFIFO_BORDER_BASE(pfifo) NETX_PFIFO_REG(0x80 + ((pfifo)<<2)) -#define NETX_PFIFO_RESET NETX_PFIFO_REG(0x100) -#define NETX_PFIFO_FULL NETX_PFIFO_REG(0x104) -#define NETX_PFIFO_EMPTY NETX_PFIFO_REG(0x108) -#define NETX_PFIFO_OVEFLOW NETX_PFIFO_REG(0x10c) -#define NETX_PFIFO_UNDERRUN NETX_PFIFO_REG(0x110) -#define NETX_PFIFO_FILL_LEVEL(pfifo) NETX_PFIFO_REG(0x180 + ((pfifo)<<2)) -#define NETX_PFIFO_XPEC_ISR(xpec) NETX_PFIFO_REG(0x400 + ((xpec) << 2)) - - -/******************************* - * Memory Controller * - *******************************/ - -/* Registers */ -#define NETX_MEMCR_REG(ofs) IOMEM(NETX_VA_MEMCR + (ofs)) -#define NETX_MEMCR_SRAM_CTRL(cs) NETX_MEMCR_REG(0x0 + 4 * (cs)) /* SRAM for CS 0..2 */ -#define NETX_MEMCR_SDRAM_CFG_CTRL NETX_MEMCR_REG(0x40) -#define NETX_MEMCR_SDRAM_TIMING_CTRL NETX_MEMCR_REG(0x44) -#define NETX_MEMCR_SDRAM_MODE NETX_MEMCR_REG(0x48) -#define NETX_MEMCR_SDRAM_EXT_MODE NETX_MEMCR_REG(0x4c) -#define NETX_MEMCR_PRIO_TIMESLOT_CTRL NETX_MEMCR_REG(0x80) -#define NETX_MEMCR_PRIO_ACCESS_CTRL NETX_MEMCR_REG(0x84) - -/* Bits */ -#define NETX_MEMCR_SRAM_CTRL_WIDTHEXTMEM(x) (((x) & 0x3) << 24) -#define NETX_MEMCR_SRAM_CTRL_WSPOSTPAUSEEXTMEM(x) (((x) & 0x3) << 16) -#define NETX_MEMCR_SRAM_CTRL_WSPREPASEEXTMEM(x) (((x) & 0x3) << 8) -#define NETX_MEMCR_SRAM_CTRL_WSEXTMEM(x) (((x) & 0x1f) << 0) - - -/******************************* - * Dual Port Memory * - *******************************/ - -/* Registers */ -#define NETX_DPMAS_REG(ofs) IOMEM(NETX_VA_DPMAS + (ofs)) -#define NETX_DPMAS_SYS_STAT NETX_DPMAS_REG(0x4d8) -#define NETX_DPMAS_INT_STAT NETX_DPMAS_REG(0x4e0) -#define NETX_DPMAS_INT_EN NETX_DPMAS_REG(0x4f0) -#define NETX_DPMAS_IF_CONF0 NETX_DPMAS_REG(0x608) -#define NETX_DPMAS_IF_CONF1 NETX_DPMAS_REG(0x60c) -#define NETX_DPMAS_EXT_CONFIG(cs) NETX_DPMAS_REG(0x610 + 4 * (cs)) -#define NETX_DPMAS_IO_MODE0 NETX_DPMAS_REG(0x620) /* I/O 32..63 */ -#define NETX_DPMAS_DRV_EN0 NETX_DPMAS_REG(0x624) -#define NETX_DPMAS_DATA0 NETX_DPMAS_REG(0x628) -#define NETX_DPMAS_IO_MODE1 NETX_DPMAS_REG(0x630) /* I/O 64..84 */ -#define NETX_DPMAS_DRV_EN1 NETX_DPMAS_REG(0x634) -#define NETX_DPMAS_DATA1 NETX_DPMAS_REG(0x638) - -/* Bits */ -#define NETX_DPMAS_INT_EN_GLB_EN (1<<31) -#define NETX_DPMAS_INT_EN_MEM_LCK (1<<30) -#define NETX_DPMAS_INT_EN_WDG (1<<29) -#define NETX_DPMAS_INT_EN_PIO72 (1<<28) -#define NETX_DPMAS_INT_EN_PIO47 (1<<27) -#define NETX_DPMAS_INT_EN_PIO40 (1<<26) -#define NETX_DPMAS_INT_EN_PIO36 (1<<25) -#define NETX_DPMAS_INT_EN_PIO35 (1<<24) - -#define NETX_DPMAS_IF_CONF0_HIF_DISABLED (0<<28) -#define NETX_DPMAS_IF_CONF0_HIF_EXT_BUS (1<<28) -#define NETX_DPMAS_IF_CONF0_HIF_UP_8BIT (2<<28) -#define NETX_DPMAS_IF_CONF0_HIF_UP_16BIT (3<<28) -#define NETX_DPMAS_IF_CONF0_HIF_IO (4<<28) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_PP (1<<14) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_OD (2<<14) -#define NETX_DPMAS_IF_CONF0_WAIT_DRV_TRI (3<<14) - -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO35 (1<<26) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO36 (1<<27) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO40 (1<<28) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO47 (1<<29) -#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO72 (1<<30) - -#define NETX_EXT_CONFIG_TALEWIDTH(x) (((x) & 0x7) << 29) -#define NETX_EXT_CONFIG_TADRHOLD(x) (((x) & 0x7) << 26) -#define NETX_EXT_CONFIG_TCSON(x) (((x) & 0x7) << 23) -#define NETX_EXT_CONFIG_TRDON(x) (((x) & 0x7) << 20) -#define NETX_EXT_CONFIG_TWRON(x) (((x) & 0x7) << 17) -#define NETX_EXT_CONFIG_TWROFF(x) (((x) & 0x1f) << 12) -#define NETX_EXT_CONFIG_TRDWRCYC(x) (((x) & 0x1f) << 7) -#define NETX_EXT_CONFIG_WAIT_POL (1<<6) -#define NETX_EXT_CONFIG_WAIT_EN (1<<5) -#define NETX_EXT_CONFIG_NRD_MODE (1<<4) -#define NETX_EXT_CONFIG_DS_MODE (1<<3) -#define NETX_EXT_CONFIG_NWR_MODE (1<<2) -#define NETX_EXT_CONFIG_16BIT (1<<1) -#define NETX_EXT_CONFIG_CS_ENABLE (1<<0) - -#define NETX_DPMAS_IO_MODE0_WRL (1<<13) -#define NETX_DPMAS_IO_MODE0_WAIT (1<<14) -#define NETX_DPMAS_IO_MODE0_READY (1<<15) -#define NETX_DPMAS_IO_MODE0_CS0 (1<<19) -#define NETX_DPMAS_IO_MODE0_EXTRD (1<<20) - -#define NETX_DPMAS_IO_MODE1_CS2 (1<<15) -#define NETX_DPMAS_IO_MODE1_CS1 (1<<16) -#define NETX_DPMAS_IO_MODE1_SAMPLE_NPOR (0<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_100MHZ (1<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_NPIO36 (2<<30) -#define NETX_DPMAS_IO_MODE1_SAMPLE_PIO36 (3<<30) - -/******************************* - * I2C * - *******************************/ -#define NETX_I2C_REG(ofs) IOMEM(NETX_VA_I2C, (ofs)) -#define NETX_I2C_CTRL NETX_I2C_REG(0x0) -#define NETX_I2C_DATA NETX_I2C_REG(0x4) - -#endif /* __ASM_ARCH_NETX_REGS_H */ diff --git a/arch/arm/mach-netx/include/mach/pfifo.h b/arch/arm/mach-netx/include/mach/pfifo.h deleted file mode 100644 index de23180bc937..000000000000 --- a/arch/arm/mach-netx/include/mach/pfifo.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/pfifo.h - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - - -#ifndef ASM_ARCH_PFIFO_H -#define ASM_ARCH_PFIFO_H - -static inline int pfifo_push(int no, unsigned int pointer) -{ - writel(pointer, NETX_PFIFO_BASE(no)); - return 0; -} - -static inline unsigned int pfifo_pop(int no) -{ - return readl(NETX_PFIFO_BASE(no)); -} - -static inline int pfifo_fill_level(int no) -{ - - return readl(NETX_PFIFO_FILL_LEVEL(no)); -} - -static inline int pfifo_full(int no) -{ - return readl(NETX_PFIFO_FULL) & (1<<no) ? 1 : 0; -} - -static inline int pfifo_empty(int no) -{ - return readl(NETX_PFIFO_EMPTY) & (1<<no) ? 1 : 0; -} - -int pfifo_request(unsigned int pfifo_mask); -void pfifo_free(unsigned int pfifo_mask); - -#endif /* ASM_ARCH_PFIFO_H */ diff --git a/arch/arm/mach-netx/include/mach/uncompress.h b/arch/arm/mach-netx/include/mach/uncompress.h deleted file mode 100644 index edc1ac997eab..000000000000 --- a/arch/arm/mach-netx/include/mach/uncompress.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/uncompress.h - * - * Copyright (C) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -/* - * The following code assumes the serial port has already been - * initialized by the bootloader. We search for the first enabled - * port in the most probable order. If you didn't setup a port in - * your bootloader then nothing will appear (which might be desired). - * - * This does not append a newline - */ - -#define REG(x) (*(volatile unsigned long *)(x)) - -#define UART1_BASE 0x100a00 -#define UART2_BASE 0x100a80 - -#define UART_DR 0x0 - -#define UART_CR 0x14 -#define CR_UART_EN (1<<0) - -#define UART_FR 0x18 -#define FR_BUSY (1<<3) -#define FR_TXFF (1<<5) - -static inline void putc(char c) -{ - unsigned long base; - - if (REG(UART1_BASE + UART_CR) & CR_UART_EN) - base = UART1_BASE; - else if (REG(UART2_BASE + UART_CR) & CR_UART_EN) - base = UART2_BASE; - else - return; - - while (REG(base + UART_FR) & FR_TXFF); - REG(base + UART_DR) = c; -} - -static inline void flush(void) -{ - unsigned long base; - - if (REG(UART1_BASE + UART_CR) & CR_UART_EN) - base = UART1_BASE; - else if (REG(UART2_BASE + UART_CR) & CR_UART_EN) - base = UART2_BASE; - else - return; - - while (REG(base + UART_FR) & FR_BUSY); -} - -/* - * nothing to do - */ -#define arch_decomp_setup() diff --git a/arch/arm/mach-netx/include/mach/xc.h b/arch/arm/mach-netx/include/mach/xc.h deleted file mode 100644 index 465d5e250ab8..000000000000 --- a/arch/arm/mach-netx/include/mach/xc.h +++ /dev/null @@ -1,30 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm/mach-netx/include/mach/xc.h - * - * Copyright (C) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#ifndef __ASM_ARCH_XC_H -#define __ASM_ARCH_XC_H - -struct xc { - int no; - unsigned int type; - unsigned int version; - void __iomem *xpec_base; - void __iomem *xmac_base; - void __iomem *sram_base; - int irq; - struct device *dev; -}; - -int xc_reset(struct xc *x); -int xc_stop(struct xc* x); -int xc_start(struct xc *x); -int xc_running(struct xc *x); -int xc_request_firmware(struct xc* x); -struct xc* request_xc(int xcno, struct device *dev); -void free_xc(struct xc *x); - -#endif /* __ASM_ARCH_XC_H */ diff --git a/arch/arm/mach-netx/nxdb500.c b/arch/arm/mach-netx/nxdb500.c deleted file mode 100644 index ad5e6747b834..000000000000 --- a/arch/arm/mach-netx/nxdb500.c +++ /dev/null @@ -1,197 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxdb500.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/dma-mapping.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/mtd/plat-ram.h> -#include <linux/platform_device.h> -#include <linux/amba/bus.h> -#include <linux/amba/clcd.h> - -#include <mach/hardware.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <mach/netx-regs.h> -#include <linux/platform_data/eth-netx.h> - -#include "generic.h" -#include "fb.h" - -static struct clcd_panel qvga = { - .mode = { - .name = "QVGA", - .refresh = 60, - .xres = 240, - .yres = 320, - .pixclock = 187617, - .left_margin = 6, - .right_margin = 26, - .upper_margin = 0, - .lower_margin = 6, - .hsync_len = 6, - .vsync_len = 1, - .sync = 0, - .vmode = FB_VMODE_NONINTERLACED, - }, - .width = -1, - .height = -1, - .tim2 = 16, - .cntl = CNTL_LCDTFT | CNTL_BGR, - .bpp = 16, - .grayscale = 0, -}; - -static inline int nxdb500_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->green.length = 5; - var->green.msb_right = 0; - - return clcdfb_check(fb, var); -} - -static int nxdb500_clcd_setup(struct clcd_fb *fb) -{ - unsigned int val; - - fb->fb.var.green.length = 5; - fb->fb.var.green.msb_right = 0; - - /* enable asic control */ - val = readl(NETX_SYSTEM_IOC_ACCESS_KEY); - writel(val, NETX_SYSTEM_IOC_ACCESS_KEY); - - writel(3, NETX_SYSTEM_IOC_CR); - - val = readl(NETX_PIO_OUTPIO); - writel(val | 1, NETX_PIO_OUTPIO); - - val = readl(NETX_PIO_OEPIO); - writel(val | 1, NETX_PIO_OEPIO); - return netx_clcd_setup(fb); -} - -static struct clcd_board clcd_data = { - .name = "netX", - .check = nxdb500_check, - .decode = clcdfb_decode, - .enable = netx_clcd_enable, - .setup = nxdb500_clcd_setup, - .mmap = netx_clcd_mmap, - .remove = netx_clcd_remove, -}; - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device netx_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device netx_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct resource netx_uart1_resources[] = { - [0] = { - .start = 0x00100A40, - .end = 0x00100A7F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART1), - .end = (NETX_IRQ_UART1), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart1_device = { - .name = "netx-uart", - .id = 1, - .num_resources = ARRAY_SIZE(netx_uart1_resources), - .resource = netx_uart1_resources, -}; - -static struct resource netx_uart2_resources[] = { - [0] = { - .start = 0x00100A80, - .end = 0x00100ABF, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART2), - .end = (NETX_IRQ_UART2), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart2_device = { - .name = "netx-uart", - .id = 2, - .num_resources = ARRAY_SIZE(netx_uart2_resources), - .resource = netx_uart2_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_eth0_device, - &netx_eth1_device, - &netx_uart0_device, - &netx_uart1_device, - &netx_uart2_device, -}; - -static void __init nxdb500_init(void) -{ - netx_fb_init(&clcd_data, &qvga); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXDB500, "Hilscher nxdb500") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxdb500_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/nxdkn.c b/arch/arm/mach-netx/nxdkn.c deleted file mode 100644 index 917381559628..000000000000 --- a/arch/arm/mach-netx/nxdkn.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxdkn.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/dma-mapping.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/mtd/plat-ram.h> -#include <linux/platform_device.h> -#include <linux/amba/bus.h> -#include <linux/amba/clcd.h> - -#include <mach/hardware.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <mach/netx-regs.h> -#include <linux/platform_data/eth-netx.h> - -#include "generic.h" - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device nxdkn_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device nxdkn_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct platform_device *devices[] __initdata = { - &nxdkn_eth0_device, - &nxdkn_eth1_device, - &netx_uart0_device, -}; - -static void __init nxdkn_init(void) -{ - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXDKN, "Hilscher nxdkn") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxdkn_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/nxeb500hmi.c b/arch/arm/mach-netx/nxeb500hmi.c deleted file mode 100644 index aa0d5b2ca712..000000000000 --- a/arch/arm/mach-netx/nxeb500hmi.c +++ /dev/null @@ -1,174 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/nxeb500hmi.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/dma-mapping.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/mtd/plat-ram.h> -#include <linux/platform_device.h> -#include <linux/amba/bus.h> -#include <linux/amba/clcd.h> - -#include <mach/hardware.h> -#include <asm/mach-types.h> -#include <asm/mach/arch.h> -#include <mach/netx-regs.h> -#include <linux/platform_data/eth-netx.h> - -#include "generic.h" -#include "fb.h" - -static struct clcd_panel qvga = { - .mode = { - .name = "QVGA", - .refresh = 60, - .xres = 240, - .yres = 320, - .pixclock = 187617, - .left_margin = 6, - .right_margin = 26, - .upper_margin = 0, - .lower_margin = 6, - .hsync_len = 6, - .vsync_len = 1, - .sync = 0, - .vmode = FB_VMODE_NONINTERLACED, - }, - .width = -1, - .height = -1, - .tim2 = 16, - .cntl = CNTL_LCDTFT | CNTL_BGR, - .bpp = 16, - .grayscale = 0, -}; - -static inline int nxeb500hmi_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) -{ - var->green.length = 5; - var->green.msb_right = 0; - - return clcdfb_check(fb, var); -} - -static int nxeb500hmi_clcd_setup(struct clcd_fb *fb) -{ - unsigned int val; - - fb->fb.var.green.length = 5; - fb->fb.var.green.msb_right = 0; - - /* enable asic control */ - val = readl(NETX_SYSTEM_IOC_ACCESS_KEY); - writel(val, NETX_SYSTEM_IOC_ACCESS_KEY); - - writel(3, NETX_SYSTEM_IOC_CR); - - /* GPIO 14 is used for display enable on newer boards */ - writel(9, NETX_GPIO_CFG(14)); - - val = readl(NETX_PIO_OUTPIO); - writel(val | 1, NETX_PIO_OUTPIO); - - val = readl(NETX_PIO_OEPIO); - writel(val | 1, NETX_PIO_OEPIO); - return netx_clcd_setup(fb); -} - -static struct clcd_board clcd_data = { - .name = "netX", - .check = nxeb500hmi_check, - .decode = clcdfb_decode, - .enable = netx_clcd_enable, - .setup = nxeb500hmi_clcd_setup, - .mmap = netx_clcd_mmap, - .remove = netx_clcd_remove, -}; - -static struct netxeth_platform_data eth0_platform_data = { - .xcno = 0, -}; - -static struct platform_device netx_eth0_device = { - .name = "netx-eth", - .id = 0, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð0_platform_data, - } -}; - -static struct netxeth_platform_data eth1_platform_data = { - .xcno = 1, -}; - -static struct platform_device netx_eth1_device = { - .name = "netx-eth", - .id = 1, - .num_resources = 0, - .resource = NULL, - .dev = { - .platform_data = ð1_platform_data, - } -}; - -static struct resource netx_cf_resources[] = { - [0] = { - .start = 0x20000000, - .end = 0x25ffffff, - .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT, - }, -}; - -static struct platform_device netx_cf_device = { - .name = "netx-cf", - .id = 0, - .resource = netx_cf_resources, - .num_resources = ARRAY_SIZE(netx_cf_resources), -}; - -static struct resource netx_uart0_resources[] = { - [0] = { - .start = 0x00100A00, - .end = 0x00100A3F, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = (NETX_IRQ_UART0), - .end = (NETX_IRQ_UART0), - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device netx_uart0_device = { - .name = "netx-uart", - .id = 0, - .num_resources = ARRAY_SIZE(netx_uart0_resources), - .resource = netx_uart0_resources, -}; - -static struct platform_device *devices[] __initdata = { - &netx_eth0_device, - &netx_eth1_device, - &netx_cf_device, - &netx_uart0_device, -}; - -static void __init nxeb500hmi_init(void) -{ - netx_fb_init(&clcd_data, &qvga); - platform_add_devices(devices, ARRAY_SIZE(devices)); -} - -MACHINE_START(NXEB500HMI, "Hilscher nxeb500hmi") - .atag_offset = 0x100, - .map_io = netx_map_io, - .init_irq = netx_init_irq, - .init_time = netx_timer_init, - .init_machine = nxeb500hmi_init, - .restart = netx_restart, -MACHINE_END diff --git a/arch/arm/mach-netx/pfifo.c b/arch/arm/mach-netx/pfifo.c deleted file mode 100644 index 2e5cc777329f..000000000000 --- a/arch/arm/mach-netx/pfifo.c +++ /dev/null @@ -1,56 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/pfifo.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mutex.h> -#include <linux/io.h> - -#include <mach/hardware.h> -#include <mach/netx-regs.h> -#include <mach/pfifo.h> - -static DEFINE_MUTEX(pfifo_lock); - -static unsigned int pfifo_used = 0; - -int pfifo_request(unsigned int pfifo_mask) -{ - int err = 0; - unsigned int val; - - mutex_lock(&pfifo_lock); - - if (pfifo_mask & pfifo_used) { - err = -EBUSY; - goto out; - } - - pfifo_used |= pfifo_mask; - - val = readl(NETX_PFIFO_RESET); - writel(val | pfifo_mask, NETX_PFIFO_RESET); - writel(val, NETX_PFIFO_RESET); - -out: - mutex_unlock(&pfifo_lock); - return err; -} - -void pfifo_free(unsigned int pfifo_mask) -{ - mutex_lock(&pfifo_lock); - pfifo_used &= ~pfifo_mask; - mutex_unlock(&pfifo_lock); -} - -EXPORT_SYMBOL(pfifo_push); -EXPORT_SYMBOL(pfifo_pop); -EXPORT_SYMBOL(pfifo_fill_level); -EXPORT_SYMBOL(pfifo_empty); -EXPORT_SYMBOL(pfifo_request); -EXPORT_SYMBOL(pfifo_free); diff --git a/arch/arm/mach-netx/time.c b/arch/arm/mach-netx/time.c deleted file mode 100644 index d9defa1ab605..000000000000 --- a/arch/arm/mach-netx/time.c +++ /dev/null @@ -1,141 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/time.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/clocksource.h> -#include <linux/clockchips.h> -#include <linux/io.h> - -#include <mach/hardware.h> -#include <asm/mach/time.h> -#include <mach/netx-regs.h> - -#define NETX_CLOCK_FREQ 100000000 -#define NETX_LATCH DIV_ROUND_CLOSEST(NETX_CLOCK_FREQ, HZ) - -#define TIMER_CLOCKEVENT 0 -#define TIMER_CLOCKSOURCE 1 - -static inline void timer_shutdown(struct clock_event_device *evt) -{ - /* disable timer */ - writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); -} - -static int netx_shutdown(struct clock_event_device *evt) -{ - timer_shutdown(evt); - - return 0; -} - -static int netx_set_oneshot(struct clock_event_device *evt) -{ - u32 tmode = NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN; - - timer_shutdown(evt); - writel(0, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT)); - writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); - - return 0; -} - -static int netx_set_periodic(struct clock_event_device *evt) -{ - u32 tmode = NETX_GPIO_COUNTER_CTRL_RST_EN | - NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN; - - timer_shutdown(evt); - writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT)); - writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT)); - - return 0; -} - -static int netx_set_next_event(unsigned long evt, - struct clock_event_device *clk) -{ - writel(0 - evt, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKEVENT)); - return 0; -} - -static struct clock_event_device netx_clockevent = { - .name = "netx-timer" __stringify(TIMER_CLOCKEVENT), - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_next_event = netx_set_next_event, - .set_state_shutdown = netx_shutdown, - .set_state_periodic = netx_set_periodic, - .set_state_oneshot = netx_set_oneshot, - .tick_resume = netx_shutdown, -}; - -/* - * IRQ handler for the timer - */ -static irqreturn_t -netx_timer_interrupt(int irq, void *dev_id) -{ - struct clock_event_device *evt = &netx_clockevent; - - /* acknowledge interrupt */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ); - - evt->event_handler(evt); - - return IRQ_HANDLED; -} - -static struct irqaction netx_timer_irq = { - .name = "NetX Timer Tick", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = netx_timer_interrupt, -}; - -/* - * Set up timer interrupt - */ -void __init netx_timer_init(void) -{ - /* disable timer initially */ - writel(0, NETX_GPIO_COUNTER_CTRL(0)); - - /* Reset the timer value to zero */ - writel(0, NETX_GPIO_COUNTER_CURRENT(0)); - - writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(0)); - - /* acknowledge interrupt */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ); - - /* Enable the interrupt in the specific timer - * register and start timer - */ - writel(COUNTER_BIT(0), NETX_GPIO_IRQ_ENABLE); - writel(NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN, - NETX_GPIO_COUNTER_CTRL(0)); - - setup_irq(NETX_IRQ_TIMER0, &netx_timer_irq); - - /* Setup timer one for clocksource */ - writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE)); - writel(0, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE)); - writel(0xffffffff, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKSOURCE)); - - writel(NETX_GPIO_COUNTER_CTRL_RUN, - NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE)); - - clocksource_mmio_init(NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE), - "netx_timer", NETX_CLOCK_FREQ, 200, 32, clocksource_mmio_readl_up); - - /* with max_delta_ns >= delta2ns(0x800) the system currently runs fine. - * Adding some safety ... */ - netx_clockevent.cpumask = cpumask_of(0); - clockevents_config_and_register(&netx_clockevent, NETX_CLOCK_FREQ, - 0xa00, 0xfffffffe); -} diff --git a/arch/arm/mach-netx/xc.c b/arch/arm/mach-netx/xc.c deleted file mode 100644 index 885a618b2651..000000000000 --- a/arch/arm/mach-netx/xc.c +++ /dev/null @@ -1,246 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mach-netx/xc.c - * - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#include <linux/init.h> -#include <linux/device.h> -#include <linux/firmware.h> -#include <linux/mutex.h> -#include <linux/slab.h> -#include <linux/io.h> -#include <linux/export.h> - -#include <mach/hardware.h> -#include <mach/irqs.h> -#include <mach/netx-regs.h> - -#include <mach/xc.h> - -static DEFINE_MUTEX(xc_lock); - -static int xc_in_use = 0; - -struct fw_desc { - unsigned int ofs; - unsigned int size; - unsigned int patch_ofs; - unsigned int patch_entries; -}; - -struct fw_header { - unsigned int magic; - unsigned int type; - unsigned int version; - unsigned int reserved[5]; - struct fw_desc fw_desc[3]; -} __attribute__ ((packed)); - -int xc_stop(struct xc *x) -{ - writel(RPU_HOLD_PC, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS); - writel(TPU_HOLD_PC, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS); - writel(XPU_HOLD_PC, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS); - return 0; -} - -int xc_start(struct xc *x) -{ - writel(0, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS); - writel(0, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS); - writel(0, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS); - return 0; -} - -int xc_running(struct xc *x) -{ - return (readl(x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS) & RPU_HOLD_PC) - || (readl(x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS) & TPU_HOLD_PC) - || (readl(x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS) & XPU_HOLD_PC) ? - 0 : 1; -} - -int xc_reset(struct xc *x) -{ - writel(0, x->xpec_base + NETX_XPEC_PC_OFS); - return 0; -} - -static int xc_check_ptr(struct xc *x, unsigned long adr, unsigned int size) -{ - if (adr >= NETX_PA_XMAC(x->no) && - adr + size < NETX_PA_XMAC(x->no) + XMAC_MEM_SIZE) - return 0; - - if (adr >= NETX_PA_XPEC(x->no) && - adr + size < NETX_PA_XPEC(x->no) + XPEC_MEM_SIZE) - return 0; - - dev_err(x->dev, "Illegal pointer in firmware found. aborting\n"); - - return -1; -} - -static int xc_patch(struct xc *x, const void *patch, int count) -{ - unsigned int val, adr; - const unsigned int *data = patch; - - int i; - for (i = 0; i < count; i++) { - adr = *data++; - val = *data++; - if (xc_check_ptr(x, adr, 4) < 0) - return -EINVAL; - - writel(val, (void __iomem *)io_p2v(adr)); - } - return 0; -} - -int xc_request_firmware(struct xc *x) -{ - int ret; - char name[16]; - const struct firmware *fw; - struct fw_header *head; - unsigned int size; - int i; - const void *src; - unsigned long dst; - - sprintf(name, "xc%d.bin", x->no); - - ret = request_firmware(&fw, name, x->dev); - - if (ret < 0) { - dev_err(x->dev, "request_firmware failed\n"); - return ret; - } - - head = (struct fw_header *)fw->data; - if (head->magic != 0x4e657458) { - if (head->magic == 0x5874654e) { - dev_err(x->dev, - "firmware magic is 'XteN'. Endianness problems?\n"); - ret = -ENODEV; - goto exit_release_firmware; - } - dev_err(x->dev, "unrecognized firmware magic 0x%08x\n", - head->magic); - ret = -ENODEV; - goto exit_release_firmware; - } - - x->type = head->type; - x->version = head->version; - - ret = -EINVAL; - - for (i = 0; i < 3; i++) { - src = fw->data + head->fw_desc[i].ofs; - dst = *(unsigned int *)src; - src += sizeof (unsigned int); - size = head->fw_desc[i].size - sizeof (unsigned int); - - if (xc_check_ptr(x, dst, size)) - goto exit_release_firmware; - - memcpy((void *)io_p2v(dst), src, size); - - src = fw->data + head->fw_desc[i].patch_ofs; - size = head->fw_desc[i].patch_entries; - ret = xc_patch(x, src, size); - if (ret < 0) - goto exit_release_firmware; - } - - ret = 0; - - exit_release_firmware: - release_firmware(fw); - - return ret; -} - -struct xc *request_xc(int xcno, struct device *dev) -{ - struct xc *x = NULL; - - mutex_lock(&xc_lock); - - if (xcno > 3) - goto exit; - if (xc_in_use & (1 << xcno)) - goto exit; - - x = kmalloc(sizeof (struct xc), GFP_KERNEL); - if (!x) - goto exit; - - if (!request_mem_region - (NETX_PA_XPEC(xcno), XPEC_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_free; - - if (!request_mem_region - (NETX_PA_XMAC(xcno), XMAC_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_release_1; - - if (!request_mem_region - (SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE, kobject_name(&dev->kobj))) - goto exit_release_2; - - x->xpec_base = (void * __iomem)io_p2v(NETX_PA_XPEC(xcno)); - x->xmac_base = (void * __iomem)io_p2v(NETX_PA_XMAC(xcno)); - x->sram_base = ioremap(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - if (!x->sram_base) - goto exit_release_3; - - x->irq = NETX_IRQ_XPEC(xcno); - - x->no = xcno; - x->dev = dev; - - xc_in_use |= (1 << xcno); - - goto exit; - - exit_release_3: - release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - exit_release_2: - release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE); - exit_release_1: - release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE); - exit_free: - kfree(x); - x = NULL; - exit: - mutex_unlock(&xc_lock); - return x; -} - -void free_xc(struct xc *x) -{ - int xcno = x->no; - - mutex_lock(&xc_lock); - - iounmap(x->sram_base); - release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE); - release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE); - release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE); - xc_in_use &= ~(1 << x->no); - kfree(x); - - mutex_unlock(&xc_lock); -} - -EXPORT_SYMBOL(free_xc); -EXPORT_SYMBOL(request_xc); -EXPORT_SYMBOL(xc_request_firmware); -EXPORT_SYMBOL(xc_reset); -EXPORT_SYMBOL(xc_running); -EXPORT_SYMBOL(xc_start); -EXPORT_SYMBOL(xc_stop); diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 820b60a50125..c54cd7ed90ba 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -663,6 +663,11 @@ config ARM_LPAE depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \ !CPU_32v4 && !CPU_32v3 select PHYS_ADDR_T_64BIT + select SWIOTLB + select ARCH_HAS_DMA_COHERENT_TO_PFN + select ARCH_HAS_DMA_MMAP_PGPROT + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select ARCH_HAS_SYNC_DMA_FOR_CPU help Say Y if you have an ARMv7 processor supporting the LPAE page table format and you would like to access memory beyond the diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4789c60a86e3..6774b03aa405 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/dma-contiguous.h> #include <linux/highmem.h> #include <linux/memblock.h> @@ -1125,6 +1126,19 @@ int arm_dma_supported(struct device *dev, u64 mask) static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent) { + /* + * When CONFIG_ARM_LPAE is set, physical address can extend above + * 32-bits, which then can't be addressed by devices that only support + * 32-bit DMA. + * Use the generic dma-direct / swiotlb ops code in that case, as that + * handles bounce buffering for us. + * + * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the + * latter is also selected by the Xen code, but that code for now relies + * on non-NULL dev_dma_ops. To be cleaned up later. + */ + if (IS_ENABLED(CONFIG_ARM_LPAE)) + return NULL; return coherent ? &arm_coherent_dma_ops : &arm_dma_ops; } @@ -2329,6 +2343,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct dma_map_ops *dma_ops; dev->archdata.dma_coherent = coherent; +#ifdef CONFIG_SWIOTLB + dev->dma_coherent = coherent; +#endif /* * Don't override the dma_ops if they have already been set. Ideally @@ -2363,3 +2380,47 @@ void arch_teardown_dma_ops(struct device *dev) /* Let arch_setup_dma_ops() start again from scratch upon re-probe */ set_dma_ops(dev, NULL); } + +#ifdef CONFIG_SWIOTLB +void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + __dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), + size, dir); +} + +void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, + size_t size, enum dma_data_direction dir) +{ + __dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), + size, dir); +} + +long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, + dma_addr_t dma_addr) +{ + return dma_to_pfn(dev, dma_addr); +} + +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return __get_dma_pgprot(attrs, prot); + return prot; +} + +void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + return __dma_alloc(dev, size, dma_handle, gfp, + __get_dma_pgprot(attrs, PAGE_KERNEL), false, + attrs, __builtin_return_address(0)); +} + +void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, unsigned long attrs) +{ + __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false); +} +#endif /* CONFIG_SWIOTLB */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 4920a206dce9..16d373d587c4 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -21,6 +21,7 @@ #include <linux/dma-contiguous.h> #include <linux/sizes.h> #include <linux/stop_machine.h> +#include <linux/swiotlb.h> #include <asm/cp15.h> #include <asm/mach-types.h> @@ -463,6 +464,10 @@ static void __init free_highpages(void) */ void __init mem_init(void) { +#ifdef CONFIG_ARM_LPAE + swiotlb_init(1); +#endif + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); /* this will put all unused low memory onto the freelists */ diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index bb1f1dbb34e8..61de992bbea3 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -52,7 +52,7 @@ ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y) ifeq ($(CONFIG_CC_IS_CLANG), y) $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built) - else ifeq ($(CROSS_COMPILE_COMPAT),) + else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),) $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built) else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),) $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT) diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index e25f7fcd7997..cffa8991880d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -462,7 +462,7 @@ #define MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28 0x1CC 0x434 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXFS_TPSMP_HTRANS0 0x1CC 0x434 0x000 0x7 0x0 #define MX8MM_IOMUXC_SAI3_RXC_SAI3_RX_BCLK 0x1D0 0x438 0x000 0x0 0x0 -#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CAPTURE2 0x1D0 0x438 0x000 0x1 0x0 +#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CLK 0x1D0 0x438 0x000 0x1 0x0 #define MX8MM_IOMUXC_SAI3_RXC_SAI5_RX_BCLK 0x1D0 0x438 0x4D0 0x2 0x2 #define MX8MM_IOMUXC_SAI3_RXC_GPIO4_IO29 0x1D0 0x438 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXC_TPSMP_HTRANS1 0x1D0 0x438 0x000 0x7 0x0 @@ -472,7 +472,7 @@ #define MX8MM_IOMUXC_SAI3_RXD_GPIO4_IO30 0x1D4 0x43C 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_RXD_TPSMP_HDATA0 0x1D4 0x43C 0x000 0x7 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_SAI3_TX_SYNC 0x1D8 0x440 0x000 0x0 0x0 -#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CLK 0x1D8 0x440 0x000 0x1 0x0 +#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CAPTURE2 0x1D8 0x440 0x000 0x1 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_SAI5_RX_DATA1 0x1D8 0x440 0x4D8 0x2 0x2 #define MX8MM_IOMUXC_SAI3_TXFS_GPIO4_IO31 0x1D8 0x440 0x000 0x5 0x0 #define MX8MM_IOMUXC_SAI3_TXFS_TPSMP_HDATA1 0x1D8 0x440 0x000 0x7 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index d09b808eff87..52aae341d0da 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -715,8 +715,7 @@ sai2: sai@308b0000 { #sound-dai-cells = <0>; - compatible = "fsl,imx8mq-sai", - "fsl,imx6sx-sai"; + compatible = "fsl,imx8mq-sai"; reg = <0x308b0000 0x10000>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MQ_CLK_SAI2_IPG>, diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 79155a8cfe7c..89e4c8b79349 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -155,6 +155,12 @@ static inline void gic_pmr_mask_irqs(void) BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF | GIC_PRIO_PSR_I_SET)); BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON); + /* + * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared + * and non-secure PMR accesses are not subject to the shifts that + * are applied to IRQ priorities + */ + BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON); gic_write_pmr(GIC_PRIO_IRQOFF); } diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 407e2bf23676..c96ffa4722d3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -35,9 +35,10 @@ */ enum ftr_type { - FTR_EXACT, /* Use a predefined safe value */ - FTR_LOWER_SAFE, /* Smaller value is safe */ - FTR_HIGHER_SAFE,/* Bigger value is safe */ + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE, /* Bigger value is safe */ + FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 987926ed535e..063c964af705 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -13,6 +13,8 @@ #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT #define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT) +#define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + /* mask/save/unmask/restore all exceptions, including interrupts. */ static inline void local_daif_mask(void) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 8e79ce9c3f5c..76a144702586 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -105,7 +105,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, ((protocol##_t *)instance)->f(instance, ##__VA_ARGS__) #define alloc_screen_info(x...) &screen_info -#define free_screen_info(x...) + +static inline void free_screen_info(efi_system_table_t *sys_table_arg, + struct screen_info *si) +{ +} /* redeclare as 'hidden' so the compiler will generate relative references */ extern struct screen_info screen_info __attribute__((__visibility__("hidden"))); diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 3c7037c6ba9b..b618017205a3 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -202,7 +202,7 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; ({ \ set_thread_flag(TIF_32BIT); \ }) -#ifdef CONFIG_GENERIC_COMPAT_VDSO +#ifdef CONFIG_COMPAT_VDSO #define COMPAT_ARCH_DLINFO \ do { \ /* \ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b7ba75809751..fb04f10a78ab 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -210,7 +210,11 @@ extern u64 vabits_user; #define __tag_reset(addr) untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else -#define __tag_set(addr, tag) (addr) +static inline const void *__tag_set(const void *addr, u8 tag) +{ + return addr; +} + #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 #endif @@ -301,8 +305,8 @@ static inline void *phys_to_virt(phys_addr_t x) #define page_to_virt(page) ({ \ unsigned long __addr = \ ((__page_to_voff(page)) | PAGE_OFFSET); \ - unsigned long __addr_tag = \ - __tag_set(__addr, page_kasan_tag(page)); \ + const void *__addr_tag = \ + __tag_set((void *)__addr, page_kasan_tag(page)); \ ((void *)__addr_tag); \ }) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 87a4b2ddc1a1..5fdcfe237338 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -301,7 +301,6 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) /* * Huge pte definitions. */ -#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT)) #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* @@ -448,8 +447,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_SECT) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 -#define pud_sect(pud) (0) -#define pud_table(pud) (1) +static inline bool pud_sect(pud_t pud) { return false; } +static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fd5b1a4efc70..844e2964b0f5 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -193,6 +193,16 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) regs->pmr_save = GIC_PRIO_IRQON; } +static inline void set_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_SSBS_BIT; +} + +static inline void set_compat_ssbs_bit(struct pt_regs *regs) +{ + regs->pstate |= PSR_AA32_SSBS_BIT; +} + static inline void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -200,7 +210,7 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->pstate = PSR_MODE_EL0t; if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(regs); regs->sp = sp; } @@ -219,7 +229,7 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, #endif if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE) - regs->pstate |= PSR_AA32_SSBS_BIT; + set_compat_ssbs_bit(regs); regs->compat_sp = sp; } diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index b1dd039023ef..1dcf63a9ac1f 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -30,7 +30,7 @@ * in the the priority mask, it indicates that PSR.I should be set and * interrupt disabling temporarily does not rely on IRQ priorities. */ -#define GIC_PRIO_IRQON 0xc0 +#define GIC_PRIO_IRQON 0xe0 #define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80) #define GIC_PRIO_PSR_I_SET (1 << 4) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index df45af931459..4d9b1f48dc39 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -8,19 +8,12 @@ #include <linux/percpu.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> +#include <linux/types.h> #include <asm/memory.h> #include <asm/ptrace.h> #include <asm/sdei.h> -struct stackframe { - unsigned long fp; - unsigned long pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - int graph; -#endif -}; - enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, @@ -28,6 +21,7 @@ enum stack_type { STACK_TYPE_OVERFLOW, STACK_TYPE_SDEI_NORMAL, STACK_TYPE_SDEI_CRITICAL, + __NR_STACK_TYPES }; struct stack_info { @@ -36,6 +30,37 @@ struct stack_info { enum stack_type type; }; +/* + * A snapshot of a frame record or fp/lr register values, along with some + * accounting information necessary for robust unwinding. + * + * @fp: The fp value in the frame record (or the real fp) + * @pc: The fp value in the frame record (or the real lr) + * + * @stacks_done: Stacks which have been entirely unwound, for which it is no + * longer valid to unwind to. + * + * @prev_fp: The fp that pointed to this frame record, or a synthetic value + * of 0. This is used to ensure that within a stack, each + * subsequent frame record is at an increasing address. + * @prev_type: The type of stack this frame record was on, or a synthetic + * value of STACK_TYPE_UNKNOWN. This is used to detect a + * transition from one stack to another. + * + * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a + * replacement lr value in the ftrace graph stack. + */ +struct stackframe { + unsigned long fp; + unsigned long pc; + DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES); + unsigned long prev_fp; + enum stack_type prev_type; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + int graph; +#endif +}; + extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); @@ -64,8 +89,9 @@ static inline bool on_irq_stack(unsigned long sp, return true; } -static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp, - struct stack_info *info) +static inline bool on_task_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { unsigned long low = (unsigned long)task_stack_page(tsk); unsigned long high = low + THREAD_SIZE; @@ -112,10 +138,13 @@ static inline bool on_overflow_stack(unsigned long sp, * We can only safely access per-cpu stacks from current in a non-preemptible * context. */ -static inline bool on_accessible_stack(struct task_struct *tsk, - unsigned long sp, - struct stack_info *info) +static inline bool on_accessible_stack(const struct task_struct *tsk, + unsigned long sp, + struct stack_info *info) { + if (info) + info->type = STACK_TYPE_UNKNOWN; + if (on_task_stack(tsk, sp, info)) return true; if (tsk != current || preemptible()) @@ -130,4 +159,27 @@ static inline bool on_accessible_stack(struct task_struct *tsk, return false; } +static inline void start_backtrace(struct stackframe *frame, + unsigned long fp, unsigned long pc) +{ + frame->fp = fp; + frame->pc = pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame->graph = 0; +#endif + + /* + * Prime the first unwind. + * + * In unwind_frame() we'll check that the FP points to a valid stack, + * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be + * treated as a transition to whichever stack that happens to be. The + * prev_fp value won't be used, but we set it to 0 such that it is + * definitely not an accessible stack address. + */ + bitmap_zero(frame->stacks_done, __NR_STACK_TYPES); + frame->prev_fp = 0; + frame->prev_type = STACK_TYPE_UNKNOWN; +} + #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index f4812777f5c5..c50ee1b7d5cd 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -16,6 +16,8 @@ #define VDSO_HAS_CLOCK_GETRES 1 +#define VDSO_HAS_32BIT_FALLBACK 1 + static __always_inline int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) @@ -52,6 +54,23 @@ long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) } static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_gettime; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + +static __always_inline int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { register struct __kernel_timespec *ts asm("r1") = _ts; @@ -72,6 +91,27 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + register struct old_timespec32 *ts asm("r1") = _ts; + register clockid_t clkid asm("r0") = _clkid; + register long ret asm ("r0"); + register long nr asm("r7") = __NR_compat_clock_getres; + + /* The checks below are required for ABI consistency with arm */ + if ((_clkid >= MAX_CLOCKS) && (_ts == NULL)) + return -EINVAL; + + asm volatile( + " swi #0\n" + : "=r" (ret) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return ret; +} + static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) { u64 res; diff --git a/arch/arm64/include/uapi/asm/bpf_perf_event.h b/arch/arm64/include/uapi/asm/bpf_perf_event.h index b551b741653d..5e1e648aeec4 100644 --- a/arch/arm64/include/uapi/asm/bpf_perf_event.h +++ b/arch/arm64/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f29f36a65175..d19d14ba9ae4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -225,8 +225,8 @@ static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will @@ -468,6 +468,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_LOWER_SAFE: ret = new < cur ? new : cur; break; + case FTR_HIGHER_OR_ZERO_SAFE: + if (!cur || !new) + break; + /* Fallthrough */ case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index f8719bd30850..48222a4760c2 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -207,16 +207,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_step_hook : &kernel_step_hook; - rcu_read_lock(); - + /* + * Since single-step exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - rcu_read_unlock(); - return retval; } NOKPROBE_SYMBOL(call_step_hook); @@ -305,14 +305,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; - rcu_read_lock(); + /* + * Since brk exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~hook->mask) == hook->imm) fn = hook->fn; } - rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 9cdc4592da3e..320a30dbe35e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -586,10 +586,8 @@ el1_sync: b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el1_sp_pc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_sp_pc + b.eq el1_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 b.eq el1_undef cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 @@ -611,9 +609,11 @@ el1_da: bl do_mem_abort kernel_exit 1 -el1_sp_pc: +el1_pc: /* - * Stack or PC alignment exception handling + * PC alignment exception handling. We don't handle SP alignment faults, + * since we will have hit a recursive exception when trying to push the + * initial pt_regs. */ mrs x0, far_el1 inherit_daif pstate=x23, tmp=x2 @@ -732,9 +732,9 @@ el0_sync: ccmp x24, #ESR_ELx_EC_WFx, #4, ne b.eq el0_sys cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp_pc + b.eq el0_sp cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 @@ -758,7 +758,7 @@ el0_sync_compat: cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap @@ -858,11 +858,15 @@ el0_fpsimd_exc: mov x1, sp bl do_fpsimd_exc b ret_to_user +el0_sp: + ldr x26, [sp, #S_SP] + b el0_sp_pc +el0_pc: + mrs x26, far_el1 el0_sp_pc: /* * Stack or PC alignment exception handling */ - mrs x26, far_el1 gic_prio_kentry_setup tmp=x0 enable_da_f #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index eec4776ae5f0..37d3912cfe06 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -406,6 +406,18 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x) #define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) +static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, + unsigned int vq) +{ + unsigned int i; + __uint128_t *p; + + for (i = 0; i < SVE_NUM_ZREGS; ++i) { + p = (__uint128_t *)ZREG(sst, vq, i); + *p = arm64_cpu_to_le128(fst->vregs[i]); + } +} + /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. @@ -423,17 +435,12 @@ static void fpsimd_to_sve(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!system_supports_sve()) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } /* @@ -459,7 +466,7 @@ static void sve_to_fpsimd(struct task_struct *task) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { + for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); } @@ -550,8 +557,6 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!test_tsk_thread_flag(task, TIF_SVE)) return; @@ -559,11 +564,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) vq = sve_vq_from_vl(task->thread.sve_vl); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); - - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } int sve_set_vector_length(struct task_struct *task, diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index dceb84520948..38ee1514cd9c 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -536,13 +536,18 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Aligned */ break; case 1: - /* Allow single byte watchpoint. */ - if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) - break; case 2: /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + + /* Fallthrough */ + case 3: + /* Allow single byte watchpoint. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; + + /* Fallthrough */ default: return -EINVAL; } diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 46e643e30708..03ff15bffbb6 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -314,18 +314,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* MOVW instruction relocations. */ case R_AARCH64_MOVW_UABS_G0_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, AARCH64_INSN_IMM_MOVKZ); @@ -393,6 +396,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 9d63514b9836..b0e03e052dd1 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -154,12 +154,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, return; } - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, callchain_trace, entry); } diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bd5dfffca272..c4452827419b 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -21,6 +21,7 @@ #include <asm/ptrace.h> #include <asm/cacheflush.h> #include <asm/debug-monitors.h> +#include <asm/daifflags.h> #include <asm/system_misc.h> #include <asm/insn.h> #include <linux/uaccess.h> @@ -168,33 +169,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * When PSTATE.D is set (masked), then software step exceptions can not be - * generated. - * SPSR's D bit shows the value of PSTATE.D immediately before the - * exception was taken. PSTATE.D is set while entering into any exception - * mode, however software clears it for any normal (none-debug-exception) - * mode in the exception entry. Therefore, when we are entering into kprobe - * breakpoint handler from any normal mode then SPSR.D bit is already - * cleared, however it is set when we are entering from any debug exception - * mode. - * Since we always need to generate single step exception after a kprobe - * breakpoint exception therefore we need to clear it unconditionally, when - * we become sure that the current breakpoint exception is for kprobe. - */ -static void __kprobes -spsr_set_debug_flag(struct pt_regs *regs, int mask) -{ - unsigned long spsr = regs->pstate; - - if (mask) - spsr |= PSR_D_BIT; - else - spsr &= ~PSR_D_BIT; - - regs->pstate = spsr; -} - -/* * Interrupts need to be disabled before single-step mode is set, and not * reenabled until after single-step mode ends. * Without disabling interrupt on local CPU, there is a chance of @@ -205,17 +179,17 @@ spsr_set_debug_flag(struct pt_regs *regs, int mask) static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - kcb->saved_irqflag = regs->pstate; + kcb->saved_irqflag = regs->pstate & DAIF_MASK; regs->pstate |= PSR_I_BIT; + /* Unmask PSTATE.D for enabling software step exceptions. */ + regs->pstate &= ~PSR_D_BIT; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - if (kcb->saved_irqflag & PSR_I_BIT) - regs->pstate |= PSR_I_BIT; - else - regs->pstate &= ~PSR_I_BIT; + regs->pstate &= ~DAIF_MASK; + regs->pstate |= kcb->saved_irqflag; } static void __kprobes @@ -252,8 +226,6 @@ static void __kprobes setup_singlestep(struct kprobe *p, set_ss_context(kcb, slot); /* mark pending ss */ - spsr_set_debug_flag(regs, 0); - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); kernel_enable_single_step(regs); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 6a869d9f304f..f674f28df663 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -398,7 +398,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, childregs->pstate |= PSR_UAO_BIT; if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) - childregs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(childregs); if (system_uses_irq_prio_masking()) childregs->pmr_save = GIC_PRIO_IRQON; @@ -443,6 +443,32 @@ void uao_thread_switch(struct task_struct *next) } /* + * Force SSBS state on context-switch, since it may be lost after migrating + * from a CPU which treats the bit as RES0 in a heterogeneous system. + */ +static void ssbs_thread_switch(struct task_struct *next) +{ + struct pt_regs *regs = task_pt_regs(next); + + /* + * Nothing to do for kernel threads, but 'regs' may be junk + * (e.g. idle task) so check the flags and bail early. + */ + if (unlikely(next->flags & PF_KTHREAD)) + return; + + /* If the mitigation is enabled, then we leave SSBS clear. */ + if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || + test_tsk_thread_flag(next, TIF_SSBD)) + return; + + if (compat_user_mode(regs)) + set_compat_ssbs_bit(regs); + else if (user_mode(regs)) + set_ssbs_bit(regs); +} + +/* * We store our current task in sp_el0, which is clobbered by userspace. Keep a * shadow copy so that we can restore this upon entry from userspace. * @@ -471,6 +497,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ptrauth_thread_switch(next); + ssbs_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -498,11 +525,8 @@ unsigned long get_wchan(struct task_struct *p) if (!stack_page) return 0; - frame.fp = thread_saved_fp(p); - frame.pc = thread_saved_pc(p); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p)); + do { if (unwind_frame(p, &frame)) goto out; diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index b21cba90f82d..a5e8b3b9d798 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -8,6 +8,7 @@ #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -29,6 +30,7 @@ static int save_return_addr(struct stackframe *frame, void *d) return 0; } } +NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { @@ -38,12 +40,9 @@ void *return_address(unsigned int level) data.level = level + 2; data.addr = NULL; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)return_address; /* dummy */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)return_address); walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) @@ -52,3 +51,4 @@ void *return_address(unsigned int level) return NULL; } EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index ea90d3bd9253..018a33e01b0e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -152,8 +152,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_crit("CPU%u: died during early boot\n", cpu); break; } - /* Fall through */ pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + /* Fall through */ case CPU_STUCK_IN_KERNEL: pr_crit("CPU%u: is stuck in kernel\n", cpu); if (status & CPU_STUCK_REASON_52_BIT_VA) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 62d395151abe..a336cb124320 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> @@ -29,9 +30,18 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ + +/* + * Unwind from one frame record (A) to the next frame record (B). + * + * We terminate early if the location of B indicates a malformed chain of frame + * records (e.g. a cycle), determined based on the location and fp value of A + * and the location (but not the fp value) of B. + */ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long fp = frame->fp; + struct stack_info info; if (fp & 0xf) return -EINVAL; @@ -39,11 +49,40 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) if (!tsk) tsk = current; - if (!on_accessible_stack(tsk, fp, NULL)) + if (!on_accessible_stack(tsk, fp, &info)) + return -EINVAL; + + if (test_bit(info.type, frame->stacks_done)) return -EINVAL; + /* + * As stacks grow downward, any valid record on the same stack must be + * at a strictly higher address than the prior record. + * + * Stacks can nest in several valid orders, e.g. + * + * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL + * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW + * + * ... but the nesting itself is strict. Once we transition from one + * stack to another, it's never valid to unwind back to that first + * stack. + */ + if (info.type == frame->prev_type) { + if (fp <= frame->prev_fp) + return -EINVAL; + } else { + set_bit(frame->prev_type, frame->stacks_done); + } + + /* + * Record this frame record's values and location. The prev_fp and + * prev_type are only meaningful to the next unwind_frame() invocation. + */ frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); + frame->prev_fp = fp; + frame->prev_type = info.type; #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && @@ -73,6 +112,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) return 0; } +NOKPROBE_SYMBOL(unwind_frame); void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) @@ -87,6 +127,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, break; } } +NOKPROBE_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { @@ -122,12 +163,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) data.skip = trace->skip; data.no_sched_functions = 0; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, save_trace, &data); } EXPORT_SYMBOL_GPL(save_stack_trace_regs); @@ -146,17 +182,15 @@ static noinline void __save_stack_trace(struct task_struct *tsk, data.no_sched_functions = nosched; if (tsk != current) { - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, thread_saved_fp(tsk), + thread_saved_pc(tsk)); } else { /* We don't want this function nor the caller */ data.skip += 2; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)__save_stack_trace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)__save_stack_trace); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif walk_stackframe(tsk, &frame, save_trace, &data); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 9f25aedeac9d..0b2946414dc9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -38,11 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs) if (!in_lock_functions(regs->pc)) return regs->pc; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, regs->regs[29], regs->pc); + do { int ret = unwind_frame(NULL, &frame); if (ret < 0) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8c03456dade6..d3313797cca9 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -100,18 +100,17 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) return; if (tsk == current) { - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)dump_backtrace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)dump_backtrace); } else { /* * task blocked in __switch_to */ - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, + thread_saved_fp(tsk), + thread_saved_pc(tsk)); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif printk("Call trace:\n"); do { diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 4ab863045188..dd2514bb1511 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -32,10 +32,10 @@ UBSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y KCOV_INSTRUMENT := n -ifeq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -else -CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -include $(c-gettimeofday-y) + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) endif # Clang versions less than 8 do not support -mcmodel=tiny @@ -57,8 +57,7 @@ $(obj)/vdso.o : $(obj)/vdso.so # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,ld) - $(call if_changed,vdso_check) + $(call if_changed,vdsold_and_vdso_check) # Strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -74,8 +73,8 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Actual build commands -quiet_cmd_vdsocc = VDSOCC $@ - cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $< +quiet_cmd_vdsold_and_vdso_check = LD $@ + cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) # Install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 60a4c6239712..1fba0776ed40 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -144,8 +144,7 @@ $(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,vdsold) - $(call if_changed,vdso_check) + $(call if_changed,vdsold_and_vdso_check) # Compilation rules for the vDSO sources $(c-obj-vdso): %.o: %.c FORCE @@ -156,14 +155,17 @@ $(asm-obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands -quiet_cmd_vdsold = VDSOL $@ +quiet_cmd_vdsold_and_vdso_check = LD32 $@ + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + +quiet_cmd_vdsold = LD32 $@ cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ -quiet_cmd_vdsocc = VDSOC $@ +quiet_cmd_vdsocc = CC32 $@ cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< -quiet_cmd_vdsocc_gettimeofday = VDSOC_GTD $@ +quiet_cmd_vdsocc_gettimeofday = CC32 $@ cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< -quiet_cmd_vdsoas = VDSOA $@ +quiet_cmd_vdsoas = AS32 $@ cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< quiet_cmd_vdsomunge = MUNGE $@ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9568c116ac7f..cfd65b63f36f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -777,6 +777,53 @@ void __init hook_debug_fault_code(int nr, debug_fault_info[nr].name = name; } +/* + * In debug exception context, we explicitly disable preemption despite + * having interrupts disabled. + * This serves two purposes: it makes it much less likely that we would + * accidentally schedule in exception context and it will force a warning + * if we somehow manage to schedule by accident. + */ +static void debug_exception_enter(struct pt_regs *regs) +{ + /* + * Tell lockdep we disabled irqs in entry.S. Do nothing if they were + * already disabled to preserve the last enabled/disabled addresses. + */ + if (interrupts_enabled(regs)) + trace_hardirqs_off(); + + if (user_mode(regs)) { + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + } else { + /* + * We might have interrupted pretty much anything. In + * fact, if we're a debug exception, we can even interrupt + * NMI processing. We don't want this code makes in_nmi() + * to return true, but we need to notify RCU. + */ + rcu_nmi_enter(); + } + + preempt_disable(); + + /* This code is a bit fragile. Test it. */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); +} +NOKPROBE_SYMBOL(debug_exception_enter); + +static void debug_exception_exit(struct pt_regs *regs) +{ + preempt_enable_no_resched(); + + if (!user_mode(regs)) + rcu_nmi_exit(); + + if (interrupts_enabled(regs)) + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(debug_exception_exit); + #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); @@ -817,12 +864,7 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, if (cortex_a76_erratum_1463225_debug_handler(regs)) return; - /* - * Tell lockdep we disabled irqs in entry.S. Do nothing if they were - * already disabled to preserve the last enabled/disabled addresses. - */ - if (interrupts_enabled(regs)) - trace_hardirqs_off(); + debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); @@ -832,7 +874,6 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, inf->sig, inf->code, (void __user *)pc, esr); } - if (interrupts_enabled(regs)) - trace_hardirqs_on(); + debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); diff --git a/arch/csky/include/uapi/asm/byteorder.h b/arch/csky/include/uapi/asm/byteorder.h index b079ec715cdf..d150cd664873 100644 --- a/arch/csky/include/uapi/asm/byteorder.h +++ b/arch/csky/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef __ASM_CSKY_BYTEORDER_H diff --git a/arch/csky/include/uapi/asm/cachectl.h b/arch/csky/include/uapi/asm/cachectl.h index ddf2f39aa925..ed7fad1ea20d 100644 --- a/arch/csky/include/uapi/asm/cachectl.h +++ b/arch/csky/include/uapi/asm/cachectl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_CSKY_CACHECTL_H #define __ASM_CSKY_CACHECTL_H diff --git a/arch/csky/include/uapi/asm/perf_regs.h b/arch/csky/include/uapi/asm/perf_regs.h index ee323d818592..49d4e147a559 100644 --- a/arch/csky/include/uapi/asm/perf_regs.h +++ b/arch/csky/include/uapi/asm/perf_regs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. #ifndef _ASM_CSKY_PERF_REGS_H diff --git a/arch/csky/include/uapi/asm/ptrace.h b/arch/csky/include/uapi/asm/ptrace.h index 4e248d5b86ef..66b2268e324e 100644 --- a/arch/csky/include/uapi/asm/ptrace.h +++ b/arch/csky/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef _CSKY_PTRACE_H diff --git a/arch/csky/include/uapi/asm/sigcontext.h b/arch/csky/include/uapi/asm/sigcontext.h index e81e7ff11e36..670c020f2cb8 100644 --- a/arch/csky/include/uapi/asm/sigcontext.h +++ b/arch/csky/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #ifndef __ASM_CSKY_SIGCONTEXT_H diff --git a/arch/csky/include/uapi/asm/unistd.h b/arch/csky/include/uapi/asm/unistd.h index ec60e49cea66..211c983c7282 100644 --- a/arch/csky/include/uapi/asm/unistd.h +++ b/arch/csky/include/uapi/asm/unistd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. #define __ARCH_WANT_SYS_CLONE diff --git a/arch/mips/cavium-octeon/octeon-usb.c b/arch/mips/cavium-octeon/octeon-usb.c index 1f730ded5224..cc88a08bc1f7 100644 --- a/arch/mips/cavium-octeon/octeon-usb.c +++ b/arch/mips/cavium-octeon/octeon-usb.c @@ -398,6 +398,7 @@ static int dwc3_octeon_clocks_start(struct device *dev, u64 base) default: dev_err(dev, "Invalid ref_clk %u, using 100000000 instead\n", clock_rate); + /* fall through */ case 100000000: mpll_mul = 0x19; if (ref_clk_sel < 2) diff --git a/arch/mips/kernel/cacheinfo.c b/arch/mips/kernel/cacheinfo.c index e0dd66881da6..f777e44653d5 100644 --- a/arch/mips/kernel/cacheinfo.c +++ b/arch/mips/kernel/cacheinfo.c @@ -69,6 +69,8 @@ static int __populate_cache_leaves(unsigned int cpu) if (c->tcache.waysize) populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED); + this_cpu_ci->cpu_map_populated = true; + return 0; } diff --git a/arch/mips/kernel/i8253.c b/arch/mips/kernel/i8253.c index 5f209f111e59..df7ddd246eaa 100644 --- a/arch/mips/kernel/i8253.c +++ b/arch/mips/kernel/i8253.c @@ -32,7 +32,8 @@ void __init setup_pit_timer(void) static int __init init_pit_clocksource(void) { - if (num_possible_cpus() > 1) /* PIT does not scale! */ + if (num_possible_cpus() > 1 || /* PIT does not scale! */ + !clockevent_state_periodic(&i8253_clockevent)) return 0; return clocksource_i8253_init(); diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index e5de6bac8197..754094b40a75 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -140,6 +140,7 @@ static int kvm_compute_return_epc(struct kvm_vcpu *vcpu, unsigned long instpc, /* These are unconditional and in j_format. */ case jal_op: arch->gprs[31] = instpc + 8; + /* fall through */ case j_op: epc += 4; epc >>= 28; diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index 7c04b17f4a48..96c13a0ab078 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -172,12 +172,15 @@ static void mipsxx_cpu_setup(void *args) case 4: w_c0_perfctrl3(0); w_c0_perfcntr3(reg.counter[3]); + /* fall through */ case 3: w_c0_perfctrl2(0); w_c0_perfcntr2(reg.counter[2]); + /* fall through */ case 2: w_c0_perfctrl1(0); w_c0_perfcntr1(reg.counter[1]); + /* fall through */ case 1: w_c0_perfctrl0(0); w_c0_perfcntr0(reg.counter[0]); @@ -195,10 +198,13 @@ static void mipsxx_cpu_start(void *args) switch (counters) { case 4: w_c0_perfctrl3(WHAT | reg.control[3]); + /* fall through */ case 3: w_c0_perfctrl2(WHAT | reg.control[2]); + /* fall through */ case 2: w_c0_perfctrl1(WHAT | reg.control[1]); + /* fall through */ case 1: w_c0_perfctrl0(WHAT | reg.control[0]); } @@ -215,10 +221,13 @@ static void mipsxx_cpu_stop(void *args) switch (counters) { case 4: w_c0_perfctrl3(0); + /* fall through */ case 3: w_c0_perfctrl2(0); + /* fall through */ case 2: w_c0_perfctrl1(0); + /* fall through */ case 1: w_c0_perfctrl0(0); } @@ -236,6 +245,7 @@ static int mipsxx_perfcount_handler(void) switch (counters) { #define HANDLE_COUNTER(n) \ + /* fall through */ \ case n + 1: \ control = r_c0_perfctrl ## n(); \ counter = r_c0_perfcntr ## n(); \ @@ -297,12 +307,15 @@ static void reset_counters(void *arg) case 4: w_c0_perfctrl3(0); w_c0_perfcntr3(0); + /* fall through */ case 3: w_c0_perfctrl2(0); w_c0_perfcntr2(0); + /* fall through */ case 2: w_c0_perfctrl1(0); w_c0_perfcntr1(0); + /* fall through */ case 1: w_c0_perfctrl0(0); w_c0_perfcntr0(0); diff --git a/arch/mips/pci/ops-bcm63xx.c b/arch/mips/pci/ops-bcm63xx.c index d02eb9d16b55..925c72348fb6 100644 --- a/arch/mips/pci/ops-bcm63xx.c +++ b/arch/mips/pci/ops-bcm63xx.c @@ -474,6 +474,7 @@ static int bcm63xx_pcie_can_access(struct pci_bus *bus, int devfn) if (PCI_SLOT(devfn) == 0) return bcm_pcie_readl(PCIE_DLSTATUS_REG) & DLSTATUS_PHYLINKUP; + /* else, fall through */ default: return false; } diff --git a/arch/mips/vdso/vdso.h b/arch/mips/vdso/vdso.h index 14b1931be69c..b65b169778e3 100644 --- a/arch/mips/vdso/vdso.h +++ b/arch/mips/vdso/vdso.h @@ -9,6 +9,7 @@ #if _MIPS_SIM != _MIPS_SIM_ABI64 && defined(CONFIG_64BIT) /* Building 32-bit VDSO for the 64-bit kernel. Fake a 32-bit Kconfig. */ +#define BUILD_VDSO32_64 #undef CONFIG_64BIT #define CONFIG_32BIT 1 #ifndef __ASSEMBLY__ diff --git a/arch/nds32/include/uapi/asm/auxvec.h b/arch/nds32/include/uapi/asm/auxvec.h index b5d58ea8decb..bc0b92ab8c15 100644 --- a/arch/nds32/include/uapi/asm/auxvec.h +++ b/arch/nds32/include/uapi/asm/auxvec.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __ASM_AUXVEC_H diff --git a/arch/nds32/include/uapi/asm/byteorder.h b/arch/nds32/include/uapi/asm/byteorder.h index 511e653c709d..c264ef12c49c 100644 --- a/arch/nds32/include/uapi/asm/byteorder.h +++ b/arch/nds32/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __NDS32_BYTEORDER_H__ diff --git a/arch/nds32/include/uapi/asm/cachectl.h b/arch/nds32/include/uapi/asm/cachectl.h index 73793662815c..31b9b439d819 100644 --- a/arch/nds32/include/uapi/asm/cachectl.h +++ b/arch/nds32/include/uapi/asm/cachectl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 1994, 1995, 1996 by Ralf Baechle // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef _ASM_CACHECTL diff --git a/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h index d54a5d6c6538..f17396db16ec 100644 --- a/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h +++ b/arch/nds32/include/uapi/asm/fp_udfiex_crtl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (C) 2005-2019 Andes Technology Corporation */ #ifndef _FP_UDF_IEX_CRTL_H #define _FP_UDF_IEX_CRTL_H diff --git a/arch/nds32/include/uapi/asm/param.h b/arch/nds32/include/uapi/asm/param.h index 2977534a6bd3..48d00328d328 100644 --- a/arch/nds32/include/uapi/asm/param.h +++ b/arch/nds32/include/uapi/asm/param.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __ASM_NDS32_PARAM_H diff --git a/arch/nds32/include/uapi/asm/ptrace.h b/arch/nds32/include/uapi/asm/ptrace.h index 1a6e01c00e6f..d76217c7c010 100644 --- a/arch/nds32/include/uapi/asm/ptrace.h +++ b/arch/nds32/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef __UAPI_ASM_NDS32_PTRACE_H diff --git a/arch/nds32/include/uapi/asm/sigcontext.h b/arch/nds32/include/uapi/asm/sigcontext.h index dc89af7ddcc3..6c1e6648878f 100644 --- a/arch/nds32/include/uapi/asm/sigcontext.h +++ b/arch/nds32/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #ifndef _ASMNDS32_SIGCONTEXT_H diff --git a/arch/nds32/include/uapi/asm/unistd.h b/arch/nds32/include/uapi/asm/unistd.h index a0b2f7b9c0f2..410795e280fe 100644 --- a/arch/nds32/include/uapi/asm/unistd.h +++ b/arch/nds32/include/uapi/asm/unistd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ // Copyright (C) 2005-2017 Andes Technology Corporation #define __ARCH_WANT_STAT64 diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 8acb8fa1f8d6..3b77d729057f 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -19,8 +19,6 @@ KBUILD_IMAGE := vmlinuz -KBUILD_DEFCONFIG := default_defconfig - NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) @@ -182,5 +180,8 @@ define archhelp @echo ' zinstall - Install compressed vmlinuz kernel' endef +archclean: + $(Q)$(MAKE) $(clean)=$(boot) + archheaders: $(Q)$(MAKE) $(build)=arch/parisc/kernel/syscalls all diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile index 2da8624e5cf6..1e5879c6a752 100644 --- a/arch/parisc/boot/compressed/Makefile +++ b/arch/parisc/boot/compressed/Makefile @@ -12,6 +12,7 @@ UBSAN_SANITIZE := n targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 targets += misc.o piggy.o sizes.h head.o real2.o firmware.o +targets += real2.S firmware.c KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING @@ -55,7 +56,8 @@ $(obj)/misc.o: $(obj)/sizes.h CPPFLAGS_vmlinux.lds += -I$(objtree)/$(obj) -DBOOTLOADER $(obj)/vmlinux.lds: $(obj)/sizes.h -$(obj)/vmlinux.bin: vmlinux +OBJCOPYFLAGS_vmlinux.bin := -R .comment -R .note -S +$(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) vmlinux.bin.all-y := $(obj)/vmlinux.bin diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S index bfd7872739a3..2ac3a643f2eb 100644 --- a/arch/parisc/boot/compressed/vmlinux.lds.S +++ b/arch/parisc/boot/compressed/vmlinux.lds.S @@ -48,8 +48,8 @@ SECTIONS *(.rodata.compressed) } - /* bootloader code and data starts behind area of extracted kernel */ - . = (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START); + /* bootloader code and data starts at least behind area of extracted kernel */ + . = MAX(ABSOLUTE(.), (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START)); /* align on next page boundary */ . = ALIGN(4096); diff --git a/arch/parisc/configs/default_defconfig b/arch/parisc/configs/defconfig index 5b877ca34ebf..5b877ca34ebf 100644 --- a/arch/parisc/configs/default_defconfig +++ b/arch/parisc/configs/defconfig diff --git a/arch/parisc/include/asm/kprobes.h b/arch/parisc/include/asm/kprobes.h index e09cf2deeafe..904034da4974 100644 --- a/arch/parisc/include/asm/kprobes.h +++ b/arch/parisc/include/asm/kprobes.h @@ -50,6 +50,10 @@ struct kprobe_ctlblk { int __kprobes parisc_kprobe_break_handler(struct pt_regs *regs); int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs); +static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + return 0; +} #endif /* CONFIG_KPROBES */ #endif /* _PARISC_KPROBES_H */ diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index d784ccdd8fef..b6fb30f2e4bf 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -181,8 +181,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, for (i = 0; i < ARRAY_SIZE(insn); i++) insn[i] = INSN_NOP; + __patch_text((void *)rec->ip, INSN_NOP); __patch_text_multiple((void *)rec->ip + 4 - sizeof(insn), - insn, sizeof(insn)); + insn, sizeof(insn)-4); return 0; } #endif diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index ba67893a1d72..df46b0e5a915 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -63,7 +63,7 @@ ENTRY_CFI(flush_tlb_all_local) /* Flush Instruction Tlb */ - LDREG ITLB_SID_BASE(%r1), %r20 +88: LDREG ITLB_SID_BASE(%r1), %r20 LDREG ITLB_SID_STRIDE(%r1), %r21 LDREG ITLB_SID_COUNT(%r1), %r22 LDREG ITLB_OFF_BASE(%r1), %arg0 @@ -103,6 +103,7 @@ fitonemiddle: /* Loop if LOOP = 1 */ add %r21, %r20, %r20 /* increment space */ fitdone: + ALTERNATIVE(88b, fitdone, ALT_COND_NO_SPLIT_TLB, INSN_NOP) /* Flush Data Tlb */ diff --git a/arch/parisc/math-emu/Makefile b/arch/parisc/math-emu/Makefile index b6c4b254901a..55c1396580a4 100644 --- a/arch/parisc/math-emu/Makefile +++ b/arch/parisc/math-emu/Makefile @@ -18,3 +18,4 @@ obj-y := frnd.o driver.o decode_exc.o fpudispatch.o denormal.o \ # other very old or stripped-down PA-RISC CPUs -- not currently supported obj-$(CONFIG_MATH_EMULATION) += unimplemented-math-emulation.o +CFLAGS_REMOVE_fpudispatch.o = -Wimplicit-fallthrough=3 diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 6dd4669ce7a5..adbd5e2144a3 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -66,6 +66,7 @@ parisc_acctyp(unsigned long code, unsigned int inst) case 0x30000000: /* coproc2 */ if (bit22set(inst)) return VM_WRITE; + /* fall through */ case 0x0: /* indexed/memory management */ if (bit22set(inst)) { diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d8dcd8820369..77f6ebf97113 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -121,6 +121,7 @@ config PPC select ARCH_32BIT_OFF_T if PPC32 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 463c63a9fcf1..11112023e327 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -302,9 +302,14 @@ #define H_SCM_UNBIND_MEM 0x3F0 #define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4 #define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8 -#define H_SCM_MEM_QUERY 0x3FC -#define H_SCM_BLOCK_CLEAR 0x400 -#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR +#define H_SCM_UNBIND_ALL 0x3FC +#define H_SCM_HEALTH 0x400 +#define H_SCM_PERFORMANCE_STATS 0x418 +#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS + +/* Scope args for H_SCM_UNBIND_ALL */ +#define H_UNBIND_SCOPE_ALL (0x1) +#define H_UNBIND_SCOPE_DRC (0x2) /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h index dc9a1ca70edf..c6bbe9778d3c 100644 --- a/arch/powerpc/include/asm/pmc.h +++ b/arch/powerpc/include/asm/pmc.h @@ -27,11 +27,10 @@ static inline void ppc_set_pmu_inuse(int inuse) #ifdef CONFIG_PPC_PSERIES get_lppaca()->pmcregs_in_use = inuse; #endif - } else { + } #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - get_paca()->pmcregs_in_use = inuse; + get_paca()->pmcregs_in_use = inuse; #endif - } #endif } diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 68473c3c471c..b0720c7c3fcf 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -49,6 +49,7 @@ #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h index b551b741653d..5e1e648aeec4 100644 --- a/arch/powerpc/include/uapi/asm/bpf_perf_event.h +++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index 01555c6ae0f5..be48c2215fa2 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -31,7 +31,7 @@ * Struct fields are always 32 or 64 bit aligned, depending on them being 32 * or 64 bit wide respectively. * - * See Documentation/virtual/kvm/ppc-pv.txt + * See Documentation/virt/kvm/ppc-pv.txt */ struct kvm_vcpu_arch_shared { __u64 scratch1; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 56dfa7a2a6f2..ea0c69236789 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -49,7 +49,8 @@ obj-y := cputable.o ptrace.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o + of_platform.o prom_parse.o \ + dma-common.o obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 7107ad86de65..92045ed64976 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -176,9 +176,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __get_user_inatomic(temp.v[1], p++); ret |= __get_user_inatomic(temp.v[2], p++); ret |= __get_user_inatomic(temp.v[3], p++); + /* fall through */ case 4: ret |= __get_user_inatomic(temp.v[4], p++); ret |= __get_user_inatomic(temp.v[5], p++); + /* fall through */ case 2: ret |= __get_user_inatomic(temp.v[6], p++); ret |= __get_user_inatomic(temp.v[7], p++); @@ -259,9 +261,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __put_user_inatomic(data.v[1], p++); ret |= __put_user_inatomic(data.v[2], p++); ret |= __put_user_inatomic(data.v[3], p++); + /* fall through */ case 4: ret |= __put_user_inatomic(data.v[4], p++); ret |= __put_user_inatomic(data.v[5], p++); + /* fall through */ case 2: ret |= __put_user_inatomic(data.v[6], p++); ret |= __put_user_inatomic(data.v[7], p++); diff --git a/arch/powerpc/kernel/dma-common.c b/arch/powerpc/kernel/dma-common.c new file mode 100644 index 000000000000..dc7ef6b17b69 --- /dev/null +++ b/arch/powerpc/kernel/dma-common.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Contains common dma routines for all powerpc platforms. + * + * Copyright (C) 2019 Shawn Anastasio. + */ + +#include <linux/mm.h> +#include <linux/dma-noncoherent.h> + +pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, + unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return pgprot_noncached(prot); + return prot; +} diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 85fdb6d879f1..54fab22c9a43 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -597,6 +597,14 @@ ppc_clone: stw r0,_TRAP(r1) /* register set saved */ b sys_clone + .globl ppc_clone3 +ppc_clone3: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */ + stw r0,_TRAP(r1) /* register set saved */ + b sys_clone3 + .globl ppc_swapcontext ppc_swapcontext: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d9105fcf4021..0a0b5310f54a 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -487,6 +487,11 @@ _GLOBAL(ppc_clone) bl sys_clone b .Lsyscall_exit +_GLOBAL(ppc_clone3) + bl save_nvgprs + bl sys_clone3 + b .Lsyscall_exit + _GLOBAL(ppc32_swapcontext) bl save_nvgprs bl compat_sys_swapcontext diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index eee5bef736c8..6ba3cc2ef8ab 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1531,7 +1531,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) * * Call convention: * - * syscall register convention is in Documentation/powerpc/syscall64-abi.txt + * syscall register convention is in Documentation/powerpc/syscall64-abi.rst * * For hypercalls, the register convention is as follows: * r0 volatile diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index f50b708d6d77..98600b276f76 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1198,6 +1198,9 @@ SYSCALL_DEFINE0(rt_sigreturn) goto bad; if (MSR_TM_ACTIVE(msr_hi<<32)) { + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto bad; /* We only recheckpoint on return if we're * transaction. */ diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2f80e270c7b0..117515564ec7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -771,6 +771,11 @@ SYSCALL_DEFINE0(rt_sigreturn) if (MSR_TM_ACTIVE(msr)) { /* We recheckpoint on return. */ struct ucontext __user *uc_transact; + + /* Trying to start TM on non TM system */ + if (!cpu_has_feature(CPU_FTR_TM)) + goto badframe; + if (__get_user(uc_transact, &uc->uc_link)) goto badframe; if (restore_tm_sigcontexts(current, &uc->uc_mcontext, diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 3331749aab20..43f736ed47f2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -516,4 +516,4 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 nospu clone3 ppc_clone3 diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 653936177857..18f244aad7aa 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -239,6 +239,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr, case 2: case 6: pte->may_write = true; + /* fall through */ case 3: case 5: case 7: diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ec1804f822af..cde3f5a4b3e4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3569,9 +3569,18 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); if (kvmhv_on_pseries()) { + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_load_hv_regs_and_go() below otherwise. + */ + unsigned long host_psscr; /* call our hypervisor to load up HV regs and go */ struct hv_guest_state hvregs; + host_psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); kvmhv_save_hv_regs(vcpu, &hvregs); hvregs.lpcr = lpcr; vcpu->arch.regs.msr = vcpu->arch.shregs.msr; @@ -3590,6 +3599,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.msr = vcpu->arch.regs.msr; vcpu->arch.shregs.dar = mfspr(SPRN_DAR); vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + mtspr(SPRN_PSSCR_PR, host_psscr); /* H_CEDE has to be handled now, not later */ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && @@ -3654,6 +3665,8 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.vpa.dirty = 1; save_pmu = lp->pmcregs_in_use; } + /* Must save pmu if this guest is capable of running nested guests */ + save_pmu |= nesting_enabled(vcpu->kvm); kvmhv_save_guest_pmu(vcpu, save_pmu); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 6ca0d7376a9f..e3ba67095895 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1986,10 +1986,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) xive->single_escalation = xive_native_has_single_escalation(); - if (ret) { - kfree(xive); + if (ret) return ret; - } return 0; } diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 5596c8ec221a..a998823f68a3 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1090,9 +1090,9 @@ static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) xive->ops = &kvmppc_xive_native_ops; if (ret) - kfree(xive); + return ret; - return ret; + return 0; } /* diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 9a5963e07a82..b8ad14bb1170 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1899,11 +1899,20 @@ void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, * * For guests on platforms before POWER9, we clamp the it limit to 1G * to avoid some funky things such as RTAS bugs etc... + * + * On POWER9 we limit to 1TB in case the host erroneously told us that + * the RMA was >1TB. Effective address bits 0:23 are treated as zero + * (meaning the access is aliased to zero i.e. addr = addr % 1TB) + * for virtual real mode addressing and so it doesn't make sense to + * have an area larger than 1TB as it can't be addressed. */ if (!early_cpu_has_feature(CPU_FTR_HVMODE)) { ppc64_rma_size = first_memblock_size; if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000); + else + ppc64_rma_size = min_t(u64, ppc64_rma_size, + 1UL << SID_SHIFT_1T); /* Finally limit subsequent allocations */ memblock_set_current_limit(ppc64_rma_size); diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0d62be3cba47..74f4555a62ba 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -21,7 +21,7 @@ static void kasan_populate_pte(pte_t *ptep, pgprot_t prot) __set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0); } -static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) +static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end) { pmd_t *pmd; unsigned long k_cur, k_next; @@ -35,7 +35,10 @@ static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_ if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte) continue; - new = pte_alloc_one_kernel(&init_mm); + if (slab_is_available()) + new = pte_alloc_one_kernel(&init_mm); + else + new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); if (!new) return -ENOMEM; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 9259337d7374..9191a66b3bc5 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -239,7 +239,7 @@ void __init paging_init(void) #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - ((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT); + 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index c8ec670ee924..a5ac371a3f06 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -11,6 +11,7 @@ #include <linux/sched.h> #include <linux/libnvdimm.h> #include <linux/platform_device.h> +#include <linux/delay.h> #include <asm/plpar_wrappers.h> @@ -43,8 +44,9 @@ struct papr_scm_priv { static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; uint64_t saved = 0; + uint64_t token; + int64_t rc; /* * When the hypervisor cannot map all the requested memory in a single @@ -64,6 +66,10 @@ static int drc_pmem_bind(struct papr_scm_priv *p) } while (rc == H_BUSY); if (rc) { + /* H_OVERLAP needs a separate error path */ + if (rc == H_OVERLAP) + return -EBUSY; + dev_err(&p->pdev->dev, "bind err: %lld\n", rc); return -ENXIO; } @@ -78,22 +84,36 @@ static int drc_pmem_bind(struct papr_scm_priv *p) static int drc_pmem_unbind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; - uint64_t rc, token; + uint64_t token = 0; + int64_t rc; - token = 0; + dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index); - /* NB: unbind has the same retry requirements mentioned above */ + /* NB: unbind has the same retry requirements as drc_pmem_bind() */ do { - rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index, - p->bound_addr, p->blocks, token); + + /* Unbind of all SCM resources associated with drcIndex */ + rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC, + p->drc_index, token); token = ret[0]; - cond_resched(); + + /* Check if we are stalled for some time */ + if (H_IS_LONG_BUSY(rc)) { + msleep(get_longbusy_msecs(rc)); + rc = H_BUSY; + } else if (rc == H_BUSY) { + cond_resched(); + } + } while (rc == H_BUSY); if (rc) dev_err(&p->pdev->dev, "unbind error: %lld\n", rc); + else + dev_dbg(&p->pdev->dev, "unbind drc %x complete\n", + p->drc_index); - return !!rc; + return rc == H_SUCCESS ? 0 : -ENXIO; } static int papr_scm_meta_get(struct papr_scm_priv *p, @@ -255,12 +275,32 @@ static const struct attribute_group *papr_scm_dimm_groups[] = { NULL, }; +static inline int papr_scm_node(int node) +{ + int min_dist = INT_MAX, dist; + int nid, min_node; + + if ((node == NUMA_NO_NODE) || node_online(node)) + return node; + + min_node = first_online_node; + for_each_online_node(nid) { + dist = node_distance(node, nid); + if (dist < min_dist) { + min_dist = dist; + min_node = nid; + } + } + return min_node; +} + static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; struct nd_mapping_desc mapping; struct nd_region_desc ndr_desc; unsigned long dimm_flags; + int target_nid, online_nid; p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; @@ -299,8 +339,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.attr_groups = region_attr_groups; - ndr_desc.numa_node = dev_to_node(&p->pdev->dev); - ndr_desc.target_node = ndr_desc.numa_node; + target_nid = dev_to_node(&p->pdev->dev); + online_nid = papr_scm_node(target_nid); + ndr_desc.numa_node = online_nid; + ndr_desc.target_node = target_nid; ndr_desc.res = &p->res; ndr_desc.of_node = p->dn; ndr_desc.provider_data = p; @@ -318,6 +360,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) ndr_desc.res, p->dn); goto err; } + if (target_nid != online_nid) + dev_info(dev, "Region registered with target node %d and online node %d", + target_nid, online_nid); return 0; @@ -389,6 +434,14 @@ static int papr_scm_probe(struct platform_device *pdev) /* request the hypervisor to bind this region to somewhere in memory */ rc = drc_pmem_bind(p); + + /* If phyp says drc memory still bound then force unbound and retry */ + if (rc == -EBUSY) { + dev_warn(&pdev->dev, "Retrying bind after unbinding\n"); + drc_pmem_unbind(p); + rc = drc_pmem_bind(p); + } + if (rc) goto err; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 082c7e1c20f0..1cdb39575eae 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -479,7 +479,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, * Now go through the entire mask until we find a valid * target. */ - for (;;) { + do { /* * We re-check online as the fallback case passes us * an untested affinity mask @@ -487,12 +487,11 @@ static int xive_find_target_in_mask(const struct cpumask *mask, if (cpu_online(cpu) && xive_try_pick_target(cpu)) return cpu; cpu = cpumask_next(cpu, mask); - if (cpu == first) - break; /* Wrap around */ if (cpu >= nr_cpu_ids) cpu = cpumask_first(mask); - } + } while (cpu != first); + return -1; } diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 40983491b95f..42b5ec223100 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -21,7 +21,6 @@ cpus { #address-cells = <1>; #size-cells = <0>; - timebase-frequency = <1000000>; cpu0: cpu@0 { compatible = "sifive,e51", "sifive,rocket0", "riscv"; device_type = "cpu"; @@ -217,5 +216,20 @@ #size-cells = <0>; status = "disabled"; }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <53>; + reg = <0x0 0x10090000 0x0 0x2000 + 0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci PRCI_CLK_GEMGXLPLL>, + <&prci PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + }; }; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 0b55c53c08c7..93d68cbd64fe 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -76,3 +76,12 @@ disable-wp; }; }; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index b7b749b18853..93205c0bf71d 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -34,6 +34,7 @@ CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_SD=y @@ -53,6 +54,8 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_EARLYCON_RISCV_SBI=y CONFIG_HVC_RISCV_SBI=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_RADEON=y @@ -66,8 +69,9 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_VIRTIO_MMIO=y -CONFIG_SPI_SIFIVE=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -83,8 +87,4 @@ CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y -CONFIG_SPI=y -CONFIG_MMC_SPI=y -CONFIG_MMC=y -CONFIG_DEVTMPFS_MOUNT=y # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 1efaeddf1e4b..16970f246860 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -22,6 +22,7 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h +generic-y += msi.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 62716653554b..d86cb17bbabe 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h index 0b9b58b57ff6..7d0b32e3b701 100644 --- a/arch/riscv/include/uapi/asm/bitsperlong.h +++ b/arch/riscv/include/uapi/asm/bitsperlong.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h index 1920debc09c0..f671e16bf6af 100644 --- a/arch/riscv/include/uapi/asm/byteorder.h +++ b/arch/riscv/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2015 Regents of the University of California diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h index 7d786145183b..4e7646077056 100644 --- a/arch/riscv/include/uapi/asm/hwcap.h +++ b/arch/riscv/include/uapi/asm/hwcap.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copied from arch/arm64/include/asm/hwcap.h * diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 92d8f7cd8f84..882547f6bd5c 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 Regents of the University of California */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index 053f809e52ce..84f2dfcfdbce 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 Regents of the University of California */ diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h index b58e00cee2ec..411dd7b52ed6 100644 --- a/arch/riscv/include/uapi/asm/ucontext.h +++ b/arch/riscv/include/uapi/asm/ucontext.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2017 SiFive, Inc. diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 0e2eeeb1fd27..13ce76cc5aff 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -18,6 +18,7 @@ #ifdef __LP64__ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_SYS_CLONE3 #endif /* __LP64__ */ #include <asm-generic/unistd.h> diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index f1d6ffe43e42..49a5852fd07d 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -37,7 +37,7 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE # these symbols in the kernel code rather than hand-coded addresses. SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--hash-style=both + -Wl,--build-id -Wl,--hash-style=both $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE $(call if_changed,vdsold) diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index 7cba96e7587b..4cf0bddb7d92 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -36,7 +36,7 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += ctype.o text_dma.o +obj-y += version.o ctype.o text_dma.o obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index ad57c2205a71..1c3b2b257637 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -8,10 +8,12 @@ void store_ipl_parmblock(void); void setup_boot_command_line(void); void parse_boot_command_line(void); void setup_memory_end(void); +void verify_facilities(void); void print_missing_facilities(void); unsigned long get_random_base(unsigned long safe_addr); extern int kaslr_enabled; +extern const char kernel_version[]; unsigned long read_ipl_report(unsigned long safe_offset); diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S index 028aab03a9e7..2087bed6e60f 100644 --- a/arch/s390/boot/head.S +++ b/arch/s390/boot/head.S @@ -361,6 +361,7 @@ ENTRY(startup_kdump) .quad 0 # INITRD_SIZE .quad 0 # OLDMEM_BASE .quad 0 # OLDMEM_SIZE + .quad kernel_version # points to kernel version string .org COMMAND_LINE .byte "root=/dev/ram0 ro" diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 3bdd8132e56b..c34a6387ce38 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -7,6 +7,7 @@ #include <asm/timex.h> #include <asm/sclp.h> #include "compressed/decompressor.h" +#include "boot.h" #define PRNG_MODE_TDES 1 #define PRNG_MODE_SHA512 2 diff --git a/arch/s390/boot/version.c b/arch/s390/boot/version.c new file mode 100644 index 000000000000..d32e58bdda6a --- /dev/null +++ b/arch/s390/boot/version.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <generated/utsrelease.h> +#include <generated/compile.h> +#include "boot.h" + +const char kernel_version[] = UTS_RELEASE + " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") " UTS_VERSION; diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index e26d4413d34c..74e78ec5beb6 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -3,6 +3,7 @@ CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -18,55 +19,71 @@ CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=512 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y +CONFIG_CHSC_SCH=y +CONFIG_VFIO_CCW=m +CONFIG_VFIO_AP=m +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y +CONFIG_REFCOUNT_FULL=y +CONFIG_LOCK_EVENT_COUNTS=y CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y -CONFIG_BLK_WBT_SQ=y +CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_CFQ_GROUP_IOSCHED=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=512 -CONFIG_NUMA=y -CONFIG_PREEMPT=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_VERIFY_SIG=y -CONFIG_EXPOLINE=y -CONFIG_EXPOLINE_AUTO=y +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,17 +99,8 @@ CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_PCI=y -CONFIG_PCI_DEBUG=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_S390=y -CONFIG_CHSC_SCH=y -CONFIG_VFIO_AP=m -CONFIG_VFIO_CCW=m -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y +CONFIG_PERCPU_STATS=y +CONFIG_GUP_BENCHMARK=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -121,9 +129,6 @@ CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m CONFIG_TCP_CONG_ADVANCED=y @@ -139,10 +144,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m @@ -264,11 +265,8 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=y -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -287,10 +285,7 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=y -CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -309,7 +304,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=y +CONFIG_NF_TABLES_BRIDGE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -375,9 +370,11 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +CONFIG_PCI=y +CONFIG_PCI_DEBUG=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y -CONFIG_CMA_SIZE_MBYTES=0 CONFIG_CONNECTOR=y CONFIG_ZRAM=m CONFIG_BLK_DEV_LOOP=m @@ -395,7 +392,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m @@ -415,17 +411,19 @@ CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m -CONFIG_SCSI_OSD_INITIATOR=m -CONFIG_SCSI_OSD_ULD=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m +CONFIG_MD_CLUSTER=m +CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=m +CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -445,23 +443,78 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m -CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_NLMON=m +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_AGERE is not set +# CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMAZON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_VENDOR_AURORA is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CADENCE is not set +# CONFIG_NET_VENDOR_CAVIUM is not set # CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_GOOGLE is not set +# CONFIG_NET_VENDOR_HP is not set +# CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +# CONFIG_MLXFW is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROCHIP is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set +# CONFIG_NET_VENDOR_MYRI is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NETERION is not set +# CONFIG_NET_VENDOR_NETRONOME is not set +# CONFIG_NET_VENDOR_NI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RENESAS is not set +# CONFIG_NET_VENDOR_ROCKER is not set +# CONFIG_NET_VENDOR_SAMSUNG is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SOLARFLARE is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_SOCIONEXT is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m +CONFIG_PPP_FILTER=y CONFIG_PPP_MPPE=m +CONFIG_PPP_MULTILINK=y CONFIG_PPPOE=m CONFIG_PPTP=m CONFIG_PPPOL2TP=m @@ -473,10 +526,13 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_NULL_TTY=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +CONFIG_PPS=m +# CONFIG_PTP_1588_CLOCK is not set # CONFIG_HWMON is not set CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y @@ -498,8 +554,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y -CONFIG_S390_AP_IOMMU=y CONFIG_S390_CCW_IOMMU=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -519,6 +575,7 @@ CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y +CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y @@ -552,8 +609,10 @@ CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m CONFIG_NFS_V3_ACL=y @@ -564,7 +623,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS=y CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y @@ -580,19 +638,112 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DLM=m +CONFIG_UNICODE=y +CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y +CONFIG_ENCRYPTED_KEYS=m +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_FORTIFY_SOURCE=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_INTEGRITY_SIGNATURE=y +CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_IMA=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y +CONFIG_IMA_WRITE_POLICY=y +CONFIG_IMA_APPRAISE=y +CONFIG_CRYPTO_USER=m +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_PCRYPT=m +CONFIG_CRYPTO_CRYPTD=m +CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m +CONFIG_CRYPTO_CFB=m +CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_KEYWRAP=m +CONFIG_CRYPTO_ADIANTUM=m +CONFIG_CRYPTO_XCBC=m +CONFIG_CRYPTO_VMAC=m +CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_RMD128=m +CONFIG_CRYPTO_RMD160=m +CONFIG_CRYPTO_RMD256=m +CONFIG_CRYPTO_RMD320=m +CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_AES_TI=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAMELLIA=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_FCRYPT=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_SALSA20=m +CONFIG_CRYPTO_SEED=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_842=m +CONFIG_CRYPTO_LZ4=m +CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m +CONFIG_CRYPTO_ANSI_CPRNG=m +CONFIG_CRYPTO_USER_API_HASH=m +CONFIG_CRYPTO_USER_API_SKCIPHER=m +CONFIG_CRYPTO_USER_API_RNG=m +CONFIG_CRYPTO_USER_API_AEAD=m +CONFIG_CRYPTO_STATS=y +CONFIG_ZCRYPT=m +CONFIG_PKEY=m +CONFIG_CRYPTO_PAES_S390=m +CONFIG_CRYPTO_SHA1_S390=m +CONFIG_CRYPTO_SHA256_S390=m +CONFIG_CRYPTO_SHA512_S390=m +CONFIG_CRYPTO_DES_S390=m +CONFIG_CRYPTO_AES_S390=m +CONFIG_CRYPTO_GHASH_S390=m +CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CORDIC=m +CONFIG_CRC32_SELFTEST=y +CONFIG_CRC4=m +CONFIG_CRC7=m +CONFIG_CRC8=m +CONFIG_RANDOM32_SELFTEST=y +CONFIG_DMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=0 +CONFIG_DMA_API_DEBUG=y +CONFIG_STRING_SELFTEST=y CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_READABLE_ASM=y CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_PAGEALLOC=y +CONFIG_PAGE_OWNER=y CONFIG_DEBUG_RODATA_TEST=y CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_SELFTEST=y @@ -645,7 +796,6 @@ CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_FUNCTION_PROFILER=y CONFIG_HIST_TRIGGERS=y -CONFIG_DMA_API_DEBUG=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y CONFIG_TEST_SORT=y @@ -657,85 +807,3 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_S390_PTDUMP=y -CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y -CONFIG_ENCRYPTED_KEYS=m -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_FORTIFY_SOURCE=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_INTEGRITY_SIGNATURE=y -CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y -CONFIG_IMA=y -CONFIG_IMA_DEFAULT_HASH_SHA256=y -CONFIG_IMA_WRITE_POLICY=y -CONFIG_IMA_APPRAISE=y -CONFIG_CRYPTO_DH=m -CONFIG_CRYPTO_ECDH=m -CONFIG_CRYPTO_USER=m -# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set -CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_CHACHA20POLY1305=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_KEYWRAP=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_CRC32=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_RMD128=m -CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_RMD256=m -CONFIG_CRYPTO_RMD320=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_AES_TI=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_842=m -CONFIG_CRYPTO_LZ4=m -CONFIG_CRYPTO_LZ4HC=m -CONFIG_CRYPTO_ANSI_CPRNG=m -CONFIG_CRYPTO_USER_API_HASH=m -CONFIG_CRYPTO_USER_API_SKCIPHER=m -CONFIG_CRYPTO_USER_API_RNG=m -CONFIG_CRYPTO_USER_API_AEAD=m -CONFIG_ZCRYPT=m -CONFIG_PKEY=m -CONFIG_CRYPTO_PAES_S390=m -CONFIG_CRYPTO_SHA1_S390=m -CONFIG_CRYPTO_SHA256_S390=m -CONFIG_CRYPTO_SHA512_S390=m -CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=y -CONFIG_PKCS7_MESSAGE_PARSER=y -CONFIG_SYSTEM_TRUSTED_KEYRING=y -CONFIG_CRC7=m -CONFIG_CRC8=m -CONFIG_RANDOM32_SELFTEST=y -CONFIG_CORDIC=m -CONFIG_CMM=m -CONFIG_APPLDATA_BASE=y -CONFIG_KVM=m -CONFIG_KVM_S390_UCONTROL=y -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index e4bc40073003..68d3ca83302b 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -12,30 +12,51 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y -# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_RDMA=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_TUNE_ZEC12=y +CONFIG_NR_CPUS=512 +CONFIG_NUMA=y +# CONFIG_NUMA_EMU is not set +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y +CONFIG_CHSC_SCH=y +CONFIG_VFIO_CCW=m +CONFIG_VFIO_AP=m +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m +CONFIG_APPLDATA_BASE=y +CONFIG_KVM=m +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -47,27 +68,18 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y -CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y -CONFIG_BLK_WBT_SQ=y +CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_CFQ_GROUP_IOSCHED=y -CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_TUNE_ZEC12=y -CONFIG_NR_CPUS=512 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_VERIFY_SIG=y -CONFIG_EXPOLINE=y -CONFIG_EXPOLINE_AUTO=y +CONFIG_IOSCHED_BFQ=y +CONFIG_BFQ_GROUP_IOSCHED=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -81,16 +93,8 @@ CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_PCI=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_S390=y -CONFIG_CHSC_SCH=y -CONFIG_VFIO_AP=m -CONFIG_VFIO_CCW=m -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y +CONFIG_PERCPU_STATS=y +CONFIG_GUP_BENCHMARK=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -119,9 +123,6 @@ CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_MODE_TRANSPORT=m -CONFIG_INET_XFRM_MODE_TUNNEL=m -CONFIG_INET_XFRM_MODE_BEET=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m CONFIG_TCP_CONG_ADVANCED=y @@ -137,10 +138,6 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_MODE_TRANSPORT=m -CONFIG_INET6_XFRM_MODE_TUNNEL=m -CONFIG_INET6_XFRM_MODE_BEET=m -CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_VTI=m CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m @@ -262,11 +259,8 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_NF_TABLES_IPV4=y -CONFIG_NFT_CHAIN_ROUTE_IPV4=m CONFIG_NF_TABLES_ARP=y -CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -285,10 +279,7 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m CONFIG_NF_TABLES_IPV6=y -CONFIG_NFT_CHAIN_ROUTE_IPV6=m -CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -307,7 +298,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=y +CONFIG_NF_TABLES_BRIDGE=m CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -372,9 +363,11 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +CONFIG_PCI=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_S390=y +CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y -CONFIG_DMA_CMA=y -CONFIG_CMA_SIZE_MBYTES=0 CONFIG_CONNECTOR=y CONFIG_ZRAM=m CONFIG_BLK_DEV_LOOP=m @@ -383,6 +376,7 @@ CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 +# CONFIG_BLK_DEV_XPRAM is not set CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_RBD=m CONFIG_BLK_DEV_NVME=m @@ -392,7 +386,6 @@ CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m @@ -412,17 +405,19 @@ CONFIG_SCSI_DH_RDAC=m CONFIG_SCSI_DH_HP_SW=m CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m -CONFIG_SCSI_OSD_INITIATOR=m -CONFIG_SCSI_OSD_ULD=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m +CONFIG_MD_CLUSTER=m +CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=m +CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_WRITECACHE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +430,7 @@ CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m CONFIG_DM_SWITCH=m +CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -442,23 +438,78 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m -CONFIG_VXLAN=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m CONFIG_NLMON=m +# CONFIG_NET_VENDOR_3COM is not set +# CONFIG_NET_VENDOR_ADAPTEC is not set +# CONFIG_NET_VENDOR_AGERE is not set +# CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_ALTEON is not set +# CONFIG_NET_VENDOR_AMAZON is not set +# CONFIG_NET_VENDOR_AMD is not set +# CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ATHEROS is not set +# CONFIG_NET_VENDOR_AURORA is not set +# CONFIG_NET_VENDOR_BROADCOM is not set +# CONFIG_NET_VENDOR_BROCADE is not set +# CONFIG_NET_VENDOR_CADENCE is not set +# CONFIG_NET_VENDOR_CAVIUM is not set # CONFIG_NET_VENDOR_CHELSIO is not set +# CONFIG_NET_VENDOR_CISCO is not set +# CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DEC is not set +# CONFIG_NET_VENDOR_DLINK is not set +# CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_GOOGLE is not set +# CONFIG_NET_VENDOR_HP is not set +# CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +# CONFIG_MLXFW is not set +# CONFIG_NET_VENDOR_MICREL is not set +# CONFIG_NET_VENDOR_MICROCHIP is not set +# CONFIG_NET_VENDOR_MICROSEMI is not set +# CONFIG_NET_VENDOR_MYRI is not set # CONFIG_NET_VENDOR_NATSEMI is not set +# CONFIG_NET_VENDOR_NETERION is not set +# CONFIG_NET_VENDOR_NETRONOME is not set +# CONFIG_NET_VENDOR_NI is not set +# CONFIG_NET_VENDOR_NVIDIA is not set +# CONFIG_NET_VENDOR_OKI is not set +# CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_QLOGIC is not set +# CONFIG_NET_VENDOR_QUALCOMM is not set +# CONFIG_NET_VENDOR_RDC is not set +# CONFIG_NET_VENDOR_REALTEK is not set +# CONFIG_NET_VENDOR_RENESAS is not set +# CONFIG_NET_VENDOR_ROCKER is not set +# CONFIG_NET_VENDOR_SAMSUNG is not set +# CONFIG_NET_VENDOR_SEEQ is not set +# CONFIG_NET_VENDOR_SOLARFLARE is not set +# CONFIG_NET_VENDOR_SILAN is not set +# CONFIG_NET_VENDOR_SIS is not set +# CONFIG_NET_VENDOR_SMSC is not set +# CONFIG_NET_VENDOR_SOCIONEXT is not set +# CONFIG_NET_VENDOR_STMICRO is not set +# CONFIG_NET_VENDOR_SUN is not set +# CONFIG_NET_VENDOR_SYNOPSYS is not set +# CONFIG_NET_VENDOR_TEHUTI is not set +# CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VIA is not set +# CONFIG_NET_VENDOR_WIZNET is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m +CONFIG_PPP_FILTER=y CONFIG_PPP_MPPE=m +CONFIG_PPP_MULTILINK=y CONFIG_PPPOE=m CONFIG_PPTP=m CONFIG_PPPOL2TP=m @@ -470,17 +521,21 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +CONFIG_NULL_TTY=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m CONFIG_HANGCHECK_TIMER=m CONFIG_TN3270_FS=y +# CONFIG_PTP_1588_CLOCK is not set # CONFIG_HWMON is not set CONFIG_WATCHDOG=y +CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m CONFIG_DRM=y CONFIG_DRM_VIRTIO_GPU=y +# CONFIG_BACKLIGHT_CLASS_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set @@ -495,8 +550,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y -CONFIG_S390_AP_IOMMU=y CONFIG_S390_CCW_IOMMU=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -546,8 +601,10 @@ CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y +CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m CONFIG_NFS_V3_ACL=y @@ -558,7 +615,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_STATS=y CONFIG_CIFS_STATS2=y CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y @@ -574,31 +630,7 @@ CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m CONFIG_DLM=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -# CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_RCU_TORTURE_TEST=m -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -CONFIG_HIST_TRIGGERS=y -CONFIG_LKDTM=m -CONFIG_PERCPU_TEST=m -CONFIG_ATOMIC64_SELFTEST=y -CONFIG_TEST_BPF=m -CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_S390_PTDUMP=y +CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m @@ -606,7 +638,6 @@ CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y @@ -615,31 +646,42 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_CRYPTO_FIPS=y -CONFIG_CRYPTO_DH=m -CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_DH=m +CONFIG_CRYPTO_ECDH=m +CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m +CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_AEGIS128L=m +CONFIG_CRYPTO_AEGIS256=m +CONFIG_CRYPTO_MORUS640=m +CONFIG_CRYPTO_MORUS1280=m +CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_KEYWRAP=m +CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_XXHASH=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m -CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m @@ -649,16 +691,19 @@ CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_SM4=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_842=m CONFIG_CRYPTO_LZ4=m CONFIG_CRYPTO_LZ4HC=m +CONFIG_CRYPTO_ZSTD=m CONFIG_CRYPTO_ANSI_CPRNG=m CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m +CONFIG_CRYPTO_STATS=y CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -669,12 +714,34 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CORDIC=m +CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m -CONFIG_CORDIC=m -CONFIG_CMM=m -CONFIG_APPLDATA_BASE=y -CONFIG_KVM=m -CONFIG_KVM_S390_UCONTROL=y -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m +CONFIG_DMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=0 +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y +CONFIG_FRAME_WARN=1024 +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_RCU_TORTURE_TEST=m +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FUNCTION_PROFILER=y +CONFIG_HIST_TRIGGERS=y +CONFIG_LKDTM=m +CONFIG_PERCPU_TEST=m +CONFIG_ATOMIC64_SELFTEST=y +CONFIG_TEST_BPF=m +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_S390_PTDUMP=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index d92bab844b73..be09a208b608 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,27 +1,33 @@ # CONFIG_SWAP is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +# CONFIG_CPU_ISOLATION is not set +# CONFIG_UTS_NS is not set +# CONFIG_PID_NS is not set +# CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_COMPAT_BRK is not set -CONFIG_PARTITION_ADVANCED=y -CONFIG_IBM_PARTITION=y -CONFIG_DEFAULT_DEADLINE=y CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 -# CONFIG_HOTPLUG_CPU is not set CONFIG_HZ_100=y # CONFIG_ARCH_RANDOM is not set -# CONFIG_COMPACTION is not set -# CONFIG_MIGRATION is not set -# CONFIG_BOUNCE is not set -# CONFIG_CHECK_STACK is not set +# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SECCOMP is not set +# CONFIG_PFAULT is not set +# CONFIG_S390_HYPFS_FS is not set +# CONFIG_VIRTUALIZATION is not set +# CONFIG_S390_GUEST is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_IBM_PARTITION=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +# CONFIG_COMPACTION is not set +# CONFIG_MIGRATION is not set +# CONFIG_BOUNCE is not set CONFIG_NET=y # CONFIG_IUCV is not set CONFIG_DEVTMPFS=y @@ -43,7 +49,6 @@ CONFIG_ZFCP=y # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set CONFIG_RAW_DRIVER=y -# CONFIG_SCLP_ASYNC is not set # CONFIG_HMC_DRV is not set # CONFIG_S390_TAPE is not set # CONFIG_VMCP is not set @@ -56,6 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +# CONFIG_DIMLIB is not set CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y @@ -64,7 +70,4 @@ CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_FTRACE is not set -# CONFIG_PFAULT is not set -# CONFIG_S390_HYPFS_FS is not set -# CONFIG_VIRTUALIZATION is not set -# CONFIG_S390_GUEST is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 42f2375c203e..e1fcc03159ef 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -118,7 +118,7 @@ do { \ return PTR_ERR(rc); \ } while(0) -static int hpyfs_vm_create_guest(struct dentry *systems_dir, +static int hypfs_vm_create_guest(struct dentry *systems_dir, struct diag2fc_data *data) { char guest_name[NAME_LEN + 1] = {}; @@ -219,7 +219,7 @@ int hypfs_vm_create_files(struct dentry *root) } for (i = 0; i < count; i++) { - rc = hpyfs_vm_create_guest(dir, &(data[i])); + rc = hypfs_vm_create_guest(dir, &(data[i])); if (rc) goto failed; } diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 9900d655014c..b8833ac983fa 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -35,6 +35,7 @@ #include <linux/typecheck.h> #include <linux/compiler.h> +#include <linux/types.h> #include <asm/atomic_ops.h> #include <asm/barrier.h> @@ -55,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -76,7 +77,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -97,7 +98,8 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -118,8 +120,8 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_xor(mask, (long *)addr); } -static inline int -test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_set_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -129,8 +131,8 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (old & mask) != 0; } -static inline int -test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -140,8 +142,8 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (old & ~mask) != 0; } -static inline int -test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch_test_and_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long old, mask; @@ -151,30 +153,31 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) return (old & mask) != 0; } -static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr |= 1 << (nr & 7); } -static inline void -__clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr &= ~(1 << (nr & 7)); } -static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline void arch___change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); *addr ^= 1 << (nr & 7); } -static inline int -__test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_set_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -184,8 +187,8 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int -__test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_clear_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -195,8 +198,8 @@ __test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int -__test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) +static inline bool arch___test_and_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned char *addr = __bitops_byte(nr, ptr); unsigned char ch; @@ -206,7 +209,8 @@ __test_and_change_bit(unsigned long nr, volatile unsigned long *ptr) return (ch >> (nr & 7)) & 1; } -static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) +static inline bool arch_test_bit(unsigned long nr, + const volatile unsigned long *ptr) { const volatile unsigned char *addr; @@ -215,28 +219,30 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr) return (*addr >> (nr & 7)) & 1; } -static inline int test_and_set_bit_lock(unsigned long nr, - volatile unsigned long *ptr) +static inline bool arch_test_and_set_bit_lock(unsigned long nr, + volatile unsigned long *ptr) { - if (test_bit(nr, ptr)) + if (arch_test_bit(nr, ptr)) return 1; - return test_and_set_bit(nr, ptr); + return arch_test_and_set_bit(nr, ptr); } -static inline void clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) +static inline void arch_clear_bit_unlock(unsigned long nr, + volatile unsigned long *ptr) { smp_mb__before_atomic(); - clear_bit(nr, ptr); + arch_clear_bit(nr, ptr); } -static inline void __clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) +static inline void arch___clear_bit_unlock(unsigned long nr, + volatile unsigned long *ptr) { smp_mb(); - __clear_bit(nr, ptr); + arch___clear_bit(nr, ptr); } +#include <asm-generic/bitops-instrumented.h> + /* * Functions which use MSB0 bit numbering. * The bits are numbered: @@ -261,7 +267,8 @@ static inline void clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) +static inline bool test_and_clear_bit_inv(unsigned long nr, + volatile unsigned long *ptr) { return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } @@ -276,8 +283,8 @@ static inline void __clear_bit_inv(unsigned long nr, volatile unsigned long *ptr return __clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } -static inline int test_bit_inv(unsigned long nr, - const volatile unsigned long *ptr) +static inline bool test_bit_inv(unsigned long nr, + const volatile unsigned long *ptr) { return test_bit(nr ^ (BITS_PER_LONG - 1), ptr); } diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a4d38092530a..823578c6b9e2 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,6 +177,8 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define ARCH_ZONE_DMA_BITS 31 + #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index db5ef22c46e4..f647d565bd6d 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -28,7 +28,7 @@ * @sliba: storage list information block address * @sla: storage list address * @slsba: storage list state block address - * @akey: access key for DLIB + * @akey: access key for SLIB * @bkey: access key for SL * @ckey: access key for SBALs * @dkey: access key for SLSB @@ -50,11 +50,10 @@ struct qdesfmt0 { /** * struct qdr - queue description record (QDR) * @qfmt: queue format - * @pfmt: implementation dependent parameter format * @ac: adapter characteristics * @iqdcnt: input queue descriptor count * @oqdcnt: output queue descriptor count - * @iqdsz: inpout queue descriptor size + * @iqdsz: input queue descriptor size * @oqdsz: output queue descriptor size * @qiba: queue information block address * @qkey: queue information block key @@ -62,8 +61,7 @@ struct qdesfmt0 { */ struct qdr { u32 qfmt : 8; - u32 pfmt : 8; - u32 : 8; + u32 : 16; u32 ac : 8; u32 : 8; u32 iqdcnt : 8; @@ -327,6 +325,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * struct qdio_initialize - qdio initialization data * @cdev: associated ccw device * @q_format: queue format + * @qdr_ac: feature flags to set * @adapter_name: name for the adapter * @qib_param_field_format: format for qib_parm_field * @qib_param_field: pointer to 128 bytes or NULL, if no param field @@ -338,6 +337,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * @input_handler: handler to be called for input queues * @output_handler: handler to be called for output queues * @queue_start_poll_array: polling handlers (one per input queue or NULL) + * @scan_threshold: # of in-use buffers that triggers scan on output queue * @int_parm: interruption parameter * @input_sbal_addr_array: address of no_input_qs * 128 pointers * @output_sbal_addr_array: address of no_output_qs * 128 pointers diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 82deb8fc8319..70bd65724ec4 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -54,6 +54,7 @@ #define INITRD_SIZE_OFFSET 0x10410 #define OLDMEM_BASE_OFFSET 0x10418 #define OLDMEM_SIZE_OFFSET 0x10420 +#define KERNEL_VERSION_OFFSET 0x10428 #define COMMAND_LINE_OFFSET 0x10480 #ifndef __ASSEMBLY__ @@ -74,7 +75,8 @@ struct parmarea { unsigned long initrd_size; /* 0x10410 */ unsigned long oldmem_base; /* 0x10418 */ unsigned long oldmem_size; /* 0x10420 */ - char pad1[0x10480 - 0x10428]; /* 0x10428 - 0x10480 */ + unsigned long kernel_version; /* 0x10428 */ + char pad1[0x10480 - 0x10430]; /* 0x10430 - 0x10480 */ char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */ }; @@ -82,6 +84,7 @@ extern int noexec_disabled; extern int memory_end_set; extern unsigned long memory_end; extern unsigned long max_physmem_end; +extern unsigned long __swsusp_reset_dma; #define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM) #define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM) diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index b6755685c7b8..9e9f75ef046a 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -34,5 +34,6 @@ #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 #endif /* _ASM_S390_UNISTD_H_ */ diff --git a/arch/s390/include/uapi/asm/bpf_perf_event.h b/arch/s390/include/uapi/asm/bpf_perf_event.h index cefe7c7cd4f6..3ed42ff6da94 100644 --- a/arch/s390/include/uapi/asm/bpf_perf_event.h +++ b/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h index fd32b1cd80d2..451ba7d08905 100644 --- a/arch/s390/include/uapi/asm/ipl.h +++ b/arch/s390/include/uapi/asm/ipl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_S390_UAPI_IPL_H #define _ASM_S390_UAPI_IPL_H diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 494c34c50716..8c5755f41dde 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -20,6 +20,7 @@ #include <linux/ioctl.h> #include <linux/compiler.h> +#include <linux/types.h> /* Name of the zcrypt device driver. */ #define ZCRYPT_NAME "zcrypt" @@ -160,17 +161,17 @@ struct ica_xcRB { * @payload_len: Payload length */ struct ep11_cprb { - uint16_t cprb_len; + __u16 cprb_len; unsigned char cprb_ver_id; unsigned char pad_000[2]; unsigned char flags; unsigned char func_id[2]; - uint32_t source_id; - uint32_t target_id; - uint32_t ret_code; - uint32_t reserved1; - uint32_t reserved2; - uint32_t payload_len; + __u32 source_id; + __u32 target_id; + __u32 ret_code; + __u32 reserved1; + __u32 reserved2; + __u32 payload_len; } __attribute__((packed)); /** @@ -179,8 +180,8 @@ struct ep11_cprb { * @dom_id: Usage domain id */ struct ep11_target_dev { - uint16_t ap_id; - uint16_t dom_id; + __u16 ap_id; + __u16 dom_id; }; /** @@ -195,14 +196,14 @@ struct ep11_target_dev { * @resp: Addr to response block */ struct ep11_urb { - uint16_t targets_num; - uint64_t targets; - uint64_t weight; - uint64_t req_no; - uint64_t req_len; - uint64_t req; - uint64_t resp_len; - uint64_t resp; + __u16 targets_num; + __u64 targets; + __u64 weight; + __u64 req_no; + __u64 req_len; + __u64 req; + __u64 resp_len; + __u64 resp; } __attribute__((packed)); /** diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index 1dded39239f8..3b664cb3ec4d 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> +#include <asm/kexec.h> int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, unsigned long addr) diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index d4e031f7b9c8..5f1fd1581330 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -34,7 +34,7 @@ struct cf_diag_csd { /* Counter set data per CPU */ unsigned char start[PAGE_SIZE]; /* Counter set at event start */ unsigned char data[PAGE_SIZE]; /* Counter set at event delete */ }; -DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd); +static DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd); /* Counter sets are stored as data stream in a page sized memory buffer and * exported to user space via raw data attached to the event sample data. diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index a90d3e945445..3054e9c035a3 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -437,4 +437,4 @@ 432 common fsmount sys_fsmount sys_fsmount 433 common fspick sys_fspick sys_fspick 434 common pidfd_open sys_pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 sys_clone3 sys_clone3 diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index 96580590ccaf..29d9470dbceb 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/export.h> #include <linux/raid/xor.h> +#include <asm/xor.h> static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 63507662828f..7b0bb475c166 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -327,6 +327,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int access, case VM_FAULT_BADACCESS: if (access == VM_EXEC && signal_return(regs) == 0) break; + /* fallthrough */ case VM_FAULT_BADMAP: /* Bad memory access. Check if it is kernel or user space. */ if (user_mode(regs)) { @@ -336,7 +337,9 @@ static noinline void do_fault_error(struct pt_regs *regs, int access, do_sigsegv(regs, si_code); break; } + /* fallthrough */ case VM_FAULT_BADCONTEXT: + /* fallthrough */ case VM_FAULT_PFAULT: do_no_context(regs); break; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 1e668b95e0c6..39c3a6e3d262 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2424,8 +2424,8 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global); * This function is assumed to be called with the guest_table_lock * held. */ -bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, - unsigned long gaddr) +static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, + unsigned long gaddr) { if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) return false; diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 99e06213a22b..54fcdf66ae96 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -17,8 +17,6 @@ #ifdef CONFIG_PGSTE -static int page_table_allocate_pgste_min = 0; -static int page_table_allocate_pgste_max = 1; int page_table_allocate_pgste = 0; EXPORT_SYMBOL(page_table_allocate_pgste); @@ -29,8 +27,8 @@ static struct ctl_table page_table_sysctl[] = { .maxlen = sizeof(int), .mode = S_IRUGO | S_IWUSR, .proc_handler = proc_dointvec_minmax, - .extra1 = &page_table_allocate_pgste_min, - .extra2 = &page_table_allocate_pgste_max, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { } }; diff --git a/arch/sh/include/uapi/asm/setup.h b/arch/sh/include/uapi/asm/setup.h index 1170dd2fb998..4bd19f80f9b0 100644 --- a/arch/sh/include/uapi/asm/setup.h +++ b/arch/sh/include/uapi/asm/setup.h @@ -1,2 +1,2 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include <asm-generic/setup.h> diff --git a/arch/sh/include/uapi/asm/types.h b/arch/sh/include/uapi/asm/types.h index f83795fdc0da..68100e108ea6 100644 --- a/arch/sh/include/uapi/asm/types.h +++ b/arch/sh/include/uapi/asm/types.h @@ -1,2 +1,2 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include <asm-generic/types.h> diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h index 64c67f2ea33f..0dace69058ab 100644 --- a/arch/sparc/include/uapi/asm/oradax.h +++ b/arch/sparc/include/uapi/asm/oradax.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ /* * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved. */ diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 830bd984182b..515c0ceeb4a3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -314,6 +314,23 @@ For 32-bit we have the following conventions - kernel is built with #endif +/* + * Mitigate Spectre v1 for conditional swapgs code paths. + * + * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to + * prevent a speculative swapgs when coming from kernel space. + * + * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path, + * to prevent the swapgs from getting speculatively skipped when coming from + * user space. + */ +.macro FENCE_SWAPGS_USER_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER +.endm +.macro FENCE_SWAPGS_KERNEL_ENTRY + ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL +.endm + .macro STACKLEAK_ERASE_NOCLOBBER #ifdef CONFIG_GCC_PLUGIN_STACKLEAK PUSH_AND_CLEAR_REGS diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2bb986f305ac..4f86928246e7 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1443,8 +1443,12 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR, ENTRY(page_fault) ASM_CLAC - pushl $0; /* %gs's slot on the stack */ + pushl $do_page_fault + jmp common_exception_read_cr2 +END(page_fault) +common_exception_read_cr2: + /* the function address is in %gs's slot on the stack */ SAVE_ALL switch_stacks=1 skip_gs=1 ENCODE_FRAME_POINTER @@ -1452,6 +1456,7 @@ ENTRY(page_fault) /* fixup %gs */ GS_TO_REG %ecx + movl PT_GS(%esp), %edi REG_TO_PTGS %ecx SET_KERNEL_GS %ecx @@ -1463,9 +1468,9 @@ ENTRY(page_fault) TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call do_page_fault + CALL_NOSPEC %edi jmp ret_from_exception -END(page_fault) +END(common_exception_read_cr2) common_exception: /* the function address is in %gs's slot on the stack */ @@ -1595,7 +1600,7 @@ END(general_protection) ENTRY(async_page_fault) ASM_CLAC pushl $do_async_page_fault - jmp common_exception + jmp common_exception_read_cr2 END(async_page_fault) #endif diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 3f5a978a02a7..be9ca198c581 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -519,7 +519,7 @@ ENTRY(interrupt_entry) testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - + FENCE_SWAPGS_USER_ENTRY /* * Switch to the thread stack. The IRET frame and orig_ax are * on the stack, as well as the return address. RDI..R12 are @@ -549,8 +549,10 @@ ENTRY(interrupt_entry) UNWIND_HINT_FUNC movq (%rdi), %rdi + jmp 2f 1: - + FENCE_SWAPGS_KERNEL_ENTRY +2: PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -1238,6 +1240,13 @@ ENTRY(paranoid_entry) */ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + /* + * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an + * unconditional CR3 write, even in the PTI case. So do an lfence + * to prevent GS speculation, regardless of whether PTI is enabled. + */ + FENCE_SWAPGS_KERNEL_ENTRY + ret END(paranoid_entry) @@ -1288,6 +1297,7 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax @@ -1301,6 +1311,8 @@ ENTRY(error_entry) pushq %r12 ret +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY .Lerror_entry_done: ret @@ -1318,7 +1330,7 @@ ENTRY(error_entry) cmpq %rax, RIP+8(%rsp) je .Lbstep_iret cmpq $.Lgs_change, RIP+8(%rsp) - jne .Lerror_entry_done + jne .Lerror_entry_done_lfence /* * hack: .Lgs_change can fail with user gsbase. If this happens, fix up @@ -1326,6 +1338,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done @@ -1340,6 +1353,7 @@ ENTRY(error_entry) * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* @@ -1431,6 +1445,7 @@ ENTRY(nmi) swapgs cld + FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9e911a96972b..648260b5f367 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -20,7 +20,6 @@ #include <asm/intel-family.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> -#include <asm/hypervisor.h> #include "../perf_event.h" @@ -263,8 +262,8 @@ static struct event_constraint intel_icl_event_constraints[] = { }; static struct extra_reg intel_icl_extra_regs[] __read_mostly = { - INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffbfffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffffbfffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), EVENT_EXTRA_END @@ -4053,7 +4052,7 @@ static bool check_msr(unsigned long msr, u64 mask) * Disable the check for real HW, so we don't * mess with potentionaly enabled registers: */ - if (hypervisor_is_type(X86_HYPER_NATIVE)) + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return true; /* @@ -4955,6 +4954,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; + /* fall through */ case INTEL_FAM6_SKYLAKE_MOBILE: case INTEL_FAM6_SKYLAKE_DESKTOP: case INTEL_FAM6_KABYLAKE_MOBILE: @@ -5004,6 +5004,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_XEON_D: pmem = true; + /* fall through */ case INTEL_FAM6_ICELAKE_MOBILE: case INTEL_FAM6_ICELAKE_DESKTOP: x86_pmu.late_ack = true; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2c8db2c19328..f1269e804e9b 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -851,7 +851,7 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 998c2cc08363..e880f2408e29 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -281,6 +281,8 @@ #define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ #define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -394,5 +396,6 @@ #define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8282b8d41209..7b0a4ee77313 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -607,15 +607,16 @@ struct kvm_vcpu_arch { /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user, maintained in the - * task_struct struct, and guest FPU contexts. While running a VCPU, - * the VCPU thread will have the guest FPU context. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ + struct fpu *user_fpu; struct fpu *guest_fpu; u64 xcr0; diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index ae91429129a6..ba71a63cdac4 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -96,6 +96,8 @@ long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #else +#define VDSO_HAS_32BIT_FALLBACK 1 + static __always_inline long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -114,6 +116,23 @@ long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) } static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + long ret; + + asm ( + "mov %%ebx, %%edx \n" + "mov %[clock], %%ebx \n" + "call __kernel_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret), "=m" (*_ts) + : "0" (__NR_clock_gettime), [clock] "g" (_clkid), "c" (_ts) + : "edx"); + + return ret; +} + +static __always_inline long gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz) { @@ -148,6 +167,23 @@ clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +static __always_inline +long clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + long ret; + + asm ( + "mov %%ebx, %%edx \n" + "mov %[clock], %%ebx \n" + "call __kernel_vsyscall \n" + "mov %%edx, %%ebx \n" + : "=a" (ret), "=m" (*_ts) + : "0" (__NR_clock_getres), [clock] "g" (_clkid), "c" (_ts) + : "edx"); + + return ret; +} + #endif #ifdef CONFIG_PARAVIRT_CLOCK diff --git a/arch/x86/include/uapi/asm/byteorder.h b/arch/x86/include/uapi/asm/byteorder.h index 484e3cfd7ef2..149143cab9ff 100644 --- a/arch/x86/include/uapi/asm/byteorder.h +++ b/arch/x86/include/uapi/asm/byteorder.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_BYTEORDER_H #define _ASM_X86_BYTEORDER_H diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h index 6ebaae90e207..8b2effe6efb8 100644 --- a/arch/x86/include/uapi/asm/hwcap2.h +++ b/arch/x86/include/uapi/asm/hwcap2.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_HWCAP2_H #define _ASM_X86_HWCAP2_H diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h index 6b18e88de8a6..7114801d0499 100644 --- a/arch/x86/include/uapi/asm/sigcontext32.h +++ b/arch/x86/include/uapi/asm/sigcontext32.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H diff --git a/arch/x86/include/uapi/asm/types.h b/arch/x86/include/uapi/asm/types.h index df55e1ddb0c9..9d5c11a24279 100644 --- a/arch/x86/include/uapi/asm/types.h +++ b/arch/x86/include/uapi/asm/types.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_TYPES_H #define _ASM_X86_TYPES_H diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 66ca906aa790..c6fa3ef10b4e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -34,6 +34,7 @@ #include "cpu.h" +static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); @@ -98,17 +99,11 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_STIBP)) x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper spectre mitigation before patching alternatives */ + /* Select the proper CPU mitigations before patching alternatives: */ + spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); - - /* - * Select proper mitigation for any exposure to the Speculative Store - * Bypass vulnerability. - */ ssb_select_mitigation(); - l1tf_select_mitigation(); - mds_select_mitigation(); arch_smt_update(); @@ -274,6 +269,98 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Spectre V1 : " fmt + +enum spectre_v1_mitigation { + SPECTRE_V1_MITIGATION_NONE, + SPECTRE_V1_MITIGATION_AUTO, +}; + +static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = + SPECTRE_V1_MITIGATION_AUTO; + +static const char * const spectre_v1_strings[] = { + [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", + [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", +}; + +/* + * Does SMAP provide full mitigation against speculative kernel access to + * userspace? + */ +static bool smap_works_speculatively(void) +{ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return false; + + /* + * On CPUs which are vulnerable to Meltdown, SMAP does not + * prevent speculative access to user data in the L1 cache. + * Consider SMAP to be non-functional as a mitigation on these + * CPUs. + */ + if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) + return false; + + return true; +} + +static void __init spectre_v1_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return; + } + + if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { + /* + * With Spectre v1, a user can speculatively control either + * path of a conditional swapgs with a user-controlled GS + * value. The mitigation is to add lfences to both code paths. + * + * If FSGSBASE is enabled, the user can put a kernel address in + * GS, in which case SMAP provides no protection. + * + * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the + * FSGSBASE enablement patches have been merged. ] + * + * If FSGSBASE is disabled, the user can only put a user space + * address in GS. That makes an attack harder, but still + * possible if there's no SMAP protection. + */ + if (!smap_works_speculatively()) { + /* + * Mitigation can be provided from SWAPGS itself or + * PTI as the CR3 write in the Meltdown mitigation + * is serializing. + * + * If neither is there, mitigate with an LFENCE to + * stop speculation through swapgs. + */ + if (boot_cpu_has_bug(X86_BUG_SWAPGS) && + !boot_cpu_has(X86_FEATURE_PTI)) + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); + + /* + * Enable lfences in the kernel entry (non-swapgs) + * paths, to prevent user entry from speculatively + * skipping swapgs. + */ + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); + } + } + + pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); +} + +static int __init nospectre_v1_cmdline(char *str) +{ + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return 0; +} +early_param("nospectre_v1", nospectre_v1_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = @@ -1226,7 +1313,7 @@ static ssize_t l1tf_show_state(char *buf) static ssize_t mds_show_state(char *buf) { - if (!hypervisor_is_type(X86_HYPER_NATIVE)) { + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sprintf(buf, "%s; SMT Host state unknown\n", mds_strings[mds_mitigation]); } @@ -1290,7 +1377,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 11472178e17f..f125bf7ecb6f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1022,6 +1022,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_L1TF BIT(3) #define NO_MDS BIT(4) #define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1048,30 +1049,38 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), {} }; @@ -1108,6 +1117,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } + if (!cpu_matches(NO_SWAPGS)) + setup_force_cpu_bug(X86_BUG_SWAPGS); + if (cpu_matches(NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index a6342c899be5..f3d3e9646a99 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -193,10 +193,10 @@ ENTRY(secondary_startup_64) /* Set up %gs. * - * The base of %gs always points to the bottom of the irqstack - * union. If the stack protector canary is enabled, it is - * located at %gs:40. Note that, on SMP, the boot cpu uses - * init data section till per cpu areas are set up. + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx movl initial_gs(%rip),%eax diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c43e96a938d0..c6f791bc481e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -827,10 +827,6 @@ int __init hpet_enable(void) if (!hpet_cfg_working()) goto out_nohpet; - /* Validate that the counter is counting */ - if (!hpet_counting()) - goto out_nohpet; - /* * Read the period and check for a sane value: */ @@ -896,6 +892,14 @@ int __init hpet_enable(void) } hpet_print_config(); + /* + * Validate that the counter is counting. This needs to be done + * after sanitizing the config registers to properly deal with + * force enabled HPETs. + */ + if (!hpet_counting()) + goto out_nohpet; + clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq); if (id & HPET_ID_LEGSUP) { diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 4f36d3241faf..2d6898c2cb64 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -100,7 +100,7 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; - if (!access_ok(fp, sizeof(*frame))) + if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE)) return 0; ret = 1; diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 8eb67a670b10..653b7f617b61 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -230,9 +230,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { {}, }; +/* + * Some devices have a portrait LCD but advertise a landscape resolution (and + * pitch). We simply swap width and height for these devices so that we can + * correctly deal with some of them coming with multiple resolutions. + */ +static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { + { + /* + * Lenovo MIIX310-10ICR, only some batches have the troublesome + * 800x1280 portrait screen. Luckily the portrait version has + * its own BIOS version, so we match on that. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), + }, + }, + { + /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo MIIX 320-10ICR"), + }, + }, + { + /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo ideapad D330-10IGM"), + }, + }, + {}, +}; + __init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) dmi_check_system(efifb_dmi_system_table); + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + dmi_check_system(efifb_dmi_swap_width_height)) { + u16 temp = screen_info.lfb_width; + + screen_info.lfb_width = screen_info.lfb_height; + screen_info.lfb_height = temp; + screen_info.lfb_linelength = 4 * screen_info.lfb_width; + } } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8f72526e2f68..24843cf49579 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, /* * Currently, fast page fault only works for direct mapping * since the gfn is not stable for indirect shadow page. See - * Documentation/virtual/kvm/locking.txt to get more detail. + * Documentation/virt/kvm/locking.txt to get more detail. */ fault_handled = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 19f69df96758..7eafc6907861 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2143,12 +2143,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!svm->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_svm; + } + svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!svm->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_svm; + goto free_user_fpu; } err = kvm_vcpu_init(&svm->vcpu, kvm, id); @@ -2211,6 +2219,8 @@ uninit: kvm_vcpu_uninit(&svm->vcpu); free_svm: kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); free_partial_svm: kmem_cache_free(kvm_vcpu_cache, svm); out: @@ -2241,6 +2251,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, svm); } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0f1378789bd0..ced9fba32598 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu); + vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); @@ -232,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu) vmx->vmcs01.shadow_vmcs = NULL; } kfree(vmx->nested.cached_vmcs12); + vmx->nested.cached_vmcs12 = NULL; kfree(vmx->nested.cached_shadow_vmcs12); + vmx->nested.cached_shadow_vmcs12 = NULL; /* Unpin physical memory we referred to in the vmcs02 */ if (vmx->nested.apic_access_page) { kvm_release_page_dirty(vmx->nested.apic_access_page); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a279447eb75b..074385c86c09 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6598,6 +6598,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); kmem_cache_free(kvm_vcpu_cache, vmx); } @@ -6613,12 +6614,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); + vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache, + GFP_KERNEL_ACCOUNT); + if (!vmx->vcpu.arch.user_fpu) { + printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n"); + err = -ENOMEM; + goto free_partial_vcpu; + } + vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache, GFP_KERNEL_ACCOUNT); if (!vmx->vcpu.arch.guest_fpu) { printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n"); err = -ENOMEM; - goto free_partial_vcpu; + goto free_user_fpu; } vmx->vpid = allocate_vpid(); @@ -6721,6 +6730,8 @@ uninit_vcpu: free_vcpu: free_vpid(vmx->vpid); kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu); +free_user_fpu: + kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu); free_partial_vcpu: kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 58305cf81182..c6d951cbd76c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops->vcpu_load(vcpu, cpu); + fpregs_assert_state_consistent(); + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + switch_fpu_return(); + /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -7202,7 +7206,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id) rcu_read_unlock(); - if (target) + if (target && READ_ONCE(target->ready)) kvm_vcpu_yield_to(target); } @@ -7242,6 +7246,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) break; case KVM_HC_KICK_CPU: kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + kvm_sched_yield(vcpu->kvm, a1); ret = 0; break; #ifdef CONFIG_X86_64 @@ -7990,9 +7995,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) trace_kvm_entry(vcpu->vcpu_id); guest_enter_irqoff(); - fpregs_assert_state_consistent(); - if (test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_return(); + /* The preempt notifier should have taken care of the FPU already. */ + WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD)); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -8270,7 +8274,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { fpregs_lock(); - copy_fpregs_to_fpstate(¤t->thread.fpu); + copy_fpregs_to_fpstate(vcpu->arch.user_fpu); /* PKRU is separately restored in kvm_x86_ops->run. */ __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state, ~XFEATURE_MASK_PKRU); @@ -8287,7 +8291,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpregs_lock(); copy_fpregs_to_fpstate(vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(¤t->thread.fpu.state); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state); fpregs_mark_activate(); fpregs_unlock(); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 6c46095cd0d9..9ceacd1156db 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -177,13 +177,14 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); - if (!pmd_present(*pmd_k)) - return NULL; - if (!pmd_present(*pmd)) + if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); + + if (!pmd_present(*pmd_k)) + return NULL; else - BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k)); + BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } @@ -203,17 +204,13 @@ void vmalloc_sync_all(void) spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; - pmd_t *ret; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - ret = vmalloc_sync_one(page_address(page), address); + vmalloc_sync_one(page_address(page), address); spin_unlock(pgt_lock); - - if (!ret) - break; } spin_unlock(&pgd_lock); } diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 60c220020054..80828b95a51f 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -14,6 +14,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/asmmacro.h> #include <asm/processor.h> #include <asm/coprocessor.h> #include <asm/thread_info.h> diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 72860325245a..586fcfe227ea 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -3354,38 +3354,57 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq) * there is no active group, then the primary expectation for * this device is probably a high throughput. * - * We are now left only with explaining the additional - * compound condition that is checked below for deciding - * whether the scenario is asymmetric. To explain this - * compound condition, we need to add that the function + * We are now left only with explaining the two sub-conditions in the + * additional compound condition that is checked below for deciding + * whether the scenario is asymmetric. To explain the first + * sub-condition, we need to add that the function * bfq_asymmetric_scenario checks the weights of only - * non-weight-raised queues, for efficiency reasons (see - * comments on bfq_weights_tree_add()). Then the fact that - * bfqq is weight-raised is checked explicitly here. More - * precisely, the compound condition below takes into account - * also the fact that, even if bfqq is being weight-raised, - * the scenario is still symmetric if all queues with requests - * waiting for completion happen to be - * weight-raised. Actually, we should be even more precise - * here, and differentiate between interactive weight raising - * and soft real-time weight raising. + * non-weight-raised queues, for efficiency reasons (see comments on + * bfq_weights_tree_add()). Then the fact that bfqq is weight-raised + * is checked explicitly here. More precisely, the compound condition + * below takes into account also the fact that, even if bfqq is being + * weight-raised, the scenario is still symmetric if all queues with + * requests waiting for completion happen to be + * weight-raised. Actually, we should be even more precise here, and + * differentiate between interactive weight raising and soft real-time + * weight raising. + * + * The second sub-condition checked in the compound condition is + * whether there is a fair amount of already in-flight I/O not + * belonging to bfqq. If so, I/O dispatching is to be plugged, for the + * following reason. The drive may decide to serve in-flight + * non-bfqq's I/O requests before bfqq's ones, thereby delaying the + * arrival of new I/O requests for bfqq (recall that bfqq is sync). If + * I/O-dispatching is not plugged, then, while bfqq remains empty, a + * basically uncontrolled amount of I/O from other queues may be + * dispatched too, possibly causing the service of bfqq's I/O to be + * delayed even longer in the drive. This problem gets more and more + * serious as the speed and the queue depth of the drive grow, + * because, as these two quantities grow, the probability to find no + * queue busy but many requests in flight grows too. By contrast, + * plugging I/O dispatching minimizes the delay induced by already + * in-flight I/O, and enables bfqq to recover the bandwidth it may + * lose because of this delay. * * As a side note, it is worth considering that the above - * device-idling countermeasures may however fail in the - * following unlucky scenario: if idling is (correctly) - * disabled in a time period during which all symmetry - * sub-conditions hold, and hence the device is allowed to - * enqueue many requests, but at some later point in time some - * sub-condition stops to hold, then it may become impossible - * to let requests be served in the desired order until all - * the requests already queued in the device have been served. + * device-idling countermeasures may however fail in the following + * unlucky scenario: if I/O-dispatch plugging is (correctly) disabled + * in a time period during which all symmetry sub-conditions hold, and + * therefore the device is allowed to enqueue many requests, but at + * some later point in time some sub-condition stops to hold, then it + * may become impossible to make requests be served in the desired + * order until all the requests already queued in the device have been + * served. The last sub-condition commented above somewhat mitigates + * this problem for weight-raised queues. */ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, struct bfq_queue *bfqq) { return (bfqq->wr_coeff > 1 && - bfqd->wr_busy_queues < - bfq_tot_busy_queues(bfqd)) || + (bfqd->wr_busy_queues < + bfq_tot_busy_queues(bfqd) || + bfqd->rq_in_driver >= + bfqq->dispatched + 4)) || bfq_asymmetric_scenario(bfqd, bfqq); } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 24ed26957367..55a7dc227dfb 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -54,7 +54,7 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ -static bool blkcg_debug_stats = false; +bool blkcg_debug_stats = false; static struct workqueue_struct *blkcg_punt_bio_wq; static bool blkcg_policy_enabled(struct request_queue *q, @@ -944,10 +944,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) dbytes, dios); } - if (!blkcg_debug_stats) - goto next; - - if (atomic_read(&blkg->use_delay)) { + if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { has_stats = true; off += scnprintf(buf+off, size-off, " use_delay=%d delay_nsec=%llu", @@ -967,7 +964,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) has_stats = true; off += written; } -next: + if (has_stats) { if (off < size - 1) { off += scnprintf(buf+off, size-off, "\n"); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index d973c38ee4fd..0fff7b56df0e 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -917,6 +917,9 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf, unsigned long long avg_lat; unsigned long long cur_win; + if (!blkcg_debug_stats) + return 0; + if (iolat->ssd) return iolatency_ssd_stat(iolat, buf, size); diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index cf22ab00fefb..126021fc3a11 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -61,15 +61,6 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) e->type->ops.completed_request(rq, now); } -static inline void blk_mq_sched_started_request(struct request *rq) -{ - struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.started_request) - e->type->ops.started_request(rq); -} - static inline void blk_mq_sched_requeue_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/block/blk-mq.c b/block/blk-mq.c index b038ec680e84..f78d3287dd82 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -669,8 +669,6 @@ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; - blk_mq_sched_started_request(rq); - trace_block_rq_issue(q, rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { @@ -1960,9 +1958,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); - if (bio->bi_opf & REQ_NOWAIT) + + cookie = BLK_QC_T_NONE; + if (bio->bi_opf & REQ_NOWAIT_INLINE) + cookie = BLK_QC_T_EAGAIN; + else if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); - return BLK_QC_T_NONE; + return cookie; } trace_block_getrq(q, bio, bio->bi_opf); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 659ccb8b693f..3954c0dc1443 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -202,6 +202,7 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, return -1; data->got_token = true; + smp_wmb(); list_del_init(&curr->entry); wake_up_process(data->task); return 1; @@ -244,7 +245,9 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, return; prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); + has_sleeper = !wq_has_single_sleeper(&rqw->wait); do { + /* The memory barrier in set_task_state saves us here. */ if (data.got_token) break; if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { @@ -255,12 +258,14 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ + smp_rmb(); if (data.got_token) cleanup_cb(rqw, private_data); break; } io_schedule(); - has_sleeper = false; + has_sleeper = true; + set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 2ae348c101a0..2c1831207a8f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -752,7 +752,8 @@ void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask) * page (which might not be idential to the Linux PAGE_SIZE). Because * of that they are not limited by our notion of "segment size". */ - q->limits.max_segment_size = UINT_MAX; + if (mask) + q->limits.max_segment_size = UINT_MAX; } EXPORT_SYMBOL(blk_queue_virt_boundary); diff --git a/block/genhd.c b/block/genhd.c index 97887e59f3b2..54f1f0d381f4 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1969,7 +1969,7 @@ static const struct attribute *disk_events_attrs[] = { * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to - * /sys/module/block/events_dfl_poll_msecs. + * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index d4551e33fa71..8569b79e8b58 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -611,8 +611,8 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id, /* Move to ITS specific data */ its = (struct acpi_iort_its_group *)node->node_data; - if (idx > its->its_count) { - dev_err(dev, "requested ITS ID index [%d] is greater than available [%d]\n", + if (idx >= its->its_count) { + dev_err(dev, "requested ITS ID index [%d] overruns ITS entries [%d]\n", idx, its->its_count); return -ENXIO; } diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 28cffaaf9d82..f616b16c1f0b 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -232,13 +232,15 @@ int acpi_device_set_power(struct acpi_device *device, int state) if (device->power.flags.power_resources) result = acpi_power_transition(device, target_state); } else { + int cur_state = device->power.state; + if (device->power.flags.power_resources) { result = acpi_power_transition(device, ACPI_STATE_D0); if (result) goto end; } - if (device->power.state == ACPI_STATE_D0) { + if (cur_state == ACPI_STATE_D0) { int psc; /* Nothing to do here if _PSC is not present. */ diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index c02fa27dd3f3..1413324982f0 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1282,7 +1282,7 @@ static ssize_t hw_error_scrub_store(struct device *dev, if (rc) return rc; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); @@ -1299,7 +1299,7 @@ static ssize_t hw_error_scrub_store(struct device *dev, break; } } - device_unlock(dev); + nfit_device_unlock(dev); if (rc) return rc; return size; @@ -1319,7 +1319,7 @@ static ssize_t scrub_show(struct device *dev, ssize_t rc = -ENXIO; bool busy; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (!nd_desc) { device_unlock(dev); @@ -1339,7 +1339,7 @@ static ssize_t scrub_show(struct device *dev, } mutex_unlock(&acpi_desc->init_mutex); - device_unlock(dev); + nfit_device_unlock(dev); return rc; } @@ -1356,14 +1356,14 @@ static ssize_t scrub_store(struct device *dev, if (val != 1) return -EINVAL; - device_lock(dev); + nfit_device_lock(dev); nd_desc = dev_get_drvdata(dev); if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); rc = acpi_nfit_ars_rescan(acpi_desc, ARS_REQ_LONG); } - device_unlock(dev); + nfit_device_unlock(dev); if (rc) return rc; return size; @@ -1749,9 +1749,9 @@ static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data) struct acpi_device *adev = data; struct device *dev = &adev->dev; - device_lock(dev->parent); + nfit_device_lock(dev->parent); __acpi_nvdimm_notify(dev, event); - device_unlock(dev->parent); + nfit_device_unlock(dev->parent); } static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method) @@ -3457,8 +3457,8 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) struct device *dev = acpi_desc->dev; /* Bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ - device_lock(dev); - device_unlock(dev); + nfit_device_lock(dev); + nfit_device_unlock(dev); /* Bounce the init_mutex to complete initial registration */ mutex_lock(&acpi_desc->init_mutex); @@ -3602,8 +3602,8 @@ void acpi_nfit_shutdown(void *data) * acpi_nfit_ars_rescan() submissions have had a chance to * either submit or see ->cancel set. */ - device_lock(bus_dev); - device_unlock(bus_dev); + nfit_device_lock(bus_dev); + nfit_device_unlock(bus_dev); flush_workqueue(nfit_wq); } @@ -3746,9 +3746,9 @@ EXPORT_SYMBOL_GPL(__acpi_nfit_notify); static void acpi_nfit_notify(struct acpi_device *adev, u32 event) { - device_lock(&adev->dev); + nfit_device_lock(&adev->dev); __acpi_nfit_notify(&adev->dev, adev->handle, event); - device_unlock(&adev->dev); + nfit_device_unlock(&adev->dev); } static const struct acpi_device_id acpi_nfit_ids[] = { diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 6ee2b02af73e..24241941181c 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -312,6 +312,30 @@ static inline struct acpi_nfit_desc *to_acpi_desc( return container_of(nd_desc, struct acpi_nfit_desc, nd_desc); } +#ifdef CONFIG_PROVE_LOCKING +static inline void nfit_device_lock(struct device *dev) +{ + device_lock(dev); + mutex_lock(&dev->lockdep_mutex); +} + +static inline void nfit_device_unlock(struct device *dev) +{ + mutex_unlock(&dev->lockdep_mutex); + device_unlock(dev); +} +#else +static inline void nfit_device_lock(struct device *dev) +{ + device_lock(dev); +} + +static inline void nfit_device_unlock(struct device *dev) +{ + device_unlock(dev); +} +#endif + const guid_t *to_nfit_uuid(enum nfit_uuids id); int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz); void acpi_nfit_shutdown(void *data); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 0e28270b0fd8..aad6be5c0af0 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2204,6 +2204,12 @@ int __init acpi_scan_init(void) acpi_gpe_apply_masked_gpes(); acpi_update_all_gpes(); + /* + * Although we call __add_memory() that is documented to require the + * device_hotplug_lock, it is not necessary here because this is an + * early code when userspace or any other code path cannot trigger + * hotplug/hotunplug operations. + */ mutex_lock(&acpi_scan_lock); /* * Enumerate devices in the ACPI namespace. diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 38a59a630cd4..dc1c83eafc22 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2988,7 +2988,7 @@ static void binder_transaction(struct binder_proc *proc, else return_error = BR_DEAD_REPLY; mutex_unlock(&context->context_mgr_node_lock); - if (target_node && target_proc == proc) { + if (target_node && target_proc->pid == proc->pid) { binder_user_error("%d:%d got transaction to context manager from process owning it\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; @@ -3239,7 +3239,8 @@ static void binder_transaction(struct binder_proc *proc, buffer_offset = off_start_offset; off_end_offset = off_start_offset + tr->offsets_size; sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); - sg_buf_end_offset = sg_buf_offset + extra_buffers_size; + sg_buf_end_offset = sg_buf_offset + extra_buffers_size - + ALIGN(secctx_sz, sizeof(u64)); off_min = 0; for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 72312ad2e142..9e9583a6bba9 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -338,6 +338,9 @@ static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port, hpriv->phys[port] = NULL; rc = 0; break; + case -EPROBE_DEFER: + /* Do not complain yet */ + break; default: dev_err(dev, @@ -408,7 +411,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, hpriv->mmio = devm_ioremap_resource(dev, platform_get_resource(pdev, IORESOURCE_MEM, 0)); if (IS_ERR(hpriv->mmio)) { - dev_err(dev, "no mmio space\n"); rc = PTR_ERR(hpriv->mmio); goto err_out; } diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index 173e6f2dd9af..eefda51f97d3 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -56,7 +56,7 @@ static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev) unsigned int ret; struct rm_feature_desc *desc; struct ata_taskfile tf; - static const char cdb[] = { GPCMD_GET_CONFIGURATION, + static const char cdb[ATAPI_CDB_LEN] = { GPCMD_GET_CONFIGURATION, 2, /* only 1 feature descriptor requested */ 0, 3, /* 3, removable medium feature */ 0, 0, 0,/* reserved */ diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 302cf0ba1600..8c7a996d1f16 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -63,6 +63,7 @@ #include <asm/byteorder.h> #include <linux/vmalloc.h> #include <linux/jiffies.h> +#include <linux/nospec.h> #include "iphase.h" #include "suni.h" #define swap_byte_order(x) (((x & 0xff) << 8) | ((x & 0xff00) >> 8)) @@ -2760,8 +2761,11 @@ static int ia_ioctl(struct atm_dev *dev, unsigned int cmd, void __user *arg) } if (copy_from_user(&ia_cmds, arg, sizeof ia_cmds)) return -EFAULT; board = ia_cmds.status; - if ((board < 0) || (board > iadev_count)) - board = 0; + + if ((board < 0) || (board > iadev_count)) + board = 0; + board = array_index_nospec(board, iadev_count + 1); + iadev = ia_dev[board]; switch (ia_cmds.cmd) { case MEMDUMP: diff --git a/drivers/base/core.c b/drivers/base/core.c index da84a73f2ba6..636058bbf48a 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1663,6 +1663,9 @@ void device_initialize(struct device *dev) kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); mutex_init(&dev->mutex); +#ifdef CONFIG_PROVE_LOCKING + mutex_init(&dev->lockdep_mutex); +#endif lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); @@ -2211,6 +2214,24 @@ void put_device(struct device *dev) } EXPORT_SYMBOL_GPL(put_device); +bool kill_device(struct device *dev) +{ + /* + * Require the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + lockdep_assert_held(&dev->mutex); + + if (dev->p->dead) + return false; + dev->p->dead = true; + return true; +} +EXPORT_SYMBOL_GPL(kill_device); + /** * device_del - delete device from system. * @dev: device. @@ -2230,15 +2251,8 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf; - /* - * Hold the device lock and set the "dead" flag to guarantee that - * the update behavior is consistent with the other bitfields near - * it and that we cannot have an asynchronous probe routine trying - * to run while we are tearing out the bus/class/sysfs from - * underneath the device. - */ device_lock(dev); - dev->p->dead = true; + kill_device(dev); device_unlock(dev); /* Notify clients of device removal. This call must come diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h index 7048a41973ed..7ecd590e67fe 100644 --- a/drivers/base/firmware_loader/firmware.h +++ b/drivers/base/firmware_loader/firmware.h @@ -141,8 +141,8 @@ int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed); int fw_map_paged_buf(struct fw_priv *fw_priv); #else static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {} -int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } -int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } +static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } +static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } #endif #endif /* __FIRMWARE_LOADER_H */ diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 85f20e371f2f..bd7d3bb8b890 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1726,6 +1726,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* MSch: invalidate default_params */ default_params[drive].blocks = 0; set_capacity(floppy->disk, MAX_DISK_SIZE * 2); + /* Fall through */ case FDFMTEND: case FDFLUSH: /* invalidate the buffer track to force a reread */ diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 90ebfcae0ce6..2b3103c30857 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -5417,7 +5417,7 @@ static int drbd_do_auth(struct drbd_connection *connection) unsigned int key_len; char secret[SHARED_SECRET_MAX]; /* 64 byte */ unsigned int resp_size; - SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm); + struct shash_desc *desc; struct packet_info pi; struct net_conf *nc; int err, rv; @@ -5430,6 +5430,13 @@ static int drbd_do_auth(struct drbd_connection *connection) memcpy(secret, nc->shared_secret, key_len); rcu_read_unlock(); + desc = kmalloc(sizeof(struct shash_desc) + + crypto_shash_descsize(connection->cram_hmac_tfm), + GFP_KERNEL); + if (!desc) { + rv = -1; + goto fail; + } desc->tfm = connection->cram_hmac_tfm; rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len); @@ -5571,7 +5578,10 @@ static int drbd_do_auth(struct drbd_connection *connection) kfree(peers_ch); kfree(response); kfree(right_response); - shash_desc_zero(desc); + if (desc) { + shash_desc_zero(desc); + kfree(desc); + } return rv; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 44c9985f352a..3036883fc9f8 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -924,6 +924,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct file *file; struct inode *inode; struct address_space *mapping; + struct block_device *claimed_bdev = NULL; int lo_flags = 0; int error; loff_t size; @@ -942,10 +943,11 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - bdgrab(bdev); - error = blkdev_get(bdev, mode | FMODE_EXCL, loop_set_fd); - if (error) + claimed_bdev = bd_start_claiming(bdev, loop_set_fd); + if (IS_ERR(claimed_bdev)) { + error = PTR_ERR(claimed_bdev); goto out_putf; + } } error = mutex_lock_killable(&loop_ctl_mutex); @@ -1015,15 +1017,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); - if (!(mode & FMODE_EXCL)) - blkdev_put(bdev, mode | FMODE_EXCL); + if (claimed_bdev) + bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: - if (!(mode & FMODE_EXCL)) - blkdev_put(bdev, mode | FMODE_EXCL); + if (claimed_bdev) + bd_abort_claiming(bdev, claimed_bdev, loop_set_fd); out_putf: fput(file); out: diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9bcde2325893..e21d2ded732b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1231,7 +1231,7 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, struct block_device *bdev) { sock_shutdown(nbd); - kill_bdev(bdev); + __invalidate_device(bdev, true); nbd_bdev_reset(bdev); if (test_and_clear_bit(NBD_HAS_CONFIG_REF, &nbd->config->runtime_flags)) diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c index a55be205b91a..dbfe34664633 100644 --- a/drivers/bluetooth/hci_ath.c +++ b/drivers/bluetooth/hci_ath.c @@ -98,6 +98,9 @@ static int ath_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + ath = kzalloc(sizeof(*ath), GFP_KERNEL); if (!ath) return -ENOMEM; diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 8905ad2edde7..ae2624fce913 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -406,6 +406,9 @@ static int bcm_open(struct hci_uart *hu) bt_dev_dbg(hu->hdev, "hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + bcm = kzalloc(sizeof(*bcm), GFP_KERNEL); if (!bcm) return -ENOMEM; diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index 207bae5e0d46..31f25153087d 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -391,6 +391,9 @@ static int intel_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + intel = kzalloc(sizeof(*intel), GFP_KERNEL); if (!intel) return -ENOMEM; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 8950e07889fe..85a30fb9177b 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -292,6 +292,19 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +/* Check the underlying device or tty has flow control support */ +bool hci_uart_has_flow_control(struct hci_uart *hu) +{ + /* serdev nodes check if the needed operations are present */ + if (hu->serdev) + return true; + + if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset) + return true; + + return false; +} + /* Flow control or un-flow control the device */ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) { diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c index f98e5cc343b2..fbc3f7c3a5c7 100644 --- a/drivers/bluetooth/hci_mrvl.c +++ b/drivers/bluetooth/hci_mrvl.c @@ -59,6 +59,9 @@ static int mrvl_open(struct hci_uart *hu) BT_DBG("hu %p", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + mrvl = kzalloc(sizeof(*mrvl), GFP_KERNEL); if (!mrvl) return -ENOMEM; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 9a5c9c1f9484..82a0a3691a63 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -473,6 +473,9 @@ static int qca_open(struct hci_uart *hu) BT_DBG("hu %p qca_open", hu); + if (!hci_uart_has_flow_control(hu)) + return -EOPNOTSUPP; + qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL); if (!qca) return -ENOMEM; diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index f11af3912ce6..6ab631101019 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -104,6 +104,7 @@ int hci_uart_wait_until_sent(struct hci_uart *hu); int hci_uart_init_ready(struct hci_uart *hu); void hci_uart_init_work(struct work_struct *work); void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed); +bool hci_uart_has_flow_control(struct hci_uart *hu); void hci_uart_set_flow_control(struct hci_uart *hu, bool enable); void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed, unsigned int oper_speed); diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 5c39f20378b8..9ac6671bb514 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -567,8 +567,7 @@ static inline unsigned long hpet_time_div(struct hpets *hpets, unsigned long long m; m = hpets->hp_tick_freq + (dis >> 1); - do_div(m, dis); - return (unsigned long)m; + return div64_ul(m, dis); } static int diff --git a/drivers/char/ipmi/ipmb_dev_int.c b/drivers/char/ipmi/ipmb_dev_int.c index 57204335c5f5..285e0b8f9a97 100644 --- a/drivers/char/ipmi/ipmb_dev_int.c +++ b/drivers/char/ipmi/ipmb_dev_int.c @@ -76,7 +76,7 @@ static ssize_t ipmb_read(struct file *file, char __user *buf, size_t count, struct ipmb_dev *ipmb_dev = to_ipmb_dev(file); struct ipmb_request_elem *queue_elem; struct ipmb_msg msg; - ssize_t ret; + ssize_t ret = 0; memset(&msg, 0, sizeof(msg)); diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index d47ad10a35fe..4838c6a9f0f2 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -77,6 +77,18 @@ static int tpm_go_idle(struct tpm_chip *chip) return chip->ops->go_idle(chip); } +static void tpm_clk_enable(struct tpm_chip *chip) +{ + if (chip->ops->clk_enable) + chip->ops->clk_enable(chip, true); +} + +static void tpm_clk_disable(struct tpm_chip *chip) +{ + if (chip->ops->clk_enable) + chip->ops->clk_enable(chip, false); +} + /** * tpm_chip_start() - power on the TPM * @chip: a TPM chip to use @@ -89,13 +101,12 @@ int tpm_chip_start(struct tpm_chip *chip) { int ret; - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, true); + tpm_clk_enable(chip); if (chip->locality == -1) { ret = tpm_request_locality(chip); if (ret) { - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); return ret; } } @@ -103,8 +114,7 @@ int tpm_chip_start(struct tpm_chip *chip) ret = tpm_cmd_ready(chip); if (ret) { tpm_relinquish_locality(chip); - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); return ret; } @@ -124,8 +134,7 @@ void tpm_chip_stop(struct tpm_chip *chip) { tpm_go_idle(chip); tpm_relinquish_locality(chip); - if (chip->ops->clk_enable) - chip->ops->clk_enable(chip, false); + tpm_clk_disable(chip); } EXPORT_SYMBOL_GPL(tpm_chip_stop); @@ -545,6 +554,20 @@ static int tpm_add_hwrng(struct tpm_chip *chip) return hwrng_register(&chip->hwrng); } +static int tpm_get_pcr_allocation(struct tpm_chip *chip) +{ + int rc; + + rc = (chip->flags & TPM_CHIP_FLAG_TPM2) ? + tpm2_get_pcr_allocation(chip) : + tpm1_get_pcr_allocation(chip); + + if (rc > 0) + return -ENODEV; + + return rc; +} + /* * tpm_chip_register() - create a character device for the TPM chip * @chip: TPM chip to use. @@ -564,6 +587,12 @@ int tpm_chip_register(struct tpm_chip *chip) if (rc) return rc; rc = tpm_auto_startup(chip); + if (rc) { + tpm_chip_stop(chip); + return rc; + } + + rc = tpm_get_pcr_allocation(chip); tpm_chip_stop(chip); if (rc) return rc; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index e503ffc3aa39..a7fea3e0ca86 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -394,6 +394,7 @@ int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, const char *desc, size_t min_cap_length); int tpm1_get_random(struct tpm_chip *chip, u8 *out, size_t max); +int tpm1_get_pcr_allocation(struct tpm_chip *chip); unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm_pm_suspend(struct device *dev); int tpm_pm_resume(struct device *dev); @@ -449,6 +450,7 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); +ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip); int tpm2_auto_startup(struct tpm_chip *chip); void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type); unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index faacbe1ffa1a..149e953ca369 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -699,18 +699,6 @@ int tpm1_auto_startup(struct tpm_chip *chip) goto out; } - chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks), - GFP_KERNEL); - if (!chip->allocated_banks) { - rc = -ENOMEM; - goto out; - } - - chip->allocated_banks[0].alg_id = TPM_ALG_SHA1; - chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1]; - chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1; - chip->nr_allocated_banks = 1; - return rc; out: if (rc > 0) @@ -779,3 +767,27 @@ int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) return rc; } +/** + * tpm1_get_pcr_allocation() - initialize the allocated bank + * @chip: TPM chip to use. + * + * The function initializes the SHA1 allocated bank to extend PCR + * + * Return: + * * 0 on success, + * * < 0 on error. + */ +int tpm1_get_pcr_allocation(struct tpm_chip *chip) +{ + chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks), + GFP_KERNEL); + if (!chip->allocated_banks) + return -ENOMEM; + + chip->allocated_banks[0].alg_id = TPM_ALG_SHA1; + chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1]; + chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1; + chip->nr_allocated_banks = 1; + + return 0; +} diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index d103545e4055..ba9acae83bff 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -840,7 +840,7 @@ struct tpm2_pcr_selection { u8 pcr_select[3]; } __packed; -static ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) +ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip) { struct tpm2_pcr_selection pcr_selection; struct tpm_buf buf; @@ -1040,10 +1040,6 @@ int tpm2_auto_startup(struct tpm_chip *chip) goto out; } - rc = tpm2_get_pcr_allocation(chip); - if (rc) - goto out; - rc = tpm2_get_cc_attrs_tbl(chip); out: diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index 44db83a6d01c..44a46dcc0518 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -141,6 +141,8 @@ static int clk_generated_determine_rate(struct clk_hw *hw, continue; div = DIV_ROUND_CLOSEST(parent_rate, req->rate); + if (div > GENERATED_MAX_DIV + 1) + div = GENERATED_MAX_DIV + 1; clk_generated_best_diff(req, parent, parent_rate, div, &best_diff, &best_rate); diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 1aa5f4059251..73b7e238eee7 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -25,9 +25,11 @@ static const struct mtk_fixed_clk top_fixed_clks[] = { FIXED_CLK(CLK_TOP_UNIVP_192M, "univpll_192m", "univpll", 192000000), }; +static const struct mtk_fixed_factor top_early_divs[] = { + FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, 2), +}; + static const struct mtk_fixed_factor top_divs[] = { - FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, - 2), FACTOR(CLK_TOP_F26M_CK_D2, "csw_f26m_ck_d2", "clk26m", 1, 2), FACTOR(CLK_TOP_SYSPLL_CK, "syspll_ck", "mainpll", 1, @@ -1148,37 +1150,57 @@ static int clk_mt8183_apmixed_probe(struct platform_device *pdev) return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data); } +static struct clk_onecell_data *top_clk_data; + +static void clk_mt8183_top_init_early(struct device_node *node) +{ + int i; + + top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + + for (i = 0; i < CLK_TOP_NR_CLK; i++) + top_clk_data->clks[i] = ERR_PTR(-EPROBE_DEFER); + + mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), + top_clk_data); + + of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data); +} + +CLK_OF_DECLARE_DRIVER(mt8183_topckgen, "mediatek,mt8183-topckgen", + clk_mt8183_top_init_early); + static int clk_mt8183_top_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); void __iomem *base; - struct clk_onecell_data *clk_data; struct device_node *node = pdev->dev.of_node; base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(base)) return PTR_ERR(base); - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), - clk_data); + top_clk_data); + + mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), + top_clk_data); - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); + mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes), - node, &mt8183_clk_lock, clk_data); + node, &mt8183_clk_lock, top_clk_data); mtk_clk_register_composites(top_aud_muxes, ARRAY_SIZE(top_aud_muxes), - base, &mt8183_clk_lock, clk_data); + base, &mt8183_clk_lock, top_clk_data); mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs), - base, &mt8183_clk_lock, clk_data); + base, &mt8183_clk_lock, top_clk_data); mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks), - clk_data); + top_clk_data); - return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data); + return of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data); } static int clk_mt8183_infra_probe(struct platform_device *pdev) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index 52bbb9ce3807..d4075b130674 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -572,17 +572,11 @@ static int cpg_mssr_reset(struct reset_controller_dev *rcdev, unsigned int reg = id / 32; unsigned int bit = id % 32; u32 bitmask = BIT(bit); - unsigned long flags; - u32 value; dev_dbg(priv->dev, "reset %u%02u\n", reg, bit); /* Reset module */ - spin_lock_irqsave(&priv->rmw_lock, flags); - value = readl(priv->base + SRCR(reg)); - value |= bitmask; - writel(value, priv->base + SRCR(reg)); - spin_unlock_irqrestore(&priv->rmw_lock, flags); + writel(bitmask, priv->base + SRCR(reg)); /* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */ udelay(35); @@ -599,16 +593,10 @@ static int cpg_mssr_assert(struct reset_controller_dev *rcdev, unsigned long id) unsigned int reg = id / 32; unsigned int bit = id % 32; u32 bitmask = BIT(bit); - unsigned long flags; - u32 value; dev_dbg(priv->dev, "assert %u%02u\n", reg, bit); - spin_lock_irqsave(&priv->rmw_lock, flags); - value = readl(priv->base + SRCR(reg)); - value |= bitmask; - writel(value, priv->base + SRCR(reg)); - spin_unlock_irqrestore(&priv->rmw_lock, flags); + writel(bitmask, priv->base + SRCR(reg)); return 0; } diff --git a/drivers/clk/sprd/Kconfig b/drivers/clk/sprd/Kconfig index 91d3d721c801..3c219af25100 100644 --- a/drivers/clk/sprd/Kconfig +++ b/drivers/clk/sprd/Kconfig @@ -3,6 +3,7 @@ config SPRD_COMMON_CLK tristate "Clock support for Spreadtrum SoCs" depends on ARCH_SPRD || COMPILE_TEST default ARCH_SPRD + select REGMAP_MMIO if SPRD_COMMON_CLK diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index 93f39a1d4c3d..c66f566a854c 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -131,10 +131,18 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) int err = -ENODEV; cpu = of_get_cpu_node(policy->cpu, NULL); + if (!cpu) + goto out; + max_freqp = of_get_property(cpu, "clock-frequency", NULL); of_node_put(cpu); - if (!cpu) + if (!max_freqp) { + err = -EINVAL; goto out; + } + + /* we need the freq in kHz */ + max_freq = *max_freqp / 1000; dn = of_find_compatible_node(NULL, NULL, "1682m-sdc"); if (!dn) @@ -171,16 +179,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) } pr_debug("init cpufreq on CPU %d\n", policy->cpu); - - max_freqp = of_get_property(cpu, "clock-frequency", NULL); - if (!max_freqp) { - err = -EINVAL; - goto out_unmap_sdcpwr; - } - - /* we need the freq in kHz */ - max_freq = *max_freqp / 1000; - pr_debug("max clock-frequency is at %u kHz\n", max_freq); pr_debug("initializing frequency table\n"); @@ -199,9 +197,6 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency()); return 0; -out_unmap_sdcpwr: - iounmap(sdcpwr_mapbase); - out_unmap_sdcasr: iounmap(sdcasr_mapbase); out: diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 3dc1cbf849db..b785e936244f 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -957,7 +957,7 @@ static void set_broadcast_channel(struct fw_device *device, int generation) device->bc_implemented = BC_IMPLEMENTED; break; } - /* else fall through to case address error */ + /* else, fall through - to case address error */ case RCODE_ADDRESS_ERROR: device->bc_implemented = BC_UNIMPLEMENTED; } diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c index 42566b7be8f5..df8a56a979b9 100644 --- a/drivers/firewire/core-iso.c +++ b/drivers/firewire/core-iso.c @@ -284,7 +284,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation, if ((data[0] & bit) == (data[1] & bit)) continue; - /* 1394-1995 IRM, fall through to retry. */ + /* fall through - It's a 1394-1995 IRM, retry. */ default: if (retry) { retry--; diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 46bd22dde535..94a13fca8267 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -54,6 +54,7 @@ static u32 *count_ports(u32 *sid, int *total_port_count, int *child_port_count) switch (port_type) { case SELFID_PORT_CHILD: (*child_port_count)++; + /* fall through */ case SELFID_PORT_PARENT: case SELFID_PORT_NCONN: (*total_port_count)++; diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 53446e39a32c..ba8d3d0ef32c 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -157,7 +157,7 @@ config DMI_SCAN_MACHINE_NON_EFI_FALLBACK config ISCSI_IBFT_FIND bool "iSCSI Boot Firmware Table Attributes" - depends on X86 && ACPI + depends on X86 && ISCSI_IBFT default n help This option enables the kernel to find the region of memory @@ -168,7 +168,8 @@ config ISCSI_IBFT_FIND config ISCSI_IBFT tristate "iSCSI Boot Firmware Table Attributes module" select ISCSI_BOOT_SYSFS - depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL + select ISCSI_IBFT_FIND if X86 + depends on ACPI && SCSI && SCSI_LOWLEVEL default n help This option enables support for detection and exposing of iSCSI diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index ab3aa3983833..7e12cbdf957c 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -84,6 +84,10 @@ MODULE_DESCRIPTION("sysfs interface to BIOS iBFT information"); MODULE_LICENSE("GPL"); MODULE_VERSION(IBFT_ISCSI_VERSION); +#ifndef CONFIG_ISCSI_IBFT_FIND +struct acpi_table_ibft *ibft_addr; +#endif + struct ibft_hdr { u8 id; u8 version; diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 474f304ec109..cdd4f73b4869 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -40,6 +40,7 @@ config ALTERA_PR_IP_CORE_PLAT config FPGA_MGR_ALTERA_PS_SPI tristate "Altera FPGA Passive Serial over SPI" depends on SPI + select BITREVERSE help FPGA manager driver support for Altera Arria/Cyclone/Stratix using the passive serial interface over SPI. diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3ee99d070608..f497003f119c 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -956,9 +956,11 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) } if (eflags & GPIOEVENT_REQUEST_RISING_EDGE) - irqflags |= IRQF_TRIGGER_RISING; + irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? + IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING; if (eflags & GPIOEVENT_REQUEST_FALLING_EDGE) - irqflags |= IRQF_TRIGGER_FALLING; + irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? + IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING; irqflags |= IRQF_ONESHOT; INIT_KFIFO(le->events); @@ -1392,12 +1394,17 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, for (i = 0; i < chip->ngpio; i++) { struct gpio_desc *desc = &gdev->descs[i]; - if (chip->get_direction && gpiochip_line_is_valid(chip, i)) - desc->flags = !chip->get_direction(chip, i) ? - (1 << FLAG_IS_OUT) : 0; - else - desc->flags = !chip->direction_input ? - (1 << FLAG_IS_OUT) : 0; + if (chip->get_direction && gpiochip_line_is_valid(chip, i)) { + if (!chip->get_direction(chip, i)) + set_bit(FLAG_IS_OUT, &desc->flags); + else + clear_bit(FLAG_IS_OUT, &desc->flags); + } else { + if (!chip->direction_input) + set_bit(FLAG_IS_OUT, &desc->flags); + else + clear_bit(FLAG_IS_OUT, &desc->flags); + } } acpi_gpiochip_add(chip); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 1d80222587ad..3c88420e3497 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -394,7 +394,7 @@ config DRM_R128 config DRM_I810 tristate "Intel I810" # !PREEMPT because of missing ioctl locking - depends on DRM && AGP && AGP_INTEL && (!PREEMPT || BROKEN) + depends on DRM && AGP && AGP_INTEL && (!PREEMPTION || BROKEN) help Choose this option if you have an Intel I810 graphics card. If M is selected, the module will be called i810. AGP support is required diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 1d3ee9c42f7e..6a5c96e519b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1140,7 +1140,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( adev->asic_type != CHIP_FIJI && adev->asic_type != CHIP_POLARIS10 && adev->asic_type != CHIP_POLARIS11 && - adev->asic_type != CHIP_POLARIS12) ? + adev->asic_type != CHIP_POLARIS12 && + adev->asic_type != CHIP_VEGAM) ? VI_BO_SIZE_ALIGN : 1; mapping_flags = AMDGPU_VM_PAGE_READABLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index e069de8b54e6..4e4094f842e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1044,29 +1044,27 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p, return r; } - fence = amdgpu_ctx_get_fence(ctx, entity, - deps[i].handle); + fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle); + amdgpu_ctx_put(ctx); + + if (IS_ERR(fence)) + return PTR_ERR(fence); + else if (!fence) + continue; if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) { - struct drm_sched_fence *s_fence = to_drm_sched_fence(fence); + struct drm_sched_fence *s_fence; struct dma_fence *old = fence; + s_fence = to_drm_sched_fence(fence); fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(old); } - if (IS_ERR(fence)) { - r = PTR_ERR(fence); - amdgpu_ctx_put(ctx); + r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true); + dma_fence_put(fence); + if (r) return r; - } else if (fence) { - r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, - true); - dma_fence_put(fence); - amdgpu_ctx_put(ctx); - if (r) - return r; - } } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 6d54decef7f8..5652cc72ed3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -707,7 +707,7 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf, thread = (*pos & GENMASK_ULL(59, 52)) >> 52; bank = (*pos & GENMASK_ULL(61, 60)) >> 60; - data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL); + data = kcalloc(1024, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f2e8b4238efd..5376328d3fd0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -148,7 +148,7 @@ struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; int amdgpu_ras_enable = -1; -uint amdgpu_ras_mask = 0xffffffff; +uint amdgpu_ras_mask = 0xfffffffb; /** * DOC: vramlimit (int) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8b7efd0a7028..2b546567853b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -159,12 +159,16 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev, struct amdgpu_device *adev = ddev->dev_private; enum amd_pm_state_type pm; - if (is_support_sw_smu(adev) && adev->smu.ppt_funcs->get_current_power_state) - pm = amdgpu_smu_get_current_power_state(adev); - else if (adev->powerplay.pp_funcs->get_current_power_state) + if (is_support_sw_smu(adev)) { + if (adev->smu.ppt_funcs->get_current_power_state) + pm = amdgpu_smu_get_current_power_state(adev); + else + pm = adev->pm.dpm.user_state; + } else if (adev->powerplay.pp_funcs->get_current_power_state) { pm = amdgpu_dpm_get_current_power_state(adev); - else + } else { pm = adev->pm.dpm.user_state; + } return snprintf(buf, PAGE_SIZE, "%s\n", (pm == POWER_STATE_TYPE_BATTERY) ? "battery" : @@ -191,7 +195,11 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev, goto fail; } - if (adev->powerplay.pp_funcs->dispatch_tasks) { + if (is_support_sw_smu(adev)) { + mutex_lock(&adev->pm.mutex); + adev->pm.dpm.user_state = state; + mutex_unlock(&adev->pm.mutex); + } else if (adev->powerplay.pp_funcs->dispatch_tasks) { amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_ENABLE_USER_STATE, &state); } else { mutex_lock(&adev->pm.mutex); @@ -1734,7 +1742,7 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev, return -EINVAL; if (is_support_sw_smu(adev)) { - err = smu_get_current_rpm(&adev->smu, &speed); + err = smu_get_fan_speed_rpm(&adev->smu, &speed); if (err) return err; } else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) { @@ -1794,7 +1802,7 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev, return -EINVAL; if (is_support_sw_smu(adev)) { - err = smu_get_current_rpm(&adev->smu, &rpm); + err = smu_get_fan_speed_rpm(&adev->smu, &rpm); if (err) return err; } else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) { @@ -3067,28 +3075,44 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK, (void *)&value64, &size)) seq_printf(m, "SMC Feature Mask: 0x%016llx\n", value64); - /* UVD clocks */ - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) { - if (!value) { - seq_printf(m, "UVD: Disabled\n"); - } else { - seq_printf(m, "UVD: Enabled\n"); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (DCLK)\n", value/100); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + if (adev->asic_type > CHIP_VEGA20) { + /* VCN clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "VCN: Disabled\n"); + } else { + seq_printf(m, "VCN: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (DCLK)\n", value/100); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + } } - } - seq_printf(m, "\n"); + seq_printf(m, "\n"); + } else { + /* UVD clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "UVD: Disabled\n"); + } else { + seq_printf(m, "UVD: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (DCLK)\n", value/100); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (VCLK)\n", value/100); + } + } + seq_printf(m, "\n"); - /* VCE clocks */ - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) { - if (!value) { - seq_printf(m, "VCE: Disabled\n"); - } else { - seq_printf(m, "VCE: Enabled\n"); - if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size)) - seq_printf(m, "\t%u MHz (ECCLK)\n", value/100); + /* VCE clocks */ + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) { + if (!value) { + seq_printf(m, "VCE: Disabled\n"); + } else { + seq_printf(m, "VCE: Enabled\n"); + if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size)) + seq_printf(m, "\t%u MHz (ECCLK)\n", value/100); + } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 1a4412e47810..fac7aa2c244f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -136,11 +136,6 @@ static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev, static int amdgpu_ras_release_vram(struct amdgpu_device *adev, struct amdgpu_bo **bo_ptr); -static void amdgpu_ras_self_test(struct amdgpu_device *adev) -{ - /* TODO */ -} - static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { @@ -689,6 +684,12 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, if (!obj) return -EINVAL; + if (block_info.block_id != TA_RAS_BLOCK__UMC) { + DRM_INFO("%s error injection is not supported yet\n", + ras_block_str(info->head.block)); + return -EINVAL; + } + ret = psp_ras_trigger_error(&adev->psp, &block_info); if (ret) DRM_ERROR("RAS ERROR: inject %s error failed ret %d\n", @@ -1557,6 +1558,12 @@ int amdgpu_ras_init(struct amdgpu_device *adev) amdgpu_ras_check_supported(adev, &con->hw_supported, &con->supported); + if (!con->hw_supported) { + amdgpu_ras_set_context(adev, NULL); + kfree(con); + return 0; + } + con->features = 0; INIT_LIST_HEAD(&con->head); /* Might need get this flag from vbios. */ @@ -1570,8 +1577,6 @@ int amdgpu_ras_init(struct amdgpu_device *adev) if (amdgpu_ras_fs_init(adev)) goto fs_out; - amdgpu_ras_self_test(adev); - DRM_INFO("RAS INFO: ras initialized successfully, " "hardware ability[%x] ras_mask[%x]\n", con->hw_supported, con->supported); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 1675d5837c3c..32773b7523d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -1441,6 +1441,15 @@ static void gfx_v10_0_init_compute_vmid(struct amdgpu_device *adev) } nv_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0); + } } static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) @@ -4611,6 +4620,7 @@ gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, TIME_STAMP_INT_ENABLE, 0); WREG32(cp_int_cntl_reg, cp_int_cntl); + break; case AMDGPU_IRQ_STATE_ENABLE: cp_int_cntl = RREG32(cp_int_cntl_reg); cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 0db9f488da7e..21187275dfd3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -1879,6 +1879,15 @@ static void gfx_v7_0_init_compute_vmid(struct amdgpu_device *adev) } cik_srbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32(amdgpu_gds_reg_offset[i].mem_base, 0); + WREG32(amdgpu_gds_reg_offset[i].mem_size, 0); + WREG32(amdgpu_gds_reg_offset[i].gws, 0); + WREG32(amdgpu_gds_reg_offset[i].oa, 0); + } } static void gfx_v7_0_config_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5f401b41ef7c..751567f78567 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3706,6 +3706,15 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev) } vi_srbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32(amdgpu_gds_reg_offset[i].mem_base, 0); + WREG32(amdgpu_gds_reg_offset[i].mem_size, 0); + WREG32(amdgpu_gds_reg_offset[i].gws, 0); + WREG32(amdgpu_gds_reg_offset[i].oa, 0); + } } static void gfx_v8_0_config_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f4c4eea62526..1cf639a51178 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1918,6 +1918,15 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev) } soc15_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); + + /* Initialize all compute VMIDs to have no GDS, GWS, or OA + acccess. These should be enabled by FW for target VMIDs. */ + for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) { + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0); + WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0); + } } static void gfx_v9_0_constants_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 988c0adaca91..1cfc2620b2dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -372,11 +372,8 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev) WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH, upper_32_bits(adev->vcn.gpu_addr)); offset = size; - /* No signed header for now from firmware WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, AMDGPU_UVD_FIRMWARE_OFFSET >> 3); - */ - WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0); } WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 792371442195..4e3fc284f6ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -668,6 +668,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev, case CHIP_RAVEN: pcache_info = raven_cache_info; num_of_cache_types = ARRAY_SIZE(raven_cache_info); + break; case CHIP_NAVI10: pcache_info = navi10_cache_info; num_of_cache_types = ARRAY_SIZE(navi10_cache_info); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c index 4f8a6ffc5775..9cd3eb2d90bd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c @@ -429,7 +429,6 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type, switch (type) { case KFD_MQD_TYPE_CP: - pr_debug("%s@%i\n", __func__, __LINE__); case KFD_MQD_TYPE_COMPUTE: pr_debug("%s@%i\n", __func__, __LINE__); mqd->allocate_mqd = allocate_mqd; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index c1a92c16535c..5cc3acccda2a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -262,12 +262,12 @@ void dce110_clk_mgr_construct( struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce110_max_clks_by_state, sizeof(dce110_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->regs = &disp_clk_regs; clk_mgr->clk_mgr_shift = &disp_clk_shift; clk_mgr->clk_mgr_mask = &disp_clk_mask; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c index 778392c73187..7c746ef1e32e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c @@ -226,12 +226,12 @@ void dce112_clk_mgr_construct( struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce112_max_clks_by_state, sizeof(dce112_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->regs = &disp_clk_regs; clk_mgr->clk_mgr_shift = &disp_clk_shift; clk_mgr->clk_mgr_mask = &disp_clk_mask; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c index 906310c3e2eb..5399b8cf6b75 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce120/dce120_clk_mgr.c @@ -127,12 +127,12 @@ static struct clk_mgr_funcs dce120_funcs = { void dce120_clk_mgr_construct(struct dc_context *ctx, struct clk_mgr_internal *clk_mgr) { + dce_clk_mgr_construct(ctx, clk_mgr); + memcpy(clk_mgr->max_clks_by_state, dce120_max_clks_by_state, sizeof(dce120_max_clks_by_state)); - dce_clk_mgr_construct(ctx, clk_mgr); - clk_mgr->base.dprefclk_khz = 600000; clk_mgr->base.funcs = &dce120_funcs; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 08a774fc7b67..50bfb5921de0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -301,6 +301,8 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, void dcn2_init_clocks(struct clk_mgr *clk_mgr) { memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); + // Assumption is that boot state always supports pstate + clk_mgr->clks.p_state_change_support = true; } void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base) @@ -331,6 +333,7 @@ void dcn20_clk_mgr_construct( struct dccg *dccg) { clk_mgr->base.ctx = ctx; + clk_mgr->pp_smu = pp_smu; clk_mgr->base.funcs = &dcn2_funcs; clk_mgr->regs = &clk_mgr_regs; clk_mgr->clk_mgr_shift = &clk_mgr_shift; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 4ef4dc63e221..fa20201eef3a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -502,8 +502,10 @@ void dc_stream_set_static_screen_events(struct dc *dc, static void destruct(struct dc *dc) { - dc_release_state(dc->current_state); - dc->current_state = NULL; + if (dc->current_state) { + dc_release_state(dc->current_state); + dc->current_state = NULL; + } destroy_links(dc); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 8dbf759eba45..355b4ba12796 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -532,6 +532,7 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) uint32_t read_dpcd_retry_cnt = 10; enum dc_status status = DC_ERROR_UNEXPECTED; int i; + union max_down_spread max_down_spread = { {0} }; // Read DPCD 00101h to find out the number of lanes currently set for (i = 0; i < read_dpcd_retry_cnt; i++) { @@ -553,8 +554,6 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) msleep(8); } - ASSERT(status == DC_OK); - // Read DPCD 00100h to find if standard link rates are set core_link_read_dpcd(link, DP_LINK_BW_SET, &link_bw_set, sizeof(link_bw_set)); @@ -576,6 +575,12 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link) link->cur_link_settings.link_rate = link_bw_set; link->cur_link_settings.use_link_rate_set = false; } + // Read DPCD 00003h to find the max down spread. + core_link_read_dpcd(link, DP_MAX_DOWNSPREAD, + &max_down_spread.raw, sizeof(max_down_spread)); + link->cur_link_settings.link_spread = + max_down_spread.bits.MAX_DOWN_SPREAD ? + LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED; } static bool detect_dp( @@ -717,13 +722,6 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) return false; } - if (link->connector_signal == SIGNAL_TYPE_EDP) { - /* On detect, we want to make sure current link settings are - * up to date, especially if link was powered on by GOP. - */ - read_edp_current_link_settings_on_detect(link); - } - prev_sink = link->local_sink; if (prev_sink != NULL) { dc_sink_retain(prev_sink); @@ -765,6 +763,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) } case SIGNAL_TYPE_EDP: { + read_edp_current_link_settings_on_detect(link); detect_edp_sink_caps(link); sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C_OVER_AUX; @@ -2329,7 +2328,7 @@ bool dc_link_set_backlight_level(const struct dc_link *link, if (core_dc->current_state->res_ctx.pipe_ctx[i].stream) { if (core_dc->current_state->res_ctx. pipe_ctx[i].stream->link - == link) + == link) { /* DMCU -1 for all controller id values, * therefore +1 here */ @@ -2337,6 +2336,13 @@ bool dc_link_set_backlight_level(const struct dc_link *link, core_dc->current_state-> res_ctx.pipe_ctx[i].stream_res.tg->inst + 1; + + /* Disable brightness ramping when the display is blanked + * as it can hang the DMCU + */ + if (core_dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL) + frame_ramp = 0; + } } } abm->funcs->set_backlight_level_pwm( @@ -2984,8 +2990,10 @@ void dc_link_set_preferred_link_settings(struct dc *dc, /* Retrain with preferred link settings only relevant for * DP signal type + * Check for non-DP signal or if passive dongle present */ - if (!dc_is_dp_signal(link->connector_signal)) + if (!dc_is_dp_signal(link->connector_signal) || + link->dongle_max_pix_clk > 0) return; for (i = 0; i < MAX_PIPES; i++) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 056be4c34a98..2c7aaed907b9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2230,18 +2230,25 @@ static void get_active_converter_info( link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE; ddc_service_set_dongle_type(link->ddc, link->dpcd_caps.dongle_type); + link->dpcd_caps.is_branch_dev = false; return; } /* DPCD 0x5 bit 0 = 1, it indicate it's branch device */ - link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT; + if (ds_port.fields.PORT_TYPE == DOWNSTREAM_DP) { + link->dpcd_caps.is_branch_dev = false; + } + + else { + link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT; + } switch (ds_port.fields.PORT_TYPE) { case DOWNSTREAM_VGA: link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_VGA_CONVERTER; break; - case DOWNSTREAM_DVI_HDMI: - /* At this point we don't know is it DVI or HDMI, + case DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS: + /* At this point we don't know is it DVI or HDMI or DP++, * assume DVI.*/ link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_DVI_CONVERTER; break; @@ -2258,6 +2265,10 @@ static void get_active_converter_info( det_caps, sizeof(det_caps)); switch (port_caps->bits.DWN_STRM_PORTX_TYPE) { + /*Handle DP case as DONGLE_NONE*/ + case DOWN_STREAM_DETAILED_DP: + link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE; + break; case DOWN_STREAM_DETAILED_VGA: link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_VGA_CONVERTER; @@ -2267,6 +2278,8 @@ static void get_active_converter_info( DISPLAY_DONGLE_DP_DVI_CONVERTER; break; case DOWN_STREAM_DETAILED_HDMI: + case DOWN_STREAM_DETAILED_DP_PLUS_PLUS: + /*Handle DP++ active converter case, process DP++ case as HDMI case according DP1.4 spec*/ link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_HDMI_CONVERTER; @@ -2282,14 +2295,18 @@ static void get_active_converter_info( link->dpcd_caps.dongle_caps.is_dp_hdmi_s3d_converter = hdmi_caps.bits.FRAME_SEQ_TO_FRAME_PACK; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through = - hdmi_caps.bits.YCrCr422_PASS_THROUGH; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through = - hdmi_caps.bits.YCrCr420_PASS_THROUGH; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter = - hdmi_caps.bits.YCrCr422_CONVERSION; - link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter = - hdmi_caps.bits.YCrCr420_CONVERSION; + /*YCBCR capability only for HDMI case*/ + if (port_caps->bits.DWN_STRM_PORTX_TYPE + == DOWN_STREAM_DETAILED_HDMI) { + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through = + hdmi_caps.bits.YCrCr422_PASS_THROUGH; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through = + hdmi_caps.bits.YCrCr420_PASS_THROUGH; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter = + hdmi_caps.bits.YCrCr422_CONVERSION; + link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter = + hdmi_caps.bits.YCrCr420_CONVERSION; + } link->dpcd_caps.dongle_caps.dp_hdmi_max_bpc = translate_dpcd_max_bpc( diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 51a78283a86d..2ceaab4fb5de 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -258,7 +258,7 @@ bool resource_construct( * PORT_CONNECTIVITY == 1 (as instructed by HW team). */ update_num_audio(&straps, &num_audio, &pool->audio_support); - for (i = 0; i < pool->pipe_count && i < num_audio; i++) { + for (i = 0; i < caps->num_audio; i++) { struct audio *aud = create_funcs->create_audio(ctx, i); if (aud == NULL) { @@ -1669,6 +1669,12 @@ static struct audio *find_first_free_audio( return pool->audios[i]; } } + + /* use engine id to find free audio */ + if ((id < pool->audio_count) && (res_ctx->is_audio_acquired[id] == false)) { + return pool->audios[id]; + } + /*not found the matching one, first come first serve*/ for (i = 0; i < pool->audio_count; i++) { if (res_ctx->is_audio_acquired[i] == false) { @@ -1833,6 +1839,7 @@ static int get_norm_pix_clk(const struct dc_crtc_timing *timing) pix_clk /= 2; if (timing->pixel_encoding != PIXEL_ENCODING_YCBCR422) { switch (timing->display_color_depth) { + case COLOR_DEPTH_666: case COLOR_DEPTH_888: normalized_pix_clk = pix_clk; break; @@ -1979,7 +1986,7 @@ enum dc_status resource_map_pool_resources( /* TODO: Add check if ASIC support and EDID audio */ if (!stream->converter_disable_audio && dc_is_audio_capable_signal(pipe_ctx->stream->signal) && - stream->audio_info.mode_count) { + stream->audio_info.mode_count && stream->audio_info.flags.all) { pipe_ctx->stream_res.audio = find_first_free_audio( &context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index af7f8be230f7..352862370390 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -612,7 +612,8 @@ bool dc_stream_set_dynamic_metadata(struct dc *dc, pipe_ctx->stream->dmdata_address = attr->address; - if (pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) { + if (pipe_ctx->stream_res.stream_enc && + pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) { if (pipe_ctx->stream->dmdata_address.quad_part != 0) { /* if using dynamic meta, don't set up generic infopackets */ pipe_ctx->stream_res.encoder_info_frame.hdrsmd.valid = false; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c index f8903bcabe49..58bd131d5b48 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c @@ -239,6 +239,10 @@ static void dmcu_set_backlight_level( s2 |= (backlight_8_bit << ATOM_S2_CURRENT_BL_LEVEL_SHIFT); REG_WRITE(BIOS_SCRATCH_2, s2); + + /* waitDMCUReadyForCmd */ + REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, + 0, 1, 80000); } static void dce_abm_init(struct abm *abm) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 858a58856ebd..fafb4b470140 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -965,11 +965,17 @@ void hwss_edp_backlight_control( void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) { /* notify audio driver for audio modes of monitor */ - struct dc *core_dc = pipe_ctx->stream->ctx->dc; + struct dc *core_dc; struct pp_smu_funcs *pp_smu = NULL; - struct clk_mgr *clk_mgr = core_dc->clk_mgr; + struct clk_mgr *clk_mgr; unsigned int i, num_audio = 1; + if (!pipe_ctx->stream) + return; + + core_dc = pipe_ctx->stream->ctx->dc; + clk_mgr = core_dc->clk_mgr; + if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true) return; @@ -999,9 +1005,15 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx) void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) { - struct dc *dc = pipe_ctx->stream->ctx->dc; + struct dc *dc; struct pp_smu_funcs *pp_smu = NULL; - struct clk_mgr *clk_mgr = dc->clk_mgr; + struct clk_mgr *clk_mgr; + + if (!pipe_ctx || !pipe_ctx->stream) + return; + + dc = pipe_ctx->stream->ctx->dc; + clk_mgr = dc->clk_mgr; if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == false) return; @@ -1009,6 +1021,8 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control( pipe_ctx->stream_res.stream_enc, true); if (pipe_ctx->stream_res.audio) { + pipe_ctx->stream_res.audio->enabled = false; + if (dc->res_pool->pp_smu) pp_smu = dc->res_pool->pp_smu; @@ -1039,8 +1053,6 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option) /* dal_audio_disable_azalia_audio_jack_presence(stream->audio, * stream->stream_engine_id); */ - if (pipe_ctx->stream_res.audio) - pipe_ctx->stream_res.audio->enabled = false; } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index e50a696fcb5d..2118ea21d7e9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1195,16 +1195,7 @@ static void dcn10_init_hw(struct dc *dc) * everything down. */ if (dcb->funcs->is_accelerated_mode(dcb) || dc->config.power_down_display_on_boot) { - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct hubp *hubp = dc->res_pool->hubps[i]; - struct dpp *dpp = dc->res_pool->dpps[i]; - - hubp->funcs->hubp_init(hubp); - dc->res_pool->opps[i]->mpc_tree_params.opp_id = dc->res_pool->opps[i]->inst; - plane_atomic_power_down(dc, dpp, hubp); - } - - apply_DEGVIDCN10_253_wa(dc); + dc->hwss.init_pipes(dc, dc->current_state); } for (i = 0; i < dc->res_pool->audio_count; i++) { @@ -1375,10 +1366,6 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx, return result; } - - - - static bool dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx, const struct dc_stream_state *stream) @@ -2516,6 +2503,12 @@ static void dcn10_apply_ctx_for_surface( if (removed_pipe[i]) dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]); + for (i = 0; i < dc->res_pool->pipe_count; i++) + if (removed_pipe[i]) { + dc->hwss.optimize_bandwidth(dc, context); + break; + } + if (dc->hwseq->wa.DEGVIDCN10_254) hubbub1_wm_change_req_wa(dc->res_pool->hubbub); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 1a20461c2937..a12530a3ab9c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -508,7 +508,7 @@ static const struct resource_caps rv2_res_cap = { .num_audio = 3, .num_stream_encoder = 3, .num_pll = 3, - .num_ddc = 3, + .num_ddc = 4, }; static const struct dc_plane_cap plane_cap = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c index 51a3dfe97f0e..31aa6ee5cd5b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c @@ -102,14 +102,19 @@ void dccg2_init(struct dccg *dccg) switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) { case 6: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1); + /* Fall through */ case 5: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1); + /* Fall through */ case 4: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1); + /* Fall through */ case 3: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1); + /* Fall through */ case 2: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1); + /* Fall through */ case 1: REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1); break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c index ece6e136437b..6e2dbd03f9bf 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c @@ -337,6 +337,7 @@ static enum dcn_hubbub_page_table_block_size page_table_block_size_to_hw(unsigne break; default: ASSERT(false); + block_size = page_table_block_size; break; } @@ -366,25 +367,24 @@ int hubbub2_init_dchub_sys_ctx(struct hubbub *hubbub, struct dcn_vmid_page_table_config phys_config; REG_SET(DCN_VM_FB_LOCATION_BASE, 0, - FB_BASE, pa_config->system_aperture.fb_base); + FB_BASE, pa_config->system_aperture.fb_base >> 24); REG_SET(DCN_VM_FB_LOCATION_TOP, 0, - FB_TOP, pa_config->system_aperture.fb_top); + FB_TOP, pa_config->system_aperture.fb_top >> 24); REG_SET(DCN_VM_FB_OFFSET, 0, - FB_OFFSET, pa_config->system_aperture.fb_offset); + FB_OFFSET, pa_config->system_aperture.fb_offset >> 24); REG_SET(DCN_VM_AGP_BOT, 0, - AGP_BOT, pa_config->system_aperture.agp_bot); + AGP_BOT, pa_config->system_aperture.agp_bot >> 24); REG_SET(DCN_VM_AGP_TOP, 0, - AGP_TOP, pa_config->system_aperture.agp_top); + AGP_TOP, pa_config->system_aperture.agp_top >> 24); REG_SET(DCN_VM_AGP_BASE, 0, - AGP_BASE, pa_config->system_aperture.agp_base); + AGP_BASE, pa_config->system_aperture.agp_base >> 24); if (pa_config->gart_config.page_table_start_addr != pa_config->gart_config.page_table_end_addr) { - phys_config.depth = 1; - phys_config.block_size = 4096; phys_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr >> 12; phys_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr >> 12; phys_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr; - + phys_config.depth = 0; + phys_config.block_size = 0; // Init VMID 0 based on PA config dcn20_vmid_setup(&hubbub1->vmid[0], &phys_config); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 0b84a322b8a2..d810c8940129 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1153,8 +1153,8 @@ void dcn20_enable_plane( apt.sys_default.quad_part = 0; - apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.start_addr; - apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.end_addr; + apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.start_addr; + apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.end_addr; // Program system aperture settings pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt); @@ -1242,6 +1242,8 @@ void dcn20_pipe_control_lock_global( CRTC_STATE_VACTIVE); pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg, CRTC_STATE_VBLANK); + pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg, + CRTC_STATE_VACTIVE); pipe->stream_res.tg->funcs->lock_doublebuffer_disable( pipe->stream_res.tg); } @@ -1263,6 +1265,17 @@ void dcn20_pipe_control_lock( if (pipe->plane_state != NULL) flip_immediate = pipe->plane_state->flip_immediate; + if (flip_immediate && lock) { + while (pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp)) { + udelay(1); + } + + if (pipe->bottom_pipe != NULL) + while (pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp)) { + udelay(1); + } + } + /* In flip immediate and pipe splitting case, we need to use GSL * for synchronization. Only do setup on locking and on flip type change. */ @@ -1740,8 +1753,11 @@ static void dcn20_reset_back_end_for_pipe( else if (pipe_ctx->stream_res.audio) { dc->hwss.disable_audio_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE); } - } +#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT + else if (pipe_ctx->stream_res.dsc) + dp_set_dsc_enable(pipe_ctx, false); +#endif /* by upper caller loop, parent pipe: pipe0, will be reset last. * back end share by all pipes and will be disable only when disable diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 26a66ccf6e72..1ae973962d53 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -535,7 +535,7 @@ void dcn20_timing_generator_init(struct optc *optc1) optc1->min_h_blank = 32; optc1->min_v_blank = 3; optc1->min_v_blank_interlace = 5; - optc1->min_h_sync_width = 8; + optc1->min_h_sync_width = 4;// Minimum HSYNC = 8 pixels asked By HW in the first place for no actual reason. Oculus Rift S will not light up with 8 as it's hsyncWidth is 6. Changing it to 4 to fix that issue. optc1->min_v_sync_width = 1; optc1->comb_opp_id = 0xf; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d200bc3cec71..b949e202d6cb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -2643,6 +2643,10 @@ static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_ if (dc->bb_overrides.min_dcfclk_mhz > 0) min_dcfclk = dc->bb_overrides.min_dcfclk_mhz; + else + // Accounting for SOC/DCF relationship, we can go as high as + // 506Mhz in Vmin. We need to code 507 since SMU will round down to 506. + min_dcfclk = 507; for (i = 0; i < num_states; i++) { int min_fclk_required_by_uclk; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c index 27679ef6ebe8..96c263223315 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_vmid.c @@ -23,6 +23,8 @@ * */ +#include <linux/delay.h> + #include "dcn20_vmid.h" #include "reg_helper.h" @@ -36,6 +38,38 @@ #define FN(reg_name, field_name) \ vmid->shifts->field_name, vmid->masks->field_name +static void dcn20_wait_for_vmid_ready(struct dcn20_vmid *vmid) +{ + /* According the hardware spec, we need to poll for the lowest + * bit of PAGE_TABLE_BASE_ADDR_LO32 = 1 any time a GPUVM + * context is updated. We can't use REG_WAIT here since we + * don't have a seperate field to wait on. + * + * TODO: Confirm timeout / poll interval with hardware team + */ + + int max_times = 10000; + int delay_us = 5; + int i; + + for (i = 0; i < max_times; ++i) { + uint32_t entry_lo32; + + REG_GET(PAGE_TABLE_BASE_ADDR_LO32, + VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32, + &entry_lo32); + + if (entry_lo32 & 0x1) + return; + + udelay(delay_us); + } + + /* VM setup timed out */ + DC_LOG_WARNING("Timeout while waiting for GPUVM context update\n"); + ASSERT(0); +} + void dcn20_vmid_setup(struct dcn20_vmid *vmid, const struct dcn_vmid_page_table_config *config) { REG_SET(PAGE_TABLE_START_ADDR_HI32, 0, @@ -54,6 +88,9 @@ void dcn20_vmid_setup(struct dcn20_vmid *vmid, const struct dcn_vmid_page_table_ REG_SET(PAGE_TABLE_BASE_ADDR_HI32, 0, VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_HI32, (config->page_table_base_addr >> 32) & 0xFFFFFFFF); + /* Note: per hardware spec PAGE_TABLE_BASE_ADDR_LO32 must be programmed last in sequence */ REG_SET(PAGE_TABLE_BASE_ADDR_LO32, 0, VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32, config->page_table_base_addr & 0xFFFFFFFF); + + dcn20_wait_for_vmid_ready(vmid); } diff --git a/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c b/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c index 67089765780b..340ef4d41ebd 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/drm_dsc_dc.c @@ -377,6 +377,12 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg) vdsc_cfg->rc_bits = (hrd_delay * vdsc_cfg->bits_per_pixel) / 16; vdsc_cfg->initial_dec_delay = hrd_delay - vdsc_cfg->initial_xmit_delay; + /* As per DSC spec v1.2a recommendation: */ + if (vdsc_cfg->native_420) + vdsc_cfg->second_line_offset_adj = 512; + else + vdsc_cfg->second_line_offset_adj = 0; + return 0; } EXPORT_SYMBOL(drm_dsc_compute_rc_parameters); diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index c89393c19232..a148ffde8b12 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -212,7 +212,7 @@ struct resource_pool { struct clock_source *clock_sources[MAX_CLOCK_SOURCES]; unsigned int clk_src_count; - struct audio *audios[MAX_PIPES]; + struct audio *audios[MAX_AUDIOS]; unsigned int audio_count; struct audio_support audio_support; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index 959f5b654611..9502478c4a1b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -61,8 +61,8 @@ enum dcn_hubbub_page_table_depth { }; enum dcn_hubbub_page_table_block_size { - DCN_PAGE_TABLE_BLOCK_SIZE_4KB, - DCN_PAGE_TABLE_BLOCK_SIZE_64KB + DCN_PAGE_TABLE_BLOCK_SIZE_4KB = 0, + DCN_PAGE_TABLE_BLOCK_SIZE_64KB = 4, }; struct dcn_hubbub_phys_addr_config { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h index 8759ec03aede..f82365e2d03c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h @@ -34,6 +34,7 @@ * Data types shared between different Virtual HW blocks ******************************************************************************/ +#define MAX_AUDIOS 7 #define MAX_PIPES 6 #if defined(CONFIG_DRM_AMD_DC_DCN2_0) #define MAX_DWB_PIPES 1 diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h index 1c66166d0a94..2c90d1b46c8b 100644 --- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h +++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h @@ -43,7 +43,7 @@ enum dpcd_revision { enum dpcd_downstream_port_type { DOWNSTREAM_DP = 0, DOWNSTREAM_VGA, - DOWNSTREAM_DVI_HDMI, + DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS,/* DVI, HDMI, DP++ */ DOWNSTREAM_NONDDC /* has no EDID (TV,CV) */ }; diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 9f661bf96ed0..5b1ebb7f995a 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -123,6 +123,7 @@ enum amd_pp_sensors { AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK, AMDGPU_PP_SENSOR_MIN_FAN_RPM, AMDGPU_PP_SENSOR_MAX_FAN_RPM, + AMDGPU_PP_SENSOR_VCN_POWER_STATE, }; enum amd_pp_task { diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index f1565c448de5..0685a3388e38 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -137,12 +137,37 @@ int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type, { int ret = 0, clk_id = 0; uint32_t param = 0; + uint32_t clock_limit; if (!min && !max) return -EINVAL; - if (!smu_clk_dpm_is_enabled(smu, clk_type)) + if (!smu_clk_dpm_is_enabled(smu, clk_type)) { + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + clock_limit = smu->smu_table.boot_values.uclk; + break; + case SMU_GFXCLK: + case SMU_SCLK: + clock_limit = smu->smu_table.boot_values.gfxclk; + break; + case SMU_SOCCLK: + clock_limit = smu->smu_table.boot_values.socclk; + break; + default: + clock_limit = 0; + break; + } + + /* clock in Mhz unit */ + if (min) + *min = clock_limit / 100; + if (max) + *max = clock_limit / 100; + return 0; + } mutex_lock(&smu->mutex); clk_id = smu_clk_get_index(smu, clk_type); @@ -281,7 +306,8 @@ int smu_get_power_num_states(struct smu_context *smu, /* not support power state */ memset(state_info, 0, sizeof(struct pp_states_info)); - state_info->nums = 0; + state_info->nums = 1; + state_info->states[0] = POWER_STATE_TYPE_DEFAULT; return 0; } @@ -312,6 +338,10 @@ int smu_common_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, *(uint32_t *)data = smu_feature_is_enabled(smu, SMU_FEATURE_DPM_VCE_BIT) ? 1 : 0; *size = 4; break; + case AMDGPU_PP_SENSOR_VCN_POWER_STATE: + *(uint32_t *)data = smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT) ? 1 : 0; + *size = 4; + break; default: ret = -EINVAL; break; @@ -698,6 +728,12 @@ static int smu_sw_init(void *handle) return ret; } + ret = smu_register_irq_handler(smu); + if (ret) { + pr_err("Failed to register smc irq handler!\n"); + return ret; + } + return 0; } @@ -707,6 +743,9 @@ static int smu_sw_fini(void *handle) struct smu_context *smu = &adev->smu; int ret; + kfree(smu->irq_source); + smu->irq_source = NULL; + ret = smu_smc_table_sw_fini(smu); if (ret) { pr_err("Failed to sw fini smc table!\n"); @@ -1063,10 +1102,6 @@ static int smu_hw_init(void *handle) if (ret) goto failed; - ret = smu_register_irq_handler(smu); - if (ret) - goto failed; - if (!smu->pm_enabled) adev->pm.dpm_enabled = false; else @@ -1096,9 +1131,6 @@ static int smu_hw_fini(void *handle) kfree(table_context->overdrive_table); table_context->overdrive_table = NULL; - kfree(smu->irq_source); - smu->irq_source = NULL; - ret = smu_fini_fb_allocations(smu); if (ret) return ret; @@ -1349,13 +1381,49 @@ static int smu_enable_umd_pstate(void *handle, return 0; } +static int smu_default_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level) +{ + int ret = 0; + uint32_t sclk_mask, mclk_mask, soc_mask; + + switch (level) { + case AMD_DPM_FORCED_LEVEL_HIGH: + ret = smu_force_dpm_limit_value(smu, true); + break; + case AMD_DPM_FORCED_LEVEL_LOW: + ret = smu_force_dpm_limit_value(smu, false); + break; + case AMD_DPM_FORCED_LEVEL_AUTO: + case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: + ret = smu_unforce_dpm_levels(smu); + break; + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + ret = smu_get_profiling_clk_mask(smu, level, + &sclk_mask, + &mclk_mask, + &soc_mask); + if (ret) + return ret; + smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask); + smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); + smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); + break; + case AMD_DPM_FORCED_LEVEL_MANUAL: + case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT: + default: + break; + } + return ret; +} + int smu_adjust_power_state_dynamic(struct smu_context *smu, enum amd_dpm_forced_level level, bool skip_display_settings) { int ret = 0; int index = 0; - uint32_t sclk_mask, mclk_mask, soc_mask; long workload; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -1386,39 +1454,10 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu, } if (smu_dpm_ctx->dpm_level != level) { - switch (level) { - case AMD_DPM_FORCED_LEVEL_HIGH: - ret = smu_force_dpm_limit_value(smu, true); - break; - case AMD_DPM_FORCED_LEVEL_LOW: - ret = smu_force_dpm_limit_value(smu, false); - break; - - case AMD_DPM_FORCED_LEVEL_AUTO: - case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: - ret = smu_unforce_dpm_levels(smu); - break; - - case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: - case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK: - case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: - ret = smu_get_profiling_clk_mask(smu, level, - &sclk_mask, - &mclk_mask, - &soc_mask); - if (ret) - return ret; - smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask); - smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask); - smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask); - break; - - case AMD_DPM_FORCED_LEVEL_MANUAL: - case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT: - default: - break; + ret = smu_asic_set_performance_level(smu, level); + if (ret) { + ret = smu_default_set_performance_level(smu, level); } - if (!ret) smu_dpm_ctx->dpm_level = level; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index e32ae9d3373c..18e780f566fa 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -1111,6 +1111,7 @@ static int smu10_thermal_get_temperature(struct pp_hwmgr *hwmgr) static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx, void *value, int *size) { + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); uint32_t sclk, mclk; int ret = 0; @@ -1132,6 +1133,10 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_TEMP: *((uint32_t *)value) = smu10_thermal_get_temperature(hwmgr); break; + case AMDGPU_PP_SENSOR_VCN_POWER_STATE: + *(uint32_t *)value = smu10_data->vcn_power_gated ? 0 : 1; + *size = 4; + break; default: ret = -EINVAL; break; @@ -1175,18 +1180,22 @@ static int smu10_powergate_sdma(struct pp_hwmgr *hwmgr, bool gate) static void smu10_powergate_vcn(struct pp_hwmgr *hwmgr, bool bgate) { + struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend); + if (bgate) { amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_GATE); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_PowerDownVcn, 0); + smu10_data->vcn_power_gated = true; } else { smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_PowerUpVcn, 0); amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_UNGATE); + smu10_data->vcn_power_gated = false; } } diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h index 1af992fb0bde..208e6711d506 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h @@ -429,7 +429,6 @@ struct smu_table_context struct smu_table *tables; uint32_t table_count; struct smu_table memory_pool; - uint16_t software_shutdown_temp; uint8_t thermal_controller_type; uint16_t TDPODLimit; @@ -613,6 +612,7 @@ struct pptable_funcs { int (*tables_init)(struct smu_context *smu, struct smu_table *tables); int (*set_thermal_fan_table)(struct smu_context *smu); int (*get_fan_speed_percent)(struct smu_context *smu, uint32_t *speed); + int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed); int (*set_watermarks_table)(struct smu_context *smu, void *watermarks, struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); int (*get_current_clk_freq_by_table)(struct smu_context *smu, @@ -621,6 +621,7 @@ struct pptable_funcs { int (*get_thermal_temperature_range)(struct smu_context *smu, struct smu_temperature_range *range); int (*get_uclk_dpm_states)(struct smu_context *smu, uint32_t *clocks_in_khz, uint32_t *num_states); int (*set_default_od_settings)(struct smu_context *smu, bool initialize); + int (*set_performance_level)(struct smu_context *smu, enum amd_dpm_forced_level level); }; struct smu_funcs @@ -685,7 +686,6 @@ struct smu_funcs int (*set_watermarks_for_clock_ranges)(struct smu_context *smu, struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges); int (*conv_power_profile_to_pplib_workload)(int power_profile); - int (*get_current_rpm)(struct smu_context *smu, uint32_t *speed); uint32_t (*get_fan_control_mode)(struct smu_context *smu); int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode); int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed); @@ -751,8 +751,6 @@ struct smu_funcs ((smu)->funcs->init_max_sustainable_clocks ? (smu)->funcs->init_max_sustainable_clocks((smu)) : 0) #define smu_set_default_od_settings(smu, initialize) \ ((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0) -#define smu_get_current_rpm(smu, speed) \ - ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0) #define smu_set_fan_speed_rpm(smu, speed) \ ((smu)->funcs->set_fan_speed_rpm ? (smu)->funcs->set_fan_speed_rpm((smu), (speed)) : 0) #define smu_send_smc_msg(smu, msg) \ @@ -841,6 +839,8 @@ struct smu_funcs ((smu)->ppt_funcs->get_fan_speed_percent ? (smu)->ppt_funcs->get_fan_speed_percent((smu), (speed)) : 0) #define smu_set_fan_speed_percent(smu, speed) \ ((smu)->funcs->set_fan_speed_percent ? (smu)->funcs->set_fan_speed_percent((smu), (speed)) : 0) +#define smu_get_fan_speed_rpm(smu, speed) \ + ((smu)->ppt_funcs->get_fan_speed_rpm ? (smu)->ppt_funcs->get_fan_speed_rpm((smu), (speed)) : 0) #define smu_msg_get_index(smu, msg) \ ((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_msg_index? (smu)->ppt_funcs->get_smu_msg_index((smu), (msg)) : -EINVAL) : -EINVAL) @@ -918,6 +918,9 @@ struct smu_funcs ((smu)->funcs->baco_get_state? (smu)->funcs->baco_get_state((smu), (state)) : 0) #define smu_baco_reset(smu) \ ((smu)->funcs->baco_reset? (smu)->funcs->baco_reset((smu)) : 0) +#define smu_asic_set_performance_level(smu, level) \ + ((smu)->ppt_funcs->set_performance_level? (smu)->ppt_funcs->set_performance_level((smu), (level)) : -EINVAL); + extern int smu_get_atom_data_table(struct smu_context *smu, uint32_t table, uint16_t *size, uint8_t *frev, uint8_t *crev, diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 2dae0ae0829e..cc0a3b2256af 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -23,6 +23,7 @@ #include "pp_debug.h" #include <linux/firmware.h> +#include <linux/pci.h> #include "amdgpu.h" #include "amdgpu_smu.h" #include "atomfirmware.h" @@ -577,28 +578,20 @@ static int navi10_set_default_dpm_table(struct smu_context *smu) static int navi10_dpm_set_uvd_enable(struct smu_context *smu, bool enable) { int ret = 0; - struct smu_power_context *smu_power = &smu->smu_power; - struct smu_power_gate *power_gate = &smu_power->power_gate; - if (enable && power_gate->uvd_gated) { - if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) { - ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 1); - if (ret) - return ret; - } - power_gate->uvd_gated = false; + if (enable) { + ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 1); + if (ret) + return ret; } else { - if (!enable && !power_gate->uvd_gated) { - if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) { - ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn); - if (ret) - return ret; - } - power_gate->uvd_gated = true; - } + ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn); + if (ret) + return ret; } - return 0; + ret = smu_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, enable); + + return ret; } static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, @@ -626,11 +619,26 @@ static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, return ret; } +static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) +{ + PPTable_t *pptable = smu->smu_table.driver_pptable; + DpmDescriptor_t *dpm_desc = NULL; + uint32_t clk_index = 0; + + clk_index = smu_clk_get_index(smu, clk_type); + dpm_desc = &pptable->DpmDescriptor[clk_index]; + + /* 0 - Fine grained DPM, 1 - Discrete DPM */ + return dpm_desc->SnapToDiscrete == 0 ? true : false; +} + static int navi10_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { int i, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; + uint32_t freq_values[3] = {0}; + uint32_t mark_index = 0; switch (clk_type) { case SMU_GFXCLK: @@ -643,22 +651,42 @@ static int navi10_print_clk_levels(struct smu_context *smu, ret = smu_get_current_clk_freq(smu, clk_type, &cur_value); if (ret) return size; + /* 10KHz -> MHz */ cur_value = cur_value / 100; - size += sprintf(buf, "current clk: %uMhz\n", cur_value); - ret = smu_get_dpm_level_count(smu, clk_type, &count); if (ret) return size; - for (i = 0; i < count; i++) { - ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value); + if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + for (i = 0; i < count; i++) { + ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value); + if (ret) + return size; + + size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, + cur_value == value ? "*" : ""); + } + } else { + ret = smu_get_dpm_freq_by_index(smu, clk_type, 0, &freq_values[0]); + if (ret) + return size; + ret = smu_get_dpm_freq_by_index(smu, clk_type, count - 1, &freq_values[2]); if (ret) return size; - size += sprintf(buf + size, "%d: %uMhz %s\n", i, value, - cur_value == value ? "*" : ""); + freq_values[1] = cur_value; + mark_index = cur_value == freq_values[0] ? 0 : + cur_value == freq_values[2] ? 2 : 1; + if (mark_index != 1) + freq_values[1] = (freq_values[0] + freq_values[2]) / 2; + + for (i = 0; i < 3; i++) { + size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i], + i == mark_index ? "*" : ""); + } + } break; default: @@ -919,12 +947,13 @@ static bool navi10_is_dpm_running(struct smu_context *smu) return !!(feature_enabled & SMC_DPM_FEATURE); } -static int navi10_get_fan_speed(struct smu_context *smu, uint16_t *value) +static int navi10_get_fan_speed_rpm(struct smu_context *smu, + uint32_t *speed) { SmuMetrics_t metrics; int ret = 0; - if (!value) + if (!speed) return -EINVAL; memset(&metrics, 0, sizeof(metrics)); @@ -934,7 +963,7 @@ static int navi10_get_fan_speed(struct smu_context *smu, uint16_t *value) if (ret) return ret; - *value = metrics.CurrFanSpeed; + *speed = metrics.CurrFanSpeed; return ret; } @@ -944,10 +973,10 @@ static int navi10_get_fan_speed_percent(struct smu_context *smu, { int ret = 0; uint32_t percent = 0; - uint16_t current_rpm; + uint32_t current_rpm; PPTable_t *pptable = smu->smu_table.driver_pptable; - ret = navi10_get_fan_speed(smu, ¤t_rpm); + ret = navi10_get_fan_speed_rpm(smu, ¤t_rpm); if (ret) return ret; @@ -1530,6 +1559,76 @@ static int navi10_set_ppfeature_status(struct smu_context *smu, return 0; } +static int navi10_set_peak_clock_by_device(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + uint32_t sclk_freq = 0, uclk_freq = 0; + uint32_t uclk_level = 0; + + switch (adev->pdev->revision) { + case 0xf0: /* XTX */ + case 0xc0: + sclk_freq = NAVI10_PEAK_SCLK_XTX; + break; + case 0xf1: /* XT */ + case 0xc1: + sclk_freq = NAVI10_PEAK_SCLK_XT; + break; + default: /* XL */ + sclk_freq = NAVI10_PEAK_SCLK_XL; + break; + } + + ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level); + if (ret) + return ret; + ret = smu_get_dpm_freq_by_index(smu, SMU_UCLK, uclk_level - 1, &uclk_freq); + if (ret) + return ret; + + ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq); + if (ret) + return ret; + ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq); + if (ret) + return ret; + + return ret; +} + +static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level) +{ + int ret = 0; + + switch (level) { + case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK: + ret = navi10_set_peak_clock_by_device(smu); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int navi10_get_thermal_temperature_range(struct smu_context *smu, + struct smu_temperature_range *range) +{ + struct smu_table_context *table_context = &smu->smu_table; + struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table; + + if (!range || !powerplay_table) + return -EINVAL; + + /* The unit is temperature */ + range->min = 0; + range->max = powerplay_table->software_shutdown_temp; + + return 0; +} + static const struct pptable_funcs navi10_ppt_funcs = { .tables_init = navi10_tables_init, .alloc_dpm_context = navi10_allocate_dpm_context, @@ -1557,6 +1656,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .unforce_dpm_levels = navi10_unforce_dpm_levels, .is_dpm_running = navi10_is_dpm_running, .get_fan_speed_percent = navi10_get_fan_speed_percent, + .get_fan_speed_rpm = navi10_get_fan_speed_rpm, .get_power_profile_mode = navi10_get_power_profile_mode, .set_power_profile_mode = navi10_set_power_profile_mode, .get_profiling_clk_mask = navi10_get_profiling_clk_mask, @@ -1565,6 +1665,8 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_uclk_dpm_states = navi10_get_uclk_dpm_states, .get_ppfeature_status = navi10_get_ppfeature_status, .set_ppfeature_status = navi10_set_ppfeature_status, + .set_performance_level = navi10_set_performance_level, + .get_thermal_temperature_range = navi10_get_thermal_temperature_range, }; void navi10_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h index 957288e22f47..620ff17c2fef 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h @@ -23,6 +23,10 @@ #ifndef __NAVI10_PPT_H__ #define __NAVI10_PPT_H__ +#define NAVI10_PEAK_SCLK_XTX (1830) +#define NAVI10_PEAK_SCLK_XT (1755) +#define NAVI10_PEAK_SCLK_XL (1625) + extern void navi10_set_ppt_funcs(struct smu_context *smu); #endif diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index 95c7c4dae523..ac5b26228e75 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -1124,10 +1124,8 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, struct smu_temperature_range *range) { struct amdgpu_device *adev = smu->adev; - int low = SMU_THERMAL_MINIMUM_ALERT_TEMP * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + int low = SMU_THERMAL_MINIMUM_ALERT_TEMP; + int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP; uint32_t val; if (!range) @@ -1138,6 +1136,9 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, if (high > range->max) high = range->max; + low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP, range->min); + high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP, range->max); + if (low > high) return -EINVAL; @@ -1146,8 +1147,8 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu, val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTH_MASK, 0); val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTL_MASK, 0); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES)); - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high & 0xff)); + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low & 0xff)); val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK); WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); @@ -1186,7 +1187,10 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu) if (!smu->pm_enabled) return ret; + ret = smu_get_thermal_temperature_range(smu, &range); + if (ret) + return ret; if (smu->smu_table.thermal_controller_type) { ret = smu_v11_0_set_thermal_range(smu, &range); @@ -1202,15 +1206,17 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu) return ret; } - adev->pm.dpm.thermal.min_temp = range.min; - adev->pm.dpm.thermal.max_temp = range.max; - adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max; - adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min; - adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max; - adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max; - adev->pm.dpm.thermal.min_mem_temp = range.mem_min; - adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max; - adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max; + adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; return ret; } @@ -1371,23 +1377,6 @@ static int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable) return ret; } -static int smu_v11_0_get_current_rpm(struct smu_context *smu, - uint32_t *current_rpm) -{ - int ret; - - ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm); - - if (ret) { - pr_err("Attempt to get current RPM from SMC Failed!\n"); - return ret; - } - - smu_read_smc_arg(smu, current_rpm); - - return 0; -} - static uint32_t smu_v11_0_get_fan_control_mode(struct smu_context *smu) { @@ -1773,7 +1762,6 @@ static const struct smu_funcs smu_v11_0_funcs = { .set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk, .display_clock_voltage_request = smu_v11_0_display_clock_voltage_request, .set_watermarks_for_clock_ranges = smu_v11_0_set_watermarks_for_clock_ranges, - .get_current_rpm = smu_v11_0_get_current_rpm, .get_fan_control_mode = smu_v11_0_get_fan_control_mode, .set_fan_control_mode = smu_v11_0_set_fan_control_mode, .set_fan_speed_percent = smu_v11_0_set_fan_speed_percent, diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c index bb9bb09cfc7a..dd6fd1c8bf24 100644 --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c @@ -450,7 +450,6 @@ static int vega20_store_powerplay_table(struct smu_context *smu) memcpy(table_context->driver_pptable, &powerplay_table->smcPPTable, sizeof(PPTable_t)); - table_context->software_shutdown_temp = powerplay_table->usSoftwareShutdownTemp; table_context->thermal_controller_type = powerplay_table->ucThermalControllerType; table_context->TDPODLimit = le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE]); @@ -3015,6 +3014,23 @@ static int vega20_set_thermal_fan_table(struct smu_context *smu) return ret; } +static int vega20_get_fan_speed_rpm(struct smu_context *smu, + uint32_t *speed) +{ + int ret; + + ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm); + + if (ret) { + pr_err("Attempt to get current RPM from SMC Failed!\n"); + return ret; + } + + smu_read_smc_arg(smu, speed); + + return 0; +} + static int vega20_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed) { @@ -3022,7 +3038,7 @@ static int vega20_get_fan_speed_percent(struct smu_context *smu, uint32_t current_rpm = 0, percent = 0; PPTable_t *pptable = smu->smu_table.driver_pptable; - ret = smu_get_current_rpm(smu, ¤t_rpm); + ret = vega20_get_fan_speed_rpm(smu, ¤t_rpm); if (ret) return ret; @@ -3217,35 +3233,24 @@ static int vega20_set_watermarks_table(struct smu_context *smu, return 0; } -static const struct smu_temperature_range vega20_thermal_policy[] = -{ - {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000}, - { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000}, -}; - static int vega20_get_thermal_temperature_range(struct smu_context *smu, struct smu_temperature_range *range) { - + struct smu_table_context *table_context = &smu->smu_table; + ATOM_Vega20_POWERPLAYTABLE *powerplay_table = table_context->power_play_table; PPTable_t *pptable = smu->smu_table.driver_pptable; - if (!range) + if (!range || !powerplay_table) return -EINVAL; - memcpy(range, &vega20_thermal_policy[0], sizeof(struct smu_temperature_range)); - - range->max = pptable->TedgeLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->hotspot_crit_max = pptable->ThotspotLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT) * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->mem_crit_max = pptable->ThbmLimit * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM)* - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + /* The unit is temperature */ + range->min = 0; + range->max = powerplay_table->usSoftwareShutdownTemp; + range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE); + range->hotspot_crit_max = pptable->ThotspotLimit; + range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT); + range->mem_crit_max = pptable->ThbmLimit; + range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM); return 0; @@ -3293,6 +3298,7 @@ static const struct pptable_funcs vega20_ppt_funcs = { .is_dpm_running = vega20_is_dpm_running, .set_thermal_fan_table = vega20_set_thermal_fan_table, .get_fan_speed_percent = vega20_get_fan_speed_percent, + .get_fan_speed_rpm = vega20_get_fan_speed_rpm, .set_watermarks_table = vega20_set_watermarks_table, .get_thermal_temperature_range = vega20_get_thermal_temperature_range }; diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index bc19dbd531ef..359030d5d818 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -191,6 +191,7 @@ int bochs_kms_init(struct bochs_device *bochs) bochs->dev->mode_config.fb_base = bochs->fb_base; bochs->dev->mode_config.preferred_depth = 24; bochs->dev->mode_config.prefer_shadow = 0; + bochs->dev->mode_config.prefer_shadow_fbdev = 1; bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; bochs->dev->mode_config.funcs = &bochs_mode_funcs; diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index ee777469293a..e4e22bbae2a7 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -48,6 +48,7 @@ config DRM_DUMB_VGA_DAC config DRM_LVDS_ENCODER tristate "Transparent parallel to LVDS encoder support" depends on OF + select DRM_KMS_HELPER select DRM_PANEL_BRIDGE help Support for transparent parallel to LVDS encoders that don't require @@ -116,9 +117,10 @@ config DRM_THINE_THC63LVD1024 config DRM_TOSHIBA_TC358764 tristate "TC358764 DSI/LVDS bridge" - depends on DRM && DRM_PANEL depends on OF select DRM_MIPI_DSI + select DRM_KMS_HELPER + select DRM_PANEL help Toshiba TC358764 DSI/LVDS bridge driver. diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index 410572f14257..e1dafb0cc5e2 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -254,7 +254,6 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u struct drm_device *dev = client->dev; struct drm_client_buffer *buffer; struct drm_gem_object *obj; - void *vaddr; int ret; buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); @@ -281,6 +280,36 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u buffer->gem = obj; + return buffer; + +err_delete: + drm_client_buffer_delete(buffer); + + return ERR_PTR(ret); +} + +/** + * drm_client_buffer_vmap - Map DRM client buffer into address space + * @buffer: DRM client buffer + * + * This function maps a client buffer into kernel address space. If the + * buffer is already mapped, it returns the mapping's address. + * + * Client buffer mappings are not ref'counted. Each call to + * drm_client_buffer_vmap() should be followed by a call to + * drm_client_buffer_vunmap(); or the client buffer should be mapped + * throughout its lifetime. + * + * Returns: + * The mapped memory's address + */ +void *drm_client_buffer_vmap(struct drm_client_buffer *buffer) +{ + void *vaddr; + + if (buffer->vaddr) + return buffer->vaddr; + /* * FIXME: The dependency on GEM here isn't required, we could * convert the driver handle to a dma-buf instead and use the @@ -289,21 +318,30 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u * fd_install step out of the driver backend hooks, to make that * final step optional for internal users. */ - vaddr = drm_gem_vmap(obj); - if (IS_ERR(vaddr)) { - ret = PTR_ERR(vaddr); - goto err_delete; - } + vaddr = drm_gem_vmap(buffer->gem); + if (IS_ERR(vaddr)) + return vaddr; buffer->vaddr = vaddr; - return buffer; - -err_delete: - drm_client_buffer_delete(buffer); + return vaddr; +} +EXPORT_SYMBOL(drm_client_buffer_vmap); - return ERR_PTR(ret); +/** + * drm_client_buffer_vunmap - Unmap DRM client buffer + * @buffer: DRM client buffer + * + * This function removes a client buffer's memory mapping. Calling this + * function is only required by clients that manage their buffer mappings + * by themselves. + */ +void drm_client_buffer_vunmap(struct drm_client_buffer *buffer) +{ + drm_gem_vunmap(buffer->gem, buffer->vaddr); + buffer->vaddr = NULL; } +EXPORT_SYMBOL(drm_client_buffer_vunmap); static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer) { diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 56d36779d213..c8922b7cac09 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -859,7 +859,7 @@ bool drm_client_rotation(struct drm_mode_set *modeset, unsigned int *rotation) * simple XOR between the two handle the addition nicely. */ cmdline = &connector->cmdline_mode; - if (cmdline->specified) { + if (cmdline->specified && cmdline->rotation_reflection) { unsigned int cmdline_rest, panel_rest; unsigned int cmdline_rot, panel_rot; unsigned int sum_rot, sum_rest; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 1984e5c54d58..a7ba5b4902d6 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -403,6 +403,7 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) struct drm_clip_rect *clip = &helper->dirty_clip; struct drm_clip_rect clip_copy; unsigned long flags; + void *vaddr; spin_lock_irqsave(&helper->dirty_lock, flags); clip_copy = *clip; @@ -412,10 +413,20 @@ static void drm_fb_helper_dirty_work(struct work_struct *work) /* call dirty callback only when it has been really touched */ if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) { + /* Generic fbdev uses a shadow buffer */ - if (helper->buffer) + if (helper->buffer) { + vaddr = drm_client_buffer_vmap(helper->buffer); + if (IS_ERR(vaddr)) + return; drm_fb_helper_dirty_blit_real(helper, &clip_copy); - helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1); + } + if (helper->fb->funcs->dirty) + helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, + &clip_copy, 1); + + if (helper->buffer) + drm_client_buffer_vunmap(helper->buffer); } } @@ -604,6 +615,16 @@ void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper) } EXPORT_SYMBOL(drm_fb_helper_unlink_fbi); +static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper) +{ + struct drm_device *dev = fb_helper->dev; + struct drm_framebuffer *fb = fb_helper->fb; + + return dev->mode_config.prefer_shadow_fbdev || + dev->mode_config.prefer_shadow || + fb->funcs->dirty; +} + static void drm_fb_helper_dirty(struct fb_info *info, u32 x, u32 y, u32 width, u32 height) { @@ -611,7 +632,7 @@ static void drm_fb_helper_dirty(struct fb_info *info, u32 x, u32 y, struct drm_clip_rect *clip = &helper->dirty_clip; unsigned long flags; - if (!helper->fb->funcs->dirty) + if (!drm_fbdev_use_shadow_fb(helper)) return; spin_lock_irqsave(&helper->dirty_lock, flags); @@ -2178,6 +2199,7 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, struct drm_framebuffer *fb; struct fb_info *fbi; u32 format; + void *vaddr; DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n", sizes->surface_width, sizes->surface_height, @@ -2200,16 +2222,10 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, fbi->fbops = &drm_fbdev_fb_ops; fbi->screen_size = fb->height * fb->pitches[0]; fbi->fix.smem_len = fbi->screen_size; - fbi->screen_buffer = buffer->vaddr; - /* Shamelessly leak the physical address to user-space */ -#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) - if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0) - fbi->fix.smem_start = - page_to_phys(virt_to_page(fbi->screen_buffer)); -#endif + drm_fb_helper_fill_info(fbi, fb_helper, sizes); - if (fb->funcs->dirty) { + if (drm_fbdev_use_shadow_fb(fb_helper)) { struct fb_ops *fbops; void *shadow; @@ -2231,6 +2247,19 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper, fbi->fbdefio = &drm_fbdev_defio; fb_deferred_io_init(fbi); + } else { + /* buffer is mapped for HW framebuffer */ + vaddr = drm_client_buffer_vmap(fb_helper->buffer); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + fbi->screen_buffer = vaddr; + /* Shamelessly leak the physical address to user-space */ +#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) + if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0) + fbi->fix.smem_start = + page_to_phys(virt_to_page(fbi->screen_buffer)); +#endif } return 0; diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 0b72468e8131..57564318ceea 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -835,7 +835,7 @@ static int atomic_remove_fb(struct drm_framebuffer *fb) struct drm_device *dev = fb->dev; struct drm_atomic_state *state; struct drm_plane *plane; - struct drm_connector *conn; + struct drm_connector *conn __maybe_unused; struct drm_connector_state *conn_state; int i, ret; unsigned plane_mask; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 74a5739df506..80fcd5dc1558 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1686,7 +1686,7 @@ static int drm_mode_parse_cmdline_options(char *str, size_t len, * * Additionals options can be provided following the mode, using a comma to * separate each option. Valid options can be found in - * Documentation/fb/modedb.txt. + * Documentation/fb/modedb.rst. * * The intermediate drm_cmdline_mode structure is required to store additional * options from the command line modline like the force-enable/disable flag. diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 60ce4a8ad9e1..6f7d3b3b3628 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -2,6 +2,7 @@ config DRM_EXYNOS tristate "DRM Support for Samsung SoC EXYNOS Series" depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST) + depends on MMU select DRM_KMS_HELPER select VIDEOMODE_HELPERS select SND_SOC_HDMI_CODEC if SND_SOC diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index a594ab7be2c0..164d914cbe9a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -44,7 +44,7 @@ static unsigned int fimc_mask = 0xc; module_param_named(fimc_devs, fimc_mask, uint, 0644); MODULE_PARM_DESC(fimc_devs, "Alias mask for assigning FIMC devices to Exynos DRM"); -#define get_fimc_context(dev) platform_get_drvdata(to_platform_device(dev)) +#define get_fimc_context(dev) dev_get_drvdata(dev) enum { FIMC_CLK_LCLK, diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 50904eee96f7..2a3382d43bc9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -267,7 +267,7 @@ static inline void g2d_hw_reset(struct g2d_data *g2d) static int g2d_init_cmdlist(struct g2d_data *g2d) { struct device *dev = g2d->dev; - struct g2d_cmdlist_node *node = g2d->cmdlist_node; + struct g2d_cmdlist_node *node; int nr; int ret; struct g2d_buf_info *buf_info; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 1e4b21c49a06..1c524db9570f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -58,7 +58,7 @@ #define GSC_COEF_DEPTH 3 #define GSC_AUTOSUSPEND_DELAY 2000 -#define get_gsc_context(dev) platform_get_drvdata(to_platform_device(dev)) +#define get_gsc_context(dev) dev_get_drvdata(dev) #define gsc_read(offset) readl(ctx->regs + (offset)) #define gsc_write(cfg, offset) writel(cfg, ctx->regs + (offset)) diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index 9af096479e1c..b24ba948b725 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -94,12 +94,12 @@ static inline int scaler_reset(struct scaler_context *scaler) scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG); do { cpu_relax(); - } while (retry > 1 && + } while (--retry > 1 && scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET); do { cpu_relax(); scaler_write(1, SCALER_INT_EN); - } while (retry > 0 && scaler_read(SCALER_INT_EN) != 1); + } while (--retry > 0 && scaler_read(SCALER_INT_EN) != 1); return retry ? 0 : -EIO; } diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 91355c2ea8a5..8cace65f50ce 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -16,7 +16,6 @@ subdir-ccflags-y := -Wall -Wextra subdir-ccflags-y += $(call cc-disable-warning, unused-parameter) subdir-ccflags-y += $(call cc-disable-warning, type-limits) subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers) -subdir-ccflags-y += $(call cc-disable-warning, implicit-fallthrough) subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) # clang warnings subdir-ccflags-y += $(call cc-disable-warning, sign-compare) diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index c4710889cb32..3ef4e9f573cf 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -765,7 +765,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) } if (bdb->version >= 226) { - u32 wakeup_time = psr_table->psr2_tp2_tp3_wakeup_time; + u32 wakeup_time = psr->psr2_tp2_tp3_wakeup_time; wakeup_time = (wakeup_time >> (2 * panel_type)) & 0x3; switch (wakeup_time) { diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 753ac3165061..7b908e10d32e 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -178,6 +178,8 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv) clpchgroup = (sa->deburst * deinterleave / num_channels) << i; bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; + bi->num_qgv_points = qi.num_points; + for (j = 0; j < qi.num_points; j++) { const struct intel_qgv_point *sp = &qi.points[j]; int ct, bw; @@ -195,7 +197,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv) bi->deratedbw[j] = min(maxdebw, bw * 9 / 10); /* 90% */ - DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%d\n", + DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%u\n", i, j, bi->num_planes, bi->deratedbw[j]); } @@ -211,14 +213,17 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, { int i; - /* Did we initialize the bw limits successfully? */ - if (dev_priv->max_bw[0].num_planes == 0) - return UINT_MAX; - for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) { const struct intel_bw_info *bi = &dev_priv->max_bw[i]; + /* + * Pcode will not expose all QGV points when + * SAGV is forced to off/min/med/max. + */ + if (qgv_point >= bi->num_qgv_points) + return UINT_MAX; + if (num_planes >= bi->num_planes) return bi->deratedbw[qgv_point]; } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 8993ab283562..0d19bbd08122 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2240,6 +2240,17 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) min_cdclk = max(2 * 96000, min_cdclk); /* + * "For DP audio configuration, cdclk frequency shall be set to + * meet the following requirements: + * DP Link Frequency(MHz) | Cdclk frequency(MHz) + * 270 | 320 or higher + * 162 | 200 or higher" + */ + if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && + intel_crtc_has_dp_encoder(crtc_state) && crtc_state->has_audio) + min_cdclk = max(crtc_state->port_clock, min_cdclk); + + /* * On Valleyview some DSI panels lose (v|h)sync when the clock is lower * than 320000KHz. */ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 8592a7d422de..592b92782fab 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1839,7 +1839,7 @@ static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state) /* FIXME: assert CPU port conditions for SNB+ */ } - trace_intel_pipe_enable(dev_priv, pipe); + trace_intel_pipe_enable(crtc); reg = PIPECONF(cpu_transcoder); val = I915_READ(reg); @@ -1880,7 +1880,7 @@ static void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state) */ assert_planes_disabled(crtc); - trace_intel_pipe_disable(dev_priv, pipe); + trace_intel_pipe_disable(crtc); reg = PIPECONF(cpu_transcoder); val = I915_READ(reg); @@ -12042,7 +12042,7 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state) case INTEL_OUTPUT_DDI: if (WARN_ON(!HAS_DDI(to_i915(dev)))) break; - /* else: fall through */ + /* else, fall through */ case INTEL_OUTPUT_DP: case INTEL_OUTPUT_HDMI: case INTEL_OUTPUT_EDP: diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index c93ad512014c..2d1939db108f 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -438,16 +438,23 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv, #define ICL_AUX_PW_TO_CH(pw_idx) \ ((pw_idx) - ICL_PW_CTL_IDX_AUX_A + AUX_CH_A) +#define ICL_TBT_AUX_PW_TO_CH(pw_idx) \ + ((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C) + static void icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - enum aux_ch aux_ch = ICL_AUX_PW_TO_CH(power_well->desc->hsw.idx); + int pw_idx = power_well->desc->hsw.idx; + bool is_tbt = power_well->desc->hsw.is_tc_tbt; + enum aux_ch aux_ch; u32 val; + aux_ch = is_tbt ? ICL_TBT_AUX_PW_TO_CH(pw_idx) : + ICL_AUX_PW_TO_CH(pw_idx); val = I915_READ(DP_AUX_CH_CTL(aux_ch)); val &= ~DP_AUX_CH_CTL_TBT_IO; - if (power_well->desc->hsw.is_tc_tbt) + if (is_tbt) val |= DP_AUX_CH_CTL_TBT_IO; I915_WRITE(DP_AUX_CH_CTL(aux_ch), val); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 4336df46fe78..d0fc34826771 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -231,6 +231,7 @@ static int intel_dp_get_fia_supported_lane_count(struct intel_dp *intel_dp) switch (lane_info) { default: MISSING_CASE(lane_info); + /* fall through */ case 1: case 2: case 4: diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index 2f4894e9a03d..5ddbe71ab423 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -478,13 +478,13 @@ struct psr_table { /* TP wake up time in multiple of 100 */ u16 tp1_wakeup_time; u16 tp2_tp3_wakeup_time; - - /* PSR2 TP2/TP3 wakeup time for 16 panels */ - u32 psr2_tp2_tp3_wakeup_time; } __packed; struct bdb_psr { struct psr_table psr_table[16]; + + /* PSR2 TP2/TP3 wakeup time for 16 panels */ + u32 psr2_tp2_tp3_wakeup_time; } __packed; /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 391621ee3cbb..39a661927d8e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -341,7 +341,7 @@ err: */ if (!i915_terminally_wedged(i915)) return VM_FAULT_SIGBUS; - /* else: fall through */ + /* else, fall through */ case -EAGAIN: /* * EAGAIN means the gpu is hung and we'll wait for the error diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index b36ad269f4ea..65eb430cedba 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -268,7 +268,7 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, switch (type) { default: MISSING_CASE(type); - /* fallthrough to use PAGE_KERNEL anyway */ + /* fallthrough - to use PAGE_KERNEL anyway */ case I915_MAP_WB: pgprot = PAGE_KERNEL; break; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 05011d4a3b88..914b5d4112bb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -253,14 +253,15 @@ void i915_gem_resume(struct drm_i915_private *i915) i915_gem_restore_gtt_mappings(i915); i915_gem_restore_fences(i915); + if (i915_gem_init_hw(i915)) + goto err_wedged; + /* * As we didn't flush the kernel context before suspend, we cannot * guarantee that the context image is complete. So let's just reset * it and start again. */ - intel_gt_resume(i915); - - if (i915_gem_init_hw(i915)) + if (intel_gt_resume(i915)) goto err_wedged; intel_uc_resume(i915); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 528b61678334..2caa594322bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -664,7 +664,15 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, for_each_sgt_page(page, sgt_iter, pages) { if (obj->mm.dirty) - set_page_dirty(page); + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + */ + set_page_dirty_lock(page); mark_page_accessed(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 2c454f227c2e..23120901c55f 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -126,6 +126,7 @@ static void intel_context_retire(struct i915_active *active) if (ce->state) __context_unpin_state(ce->state); + intel_ring_unpin(ce->ring); intel_context_put(ce); } @@ -160,27 +161,35 @@ int intel_context_active_acquire(struct intel_context *ce, unsigned long flags) intel_context_get(ce); + err = intel_ring_pin(ce->ring); + if (err) + goto err_put; + if (!ce->state) return 0; err = __context_pin_state(ce->state, flags); - if (err) { - i915_active_cancel(&ce->active); - intel_context_put(ce); - return err; - } + if (err) + goto err_ring; /* Preallocate tracking nodes */ if (!i915_gem_context_is_kernel(ce->gem_context)) { err = i915_active_acquire_preallocate_barrier(&ce->active, ce->engine); - if (err) { - i915_active_release(&ce->active); - return err; - } + if (err) + goto err_state; } return 0; + +err_state: + __context_unpin_state(ce->state); +err_ring: + intel_ring_unpin(ce->ring); +err_put: + intel_context_put(ce); + i915_active_cancel(&ce->active); + return err; } void intel_context_active_release(struct intel_context *ce) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 7fd33e81c2d9..f25632c9b292 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -969,9 +969,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type) u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv) { const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; + unsigned int slice = fls(sseu->slice_mask) - 1; + unsigned int subslice; u32 mcr_s_ss_select; - u32 slice = fls(sseu->slice_mask); - u32 subslice = fls(sseu->subslice_mask[slice]); + + GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask)); + subslice = fls(sseu->subslice_mask[slice]); + GEM_BUG_ON(!subslice); + subslice--; if (IS_GEN(dev_priv, 10)) mcr_s_ss_select = GEN8_MCR_SLICE(slice) | @@ -1471,6 +1476,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; + unsigned long flags; if (header) { va_list ap; @@ -1490,10 +1496,9 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_engine_count(error, engine), i915_reset_count(error)); - rcu_read_lock(); - drm_printf(m, "\tRequests:\n"); + spin_lock_irqsave(&engine->active.lock, flags); rq = intel_engine_find_active_request(engine); if (rq) { print_request(m, rq, "\t\tactive "); @@ -1513,8 +1518,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, print_request_ring(m, rq); } - - rcu_read_unlock(); + spin_unlock_irqrestore(&engine->active.lock, flags); wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm); if (wakeref) { @@ -1672,7 +1676,6 @@ struct i915_request * intel_engine_find_active_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; - unsigned long flags; /* * We are called by the error capture, reset and to dump engine @@ -1685,7 +1688,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) * At all other times, we must assume the GPU is still running, but * we only care about the snapshot of this moment. */ - spin_lock_irqsave(&engine->active.lock, flags); + lockdep_assert_held(&engine->active.lock); list_for_each_entry(request, &engine->active.requests, sched.link) { if (i915_request_completed(request)) continue; @@ -1700,7 +1703,6 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) active = request; break; } - spin_unlock_irqrestore(&engine->active.lock, flags); return active; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 2ce00d3dc42a..ae5b6baf6dff 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -142,27 +142,3 @@ void intel_engine_init__pm(struct intel_engine_cs *engine) { intel_wakeref_init(&engine->wakeref); } - -int intel_engines_resume(struct drm_i915_private *i915) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - int err = 0; - - intel_gt_pm_get(i915); - for_each_engine(engine, i915, id) { - intel_engine_pm_get(engine); - engine->serial++; /* kernel context lost */ - err = engine->resume(engine); - intel_engine_pm_put(engine); - if (err) { - dev_err(i915->drm.dev, - "Failed to restart %s (%d)\n", - engine->name, err); - break; - } - } - intel_gt_pm_put(i915); - - return err; -} diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index b326cd993d60..a11c893f64c6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -7,16 +7,22 @@ #ifndef INTEL_ENGINE_PM_H #define INTEL_ENGINE_PM_H +#include "intel_engine_types.h" +#include "intel_wakeref.h" + struct drm_i915_private; -struct intel_engine_cs; void intel_engine_pm_get(struct intel_engine_cs *engine); void intel_engine_pm_put(struct intel_engine_cs *engine); +static inline bool +intel_engine_pm_get_if_awake(struct intel_engine_cs *engine) +{ + return intel_wakeref_get_if_active(&engine->wakeref); +} + void intel_engine_park(struct intel_engine_cs *engine); void intel_engine_init__pm(struct intel_engine_cs *engine); -int intel_engines_resume(struct drm_i915_private *i915); - #endif /* INTEL_ENGINE_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 868b220214f8..43e975a26016 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -70,6 +70,18 @@ struct intel_ring { struct list_head request_list; struct list_head active_link; + /* + * As we have two types of rings, one global to the engine used + * by ringbuffer submission and those that are exclusive to a + * context used by execlists, we have to play safe and allow + * atomic updates to the pin_count. However, the actual pinning + * of the context is either done during initialisation for + * ringbuffer submission or serialised as part of the context + * pinning for execlists, and so we do not need a mutex ourselves + * to serialise intel_ring_pin/intel_ring_unpin. + */ + atomic_t pin_count; + u32 head; u32 tail; u32 emit; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 7b5967751762..9f8f7f54191f 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -5,6 +5,7 @@ */ #include "i915_drv.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_pm.h" #include "intel_wakeref.h" @@ -118,10 +119,11 @@ void intel_gt_sanitize(struct drm_i915_private *i915, bool force) intel_engine_reset(engine, false); } -void intel_gt_resume(struct drm_i915_private *i915) +int intel_gt_resume(struct drm_i915_private *i915) { struct intel_engine_cs *engine; enum intel_engine_id id; + int err = 0; /* * After resume, we may need to poke into the pinned kernel @@ -129,9 +131,12 @@ void intel_gt_resume(struct drm_i915_private *i915) * Only the kernel contexts should remain pinned over suspend, * allowing us to fixup the user contexts on their first pin. */ + intel_gt_pm_get(i915); for_each_engine(engine, i915, id) { struct intel_context *ce; + intel_engine_pm_get(engine); + ce = engine->kernel_context; if (ce) ce->ops->reset(ce); @@ -139,5 +144,19 @@ void intel_gt_resume(struct drm_i915_private *i915) ce = engine->preempt_context; if (ce) ce->ops->reset(ce); + + engine->serial++; /* kernel context lost */ + err = engine->resume(engine); + + intel_engine_pm_put(engine); + if (err) { + dev_err(i915->drm.dev, + "Failed to restart %s (%d)\n", + engine->name, err); + break; + } } + intel_gt_pm_put(i915); + + return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index 7dd1130a19a4..53f342b20181 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -22,6 +22,6 @@ void intel_gt_pm_put(struct drm_i915_private *i915); void intel_gt_pm_init(struct drm_i915_private *i915); void intel_gt_sanitize(struct drm_i915_private *i915, bool force); -void intel_gt_resume(struct drm_i915_private *i915); +int intel_gt_resume(struct drm_i915_private *i915); #endif /* INTEL_GT_PM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index b42b5f158295..82b7ace62d97 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1414,6 +1414,7 @@ static void execlists_context_destroy(struct kref *kref) { struct intel_context *ce = container_of(kref, typeof(*ce), ref); + GEM_BUG_ON(!i915_active_is_idle(&ce->active)); GEM_BUG_ON(intel_context_is_pinned(ce)); if (ce->state) @@ -1426,7 +1427,6 @@ static void execlists_context_unpin(struct intel_context *ce) { i915_gem_context_unpin_hw_id(ce->gem_context); i915_gem_object_unpin_map(ce->state->obj); - intel_ring_unpin(ce->ring); } static void @@ -1478,13 +1478,9 @@ __execlists_context_pin(struct intel_context *ce, goto unpin_active; } - ret = intel_ring_pin(ce->ring); - if (ret) - goto unpin_map; - ret = i915_gem_context_pin_hw_id(ce->gem_context); if (ret) - goto unpin_ring; + goto unpin_map; ce->lrc_desc = lrc_descriptor(ce, engine); ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; @@ -1492,8 +1488,6 @@ __execlists_context_pin(struct intel_context *ce, return 0; -unpin_ring: - intel_ring_unpin(ce->ring); unpin_map: i915_gem_object_unpin_map(ce->state->obj); unpin_active: diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 4c478b38e420..3f907701ef4d 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -687,7 +687,6 @@ static void reset_prepare_engine(struct intel_engine_cs *engine) * written to the powercontext is undefined and so we may lose * GPU state upon resume, i.e. fail to restart after a reset. */ - intel_engine_pm_get(engine); intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL); engine->reset.prepare(engine); } @@ -718,16 +717,21 @@ static void revoke_mmaps(struct drm_i915_private *i915) } } -static void reset_prepare(struct drm_i915_private *i915) +static intel_engine_mask_t reset_prepare(struct drm_i915_private *i915) { struct intel_engine_cs *engine; + intel_engine_mask_t awake = 0; enum intel_engine_id id; - intel_gt_pm_get(i915); - for_each_engine(engine, i915, id) + for_each_engine(engine, i915, id) { + if (intel_engine_pm_get_if_awake(engine)) + awake |= engine->mask; reset_prepare_engine(engine); + } intel_uc_reset_prepare(i915); + + return awake; } static void gt_revoke(struct drm_i915_private *i915) @@ -761,20 +765,22 @@ static int gt_reset(struct drm_i915_private *i915, static void reset_finish_engine(struct intel_engine_cs *engine) { engine->reset.finish(engine); - intel_engine_pm_put(engine); intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL); + + intel_engine_signal_breadcrumbs(engine); } -static void reset_finish(struct drm_i915_private *i915) +static void reset_finish(struct drm_i915_private *i915, + intel_engine_mask_t awake) { struct intel_engine_cs *engine; enum intel_engine_id id; for_each_engine(engine, i915, id) { reset_finish_engine(engine); - intel_engine_signal_breadcrumbs(engine); + if (awake & engine->mask) + intel_engine_pm_put(engine); } - intel_gt_pm_put(i915); } static void nop_submit_request(struct i915_request *request) @@ -798,6 +804,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) { struct i915_gpu_error *error = &i915->gpu_error; struct intel_engine_cs *engine; + intel_engine_mask_t awake; enum intel_engine_id id; if (test_bit(I915_WEDGED, &error->flags)) @@ -817,7 +824,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - reset_prepare(i915); + awake = reset_prepare(i915); /* Even if the GPU reset fails, it should still stop the engines */ if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) @@ -841,7 +848,7 @@ static void __i915_gem_set_wedged(struct drm_i915_private *i915) for_each_engine(engine, i915, id) engine->cancel_requests(engine); - reset_finish(i915); + reset_finish(i915, awake); GEM_TRACE("end\n"); } @@ -951,6 +958,21 @@ static int do_reset(struct drm_i915_private *i915, return gt_reset(i915, stalled_mask); } +static int resume(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + int ret; + + for_each_engine(engine, i915, id) { + ret = engine->resume(engine); + if (ret) + return ret; + } + + return 0; +} + /** * i915_reset - reset chip after a hang * @i915: #drm_i915_private to reset @@ -973,6 +995,7 @@ void i915_reset(struct drm_i915_private *i915, const char *reason) { struct i915_gpu_error *error = &i915->gpu_error; + intel_engine_mask_t awake; int ret; GEM_TRACE("flags=%lx\n", error->flags); @@ -989,7 +1012,7 @@ void i915_reset(struct drm_i915_private *i915, dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason); error->reset_count++; - reset_prepare(i915); + awake = reset_prepare(i915); if (!intel_has_gpu_reset(i915)) { if (i915_modparams.reset) @@ -1024,13 +1047,17 @@ void i915_reset(struct drm_i915_private *i915, if (ret) { DRM_ERROR("Failed to initialise HW following reset (%d)\n", ret); - goto error; + goto taint; } + ret = resume(i915); + if (ret) + goto taint; + i915_queue_hangcheck(i915); finish: - reset_finish(i915); + reset_finish(i915, awake); unlock: mutex_unlock(&error->wedge_mutex); return; @@ -1081,7 +1108,7 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg) GEM_TRACE("%s flags=%lx\n", engine->name, error->flags); GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags)); - if (!intel_wakeref_active(&engine->wakeref)) + if (!intel_engine_pm_get_if_awake(engine)) return 0; reset_prepare_engine(engine); @@ -1116,12 +1143,11 @@ int i915_reset_engine(struct intel_engine_cs *engine, const char *msg) * process to program RING_MODE, HWSP and re-enable submission. */ ret = engine->resume(engine); - if (ret) - goto out; out: intel_engine_cancel_stop_cs(engine); reset_finish_engine(engine); + intel_engine_pm_put(engine); return ret; } diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c index c6023bc9452d..12010e798868 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -1149,16 +1149,16 @@ i915_emit_bb_start(struct i915_request *rq, int intel_ring_pin(struct intel_ring *ring) { struct i915_vma *vma = ring->vma; - enum i915_map_type map = i915_coherent_map_type(vma->vm->i915); unsigned int flags; void *addr; int ret; - GEM_BUG_ON(ring->vaddr); + if (atomic_fetch_inc(&ring->pin_count)) + return 0; ret = i915_timeline_pin(ring->timeline); if (ret) - return ret; + goto err_unpin; flags = PIN_GLOBAL; @@ -1172,26 +1172,31 @@ int intel_ring_pin(struct intel_ring *ring) ret = i915_vma_pin(vma, 0, 0, flags); if (unlikely(ret)) - goto unpin_timeline; + goto err_timeline; if (i915_vma_is_map_and_fenceable(vma)) addr = (void __force *)i915_vma_pin_iomap(vma); else - addr = i915_gem_object_pin_map(vma->obj, map); + addr = i915_gem_object_pin_map(vma->obj, + i915_coherent_map_type(vma->vm->i915)); if (IS_ERR(addr)) { ret = PTR_ERR(addr); - goto unpin_ring; + goto err_ring; } vma->obj->pin_global++; + GEM_BUG_ON(ring->vaddr); ring->vaddr = addr; + return 0; -unpin_ring: +err_ring: i915_vma_unpin(vma); -unpin_timeline: +err_timeline: i915_timeline_unpin(ring->timeline); +err_unpin: + atomic_dec(&ring->pin_count); return ret; } @@ -1207,16 +1212,19 @@ void intel_ring_reset(struct intel_ring *ring, u32 tail) void intel_ring_unpin(struct intel_ring *ring) { - GEM_BUG_ON(!ring->vma); - GEM_BUG_ON(!ring->vaddr); + if (!atomic_dec_and_test(&ring->pin_count)) + return; /* Discard any unused bytes beyond that submitted to hw. */ intel_ring_reset(ring, ring->tail); + GEM_BUG_ON(!ring->vma); if (i915_vma_is_map_and_fenceable(ring->vma)) i915_vma_unpin_iomap(ring->vma); else i915_gem_object_unpin_map(ring->vma->obj); + + GEM_BUG_ON(!ring->vaddr); ring->vaddr = NULL; ring->vma->obj->pin_global--; @@ -2081,10 +2089,11 @@ static void ring_destroy(struct intel_engine_cs *engine) WARN_ON(INTEL_GEN(dev_priv) > 2 && (ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0); + intel_engine_cleanup_common(engine); + intel_ring_unpin(engine->buffer); intel_ring_put(engine->buffer); - intel_engine_cleanup_common(engine); kfree(engine); } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 15e90fd2cfdc..98dfb086320f 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1098,10 +1098,25 @@ static void glk_whitelist_build(struct intel_engine_cs *engine) static void cfl_whitelist_build(struct intel_engine_cs *engine) { + struct i915_wa_list *w = &engine->whitelist; + if (engine->class != RENDER_CLASS) return; - gen9_whitelist_build(&engine->whitelist); + gen9_whitelist_build(w); + + /* + * WaAllowPMDepthAndInvocationCountAccessFromUMD:cfl,whl,cml,aml + * + * This covers 4 register which are next to one another : + * - PS_INVOCATION_COUNT + * - PS_INVOCATION_COUNT_UDW + * - PS_DEPTH_COUNT + * - PS_DEPTH_COUNT_UDW + */ + whitelist_reg_ext(w, PS_INVOCATION_COUNT, + RING_FORCE_TO_NONPRIV_RD | + RING_FORCE_TO_NONPRIV_RANGE_4); } static void cnl_whitelist_build(struct intel_engine_cs *engine) @@ -1129,6 +1144,19 @@ static void icl_whitelist_build(struct intel_engine_cs *engine) /* WaEnableStateCacheRedirectToCS:icl */ whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); + + /* + * WaAllowPMDepthAndInvocationCountAccessFromUMD:icl + * + * This covers 4 register which are next to one another : + * - PS_INVOCATION_COUNT + * - PS_INVOCATION_COUNT_UDW + * - PS_DEPTH_COUNT + * - PS_DEPTH_COUNT_UDW + */ + whitelist_reg_ext(w, PS_INVOCATION_COUNT, + RING_FORCE_TO_NONPRIV_RD | + RING_FORCE_TO_NONPRIV_RANGE_4); break; case VIDEO_DECODE_CLASS: @@ -1258,8 +1286,12 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) wa_write_or(wal, GEN7_SARCHKMD, - GEN7_DISABLE_DEMAND_PREFETCH | - GEN7_DISABLE_SAMPLER_PREFETCH); + GEN7_DISABLE_DEMAND_PREFETCH); + + /* Wa_1606682166:icl */ + wa_write_or(wal, + GEN7_SARCHKMD, + GEN7_DISABLE_SAMPLER_PREFETCH); } if (IS_GEN_RANGE(i915, 9, 11)) { diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 086801b51441..486c6953dcb1 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -66,6 +66,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) ring->base.effective_size = sz; ring->base.vaddr = (void *)(ring + 1); ring->base.timeline = &ring->timeline; + atomic_set(&ring->base.pin_count, 1); INIT_LIST_HEAD(&ring->base.request_list); intel_ring_update_space(&ring->base); diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 89da9e7cc1ba..b5c590c9ccba 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -71,13 +71,16 @@ static int igt_atomic_reset(void *arg) goto unlock; for (p = igt_atomic_phases; p->name; p++) { + intel_engine_mask_t awake; + GEM_TRACE("intel_gpu_reset under %s\n", p->name); + awake = reset_prepare(i915); p->critical_section_begin(); reset_prepare(i915); err = intel_gpu_reset(i915, ALL_ENGINES); - reset_finish(i915); p->critical_section_end(); + reset_finish(i915, awake); if (err) { pr_err("intel_gpu_reset failed under %s\n", p->name); diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 9eaf030affd0..44becd9538be 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -925,7 +925,12 @@ check_whitelisted_registers(struct intel_engine_cs *engine, err = 0; for (i = 0; i < engine->whitelist.count; i++) { - if (!fn(engine, a[i], b[i], engine->whitelist.list[i].reg)) + const struct i915_wa *wa = &engine->whitelist.list[i]; + + if (i915_mmio_reg_offset(wa->reg) & RING_FORCE_TO_NONPRIV_RD) + continue; + + if (!fn(engine, a[i], b[i], wa->reg)) err = -EINVAL; } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 6ea88270c818..b09dc315e2da 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2674,11 +2674,6 @@ static int scan_workload(struct intel_vgpu_workload *workload) gma_head == gma_tail) return 0; - if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { - ret = -EINVAL; - goto out; - } - ret = ip_gma_set(&s, gma_head); if (ret) goto out; @@ -2724,11 +2719,6 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) s.workload = workload; s.is_ctx_wa = true; - if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { - ret = -EINVAL; - goto out; - } - ret = ip_gma_set(&s, gma_head); if (ret) goto out; diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 65e847392aea..8bb292b01271 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -245,7 +245,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, plane->hw_format = fmt; plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); @@ -368,7 +368,7 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu, alpha_plane, alpha_force); plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); @@ -472,7 +472,7 @@ int intel_vgpu_decode_sprite_plane(struct intel_vgpu *vgpu, plane->drm_format = drm_format; plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK; - if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0)) + if (!vgpu_gmadr_is_valid(vgpu, plane->base)) return -EINVAL; plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 53115bdae12b..4b04af569c05 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2141,11 +2141,20 @@ static int emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm; const struct intel_gvt_device_info *info = &vgpu->gvt->device_info; unsigned long index = off >> info->gtt_entry_size_shift; + unsigned long gma; struct intel_gvt_gtt_entry e; if (bytes != 4 && bytes != 8) return -EINVAL; + gma = index << I915_GTT_PAGE_SHIFT; + if (!intel_gvt_ggtt_validate_range(vgpu, + gma, 1 << I915_GTT_PAGE_SHIFT)) { + gvt_dbg_mm("read invalid ggtt at 0x%lx\n", gma); + memset(p_data, 0, bytes); + return 0; + } + ggtt_get_guest_entry(ggtt_mm, &e, index); memcpy(p_data, (void *)&e.val64 + (off & (info->gtt_entry_size - 1)), bytes); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 144301b778df..23aa3e50cbf8 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1911,6 +1911,18 @@ static int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn, ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size); if (ret) goto err_unmap; + } else if (entry->size != size) { + /* the same gfn with different size: unmap and re-map */ + gvt_dma_unmap_page(vgpu, gfn, entry->dma_addr, entry->size); + __gvt_cache_remove_entry(vgpu, entry); + + ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size); + if (ret) + goto err_unlock; + + ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size); + if (ret) + goto err_unmap; } else { kref_get(&entry->ref); *dma_addr = entry->dma_addr; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 2144fb46d0e1..9f3fd7d96a69 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -364,16 +364,13 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) wa_ctx->indirect_ctx.shadow_va = NULL; } -static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, - struct i915_gem_context *ctx) +static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, + struct i915_gem_context *ctx) { struct intel_vgpu_mm *mm = workload->shadow_mm; struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm); int i = 0; - if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed) - return -EINVAL; - if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) { px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0]; } else { @@ -384,8 +381,6 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } - - return 0; } static int @@ -614,6 +609,8 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) static int prepare_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; + struct intel_vgpu_submission *s = &vgpu->submission; + int ring = workload->ring_id; int ret = 0; ret = intel_vgpu_pin_mm(workload->shadow_mm); @@ -622,8 +619,16 @@ static int prepare_workload(struct intel_vgpu_workload *workload) return ret; } + if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT || + !workload->shadow_mm->ppgtt_mm.shadowed) { + gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); + return -EINVAL; + } + update_shadow_pdps(workload); + set_context_ppgtt_from_shadow(workload, s->shadow[ring]->gem_context); + ret = intel_vgpu_sync_oos_pages(workload->vgpu); if (ret) { gvt_vgpu_err("fail to vgpu sync oos pages\n"); @@ -674,7 +679,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - struct intel_vgpu_submission *s = &vgpu->submission; struct i915_request *rq; int ring_id = workload->ring_id; int ret; @@ -685,13 +689,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) mutex_lock(&vgpu->vgpu_lock); mutex_lock(&dev_priv->drm.struct_mutex); - ret = set_context_ppgtt_from_shadow(workload, - s->shadow[ring_id]->gem_context); - if (ret < 0) { - gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); - goto err_req; - } - ret = intel_gvt_workload_req_alloc(workload); if (ret) goto err_req; @@ -990,6 +987,7 @@ static int workload_thread(void *priv) int ret; bool need_force_wake = (INTEL_GEN(gvt->dev_priv) >= 9); DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct intel_runtime_pm *rpm = &gvt->dev_priv->runtime_pm; kfree(p); @@ -1013,6 +1011,8 @@ static int workload_thread(void *priv) workload->ring_id, workload, workload->vgpu->id); + intel_runtime_pm_get(rpm); + gvt_dbg_sched("ring id %d will dispatch workload %p\n", workload->ring_id, workload); @@ -1042,6 +1042,7 @@ complete: intel_uncore_forcewake_put(&gvt->dev_priv->uncore, FORCEWAKE_ALL); + intel_runtime_pm_put_unchecked(rpm); if (ret && (vgpu_is_vm_unhealthy(ret))) enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); } @@ -1492,6 +1493,12 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, intel_gvt_hypervisor_read_gpa(vgpu, ring_context_gpa + RING_CTX_OFF(ctx_ctrl.val), &ctx_ctl, 4); + if (!intel_gvt_ggtt_validate_range(vgpu, start, + _RING_CTL_BUF_SIZE(ctl))) { + gvt_vgpu_err("context contain invalid rb at: 0x%x\n", start); + return ERR_PTR(-EINVAL); + } + workload = alloc_workload(vgpu); if (IS_ERR(workload)) return workload; @@ -1516,9 +1523,31 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, workload->wa_ctx.indirect_ctx.size = (indirect_ctx & INDIRECT_CTX_SIZE_MASK) * CACHELINE_BYTES; + + if (workload->wa_ctx.indirect_ctx.size != 0) { + if (!intel_gvt_ggtt_validate_range(vgpu, + workload->wa_ctx.indirect_ctx.guest_gma, + workload->wa_ctx.indirect_ctx.size)) { + kmem_cache_free(s->workloads, workload); + gvt_vgpu_err("invalid wa_ctx at: 0x%lx\n", + workload->wa_ctx.indirect_ctx.guest_gma); + return ERR_PTR(-EINVAL); + } + } + workload->wa_ctx.per_ctx.guest_gma = per_ctx & PER_CTX_ADDR_MASK; workload->wa_ctx.per_ctx.valid = per_ctx & 1; + if (workload->wa_ctx.per_ctx.valid) { + if (!intel_gvt_ggtt_validate_range(vgpu, + workload->wa_ctx.per_ctx.guest_gma, + CACHELINE_BYTES)) { + kmem_cache_free(s->workloads, workload); + gvt_vgpu_err("invalid per_ctx at: 0x%lx\n", + workload->wa_ctx.per_ctx.guest_gma); + return ERR_PTR(-EINVAL); + } + } } gvt_dbg_el("workload %p ring id %d head %x tail %x start %x ctl %x\n", diff --git a/drivers/gpu/drm/i915/gvt/trace_points.c b/drivers/gpu/drm/i915/gvt/trace_points.c index a3deed692b9c..fe552e877e09 100644 --- a/drivers/gpu/drm/i915/gvt/trace_points.c +++ b/drivers/gpu/drm/i915/gvt/trace_points.c @@ -28,8 +28,6 @@ * */ -#include "trace.h" - #ifndef __CHECKER__ #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index bc909ec5d9c3..fe7a6ec2c199 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1674,8 +1674,9 @@ struct drm_i915_private { } dram_info; struct intel_bw_info { - int num_planes; - int deratedbw[3]; + unsigned int deratedbw[3]; /* for each QGV point */ + u8 num_qgv_points; + u8 num_planes; } max_bw[6]; struct drm_private_obj bw_obj; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 190ad54fb072..8a659d3d7435 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -46,7 +46,6 @@ #include "gem/i915_gem_ioctls.h" #include "gem/i915_gem_pm.h" #include "gem/i915_gemfs.h" -#include "gt/intel_engine_pm.h" #include "gt/intel_gt_pm.h" #include "gt/intel_mocs.h" #include "gt/intel_reset.h" @@ -1307,21 +1306,13 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) intel_mocs_init_l3cc_table(dev_priv); - /* Only when the HW is re-initialised, can we replay the requests */ - ret = intel_engines_resume(dev_priv); - if (ret) - goto cleanup_uc; - intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); intel_engines_set_scheduler_caps(dev_priv); return 0; -cleanup_uc: - intel_uc_fini_hw(dev_priv); out: intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); - return ret; } @@ -1580,6 +1571,11 @@ int i915_gem_init(struct drm_i915_private *dev_priv) if (ret) goto err_uc_init; + /* Only when the HW is re-initialised, can we replay the requests */ + ret = intel_gt_resume(dev_priv); + if (ret) + goto err_init_hw; + /* * Despite its name intel_init_clock_gating applies both display * clock gating workarounds; GT mmio workarounds and the occasional @@ -1593,20 +1589,20 @@ int i915_gem_init(struct drm_i915_private *dev_priv) ret = intel_engines_verify_workarounds(dev_priv); if (ret) - goto err_init_hw; + goto err_gt; ret = __intel_engines_record_defaults(dev_priv); if (ret) - goto err_init_hw; + goto err_gt; if (i915_inject_load_failure()) { ret = -ENODEV; - goto err_init_hw; + goto err_gt; } if (i915_inject_load_failure()) { ret = -EIO; - goto err_init_hw; + goto err_gt; } intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); @@ -1620,7 +1616,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv) * HW as irrevisibly wedged, but keep enough state around that the * driver doesn't explode during runtime. */ -err_init_hw: +err_gt: mutex_unlock(&dev_priv->drm.struct_mutex); i915_gem_set_wedged(dev_priv); @@ -1630,6 +1626,7 @@ err_init_hw: i915_gem_drain_workqueue(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); +err_init_hw: intel_uc_fini_hw(dev_priv); err_uc_init: intel_uc_fini(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 8ab820145ea6..7015a97b1097 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1444,9 +1444,11 @@ unwind_pd: spin_lock(&pdp->lock); if (atomic_dec_and_test(&pd->used)) { gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe); + pdp->entry[pdpe] = vm->scratch_pd; GEM_BUG_ON(!atomic_read(&pdp->used)); atomic_dec(&pdp->used); - free_pd(vm, pd); + GEM_BUG_ON(alloc); + alloc = pd; /* defer the free to after the lock */ } spin_unlock(&pdp->lock); unwind: @@ -1515,7 +1517,9 @@ unwind_pdp: spin_lock(&pml4->lock); if (atomic_dec_and_test(&pdp->used)) { gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e); - free_pd(vm, pdp); + pml4->entry[pml4e] = vm->scratch_pdp; + GEM_BUG_ON(alloc); + alloc = pdp; /* defer the free until after the lock */ } spin_unlock(&pml4->lock); unwind: diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index b7e9fddef270..8bc76fcff70d 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1194,6 +1194,7 @@ static void error_record_engine_registers(struct i915_gpu_state *error, switch (engine->id) { default: MISSING_CASE(engine->id); + /* fall through */ case RCS0: mmio = RENDER_HWS_PGA_GEN7; break; @@ -1417,6 +1418,7 @@ static void gem_record_rings(struct i915_gpu_state *error) struct intel_engine_cs *engine = i915->engine[i]; struct drm_i915_error_engine *ee = &error->engine[i]; struct i915_request *request; + unsigned long flags; ee->engine_id = -1; @@ -1428,10 +1430,11 @@ static void gem_record_rings(struct i915_gpu_state *error) error_record_engine_registers(error, engine, ee); error_record_engine_execlists(engine, ee); + spin_lock_irqsave(&engine->active.lock, flags); request = intel_engine_find_active_request(engine); if (request) { struct i915_gem_context *ctx = request->gem_context; - struct intel_ring *ring; + struct intel_ring *ring = request->ring; ee->vm = ctx->vm ?: &ggtt->vm; @@ -1461,7 +1464,6 @@ static void gem_record_rings(struct i915_gpu_state *error) ee->rq_post = request->postfix; ee->rq_tail = request->tail; - ring = request->ring; ee->cpu_ring_head = ring->head; ee->cpu_ring_tail = ring->tail; ee->ringbuffer = @@ -1469,6 +1471,7 @@ static void gem_record_rings(struct i915_gpu_state *error) engine_record_requests(engine, request, ee); } + spin_unlock_irqrestore(&engine->active.lock, flags); ee->hws_page = i915_error_object_create(i915, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index a700c5c3d167..5140017f9a39 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1567,28 +1567,10 @@ static void config_oa_regs(struct drm_i915_private *dev_priv, } } -static int hsw_enable_metric_set(struct i915_perf_stream *stream) +static void delay_after_mux(void) { - struct drm_i915_private *dev_priv = stream->dev_priv; - const struct i915_oa_config *oa_config = stream->oa_config; - - /* PRM: - * - * OA unit is using “crclk” for its functionality. When trunk - * level clock gating takes place, OA clock would be gated, - * unable to count the events from non-render clock domain. - * Render clock gating must be disabled when OA is enabled to - * count the events from non-render domain. Unit level clock - * gating for RCS should also be disabled. - */ - I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & - ~GEN7_DOP_CLOCK_GATE_ENABLE)); - I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | - GEN6_CSUNIT_CLOCK_GATE_DISABLE)); - - config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); - - /* It apparently takes a fairly long time for a new MUX + /* + * It apparently takes a fairly long time for a new MUX * configuration to be be applied after these register writes. * This delay duration was derived empirically based on the * render_basic config but hopefully it covers the maximum @@ -1610,6 +1592,30 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream) * a delay at this location would mitigate any invalid reports. */ usleep_range(15000, 20000); +} + +static int hsw_enable_metric_set(struct i915_perf_stream *stream) +{ + struct drm_i915_private *dev_priv = stream->dev_priv; + const struct i915_oa_config *oa_config = stream->oa_config; + + /* + * PRM: + * + * OA unit is using “crclk” for its functionality. When trunk + * level clock gating takes place, OA clock would be gated, + * unable to count the events from non-render clock domain. + * Render clock gating must be disabled when OA is enabled to + * count the events from non-render domain. Unit level clock + * gating for RCS should also be disabled. + */ + I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) & + ~GEN7_DOP_CLOCK_GATE_ENABLE)); + I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE)); + + config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len); @@ -1835,6 +1841,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) return ret; config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len); + delay_after_mux(); config_oa_regs(dev_priv, oa_config->b_counter_regs, oa_config->b_counter_regs_len); @@ -2515,6 +2522,9 @@ static int i915_perf_release(struct inode *inode, struct file *file) i915_perf_destroy_locked(stream); mutex_unlock(&dev_priv->perf.lock); + /* Release the reference the perf stream kept on the driver. */ + drm_dev_put(&dev_priv->drm); + return 0; } @@ -2650,6 +2660,11 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, if (!(param->flags & I915_PERF_FLAG_DISABLED)) i915_perf_enable_locked(stream); + /* Take a reference on the driver that will be kept with stream_fd + * until its release. + */ + drm_dev_get(&dev_priv->drm); + return stream_fd; err_open: @@ -3477,9 +3492,13 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set; dev_priv->perf.oa.ops.disable_metric_set = gen10_disable_metric_set; - dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; - dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; - + if (IS_GEN(dev_priv, 10)) { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de; + } else { + dev_priv->perf.oa.ctx_oactxctrl_offset = 0x124; + dev_priv->perf.oa.ctx_flexeu0_offset = 0x78e; + } dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16); } } diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index f4ce643b3bc3..cce426b23a24 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -21,24 +21,22 @@ /* watermark/fifo updates */ TRACE_EVENT(intel_pipe_enable, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), - TP_ARGS(dev_priv, pipe), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __array(u32, frame, 3) __array(u32, scanline, 3) __field(enum pipe, pipe) ), - TP_fast_assign( - enum pipe _pipe; - for_each_pipe(dev_priv, _pipe) { - __entry->frame[_pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe); - __entry->scanline[_pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe)); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + for_each_intel_crtc(&dev_priv->drm, it__) { + __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); + __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); } - __entry->pipe = pipe; + __entry->pipe = crtc->pipe; ), TP_printk("pipe %c enable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", @@ -49,8 +47,8 @@ TRACE_EVENT(intel_pipe_enable, ); TRACE_EVENT(intel_pipe_disable, - TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe), - TP_ARGS(dev_priv, pipe), + TP_PROTO(struct intel_crtc *crtc), + TP_ARGS(crtc), TP_STRUCT__entry( __array(u32, frame, 3) @@ -59,14 +57,13 @@ TRACE_EVENT(intel_pipe_disable, ), TP_fast_assign( - enum pipe _pipe; - for_each_pipe(dev_priv, _pipe) { - __entry->frame[_pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe); - __entry->scanline[_pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe)); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_crtc *it__; + for_each_intel_crtc(&dev_priv->drm, it__) { + __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__); + __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__); } - __entry->pipe = pipe; + __entry->pipe = crtc->pipe; ), TP_printk("pipe %c disable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u", @@ -89,8 +86,7 @@ TRACE_EVENT(intel_pipe_crc, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); memcpy(__entry->crcs, crcs, sizeof(__entry->crcs)); ), @@ -112,9 +108,10 @@ TRACE_EVENT(intel_cpu_fifo_underrun, ), TP_fast_assign( + struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); __entry->pipe = pipe; - __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); ), TP_printk("pipe %c, frame=%u, scanline=%u", @@ -134,9 +131,10 @@ TRACE_EVENT(intel_pch_fifo_underrun, TP_fast_assign( enum pipe pipe = pch_transcoder; + struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe); __entry->pipe = pipe; - __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + __entry->frame = intel_crtc_get_vblank_counter(crtc); + __entry->scanline = intel_get_crtc_scanline(crtc); ), TP_printk("pch transcoder %c, frame=%u, scanline=%u", @@ -156,12 +154,10 @@ TRACE_EVENT(intel_memory_cxsr, ), TP_fast_assign( - enum pipe pipe; - for_each_pipe(dev_priv, pipe) { - __entry->frame[pipe] = - dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe); - __entry->scanline[pipe] = - intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe)); + struct intel_crtc *crtc; + for_each_intel_crtc(&dev_priv->drm, crtc) { + __entry->frame[crtc->pipe] = intel_crtc_get_vblank_counter(crtc); + __entry->scanline[crtc->pipe] = intel_get_crtc_scanline(crtc); } __entry->old = old; __entry->new = new; @@ -198,8 +194,7 @@ TRACE_EVENT(g4x_wm, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY]; __entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0]; @@ -243,8 +238,7 @@ TRACE_EVENT(vlv_wm, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->level = wm->level; __entry->cxsr = wm->cxsr; @@ -278,8 +272,7 @@ TRACE_EVENT(vlv_fifo_size, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->sprite0_start = sprite0_start; __entry->sprite1_start = sprite1_start; @@ -310,8 +303,7 @@ TRACE_EVENT(intel_update_plane, TP_fast_assign( __entry->pipe = crtc->pipe; __entry->name = plane->name; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); memcpy(__entry->src, &plane->state->src, sizeof(__entry->src)); memcpy(__entry->dst, &plane->state->dst, sizeof(__entry->dst)); @@ -338,8 +330,7 @@ TRACE_EVENT(intel_disable_plane, TP_fast_assign( __entry->pipe = crtc->pipe; __entry->name = plane->name; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); ), @@ -364,8 +355,7 @@ TRACE_EVENT(i915_pipe_update_start, TP_fast_assign( __entry->pipe = crtc->pipe; - __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev, - crtc->pipe); + __entry->frame = intel_crtc_get_vblank_counter(crtc); __entry->scanline = intel_get_crtc_scanline(crtc); __entry->min = crtc->debug.min_vbl; __entry->max = crtc->debug.max_vbl; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 502c54428570..8d1aebc3e857 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -221,13 +221,11 @@ __untrack_all_wakerefs(struct intel_runtime_pm_debug *debug, static void dump_and_free_wakeref_tracking(struct intel_runtime_pm_debug *debug) { - struct drm_printer p; + if (debug->count) { + struct drm_printer p = drm_debug_printer("i915"); - if (!debug->count) - return; - - p = drm_debug_printer("i915"); - __print_intel_runtime_pm_wakeref(&p, debug); + __print_intel_runtime_pm_wakeref(&p, debug); + } kfree(debug->owners); } diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h index 9cbb2ebf575b..38275310b196 100644 --- a/drivers/gpu/drm/i915/intel_wakeref.h +++ b/drivers/gpu/drm/i915/intel_wakeref.h @@ -66,6 +66,21 @@ intel_wakeref_get(struct intel_runtime_pm *rpm, } /** + * intel_wakeref_get_if_in_use: Acquire the wakeref + * @wf: the wakeref + * + * Acquire a hold on the wakeref, but only if the wakeref is already + * active. + * + * Returns: true if the wakeref was acquired, false otherwise. + */ +static inline bool +intel_wakeref_get_if_active(struct intel_wakeref *wf) +{ + return atomic_inc_not_zero(&wf->count); +} + +/** * intel_wakeref_put: Release the wakeref * @i915: the drm_i915_private device * @wf: the wakeref diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 1671db47aa57..e9c55d1d6c04 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -59,6 +59,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: /* copy commands into RB: */ obj = submit->bos[submit->cmd[i].idx].obj; @@ -149,6 +150,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index be39cf01e51e..dc8ec2c94301 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -115,6 +115,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 9acbbc0f3232..048c8be426f3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -428,6 +428,7 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, /* ignore if there has not been a ctx switch: */ if (priv->lastctx == ctx) break; + /* fall-thru */ case MSM_SUBMIT_CMD_BUF: OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ? CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 0e2f74163a16..0aa8a12c9952 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2221,8 +2221,6 @@ int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc, if (ret) goto fail; - spin_lock_init(&dpu_enc->enc_spinlock); - atomic_set(&dpu_enc->frame_done_timeout_ms, 0); timer_setup(&dpu_enc->frame_done_timer, dpu_encoder_frame_done_timeout, 0); @@ -2276,6 +2274,7 @@ struct drm_encoder *dpu_encoder_init(struct drm_device *dev, drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs); + spin_lock_init(&dpu_enc->enc_spinlock); dpu_enc->enabled = false; return &dpu_enc->base; diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index ff14555372d0..78d5fa230c16 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -439,6 +439,18 @@ static void mdp5_crtc_atomic_disable(struct drm_crtc *crtc, mdp5_crtc->enabled = false; } +static void mdp5_crtc_vblank_on(struct drm_crtc *crtc) +{ + struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state); + struct mdp5_interface *intf = mdp5_cstate->pipeline.intf; + u32 count; + + count = intf->mode == MDP5_INTF_DSI_MODE_COMMAND ? 0 : 0xffffffff; + drm_crtc_set_max_vblank_count(crtc, count); + + drm_crtc_vblank_on(crtc); +} + static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { @@ -475,7 +487,7 @@ static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc, } /* Restore vblank irq handling after power is enabled */ - drm_crtc_vblank_on(crtc); + mdp5_crtc_vblank_on(crtc); mdp5_crtc_mode_set_nofb(crtc); @@ -1028,6 +1040,8 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc) mdp5_crtc_destroy_state(crtc, crtc->state); __drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base); + + drm_crtc_vblank_reset(crtc); } static const struct drm_crtc_funcs mdp5_crtc_funcs = { diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index 4a60f5fca6b0..fec6ef1ae3b9 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -740,7 +740,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev) dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos; dev->driver->get_scanout_position = mdp5_get_scanoutpos; dev->driver->get_vblank_counter = mdp5_get_vblank_counter; - dev->max_vblank_count = 0xffffffff; + dev->max_vblank_count = 0; /* max_vblank_count is set on each CRTC */ dev->vblank_disable_immediate = true; return kms; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ab64ab470de7..c356f5ccf253 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -619,7 +619,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file) msm_submitqueue_init(dev, ctx); - ctx->aspace = priv->gpu->aspace; + ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL; file->driver_priv = ctx; return 0; @@ -1279,7 +1279,8 @@ static int add_gpu_components(struct device *dev, if (!np) return 0; - drm_of_component_match_add(dev, matchptr, compare_of, np); + if (of_device_is_available(np)) + drm_of_component_match_add(dev, matchptr, compare_of, np); of_node_put(np); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 8b78554cfde3..8cf6362e64bf 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -32,6 +32,46 @@ static bool use_pages(struct drm_gem_object *obj) return !msm_obj->vram_node; } +/* + * Cache sync.. this is a bit over-complicated, to fit dma-mapping + * API. Really GPU cache is out of scope here (handled on cmdstream) + * and all we need to do is invalidate newly allocated pages before + * mapping to CPU as uncached/writecombine. + * + * On top of this, we have the added headache, that depending on + * display generation, the display's iommu may be wired up to either + * the toplevel drm device (mdss), or to the mdp sub-node, meaning + * that here we either have dma-direct or iommu ops. + * + * Let this be a cautionary tail of abstraction gone wrong. + */ + +static void sync_for_device(struct msm_gem_object *msm_obj) +{ + struct device *dev = msm_obj->base.dev->dev; + + if (get_dma_ops(dev)) { + dma_sync_sg_for_device(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } else { + dma_map_sg(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } +} + +static void sync_for_cpu(struct msm_gem_object *msm_obj) +{ + struct device *dev = msm_obj->base.dev->dev; + + if (get_dma_ops(dev)) { + dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } else { + dma_unmap_sg(dev, msm_obj->sgt->sgl, + msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + } +} + /* allocate pages from VRAM carveout, used when no IOMMU: */ static struct page **get_pages_vram(struct drm_gem_object *obj, int npages) { @@ -97,8 +137,7 @@ static struct page **get_pages(struct drm_gem_object *obj) * because display controller, GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_map_sg(dev->dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + sync_for_device(msm_obj); } return msm_obj->pages; @@ -127,9 +166,7 @@ static void put_pages(struct drm_gem_object *obj) * GPU, etc. are not coherent: */ if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED)) - dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, - DMA_BIDIRECTIONAL); + sync_for_cpu(msm_obj); sg_free_table(msm_obj->sgt); kfree(msm_obj->sgt); diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8497768f1b41..126703816794 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -780,7 +780,7 @@ nv50_msto_atomic_check(struct drm_encoder *encoder, drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock, connector->display_info.bpc * 3); - if (drm_atomic_crtc_needs_modeset(crtc_state)) { + if (crtc_state->mode_changed) { slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port, asyh->dp.pbn); diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 8c92374afcf2..a835cebb6d90 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -475,6 +475,47 @@ nouveau_svm_fault_cache(struct nouveau_svm *svm, fault->inst, fault->addr, fault->access); } +static inline bool +nouveau_range_done(struct hmm_range *range) +{ + bool ret = hmm_range_valid(range); + + hmm_range_unregister(range); + return ret; +} + +static int +nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range) +{ + long ret; + + range->default_flags = 0; + range->pfn_flags_mask = -1UL; + + ret = hmm_range_register(range, mirror, + range->start, range->end, + PAGE_SHIFT); + if (ret) { + up_read(&range->vma->vm_mm->mmap_sem); + return (int)ret; + } + + if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { + up_read(&range->vma->vm_mm->mmap_sem); + return -EAGAIN; + } + + ret = hmm_range_fault(range, true); + if (ret <= 0) { + if (ret == 0) + ret = -EBUSY; + up_read(&range->vma->vm_mm->mmap_sem); + hmm_range_unregister(range); + return ret; + } + return 0; +} + static int nouveau_svm_fault(struct nvif_notify *notify) { @@ -649,10 +690,10 @@ nouveau_svm_fault(struct nvif_notify *notify) range.values = nouveau_svm_pfn_values; range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT; again: - ret = hmm_vma_fault(&svmm->mirror, &range, true); + ret = nouveau_range_fault(&svmm->mirror, &range); if (ret == 0) { mutex_lock(&svmm->mutex); - if (!hmm_vma_range_done(&range)) { + if (!nouveau_range_done(&range)) { mutex_unlock(&svmm->mutex); goto again; } @@ -666,8 +707,8 @@ again: NULL); svmm->vmm->vmm.object.client->super = false; mutex_unlock(&svmm->mutex); + up_read(&svmm->mm->mmap_sem); } - up_read(&svmm->mm->mmap_sem); /* Cancel any faults in the window whose pages didn't manage * to keep their valid bit, or stay writeable when required. diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index d594f7520b7b..7d78e6deac89 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -285,9 +285,13 @@ static int ttm_set_pages_caching(struct dma_pool *pool, static void __ttm_dma_free_page(struct dma_pool *pool, struct dma_page *d_page) { + unsigned long attrs = 0; dma_addr_t dma = d_page->dma; d_page->vaddr &= ~VADDR_FLAG_HUGE_POOL; - dma_free_coherent(pool->dev, pool->size, (void *)d_page->vaddr, dma); + if (pool->type & IS_HUGE) + attrs = DMA_ATTR_NO_WARN; + + dma_free_attrs(pool->dev, pool->size, (void *)d_page->vaddr, dma, attrs); kfree(d_page); d_page = NULL; diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c index 98bf694626f7..3a8c4a5971f7 100644 --- a/drivers/hid/hid-a4tech.c +++ b/drivers/hid/hid-a4tech.c @@ -23,12 +23,36 @@ #define A4_2WHEEL_MOUSE_HACK_7 0x01 #define A4_2WHEEL_MOUSE_HACK_B8 0x02 +#define A4_WHEEL_ORIENTATION (HID_UP_GENDESK | 0x000000b8) + struct a4tech_sc { unsigned long quirks; unsigned int hw_wheel; __s32 delayed_value; }; +static int a4_input_mapping(struct hid_device *hdev, struct hid_input *hi, + struct hid_field *field, struct hid_usage *usage, + unsigned long **bit, int *max) +{ + struct a4tech_sc *a4 = hid_get_drvdata(hdev); + + if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8 && + usage->hid == A4_WHEEL_ORIENTATION) { + /* + * We do not want to have this usage mapped to anything as it's + * nonstandard and doesn't really behave like an HID report. + * It's only selecting the orientation (vertical/horizontal) of + * the previous mouse wheel report. The input_events will be + * generated once both reports are recorded in a4_event(). + */ + return -1; + } + + return 0; + +} + static int a4_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -52,8 +76,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, struct a4tech_sc *a4 = hid_get_drvdata(hdev); struct input_dev *input; - if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput || - !usage->type) + if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput) return 0; input = field->hidinput->input; @@ -64,7 +87,7 @@ static int a4_event(struct hid_device *hdev, struct hid_field *field, return 1; } - if (usage->hid == 0x000100b8) { + if (usage->hid == A4_WHEEL_ORIENTATION) { input_event(input, EV_REL, value ? REL_HWHEEL : REL_WHEEL, a4->delayed_value); input_event(input, EV_REL, value ? REL_HWHEEL_HI_RES : @@ -131,6 +154,7 @@ MODULE_DEVICE_TABLE(hid, a4_devices); static struct hid_driver a4_driver = { .name = "a4tech", .id_table = a4_devices, + .input_mapping = a4_input_mapping, .input_mapped = a4_input_mapped, .event = a4_event, .probe = a4_probe, diff --git a/drivers/hid/hid-holtek-kbd.c b/drivers/hid/hid-holtek-kbd.c index b3d502421b79..0a38e8e9bc78 100644 --- a/drivers/hid/hid-holtek-kbd.c +++ b/drivers/hid/hid-holtek-kbd.c @@ -123,9 +123,14 @@ static int holtek_kbd_input_event(struct input_dev *dev, unsigned int type, /* Locate the boot interface, to receive the LED change events */ struct usb_interface *boot_interface = usb_ifnum_to_if(usb_dev, 0); + struct hid_device *boot_hid; + struct hid_input *boot_hid_input; - struct hid_device *boot_hid = usb_get_intfdata(boot_interface); - struct hid_input *boot_hid_input = list_first_entry(&boot_hid->inputs, + if (unlikely(boot_interface == NULL)) + return -ENODEV; + + boot_hid = usb_get_intfdata(boot_interface); + boot_hid_input = list_first_entry(&boot_hid->inputs, struct hid_input, list); return boot_hid_input->input->event(boot_hid_input->input, type, code, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0d695f8e1b2c..0a00be19f7a0 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -568,6 +568,7 @@ #define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A 0x0b4a #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE 0x134a #define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A 0x094a +#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641 0x0641 #define USB_VENDOR_ID_HUION 0x256c #define USB_DEVICE_ID_HUION_TABLET 0x006e @@ -768,7 +769,8 @@ #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER 0xc52f #define USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER_2 0xc532 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2 0xc534 -#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING 0xc539 +#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED 0xc539 +#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY 0xc53a #define USB_DEVICE_ID_SPACETRAVELLER 0xc623 #define USB_DEVICE_ID_SPACENAVIGATOR 0xc626 #define USB_DEVICE_ID_DINOVO_DESKTOP 0xc704 @@ -989,6 +991,7 @@ #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 +#define USB_DEVICE_ID_SAITEK_X52 0x075c #define USB_VENDOR_ID_SAMSUNG 0x0419 #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 6196217a7d93..cc47f948c1d0 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1125,7 +1125,7 @@ static int logi_dj_recv_query_hidpp_devices(struct dj_receiver_dev *djrcv_dev) HID_REQ_SET_REPORT); kfree(hidpp_report); - return retval; + return (retval < 0) ? retval : 0; } static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev) @@ -1832,13 +1832,17 @@ static const struct hid_device_id logi_dj_receivers[] = { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2), .driver_data = recvr_type_hidpp}, - { /* Logitech gaming receiver (0xc539) */ + { /* Logitech lightspeed receiver (0xc539) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, - USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING), + USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED), .driver_data = recvr_type_gaming_hidpp}, { /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER), .driver_data = recvr_type_27mhz}, + { /* Logitech powerplay receiver (0xc53a) */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY), + .driver_data = recvr_type_gaming_hidpp}, { /* Logitech 27 MHz HID++ 1.0 receiver (0xc517) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2), diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index e3b6245bf4b2..21268c9fa71a 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3749,15 +3749,45 @@ static const struct hid_device_id hidpp_devices[] = { { L27MHZ_DEVICE(HID_ANY_ID) }, - { /* Logitech G403 Gaming Mouse over USB */ + { /* Logitech G203/Prodigy Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC084) }, + { /* Logitech G302 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07F) }, + { /* Logitech G303 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC080) }, + { /* Logitech G400 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07E) }, + { /* Logitech G403 Wireless Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC082) }, + { /* Logitech G403 Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC083) }, + { /* Logitech G403 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC08F) }, + { /* Logitech G502 Proteus Core Gaming Mouse */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07D) }, + { /* Logitech G502 Proteus Spectrum Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC332) }, + { /* Logitech G502 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC08B) }, { /* Logitech G700 Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC06B) }, + { /* Logitech G700s Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC07C) }, + { /* Logitech G703 Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC087) }, + { /* Logitech G703 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC090) }, { /* Logitech G900 Gaming Mouse over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC081) }, + { /* Logitech G903 Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC086) }, + { /* Logitech G903 Hero Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC091) }, { /* Logitech G920 Wheel over USB */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL), .driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS}, + { /* Logitech G Pro Gaming Mouse over USB */ + HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC088) }, { /* MX5000 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305), diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 185a577c46f6..166f41f3173b 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -92,6 +92,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT }, @@ -141,6 +142,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET }, diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 93942063b51b..49dd2d905c7f 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -585,10 +585,14 @@ static void sony_set_leds(struct sony_sc *sc); static inline void sony_schedule_work(struct sony_sc *sc, enum sony_worker which) { + unsigned long flags; + switch (which) { case SONY_WORKER_STATE: - if (!sc->defer_initialization) + spin_lock_irqsave(&sc->lock, flags); + if (!sc->defer_initialization && sc->state_worker_initialized) schedule_work(&sc->state_worker); + spin_unlock_irqrestore(&sc->lock, flags); break; case SONY_WORKER_HOTPLUG: if (sc->hotplug_worker_initialized) @@ -2558,13 +2562,18 @@ static inline void sony_init_output_report(struct sony_sc *sc, static inline void sony_cancel_work_sync(struct sony_sc *sc) { + unsigned long flags; + if (sc->hotplug_worker_initialized) cancel_work_sync(&sc->hotplug_worker); - if (sc->state_worker_initialized) + if (sc->state_worker_initialized) { + spin_lock_irqsave(&sc->lock, flags); + sc->state_worker_initialized = 0; + spin_unlock_irqrestore(&sc->lock, flags); cancel_work_sync(&sc->state_worker); + } } - static int sony_input_configured(struct hid_device *hdev, struct hid_input *hidinput) { diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c index e12f2588ddeb..bdfc5ff3b2c5 100644 --- a/drivers/hid/hid-tmff.c +++ b/drivers/hid/hid-tmff.c @@ -22,6 +22,8 @@ #include "hid-ids.h" +#define THRUSTMASTER_DEVICE_ID_2_IN_1_DT 0xb320 + static const signed short ff_rumble[] = { FF_RUMBLE, -1 @@ -76,6 +78,7 @@ static int tmff_play(struct input_dev *dev, void *data, struct hid_field *ff_field = tmff->ff_field; int x, y; int left, right; /* Rumbling */ + int motor_swap; switch (effect->type) { case FF_CONSTANT: @@ -100,6 +103,13 @@ static int tmff_play(struct input_dev *dev, void *data, ff_field->logical_minimum, ff_field->logical_maximum); + /* 2-in-1 strong motor is left */ + if (hid->product == THRUSTMASTER_DEVICE_ID_2_IN_1_DT) { + motor_swap = left; + left = right; + right = motor_swap; + } + dbg_hid("(left,right)=(%08x, %08x)\n", left, right); ff_field->value[0] = left; ff_field->value[1] = right; @@ -226,6 +236,8 @@ static const struct hid_device_id tm_devices[] = { .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb304), /* FireStorm Dual Power 2 (and 3) */ .driver_data = (unsigned long)ff_rumble }, + { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, THRUSTMASTER_DEVICE_ID_2_IN_1_DT), /* Dual Trigger 2-in-1 */ + .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb323), /* Dual Trigger 3-in-1 (PC Mode) */ .driver_data = (unsigned long)ff_rumble }, { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb324), /* Dual Trigger 3-in-1 (PS3 Mode) */ diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 55b72573066b..4e11cc6fc34b 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -284,6 +284,14 @@ static int hiddev_open(struct inode *inode, struct file *file) spin_unlock_irq(&list->hiddev->list_lock); mutex_lock(&hiddev->existancelock); + /* + * recheck exist with existance lock held to + * avoid opening a disconnected device + */ + if (!list->hiddev->exist) { + res = -ENODEV; + goto bail_unlock; + } if (!list->hiddev->open++) if (list->hiddev->exist) { struct hid_device *hid = hiddev->hid; @@ -300,6 +308,10 @@ bail_normal_power: hid_hw_power(hid, PM_HINT_NORMAL); bail_unlock: mutex_unlock(&hiddev->existancelock); + + spin_lock_irq(&list->hiddev->list_lock); + list_del(&list->node); + spin_unlock_irq(&list->hiddev->list_lock); bail: file->private_data = NULL; vfree(list); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 8fc36a28081b..7a8ddc999a8e 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -533,14 +533,14 @@ static int wacom_intuos_pad(struct wacom_wac *wacom) */ buttons = (data[4] << 1) | (data[3] & 0x01); } else if (features->type == CINTIQ_COMPANION_2) { - /* d-pad right -> data[4] & 0x10 - * d-pad up -> data[4] & 0x20 - * d-pad left -> data[4] & 0x40 - * d-pad down -> data[4] & 0x80 - * d-pad center -> data[3] & 0x01 + /* d-pad right -> data[2] & 0x10 + * d-pad up -> data[2] & 0x20 + * d-pad left -> data[2] & 0x40 + * d-pad down -> data[2] & 0x80 + * d-pad center -> data[1] & 0x01 */ buttons = ((data[2] >> 4) << 7) | - ((data[1] & 0x04) << 6) | + ((data[1] & 0x04) << 4) | ((data[2] & 0x0F) << 2) | (data[1] & 0x03); } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) { diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index e7dff5febe16..d42bc0883a32 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -852,7 +852,7 @@ static const u16 NCT6106_REG_TARGET[] = { 0x111, 0x121, 0x131 }; static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 }; static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a }; -static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x17c }; +static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b }; static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c }; static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d }; @@ -3764,6 +3764,7 @@ static int nct6775_probe(struct platform_device *pdev) data->REG_FAN_TIME[0] = NCT6106_REG_FAN_STOP_TIME; data->REG_FAN_TIME[1] = NCT6106_REG_FAN_STEP_UP_TIME; data->REG_FAN_TIME[2] = NCT6106_REG_FAN_STEP_DOWN_TIME; + data->REG_TOLERANCE_H = NCT6106_REG_TOLERANCE_H; data->REG_PWM[0] = NCT6106_REG_PWM; data->REG_PWM[1] = NCT6106_REG_FAN_START_OUTPUT; data->REG_PWM[2] = NCT6106_REG_FAN_STOP_OUTPUT; diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index a7d2b16dd702..30e18eb60da7 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -408,8 +408,10 @@ static ssize_t occ_show_power_1(struct device *dev, static u64 occ_get_powr_avg(u64 *accum, u32 *samples) { - return div64_u64(get_unaligned_be64(accum) * 1000000ULL, - get_unaligned_be32(samples)); + u64 divisor = get_unaligned_be32(samples); + + return (divisor == 0) ? 0 : + div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor); } static ssize_t occ_show_power_2(struct device *dev, diff --git a/drivers/i2c/busses/i2c-at91-core.c b/drivers/i2c/busses/i2c-at91-core.c index 8d55cdd69ff4..435c7d7377a3 100644 --- a/drivers/i2c/busses/i2c-at91-core.c +++ b/drivers/i2c/busses/i2c-at91-core.c @@ -142,7 +142,7 @@ static struct at91_twi_pdata sama5d4_config = { static struct at91_twi_pdata sama5d2_config = { .clk_max_div = 7, - .clk_offset = 4, + .clk_offset = 3, .has_unre_flag = true, .has_alt_cmd = true, .has_hold_field = true, diff --git a/drivers/i2c/busses/i2c-at91-master.c b/drivers/i2c/busses/i2c-at91-master.c index e87232f2e708..a3fcc35ffd3b 100644 --- a/drivers/i2c/busses/i2c-at91-master.c +++ b/drivers/i2c/busses/i2c-at91-master.c @@ -122,9 +122,11 @@ static void at91_twi_write_next_byte(struct at91_twi_dev *dev) writeb_relaxed(*dev->buf, dev->base + AT91_TWI_THR); /* send stop when last byte has been written */ - if (--dev->buf_len == 0) + if (--dev->buf_len == 0) { if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); + at91_twi_write(dev, AT91_TWI_IDR, AT91_TWI_TXRDY); + } dev_dbg(dev->dev, "wrote 0x%x, to go %zu\n", *dev->buf, dev->buf_len); @@ -542,9 +544,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) } else { at91_twi_write_next_byte(dev); at91_twi_write(dev, AT91_TWI_IER, - AT91_TWI_TXCOMP | - AT91_TWI_NACK | - AT91_TWI_TXRDY); + AT91_TWI_TXCOMP | AT91_TWI_NACK | + (dev->buf_len ? AT91_TWI_TXRDY : 0)); } } diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 2c7f145a036e..d7fd76baec92 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -392,16 +392,18 @@ static bool bcm_iproc_i2c_slave_isr(struct bcm_iproc_i2c_dev *iproc_i2c, static void bcm_iproc_i2c_read_valid_bytes(struct bcm_iproc_i2c_dev *iproc_i2c) { struct i2c_msg *msg = iproc_i2c->msg; + uint32_t val; /* Read valid data from RX FIFO */ while (iproc_i2c->rx_bytes < msg->len) { - if (!((iproc_i2c_rd_reg(iproc_i2c, M_FIFO_CTRL_OFFSET) >> M_FIFO_RX_CNT_SHIFT) - & M_FIFO_RX_CNT_MASK)) + val = iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET); + + /* rx fifo empty */ + if (!((val >> M_RX_STATUS_SHIFT) & M_RX_STATUS_MASK)) break; msg->buf[iproc_i2c->rx_bytes] = - (iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET) >> - M_RX_DATA_SHIFT) & M_RX_DATA_MASK; + (val >> M_RX_DATA_SHIFT) & M_RX_DATA_MASK; iproc_i2c->rx_bytes++; } } diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c index cfc76b5de726..5a1235fd86bb 100644 --- a/drivers/i2c/busses/i2c-nvidia-gpu.c +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -364,7 +364,7 @@ static void gpu_i2c_remove(struct pci_dev *pdev) /* * We need gpu_i2c_suspend() even if it is stub, for runtime pm to work * correctly. Without it, lspci shows runtime pm status as "D0" for the card. - * Documentation/power/pci.txt also insists for driver to provide this. + * Documentation/power/pci.rst also insists for driver to provide this. */ static __maybe_unused int gpu_i2c_suspend(struct device *dev) { diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index d97fb857b0ea..c98ef4c4a0c9 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -435,6 +435,7 @@ static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) * fall through to the write state, as we will need to * send a byte as well */ + /* Fall through */ case STATE_WRITE: /* diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 888d89ce81df..beee7b7e0d9a 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -302,7 +302,9 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, struct ib_udata *udata, struct ib_uobject *uobj) { + enum ib_qp_type qp_type = attr->qp_type; struct ib_qp *qp; + bool is_xrc; if (!dev->ops.create_qp) return ERR_PTR(-EOPNOTSUPP); @@ -320,7 +322,8 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev, * and more importantly they are created internaly by driver, * see mlx5 create_dev_resources() as an example. */ - if (attr->qp_type < IB_QPT_XRC_INI) { + is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT; + if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) { qp->res.type = RDMA_RESTRACK_QP; if (uobj) rdma_restrack_uadd(&qp->res); diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 01faef7bc061..45d5164e9574 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -393,6 +393,9 @@ u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u8 port, u32 index) u64 sum; port_counter = &dev->port_data[port].port_counter; + if (!port_counter->hstats) + return 0; + sum = get_running_counters_hwstat_sum(dev, port, index); sum += port_counter->hstats->value[index]; @@ -594,7 +597,7 @@ void rdma_counter_init(struct ib_device *dev) struct rdma_port_counter *port_counter; u32 port; - if (!dev->ops.alloc_hw_stats || !dev->port_data) + if (!dev->port_data) return; rdma_for_each_port(dev, port) { @@ -602,6 +605,9 @@ void rdma_counter_init(struct ib_device *dev) port_counter->mode.mode = RDMA_COUNTER_MODE_NONE; mutex_init(&port_counter->lock); + if (!dev->ops.alloc_hw_stats) + continue; + port_counter->hstats = dev->ops.alloc_hw_stats(dev, port); if (!port_counter->hstats) goto fail; @@ -624,9 +630,6 @@ void rdma_counter_release(struct ib_device *dev) struct rdma_port_counter *port_counter; u32 port; - if (!dev->ops.alloc_hw_stats) - return; - rdma_for_each_port(dev, port) { port_counter = &dev->port_data[port].port_counter; kfree(port_counter->hstats); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 9773145dee09..ea8661a00651 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -94,11 +94,17 @@ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 -static LIST_HEAD(client_list); +static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); +static void ib_client_put(struct ib_client *client) +{ + if (refcount_dec_and_test(&client->uses)) + complete(&client->uses_zero); +} + /* * If client_data is registered then the corresponding client must also still * be registered. @@ -661,6 +667,14 @@ static int add_client_context(struct ib_device *device, down_write(&device->client_data_rwsem); /* + * So long as the client is registered hold both the client and device + * unregistration locks. + */ + if (!refcount_inc_not_zero(&client->uses)) + goto out_unlock; + refcount_inc(&device->refcount); + + /* * Another caller to add_client_context got here first and has already * completely initialized context. */ @@ -683,6 +697,9 @@ static int add_client_context(struct ib_device *device, return 0; out: + ib_device_put(device); + ib_client_put(client); +out_unlock: up_write(&device->client_data_rwsem); return ret; } @@ -702,7 +719,7 @@ static void remove_client_context(struct ib_device *device, client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); - downgrade_write(&device->client_data_rwsem); + up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the @@ -712,17 +729,13 @@ static void remove_client_context(struct ib_device *device, * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. - * - * It tempting to drop the client_data_rwsem too, but this is required - * to ensure that unregister_client does not return until all clients - * are completely unregistered, which is required to avoid module - * unloading races. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); - up_read(&device->client_data_rwsem); + ib_device_put(device); + ib_client_put(client); } static int alloc_port_data(struct ib_device *device) @@ -1224,7 +1237,7 @@ static int setup_device(struct ib_device *device) static void disable_device(struct ib_device *device) { - struct ib_client *client; + u32 cid; WARN_ON(!refcount_read(&device->refcount)); @@ -1232,10 +1245,19 @@ static void disable_device(struct ib_device *device) xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); + /* + * Remove clients in LIFO order, see assign_client_id. This could be + * more efficient if xarray learns to reverse iterate. Since no new + * clients can be added to this ib_device past this point we only need + * the maximum possible client_id value here. + */ down_read(&clients_rwsem); - list_for_each_entry_reverse(client, &client_list, list) - remove_client_context(device, client->client_id); + cid = highest_client_id; up_read(&clients_rwsem); + while (cid) { + cid--; + remove_client_context(device, cid); + } /* Pairs with refcount_set in enable_device */ ib_device_put(device); @@ -1662,30 +1684,31 @@ static int assign_client_id(struct ib_client *client) /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in - * registration order, and retain a linked list we can reverse iterate - * to get the LIFO order. The extra linked list can go away if xarray - * learns to reverse iterate. + * registration order. */ - if (list_empty(&client_list)) { - client->client_id = 0; - } else { - struct ib_client *last; - - last = list_last_entry(&client_list, struct ib_client, list); - client->client_id = last->client_id + 1; - } + client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) goto out; + highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - list_add_tail(&client->list, &client_list); out: up_write(&clients_rwsem); return ret; } +static void remove_client_id(struct ib_client *client) +{ + down_write(&clients_rwsem); + xa_erase(&clients, client->client_id); + for (; highest_client_id; highest_client_id--) + if (xa_load(&clients, highest_client_id - 1)) + break; + up_write(&clients_rwsem); +} + /** * ib_register_client - Register an IB client * @client:Client to register @@ -1705,6 +1728,8 @@ int ib_register_client(struct ib_client *client) unsigned long index; int ret; + refcount_set(&client->uses, 1); + init_completion(&client->uses_zero); ret = assign_client_id(client); if (ret) return ret; @@ -1740,21 +1765,30 @@ void ib_unregister_client(struct ib_client *client) unsigned long index; down_write(&clients_rwsem); + ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); - /* - * Every device still known must be serialized to make sure we are - * done with the client callbacks before we return. - */ - down_read(&devices_rwsem); - xa_for_each (&devices, index, device) + + /* We do not want to have locks while calling client->remove() */ + rcu_read_lock(); + xa_for_each (&devices, index, device) { + if (!ib_device_try_get(device)) + continue; + rcu_read_unlock(); + remove_client_context(device, client->client_id); - up_read(&devices_rwsem); - down_write(&clients_rwsem); - list_del(&client->list); - xa_erase(&clients, client->client_id); - up_write(&clients_rwsem); + ib_device_put(device); + rcu_read_lock(); + } + rcu_read_unlock(); + + /* + * remove_client_context() is not a fence, it can return even though a + * removal is ongoing. Wait until all removals are completed. + */ + wait_for_completion(&client->uses_zero); + remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index cc99479b2c09..9947d16edef2 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -3224,18 +3224,18 @@ static int ib_mad_port_open(struct ib_device *device, if (has_smi) cq_size *= 2; + port_priv->pd = ib_alloc_pd(device, 0); + if (IS_ERR(port_priv->pd)) { + dev_err(&device->dev, "Couldn't create ib_mad PD\n"); + ret = PTR_ERR(port_priv->pd); + goto error3; + } + port_priv->cq = ib_alloc_cq(port_priv->device, port_priv, cq_size, 0, IB_POLL_UNBOUND_WORKQUEUE); if (IS_ERR(port_priv->cq)) { dev_err(&device->dev, "Couldn't create ib_mad CQ\n"); ret = PTR_ERR(port_priv->cq); - goto error3; - } - - port_priv->pd = ib_alloc_pd(device, 0); - if (IS_ERR(port_priv->pd)) { - dev_err(&device->dev, "Couldn't create ib_mad PD\n"); - ret = PTR_ERR(port_priv->pd); goto error4; } @@ -3278,11 +3278,11 @@ error8: error7: destroy_mad_qp(&port_priv->qp_info[0]); error6: - ib_dealloc_pd(port_priv->pd); -error4: ib_free_cq(port_priv->cq); cleanup_recv_queue(&port_priv->qp_info[1]); cleanup_recv_queue(&port_priv->qp_info[0]); +error4: + ib_dealloc_pd(port_priv->pd); error3: kfree(port_priv); @@ -3312,8 +3312,8 @@ static int ib_mad_port_close(struct ib_device *device, int port_num) destroy_workqueue(port_priv->wq); destroy_mad_qp(&port_priv->qp_info[1]); destroy_mad_qp(&port_priv->qp_info[0]); - ib_dealloc_pd(port_priv->pd); ib_free_cq(port_priv->cq); + ib_dealloc_pd(port_priv->pd); cleanup_recv_queue(&port_priv->qp_info[1]); cleanup_recv_queue(&port_priv->qp_info[0]); /* XXX: Handle deallocation of MAD registration tables */ diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 9f8a48016b41..ffdeaf6e0b68 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -49,6 +49,7 @@ #include <linux/sched.h> #include <linux/semaphore.h> #include <linux/slab.h> +#include <linux/nospec.h> #include <linux/uaccess.h> @@ -884,11 +885,14 @@ static int ib_umad_unreg_agent(struct ib_umad_file *file, u32 __user *arg) if (get_user(id, arg)) return -EFAULT; + if (id >= IB_UMAD_MAX_AGENTS) + return -EINVAL; mutex_lock(&file->port->file_mutex); mutex_lock(&file->mutex); - if (id >= IB_UMAD_MAX_AGENTS || !__get_agent(file, id)) { + id = array_index_nospec(id, IB_UMAD_MAX_AGENTS); + if (!__get_agent(file, id)) { ret = -EINVAL; goto out; } diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index a91653aabf38..098ab883733e 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -308,6 +308,7 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev); struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl; struct bnxt_qplib_gid *gid_to_del; + u16 vlan_id = 0xFFFF; /* Delete the entry from the hardware */ ctx = *context; @@ -317,7 +318,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) if (sgid_tbl && sgid_tbl->active) { if (ctx->idx >= sgid_tbl->max) return -EINVAL; - gid_to_del = &sgid_tbl->tbl[ctx->idx]; + gid_to_del = &sgid_tbl->tbl[ctx->idx].gid; + vlan_id = sgid_tbl->tbl[ctx->idx].vlan_id; /* DEL_GID is called in WQ context(netdevice_event_work_handler) * or via the ib_unregister_device path. In the former case QP1 * may not be destroyed yet, in which case just return as FW @@ -335,7 +337,8 @@ int bnxt_re_del_gid(const struct ib_gid_attr *attr, void **context) } ctx->refcnt--; if (!ctx->refcnt) { - rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true); + rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, + vlan_id, true); if (rc) { dev_err(rdev_to_dev(rdev), "Failed to remove GID: %#x", rc); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 37928b1111df..bdbde8e22420 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -488,7 +488,7 @@ static int bnxt_qplib_alloc_sgid_tbl(struct bnxt_qplib_res *res, struct bnxt_qplib_sgid_tbl *sgid_tbl, u16 max) { - sgid_tbl->tbl = kcalloc(max, sizeof(struct bnxt_qplib_gid), GFP_KERNEL); + sgid_tbl->tbl = kcalloc(max, sizeof(*sgid_tbl->tbl), GFP_KERNEL); if (!sgid_tbl->tbl) return -ENOMEM; @@ -526,9 +526,10 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res, for (i = 0; i < sgid_tbl->max; i++) { if (memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero, sizeof(bnxt_qplib_gid_zero))) - bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i], true); + bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i].gid, + sgid_tbl->tbl[i].vlan_id, true); } - memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max); + memset(sgid_tbl->tbl, 0, sizeof(*sgid_tbl->tbl) * sgid_tbl->max); memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max); memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max); sgid_tbl->active = 0; @@ -537,7 +538,11 @@ static void bnxt_qplib_cleanup_sgid_tbl(struct bnxt_qplib_res *res, static void bnxt_qplib_init_sgid_tbl(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct net_device *netdev) { - memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max); + u32 i; + + for (i = 0; i < sgid_tbl->max; i++) + sgid_tbl->tbl[i].vlan_id = 0xffff; + memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h index 30c42c92fac7..fbda11a7ab1a 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h @@ -111,7 +111,7 @@ struct bnxt_qplib_pd_tbl { }; struct bnxt_qplib_sgid_tbl { - struct bnxt_qplib_gid *tbl; + struct bnxt_qplib_gid_info *tbl; u16 *hw_id; u16 max; u16 active; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 48793d3512ac..40296b97d21e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -213,12 +213,12 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res, index, sgid_tbl->max); return -EINVAL; } - memcpy(gid, &sgid_tbl->tbl[index], sizeof(*gid)); + memcpy(gid, &sgid_tbl->tbl[index].gid, sizeof(*gid)); return 0; } int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, - struct bnxt_qplib_gid *gid, bool update) + struct bnxt_qplib_gid *gid, u16 vlan_id, bool update) { struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl, struct bnxt_qplib_res, @@ -236,7 +236,8 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, return -ENOMEM; } for (index = 0; index < sgid_tbl->max; index++) { - if (!memcmp(&sgid_tbl->tbl[index], gid, sizeof(*gid))) + if (!memcmp(&sgid_tbl->tbl[index].gid, gid, sizeof(*gid)) && + vlan_id == sgid_tbl->tbl[index].vlan_id) break; } if (index == sgid_tbl->max) { @@ -262,8 +263,9 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, if (rc) return rc; } - memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero, + memcpy(&sgid_tbl->tbl[index].gid, &bnxt_qplib_gid_zero, sizeof(bnxt_qplib_gid_zero)); + sgid_tbl->tbl[index].vlan_id = 0xFFFF; sgid_tbl->vlan[index] = 0; sgid_tbl->active--; dev_dbg(&res->pdev->dev, @@ -296,7 +298,8 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } free_idx = sgid_tbl->max; for (i = 0; i < sgid_tbl->max; i++) { - if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid))) { + if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid)) && + sgid_tbl->tbl[i].vlan_id == vlan_id) { dev_dbg(&res->pdev->dev, "SGID entry already exist in entry %d!\n", i); *index = i; @@ -351,6 +354,7 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } /* Add GID to the sgid_tbl */ memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid)); + sgid_tbl->tbl[free_idx].vlan_id = vlan_id; sgid_tbl->active++; if (vlan_id != 0xFFFF) sgid_tbl->vlan[free_idx] = 1; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 0ec3b12b0bcd..13d9432d5ce2 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -84,6 +84,11 @@ struct bnxt_qplib_gid { u8 data[16]; }; +struct bnxt_qplib_gid_info { + struct bnxt_qplib_gid gid; + u16 vlan_id; +}; + struct bnxt_qplib_ah { struct bnxt_qplib_gid dgid; struct bnxt_qplib_pd *pd; @@ -221,7 +226,7 @@ int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res, struct bnxt_qplib_sgid_tbl *sgid_tbl, int index, struct bnxt_qplib_gid *gid); int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, - struct bnxt_qplib_gid *gid, bool update); + struct bnxt_qplib_gid *gid, u16 vlan_id, bool update); int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id, bool update, u32 *index); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index d5b643a1d9fd..67052dc3100c 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -14452,7 +14452,7 @@ void hfi1_deinit_vnic_rsm(struct hfi1_devdata *dd) clear_rcvctrl(dd, RCV_CTRL_RCV_RSM_ENABLE_SMASK); } -static void init_rxe(struct hfi1_devdata *dd) +static int init_rxe(struct hfi1_devdata *dd) { struct rsm_map_table *rmt; u64 val; @@ -14461,6 +14461,9 @@ static void init_rxe(struct hfi1_devdata *dd) write_csr(dd, RCV_ERR_MASK, ~0ull); rmt = alloc_rsm_map_table(dd); + if (!rmt) + return -ENOMEM; + /* set up QOS, including the QPN map table */ init_qos(dd, rmt); init_fecn_handling(dd, rmt); @@ -14487,6 +14490,7 @@ static void init_rxe(struct hfi1_devdata *dd) val |= ((4ull & RCV_BYPASS_HDR_SIZE_MASK) << RCV_BYPASS_HDR_SIZE_SHIFT); write_csr(dd, RCV_BYPASS, val); + return 0; } static void init_other(struct hfi1_devdata *dd) @@ -15024,7 +15028,10 @@ int hfi1_init_dd(struct hfi1_devdata *dd) goto bail_cleanup; /* set initial RXE CSRs */ - init_rxe(dd); + ret = init_rxe(dd); + if (ret) + goto bail_cleanup; + /* set initial TXE CSRs */ init_txe(dd); /* set initial non-RXE, non-TXE CSRs */ diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 0477c14633ab..024a7c2b6124 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -1835,7 +1835,6 @@ void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah) cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0) break; trdma_clean_swqe(qp, wqe); - rvt_qp_wqe_unreserve(qp, wqe); trace_hfi1_qp_send_completion(qp, wqe, qp->s_last); rvt_qp_complete_swqe(qp, wqe, @@ -1882,7 +1881,6 @@ struct rvt_swqe *do_rc_completion(struct rvt_qp *qp, if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 || cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) { trdma_clean_swqe(qp, wqe); - rvt_qp_wqe_unreserve(qp, wqe); trace_hfi1_qp_send_completion(qp, wqe, qp->s_last); rvt_qp_complete_swqe(qp, wqe, diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 92acccaaaa86..996fc298207e 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -1620,6 +1620,7 @@ static int hfi1_kern_exp_rcv_alloc_flows(struct tid_rdma_request *req, flows[i].req = req; flows[i].npagesets = 0; flows[i].pagesets[0].mapped = 0; + flows[i].resync_npkts = 0; } req->flows = flows; return 0; @@ -1673,34 +1674,6 @@ static struct tid_rdma_flow *find_flow_ib(struct tid_rdma_request *req, return NULL; } -static struct tid_rdma_flow * -__find_flow_ranged(struct tid_rdma_request *req, u16 head, u16 tail, - u32 psn, u16 *fidx) -{ - for ( ; CIRC_CNT(head, tail, MAX_FLOWS); - tail = CIRC_NEXT(tail, MAX_FLOWS)) { - struct tid_rdma_flow *flow = &req->flows[tail]; - u32 spsn, lpsn; - - spsn = full_flow_psn(flow, flow->flow_state.spsn); - lpsn = full_flow_psn(flow, flow->flow_state.lpsn); - - if (cmp_psn(psn, spsn) >= 0 && cmp_psn(psn, lpsn) <= 0) { - if (fidx) - *fidx = tail; - return flow; - } - } - return NULL; -} - -static struct tid_rdma_flow *find_flow(struct tid_rdma_request *req, - u32 psn, u16 *fidx) -{ - return __find_flow_ranged(req, req->setup_head, req->clear_tail, psn, - fidx); -} - /* TID RDMA READ functions */ u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe, struct ib_other_headers *ohdr, u32 *bth1, @@ -2788,19 +2761,7 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd, * to prevent continuous Flow Sequence errors for any * packets that could be still in the fabric. */ - flow = find_flow(req, psn, NULL); - if (!flow) { - /* - * We can't find the IB PSN matching the - * received KDETH PSN. The only thing we can - * do at this point is report the error to - * the QP. - */ - hfi1_kern_read_tid_flow_free(qp); - spin_unlock(&qp->s_lock); - rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR); - return ret; - } + flow = &req->flows[req->clear_tail]; if (priv->s_flags & HFI1_R_TID_SW_PSN) { diff = cmp_psn(psn, flow->flow_state.r_next_psn); diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index c4b243f50c76..646f61545ed6 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -54,6 +54,7 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <rdma/opa_addr.h> +#include <linux/nospec.h> #include "hfi.h" #include "common.h" @@ -1536,6 +1537,7 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) sl = rdma_ah_get_sl(ah_attr); if (sl >= ARRAY_SIZE(ibp->sl_to_sc)) return -EINVAL; + sl = array_index_nospec(sl, ARRAY_SIZE(ibp->sl_to_sc)); sc5 = ibp->sl_to_sc[sl]; if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf) diff --git a/drivers/infiniband/hw/hns/Kconfig b/drivers/infiniband/hw/hns/Kconfig index 8bf847bcd8d3..54782197c717 100644 --- a/drivers/infiniband/hw/hns/Kconfig +++ b/drivers/infiniband/hw/hns/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config INFINIBAND_HNS - tristate "HNS RoCE Driver" + bool "HNS RoCE Driver" depends on NET_VENDOR_HISILICON depends on ARM64 || (COMPILE_TEST && 64BIT) ---help--- @@ -11,7 +11,7 @@ config INFINIBAND_HNS To compile HIP06 or HIP08 driver as module, choose M here. config INFINIBAND_HNS_HIP06 - bool "Hisilicon Hip06 Family RoCE support" + tristate "Hisilicon Hip06 Family RoCE support" depends on INFINIBAND_HNS && HNS && HNS_DSAF && HNS_ENET ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip06 and @@ -21,7 +21,7 @@ config INFINIBAND_HNS_HIP06 module will be called hns-roce-hw-v1 config INFINIBAND_HNS_HIP08 - bool "Hisilicon Hip08 Family RoCE support" + tristate "Hisilicon Hip08 Family RoCE support" depends on INFINIBAND_HNS && PCI && HNS3 ---help--- RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC. diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index e105945b94a1..449a2d81319d 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -9,12 +9,8 @@ hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o -ifdef CONFIG_INFINIBAND_HNS_HIP06 hns-roce-hw-v1-objs := hns_roce_hw_v1.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v1.o -endif +obj-$(CONFIG_INFINIBAND_HNS_HIP06) += hns-roce-hw-v1.o -ifdef CONFIG_INFINIBAND_HNS_HIP08 hns-roce-hw-v2-objs := hns_roce_hw_v2.o hns_roce_hw_v2_dfx.o $(hns-roce-objs) -obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o -endif +obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o diff --git a/drivers/infiniband/hw/hns/hns_roce_db.c b/drivers/infiniband/hw/hns/hns_roce_db.c index 627aa46ef683..c00714c2f16a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_db.c +++ b/drivers/infiniband/hw/hns/hns_roce_db.c @@ -12,13 +12,15 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, struct ib_udata *udata, unsigned long virt, struct hns_roce_db *db) { + unsigned long page_addr = virt & PAGE_MASK; struct hns_roce_user_db_page *page; + unsigned int offset; int ret = 0; mutex_lock(&context->page_mutex); list_for_each_entry(page, &context->page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if (page->user_virt == page_addr) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -28,8 +30,8 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, } refcount_set(&page->refcount, 1); - page->user_virt = (virt & PAGE_MASK); - page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0); + page->user_virt = page_addr; + page->umem = ib_umem_get(udata, page_addr, PAGE_SIZE, 0, 0); if (IS_ERR(page->umem)) { ret = PTR_ERR(page->umem); kfree(page); @@ -39,10 +41,9 @@ int hns_roce_db_map_user(struct hns_roce_ucontext *context, list_add(&page->list, &context->page_list); found: - db->dma = sg_dma_address(page->umem->sg_head.sgl) + - (virt & ~PAGE_MASK); - page->umem->sg_head.sgl->offset = virt & ~PAGE_MASK; - db->virt_addr = sg_virt(page->umem->sg_head.sgl); + offset = virt - page_addr; + db->dma = sg_dma_address(page->umem->sg_head.sgl) + offset; + db->virt_addr = sg_virt(page->umem->sg_head.sgl) + offset; db->u.user_page = page; refcount_inc(&page->refcount); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 81e6dedb1e02..c07e387a07a3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -750,8 +750,10 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev) atomic_set(&free_mr->mr_free_cq->ib_cq.usecnt, 0); pd = rdma_zalloc_drv_obj(ibdev, ib_pd); - if (!pd) + if (!pd) { + ret = -ENOMEM; goto alloc_mem_failed; + } pd->device = ibdev; ret = hns_roce_alloc_pd(pd, NULL); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c2a5780cb394..e12a4404096b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5802,13 +5802,12 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, return; } - if (mpi->mdev_events.notifier_call) - mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); - mpi->mdev_events.notifier_call = NULL; - mpi->ibdev = NULL; spin_unlock(&port->mp.mpi_lock); + if (mpi->mdev_events.notifier_call) + mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); + mpi->mdev_events.notifier_call = NULL; mlx5_remove_netdev_notifier(ibdev, port_num); spin_lock(&port->mp.mpi_lock); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index c482f19958b3..f6a53455bf8b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -481,6 +481,7 @@ struct mlx5_umr_wr { u64 length; int access_flags; u32 mkey; + u8 ignore_free_state:1; }; static inline const struct mlx5_umr_wr *umr_wr(const struct ib_send_wr *wr) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 20ece6e0b2fc..b74fad08412f 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -51,22 +51,12 @@ static void clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); -static bool umr_can_modify_entity_size(struct mlx5_ib_dev *dev) -{ - return !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled); -} static bool umr_can_use_indirect_mkey(struct mlx5_ib_dev *dev) { return !MLX5_CAP_GEN(dev->mdev, umr_indirect_mkey_disabled); } -static bool use_umr(struct mlx5_ib_dev *dev, int order) -{ - return order <= mr_cache_max_order(dev) && - umr_can_modify_entity_size(dev); -} - static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); @@ -545,13 +535,16 @@ void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) return; c = order2idx(dev, mr->order); - if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) { - mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c); - return; - } + WARN_ON(c < 0 || c >= MAX_MR_CACHE_ENTRIES); - if (unreg_umr(dev, mr)) + if (unreg_umr(dev, mr)) { + mr->allocated_from_cache = false; + destroy_mkey(dev, mr); + ent = &cache->ent[c]; + if (ent->cur < ent->limit) + queue_work(cache->wq, &ent->work); return; + } ent = &cache->ent[c]; spin_lock_irq(&ent->lock); @@ -1268,7 +1261,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_mr *mr = NULL; - bool populate_mtts = false; + bool use_umr; struct ib_umem *umem; int page_shift; int npages; @@ -1300,29 +1293,30 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, if (err < 0) return ERR_PTR(err); - if (use_umr(dev, order)) { + use_umr = !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled) && + (!MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled) || + !MLX5_CAP_GEN(dev->mdev, atomic)); + + if (order <= mr_cache_max_order(dev) && use_umr) { mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont, page_shift, order, access_flags); if (PTR_ERR(mr) == -EAGAIN) { mlx5_ib_dbg(dev, "cache empty for order %d\n", order); mr = NULL; } - populate_mtts = false; } else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) { if (access_flags & IB_ACCESS_ON_DEMAND) { err = -EINVAL; pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB\n"); goto error; } - populate_mtts = true; + use_umr = false; } if (!mr) { - if (!umr_can_modify_entity_size(dev)) - populate_mtts = true; mutex_lock(&dev->slow_path_mutex); mr = reg_create(NULL, pd, virt_addr, length, umem, ncont, - page_shift, access_flags, populate_mtts); + page_shift, access_flags, !use_umr); mutex_unlock(&dev->slow_path_mutex); } @@ -1338,7 +1332,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, update_odp_mr(mr); - if (!populate_mtts) { + if (use_umr) { int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE; if (access_flags & IB_ACCESS_ON_DEMAND) @@ -1373,9 +1367,11 @@ static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) return 0; umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR | - MLX5_IB_SEND_UMR_FAIL_IF_FREE; + MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS; umrwr.wr.opcode = MLX5_IB_WR_UMR; + umrwr.pd = dev->umrc.pd; umrwr.mkey = mr->mmkey.key; + umrwr.ignore_free_state = 1; return mlx5_ib_post_send_wait(dev, &umrwr); } @@ -1577,10 +1573,10 @@ static void clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) mr->sig = NULL; } - mlx5_free_priv_descs(mr); - - if (!allocated_from_cache) + if (!allocated_from_cache) { destroy_mkey(dev, mr); + mlx5_free_priv_descs(mr); + } } static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 5b642d81e617..81da82050d05 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -246,7 +246,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, * overwrite the same MTTs. Concurent invalidations might race us, * but they will write 0s as well, so no difference in the end result. */ - + mutex_lock(&umem_odp->umem_mutex); for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) { idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift; /* @@ -278,6 +278,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start, idx - blk_start_idx + 1, 0, MLX5_IB_UPD_XLT_ZAP | MLX5_IB_UPD_XLT_ATOMIC); + mutex_unlock(&umem_odp->umem_mutex); /* * We are now sure that the device will not access the * memory. We can safely unmap it, and mark it as dirty if @@ -1771,7 +1772,7 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work) num_pending_prefetch_dec(to_mdev(w->pd->device), w->sg_list, w->num_sge, 0); - kfree(w); + kvfree(w); } int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, @@ -1813,7 +1814,7 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, if (valid_req) queue_work(system_unbound_wq, &work->work); else - kfree(work); + kvfree(work); srcu_read_unlock(&dev->mr_srcu, srcu_key); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 2a97619ed603..379328b2598f 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1713,7 +1713,6 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, } MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ); - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); memcpy(rss_key, ucmd.rx_hash_key, len); break; } @@ -4295,10 +4294,14 @@ static int set_reg_umr_segment(struct mlx5_ib_dev *dev, memset(umr, 0, sizeof(*umr)); - if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE) - umr->flags = MLX5_UMR_CHECK_FREE; /* fail if free */ - else - umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */ + if (!umrwr->ignore_free_state) { + if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE) + /* fail if free */ + umr->flags = MLX5_UMR_CHECK_FREE; + else + /* fail if not free */ + umr->flags = MLX5_UMR_CHECK_NOT_FREE; + } umr->xlt_octowords = cpu_to_be16(get_xlt_octo(umrwr->xlt_size)); if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_XLT) { diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 533157a2a3be..f97b3d65b30c 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -125,14 +125,20 @@ static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, struct qedr_dev *dev = rdma_device_to_drv_device(device, struct qedr_dev, ibdev); - return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor); + return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->attr.hw_ver); } static DEVICE_ATTR_RO(hw_rev); static ssize_t hca_type_show(struct device *device, struct device_attribute *attr, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%s\n", "HCA_TYPE_TO_SET"); + struct qedr_dev *dev = + rdma_device_to_drv_device(device, struct qedr_dev, ibdev); + + return scnprintf(buf, PAGE_SIZE, "FastLinQ QL%x %s\n", + dev->pdev->device, + rdma_protocol_iwarp(&dev->ibdev, 1) ? + "iWARP" : "RoCE"); } static DEVICE_ATTR_RO(hca_type); diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index a7cde98e73e8..9ce8a1b925d2 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -220,13 +220,12 @@ static void siw_put_work(struct siw_cm_work *work) static void siw_cep_set_inuse(struct siw_cep *cep) { unsigned long flags; - int rv; retry: spin_lock_irqsave(&cep->lock, flags); if (cep->in_use) { spin_unlock_irqrestore(&cep->lock, flags); - rv = wait_event_interruptible(cep->waitq, !cep->in_use); + wait_event_interruptible(cep->waitq, !cep->in_use); if (signal_pending(current)) flush_signals(current); goto retry; diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index f55c4e80aea4..d0f140daf659 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -612,6 +612,7 @@ static __init int siw_init_module(void) if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); + rv = -ENOMEM; goto out_error; } /* diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index 11383d9f95ef..e27bd5b35b96 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -220,12 +220,14 @@ static int siw_qp_enable_crc(struct siw_qp *qp) { struct siw_rx_stream *c_rx = &qp->rx_stream; struct siw_iwarp_tx *c_tx = &qp->tx_ctx; - int size = crypto_shash_descsize(siw_crypto_shash) + - sizeof(struct shash_desc); + int size; if (siw_crypto_shash == NULL) return -ENOENT; + size = crypto_shash_descsize(siw_crypto_shash) + + sizeof(struct shash_desc); + c_tx->mpa_crc_hd = kzalloc(size, GFP_KERNEL); c_rx->mpa_crc_hd = kzalloc(size, GFP_KERNEL); if (!c_tx->mpa_crc_hd || !c_rx->mpa_crc_hd) { diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index eb104c719629..4413aa67000e 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -23,6 +23,8 @@ #include <linux/mem_encrypt.h> #include <asm/pci-direct.h> #include <asm/iommu.h> +#include <asm/apic.h> +#include <asm/msidef.h> #include <asm/gart.h> #include <asm/x86_init.h> #include <asm/iommu_table.h> @@ -1920,6 +1922,90 @@ static int iommu_setup_msi(struct amd_iommu *iommu) return 0; } +#define XT_INT_DEST_MODE(x) (((x) & 0x1ULL) << 2) +#define XT_INT_DEST_LO(x) (((x) & 0xFFFFFFULL) << 8) +#define XT_INT_VEC(x) (((x) & 0xFFULL) << 32) +#define XT_INT_DEST_HI(x) ((((x) >> 24) & 0xFFULL) << 56) + +/** + * Setup the IntCapXT registers with interrupt routing information + * based on the PCI MSI capability block registers, accessed via + * MMIO MSI address low/hi and MSI data registers. + */ +static void iommu_update_intcapxt(struct amd_iommu *iommu) +{ + u64 val; + u32 addr_lo = readl(iommu->mmio_base + MMIO_MSI_ADDR_LO_OFFSET); + u32 addr_hi = readl(iommu->mmio_base + MMIO_MSI_ADDR_HI_OFFSET); + u32 data = readl(iommu->mmio_base + MMIO_MSI_DATA_OFFSET); + bool dm = (addr_lo >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1; + u32 dest = ((addr_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xFF); + + if (x2apic_enabled()) + dest |= MSI_ADDR_EXT_DEST_ID(addr_hi); + + val = XT_INT_VEC(data & 0xFF) | + XT_INT_DEST_MODE(dm) | + XT_INT_DEST_LO(dest) | + XT_INT_DEST_HI(dest); + + /** + * Current IOMMU implemtation uses the same IRQ for all + * 3 IOMMU interrupts. + */ + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET); + writeq(val, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET); +} + +static void _irq_notifier_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + if (iommu->dev->irq == notify->irq) { + iommu_update_intcapxt(iommu); + break; + } + } +} + +static void _irq_notifier_release(struct kref *ref) +{ +} + +static int iommu_init_intcapxt(struct amd_iommu *iommu) +{ + int ret; + struct irq_affinity_notify *notify = &iommu->intcapxt_notify; + + /** + * IntCapXT requires XTSup=1, which can be inferred + * amd_iommu_xt_mode. + */ + if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE) + return 0; + + /** + * Also, we need to setup notifier to update the IntCapXT registers + * whenever the irq affinity is changed from user-space. + */ + notify->irq = iommu->dev->irq; + notify->notify = _irq_notifier_notify, + notify->release = _irq_notifier_release, + ret = irq_set_affinity_notifier(iommu->dev->irq, notify); + if (ret) { + pr_err("Failed to register irq affinity notifier (devid=%#x, irq %d)\n", + iommu->devid, iommu->dev->irq); + return ret; + } + + iommu_update_intcapxt(iommu); + iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN); + return ret; +} + static int iommu_init_msi(struct amd_iommu *iommu) { int ret; @@ -1936,6 +2022,10 @@ static int iommu_init_msi(struct amd_iommu *iommu) return ret; enable_faults: + ret = iommu_init_intcapxt(iommu); + if (ret) + return ret; + iommu_feature_enable(iommu, CONTROL_EVT_INT_EN); if (iommu->ppr_log != NULL) diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 52c35d557fad..64edd5a9694c 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -60,6 +60,12 @@ #define MMIO_PPR_LOG_OFFSET 0x0038 #define MMIO_GA_LOG_BASE_OFFSET 0x00e0 #define MMIO_GA_LOG_TAIL_OFFSET 0x00e8 +#define MMIO_MSI_ADDR_LO_OFFSET 0x015C +#define MMIO_MSI_ADDR_HI_OFFSET 0x0160 +#define MMIO_MSI_DATA_OFFSET 0x0164 +#define MMIO_INTCAPXT_EVT_OFFSET 0x0170 +#define MMIO_INTCAPXT_PPR_OFFSET 0x0178 +#define MMIO_INTCAPXT_GALOG_OFFSET 0x0180 #define MMIO_CMD_HEAD_OFFSET 0x2000 #define MMIO_CMD_TAIL_OFFSET 0x2008 #define MMIO_EVT_HEAD_OFFSET 0x2010 @@ -150,6 +156,7 @@ #define CONTROL_GALOG_EN 0x1CULL #define CONTROL_GAINT_EN 0x1DULL #define CONTROL_XT_EN 0x32ULL +#define CONTROL_INTCAPXT_EN 0x33ULL #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) #define CTRL_INV_TO_NONE 0 @@ -592,6 +599,8 @@ struct amd_iommu { /* DebugFS Info */ struct dentry *debugfs; #endif + /* IRQ notifier for IntCapXT interrupt */ + struct irq_affinity_notify intcapxt_notify; }; static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c index 73a552914455..2b25d9c59336 100644 --- a/drivers/iommu/intel-iommu-debugfs.c +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -162,9 +162,9 @@ static inline void print_tbl_walk(struct seq_file *m) (u64)0, (u64)0, (u64)0); else seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n", - tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[0], + tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[2], tbl_wlk->pasid_tbl_entry->val[1], - tbl_wlk->pasid_tbl_entry->val[2]); + tbl_wlk->pasid_tbl_entry->val[0]); } static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac4172c02244..bdaed2da8a55 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -339,8 +339,6 @@ static void domain_exit(struct dmar_domain *domain); static void domain_remove_dev_info(struct dmar_domain *domain); static void dmar_remove_one_dev_info(struct device *dev); static void __dmar_remove_one_dev_info(struct device_domain_info *info); -static void domain_context_clear(struct intel_iommu *iommu, - struct device *dev); static int domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); static bool device_is_rmrr_locked(struct device *dev); @@ -1833,9 +1831,65 @@ static inline int guestwidth_to_adjustwidth(int gaw) return agaw; } +static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu, + int guest_width) +{ + int adjust_width, agaw; + unsigned long sagaw; + int err; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + + err = init_iova_flush_queue(&domain->iovad, + iommu_flush_iova, iova_entry_free); + if (err) + return err; + + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + if (guest_width > cap_mgaw(iommu->cap)) + guest_width = cap_mgaw(iommu->cap); + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + agaw = width_to_agaw(adjust_width); + sagaw = cap_sagaw(iommu->cap); + if (!test_bit(agaw, &sagaw)) { + /* hardware doesn't support it, choose a bigger one */ + pr_debug("Hardware doesn't support agaw %d\n", agaw); + agaw = find_next_bit(&sagaw, 5, agaw); + if (agaw >= 5) + return -ENODEV; + } + domain->agaw = agaw; + + if (ecap_coherent(iommu->ecap)) + domain->iommu_coherency = 1; + else + domain->iommu_coherency = 0; + + if (ecap_sc_support(iommu->ecap)) + domain->iommu_snooping = 1; + else + domain->iommu_snooping = 0; + + if (intel_iommu_superpage) + domain->iommu_superpage = fls(cap_super_page_val(iommu->cap)); + else + domain->iommu_superpage = 0; + + domain->nid = iommu->node; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE); + return 0; +} + static void domain_exit(struct dmar_domain *domain) { - struct page *freelist; /* Remove associated devices and clear attached or cached domains */ domain_remove_dev_info(domain); @@ -1843,9 +1897,12 @@ static void domain_exit(struct dmar_domain *domain) /* destroy iovas */ put_iova_domain(&domain->iovad); - freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + if (domain->pgd) { + struct page *freelist; - dma_free_pagelist(freelist); + freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); + dma_free_pagelist(freelist); + } free_domain_mem(domain); } @@ -2048,26 +2105,9 @@ out_unlock: return ret; } -struct domain_context_mapping_data { - struct dmar_domain *domain; - struct intel_iommu *iommu; - struct pasid_table *table; -}; - -static int domain_context_mapping_cb(struct pci_dev *pdev, - u16 alias, void *opaque) -{ - struct domain_context_mapping_data *data = opaque; - - return domain_context_mapping_one(data->domain, data->iommu, - data->table, PCI_BUS_NUM(alias), - alias & 0xff); -} - static int domain_context_mapping(struct dmar_domain *domain, struct device *dev) { - struct domain_context_mapping_data data; struct pasid_table *table; struct intel_iommu *iommu; u8 bus, devfn; @@ -2077,17 +2117,7 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev) return -ENODEV; table = intel_pasid_get_table(dev); - - if (!dev_is_pci(dev)) - return domain_context_mapping_one(domain, iommu, table, - bus, devfn); - - data.domain = domain; - data.iommu = iommu; - data.table = table; - - return pci_for_each_dma_alias(to_pci_dev(dev), - &domain_context_mapping_cb, &data); + return domain_context_mapping_one(domain, iommu, table, bus, devfn); } static int domain_context_mapped_cb(struct pci_dev *pdev, @@ -2513,31 +2543,6 @@ static int get_last_alias(struct pci_dev *pdev, u16 alias, void *opaque) return 0; } -static int domain_init(struct dmar_domain *domain, int guest_width) -{ - int adjust_width; - - init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); - domain_reserve_special_ranges(domain); - - /* calculate AGAW */ - domain->gaw = guest_width; - adjust_width = guestwidth_to_adjustwidth(guest_width); - domain->agaw = width_to_agaw(adjust_width); - - domain->iommu_coherency = 0; - domain->iommu_snooping = 0; - domain->iommu_superpage = 0; - domain->max_addr = 0; - - /* always allocate the top pgd */ - domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); - if (!domain->pgd) - return -ENOMEM; - domain_flush_cache(domain, domain->pgd, PAGE_SIZE); - return 0; -} - static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) { struct device_domain_info *info; @@ -2575,19 +2580,11 @@ static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw) domain = alloc_domain(0); if (!domain) return NULL; - - if (domain_init(domain, gaw)) { + if (domain_init(domain, iommu, gaw)) { domain_exit(domain); return NULL; } - if (init_iova_flush_queue(&domain->iovad, - iommu_flush_iova, - iova_entry_free)) { - pr_warn("iova flush queue initialization failed\n"); - intel_iommu_strict = 1; - } - out: return domain; } @@ -2692,6 +2689,8 @@ static int domain_prepare_identity_map(struct device *dev, return iommu_domain_identity_map(domain, start, end); } +static int md_domain_init(struct dmar_domain *domain, int guest_width); + static int __init si_domain_init(int hw) { struct dmar_rmrr_unit *rmrr; @@ -2702,7 +2701,7 @@ static int __init si_domain_init(int hw) if (!si_domain) return -EFAULT; - if (domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); return -EFAULT; } @@ -3564,7 +3563,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) freelist = domain_unmap(domain, start_pfn, last_pfn); - if (intel_iommu_strict || (pdev && pdev->untrusted)) { + if (intel_iommu_strict || (pdev && pdev->untrusted) || + !has_iova_flush_queue(&domain->iovad)) { iommu_flush_iotlb_psi(iommu, domain, start_pfn, nrpages, !freelist, 0); /* free iova */ @@ -4758,28 +4758,6 @@ out_free_dmar: return ret; } -static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) -{ - struct intel_iommu *iommu = opaque; - - domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); - return 0; -} - -/* - * NB - intel-iommu lacks any sort of reference counting for the users of - * dependent devices. If multiple endpoints have intersecting dependent - * devices, unbinding the driver from any one of them will possibly leave - * the others unable to operate. - */ -static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) -{ - if (!iommu || !dev || !dev_is_pci(dev)) - return; - - pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); -} - static void __dmar_remove_one_dev_info(struct device_domain_info *info) { struct dmar_domain *domain; @@ -4800,7 +4778,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) PASID_RID2PASID); iommu_disable_dev_iotlb(info); - domain_context_clear(iommu, info->dev); + domain_context_clear_one(iommu, info->bus, info->devfn); intel_pasid_free_table(info->dev); } @@ -4829,6 +4807,31 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_unlock_irqrestore(&device_domain_lock, flags); } +static int md_domain_init(struct dmar_domain *domain, int guest_width) +{ + int adjust_width; + + init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN); + domain_reserve_special_ranges(domain); + + /* calculate AGAW */ + domain->gaw = guest_width; + adjust_width = guestwidth_to_adjustwidth(guest_width); + domain->agaw = width_to_agaw(adjust_width); + + domain->iommu_coherency = 0; + domain->iommu_snooping = 0; + domain->iommu_superpage = 0; + domain->max_addr = 0; + + /* always allocate the top pgd */ + domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid); + if (!domain->pgd) + return -ENOMEM; + domain_flush_cache(domain, domain->pgd, PAGE_SIZE); + return 0; +} + static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) { struct dmar_domain *dmar_domain; @@ -4843,7 +4846,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) pr_err("Can't allocate dmar_domain\n"); return NULL; } - if (domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { + if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { pr_err("Domain initialization failed\n"); domain_exit(dmar_domain); return NULL; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index d499b2621239..3e1a8a675572 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -54,9 +54,14 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, } EXPORT_SYMBOL_GPL(init_iova_domain); +bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return !!iovad->fq; +} + static void free_iova_flush_queue(struct iova_domain *iovad) { - if (!iovad->fq) + if (!has_iova_flush_queue(iovad)) return; if (timer_pending(&iovad->fq_timer)) @@ -74,13 +79,14 @@ static void free_iova_flush_queue(struct iova_domain *iovad) int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) { + struct iova_fq __percpu *queue; int cpu; atomic64_set(&iovad->fq_flush_start_cnt, 0); atomic64_set(&iovad->fq_flush_finish_cnt, 0); - iovad->fq = alloc_percpu(struct iova_fq); - if (!iovad->fq) + queue = alloc_percpu(struct iova_fq); + if (!queue) return -ENOMEM; iovad->flush_cb = flush_cb; @@ -89,13 +95,17 @@ int init_iova_flush_queue(struct iova_domain *iovad, for_each_possible_cpu(cpu) { struct iova_fq *fq; - fq = per_cpu_ptr(iovad->fq, cpu); + fq = per_cpu_ptr(queue, cpu); fq->head = 0; fq->tail = 0; spin_lock_init(&fq->lock); } + smp_wmb(); + + iovad->fq = queue; + timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); atomic_set(&iovad->fq_timer_on, 0); @@ -127,8 +137,9 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) struct iova *cached_iova; cached_iova = rb_entry(iovad->cached32_node, struct iova, node); - if (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo) { + if (free == cached_iova || + (free->pfn_hi < iovad->dma_32bit_pfn && + free->pfn_lo >= cached_iova->pfn_lo)) { iovad->cached32_node = rb_next(&free->node); iovad->max32_alloc_size = iovad->dma_32bit_pfn; } diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 433f4d2ee956..80a740df0737 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -2,7 +2,7 @@ /* * Virtio driver for the paravirtualized IOMMU * - * Copyright (C) 2018 Arm Limited + * Copyright (C) 2019 Arm Limited */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -47,7 +47,10 @@ struct viommu_dev { /* Device configuration */ struct iommu_domain_geometry geometry; u64 pgsize_bitmap; - u8 domain_bits; + u32 first_domain; + u32 last_domain; + /* Supported MAP flags */ + u32 map_flags; u32 probe_size; }; @@ -62,6 +65,7 @@ struct viommu_domain { struct viommu_dev *viommu; struct mutex mutex; /* protects viommu pointer */ unsigned int id; + u32 map_flags; spinlock_t mappings_lock; struct rb_root_cached mappings; @@ -113,6 +117,8 @@ static int viommu_get_req_errno(void *buf, size_t len) return -ENOENT; case VIRTIO_IOMMU_S_FAULT: return -EFAULT; + case VIRTIO_IOMMU_S_NOMEM: + return -ENOMEM; case VIRTIO_IOMMU_S_IOERR: case VIRTIO_IOMMU_S_DEVERR: default: @@ -607,15 +613,15 @@ static int viommu_domain_finalise(struct viommu_dev *viommu, { int ret; struct viommu_domain *vdomain = to_viommu_domain(domain); - unsigned int max_domain = viommu->domain_bits > 31 ? ~0 : - (1U << viommu->domain_bits) - 1; vdomain->viommu = viommu; + vdomain->map_flags = viommu->map_flags; domain->pgsize_bitmap = viommu->pgsize_bitmap; domain->geometry = viommu->geometry; - ret = ida_alloc_max(&viommu->domain_ids, max_domain, GFP_KERNEL); + ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain, + viommu->last_domain, GFP_KERNEL); if (ret >= 0) vdomain->id = (unsigned int)ret; @@ -710,7 +716,7 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot) { int ret; - int flags; + u32 flags; struct virtio_iommu_req_map map; struct viommu_domain *vdomain = to_viommu_domain(domain); @@ -718,6 +724,9 @@ static int viommu_map(struct iommu_domain *domain, unsigned long iova, (prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) | (prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0); + if (flags & ~vdomain->map_flags) + return -EINVAL; + ret = viommu_add_mapping(vdomain, iova, paddr, size, flags); if (ret) return ret; @@ -1027,7 +1036,8 @@ static int viommu_probe(struct virtio_device *vdev) goto err_free_vqs; } - viommu->domain_bits = 32; + viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE; + viommu->last_domain = ~0U; /* Optional features */ virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE, @@ -1038,9 +1048,13 @@ static int viommu_probe(struct virtio_device *vdev) struct virtio_iommu_config, input_range.end, &input_end); - virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_BITS, - struct virtio_iommu_config, domain_bits, - &viommu->domain_bits); + virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.start, + &viommu->first_domain); + + virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE, + struct virtio_iommu_config, domain_range.end, + &viommu->last_domain); virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE, struct virtio_iommu_config, probe_size, @@ -1052,6 +1066,9 @@ static int viommu_probe(struct virtio_device *vdev) .force_aperture = true, }; + if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO)) + viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO; + viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap; virtio_device_ready(vdev); @@ -1130,9 +1147,10 @@ static void viommu_config_changed(struct virtio_device *vdev) static unsigned int features[] = { VIRTIO_IOMMU_F_MAP_UNMAP, - VIRTIO_IOMMU_F_DOMAIN_BITS, VIRTIO_IOMMU_F_INPUT_RANGE, + VIRTIO_IOMMU_F_DOMAIN_RANGE, VIRTIO_IOMMU_F_PROBE, + VIRTIO_IOMMU_F_MMIO, }; static struct virtio_device_id id_table[] = { diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 730fbe0e2a9d..1b5c3672aea2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3010,7 +3010,7 @@ static int its_vpe_init(struct its_vpe *vpe) if (!its_alloc_vpe_table(vpe_id)) { its_vpe_id_free(vpe_id); - its_free_pending_table(vpe->vpt_page); + its_free_pending_table(vpt_page); return -ENOMEM; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 9bca4896fa6f..96d927f0f91a 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -771,8 +771,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); + /* Fall through */ case 6: write_gicreg(0, ICC_AP0R1_EL1); + /* Fall through */ case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); @@ -786,8 +788,10 @@ static void gic_cpu_sys_reg_init(void) case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); + /* Fall through */ case 6: write_gicreg(0, ICC_AP1R1_EL1); + /* Fall through */ case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index bf2237ac5d09..4f74c15c4755 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -131,6 +131,7 @@ static struct irq_chip gpcv2_irqchip_data_chip = { .irq_unmask = imx_gpcv2_irq_unmask, .irq_set_wake = imx_gpcv2_irq_set_wake, .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_type = irq_chip_set_type_parent, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, #endif diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 3dd28382d5f5..3f09f658e8e2 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -241,12 +241,15 @@ static int mbigen_of_create_domain(struct platform_device *pdev, parent = platform_bus_type.dev_root; child = of_platform_device_create(np, NULL, parent); - if (!child) + if (!child) { + of_node_put(np); return -ENOMEM; + } if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); + of_node_put(np); return -EINVAL; } @@ -254,8 +257,10 @@ static int mbigen_of_create_domain(struct platform_device *pdev, mbigen_write_msg, &mbigen_domain_ops, mgn_chip); - if (!domain) + if (!domain) { + of_node_put(np); return -ENOMEM; + } } return 0; diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 0e224232f746..008a74a1ed44 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1394,6 +1394,7 @@ start_isoc_chain(struct usb_fifo *fifo, int num_packets_per_urb, printk(KERN_DEBUG "%s: %s: alloc urb for fifo %i failed", hw->name, __func__, fifo->fifonum); + continue; } fifo->iso[i].owner_fifo = (struct usb_fifo *) fifo; fifo->iso[i].indx = i; @@ -1692,13 +1693,23 @@ hfcsusb_stop_endpoint(struct hfcsusb *hw, int channel) static int setup_hfcsusb(struct hfcsusb *hw) { + void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL); u_char b; + int ret; if (debug & DBG_HFC_CALL_TRACE) printk(KERN_DEBUG "%s: %s\n", hw->name, __func__); + if (!dmabuf) + return -ENOMEM; + + ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf); + + memcpy(&b, dmabuf, sizeof(u_char)); + kfree(dmabuf); + /* check the chip id */ - if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) { + if (ret != 1) { printk(KERN_DEBUG "%s: %s: cannot read chip id\n", hw->name, __func__); return 1; diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 276065c888bc..23f1f41c8602 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -852,6 +852,7 @@ int smu_queue_i2c(struct smu_i2c_cmd *cmd) break; case SMU_I2C_TRANSFER_COMBINED: cmd->info.devaddr &= 0xfe; + /* fall through */ case SMU_I2C_TRANSFER_STDSUB: if (cmd->info.sublen > 3) return -EINVAL; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 26e374fbf57c..20ed838e9413 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -931,6 +931,9 @@ int bch_cached_dev_run(struct cached_dev *dc) if (dc->io_disable) { pr_err("I/O disabled on cached dev %s", dc->backing_dev_name); + kfree(env[1]); + kfree(env[2]); + kfree(buf); return -EIO; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index caaee8032afe..7b6c3ee9e755 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -882,23 +882,23 @@ EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ int device_supports_dax(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) + sector_t start, sector_t len, void *data) { int blocksize = *(int *) data; return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize, - start, len); + start, len); } /* Check devices support synchronous DAX */ -static int device_synchronous(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - return dax_synchronous(dev->dax_dev); + return dev->dax_dev && dax_synchronous(dev->dax_dev); } bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) + iterate_devices_callout_fn iterate_fn, int *blocksize) { struct dm_target *ti; unsigned i; @@ -911,7 +911,7 @@ bool dm_table_supports_dax(struct dm_table *t, return false; if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, iterate_fn, blocksize)) + !ti->type->iterate_devices(ti, iterate_fn, blocksize)) return false; } @@ -1921,7 +1921,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (dm_table_supports_dax(t, device_supports_dax, &page_size)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_synchronous, NULL)) + if (dm_table_supports_dax(t, device_dax_synchronous, NULL)) set_dax_synchronous(t->md->dax_dev); } else diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index f88094719552..f2abe27010ef 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -5,6 +5,7 @@ config EEPROM_AT24 tristate "I2C EEPROMs / RAMs / ROMs from most vendors" depends on I2C && SYSFS select NVMEM + select NVMEM_SYSFS select REGMAP_I2C help Enable this driver to get read/write support to most I2C EEPROMs @@ -34,6 +35,7 @@ config EEPROM_AT25 tristate "SPI EEPROMs from most vendors" depends on SPI && SYSFS select NVMEM + select NVMEM_SYSFS help Enable this driver to get read/write support to most SPI EEPROMs, after you configure the board init code to know about each eeprom @@ -80,6 +82,7 @@ config EEPROM_93XX46 depends on SPI && SYSFS select REGMAP select NVMEM + select NVMEM_SYSFS help Driver for the microwire EEPROM chipsets 93xx46x. The driver supports both read and write commands and also the command to diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 35bf2477693d..518945b2f737 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -685,7 +685,7 @@ static int at24_probe(struct i2c_client *client) nvmem_config.name = dev_name(dev); nvmem_config.dev = dev; nvmem_config.read_only = !writable; - nvmem_config.root_only = true; + nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO); nvmem_config.owner = THIS_MODULE; nvmem_config.compat = true; nvmem_config.base_dev = dev; diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 75294ec65257..1a2c062a57d4 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -695,8 +695,8 @@ static int goya_sw_init(struct hl_device *hdev) goto free_dma_pool; } - dev_dbg(hdev->dev, "cpu accessible memory at bus address 0x%llx\n", - hdev->cpu_accessible_dma_address); + dev_dbg(hdev->dev, "cpu accessible memory at bus address %pad\n", + &hdev->cpu_accessible_dma_address); hdev->cpu_accessible_dma_pool = gen_pool_create(ilog2(32), -1); if (!hdev->cpu_accessible_dma_pool) { @@ -4449,7 +4449,6 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry) case GOYA_ASYNC_EVENT_ID_AXI_ECC: case GOYA_ASYNC_EVENT_ID_L2_RAM_ECC: case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET: - case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT: goya_print_irq_info(hdev, event_type, false); hl_device_reset(hdev, true, false); break; @@ -4485,6 +4484,7 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry) goya_unmask_irq(hdev, event_type); break; + case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT: case GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU: case GOYA_ASYNC_EVENT_ID_TPC1_BMON_SPMU: case GOYA_ASYNC_EVENT_ID_TPC2_BMON_SPMU: diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index d74b182e19f3..6c0173772162 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -81,6 +81,9 @@ #define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ +#define MEI_DEV_ID_MCC 0x4B70 /* Mule Creek Canyon (EHL) */ +#define MEI_DEV_ID_MCC_4 0x4B75 /* Mule Creek Canyon 4 (EHL) */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 7a2b3545a7f9..57cb68f5cc64 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -98,6 +98,9 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MCC_4, MEI_ME_PCH8_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index e327f80ebe70..7102e2ebc614 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -10,6 +10,7 @@ #include <linux/kthread.h> #include <linux/scatterlist.h> #include <linux/dma-mapping.h> +#include <linux/backing-dev.h> #include <linux/mmc/card.h> #include <linux/mmc/host.h> @@ -427,6 +428,10 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) goto free_tag_set; } + if (mmc_host_is_spi(host) && host->use_spi_crc) + mq->queue->backing_dev_info->capabilities |= + BDI_CAP_STABLE_WRITES; + mq->queue->queuedata = mq; blk_queue_rq_timeout(mq->queue, 60 * HZ); diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index faaaf52a46d2..eea52e2c5a0c 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -2012,8 +2012,7 @@ static void dw_mci_tasklet_func(unsigned long priv) * delayed. Allowing the transfer to take place * avoids races and keeps things simple. */ - if ((err != -ETIMEDOUT) && - (cmd->opcode == MMC_SEND_TUNING_BLOCK)) { + if (err != -ETIMEDOUT) { state = STATE_SENDING_DATA; continue; } diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 2d736e416775..ba9a63db73da 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -73,7 +73,7 @@ #define MESON_MX_SDIO_IRQC_IF_CONFIG_MASK GENMASK(7, 6) #define MESON_MX_SDIO_IRQC_FORCE_DATA_CLK BIT(8) #define MESON_MX_SDIO_IRQC_FORCE_DATA_CMD BIT(9) - #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(10, 13) + #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(13, 10) #define MESON_MX_SDIO_IRQC_SOFT_RESET BIT(15) #define MESON_MX_SDIO_IRQC_FORCE_HALT BIT(30) #define MESON_MX_SDIO_IRQC_HALT_HOLE BIT(31) diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 6ee340a3fb3a..603a5d9f045a 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -624,6 +624,7 @@ err_cleanup_host: sdhci_cleanup_host(host); pm_runtime_disable: + pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); diff --git a/drivers/mtd/hyperbus/Kconfig b/drivers/mtd/hyperbus/Kconfig index cff6bbd226f5..b4e3caf7d799 100644 --- a/drivers/mtd/hyperbus/Kconfig +++ b/drivers/mtd/hyperbus/Kconfig @@ -14,8 +14,9 @@ if MTD_HYPERBUS config HBMC_AM654 tristate "HyperBus controller driver for AM65x SoC" + depends on ARM64 || COMPILE_TEST select MULTIPLEXER - select MUX_MMIO + imply MUX_MMIO help This is the driver for HyperBus controller on TI's AM65x and other SoCs diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c index a1f8fe1abb10..e082d632fb74 100644 --- a/drivers/mtd/nand/onenand/onenand_base.c +++ b/drivers/mtd/nand/onenand/onenand_base.c @@ -3259,6 +3259,7 @@ static void onenand_check_features(struct mtd_info *mtd) switch (density) { case ONENAND_DEVICE_DENSITY_8Gb: this->options |= ONENAND_HAS_NOP_1; + /* fall through */ case ONENAND_DEVICE_DENSITY_4Gb: if (ONENAND_IS_DDP(this)) this->options |= ONENAND_HAS_2PLANE; diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c index 1622d3145587..8ca9fad6e6ad 100644 --- a/drivers/mtd/nand/raw/nand_micron.c +++ b/drivers/mtd/nand/raw/nand_micron.c @@ -390,6 +390,14 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip) (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2) return MICRON_ON_DIE_UNSUPPORTED; + /* + * It seems that there are devices which do not support ECC officially. + * At least the MT29F2G08ABAGA / MT29F2G08ABBGA devices supports + * enabling the ECC feature but don't reflect that to the READ_ID table. + * So we have to guarantee that we disable the ECC feature directly + * after we did the READ_ID table command. Later we can evaluate the + * ECC_ENABLE support. + */ ret = micron_nand_on_die_ecc_setup(chip, true); if (ret) return MICRON_ON_DIE_UNSUPPORTED; @@ -398,13 +406,13 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip) if (ret) return MICRON_ON_DIE_UNSUPPORTED; - if (!(id[4] & MICRON_ID_ECC_ENABLED)) - return MICRON_ON_DIE_UNSUPPORTED; - ret = micron_nand_on_die_ecc_setup(chip, false); if (ret) return MICRON_ON_DIE_UNSUPPORTED; + if (!(id[4] & MICRON_ID_ECC_ENABLED)) + return MICRON_ON_DIE_UNSUPPORTED; + ret = nand_readid_op(chip, 0, id, sizeof(id)); if (ret) return MICRON_ON_DIE_UNSUPPORTED; diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 11c5bad95226..14a5fb378145 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -363,10 +363,13 @@ static int __init arcrimi_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 3: /* Node ID */ node = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 28510e33924f..cd27fdc1059b 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -197,16 +197,22 @@ static int __init com20020isa_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_info("Too many arguments\n"); + /* Fall through */ case 6: /* Timeout */ timeout = ints[6]; + /* Fall through */ case 5: /* CKP value */ clockp = ints[5]; + /* Fall through */ case 4: /* Backplane flag */ backplane = ints[4]; + /* Fall through */ case 3: /* Node ID */ node = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 2c546013a980..186bbf87bc84 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -363,8 +363,10 @@ static int __init com90io_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index ca4a57c30bf8..bd75d06ad7df 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -693,10 +693,13 @@ static int __init com90xx_setup(char *s) switch (ints[0]) { default: /* ERROR */ pr_err("Too many arguments\n"); + /* Fall through */ case 3: /* Mem address */ shmem = ints[3]; + /* Fall through */ case 2: /* IRQ */ irq = ints[2]; + /* Fall through */ case 1: /* IO address */ io = ints[1]; } diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 1360f1ffe070..f3f86ef68ae0 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -55,11 +55,6 @@ void bond_debug_register(struct bonding *bond) bond->debug_dir = debugfs_create_dir(bond->dev->name, bonding_debug_root); - if (!bond->debug_dir) { - netdev_warn(bond->dev, "failed to register to debugfs\n"); - return; - } - debugfs_create_file("rlb_hash_table", 0400, bond->debug_dir, bond, &bond_debug_rlb_hash_fops); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9b7016abca2f..02fd7822c14a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2196,6 +2196,15 @@ static void bond_miimon_commit(struct bonding *bond) bond_for_each_slave(bond, slave, iter) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: + /* For 802.3ad mode, check current slave speed and + * duplex again in case its port was disabled after + * invalid speed/duplex reporting but recovered before + * link monitoring could make a decision on the actual + * link status + */ + if (BOND_MODE(bond) == BOND_MODE_8023AD && + slave->link == BOND_LINK_UP) + bond_3ad_adapter_speed_duplex_changed(slave); continue; case BOND_LINK_UP: diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index ed3c437063dc..40b079162804 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -94,26 +94,20 @@ static inline void update_tty_status(struct ser_device *ser) } static inline void debugfs_init(struct ser_device *ser, struct tty_struct *tty) { - ser->debugfs_tty_dir = - debugfs_create_dir(tty->name, debugfsdir); - if (!IS_ERR(ser->debugfs_tty_dir)) { - debugfs_create_blob("last_tx_msg", 0400, - ser->debugfs_tty_dir, - &ser->tx_blob); + ser->debugfs_tty_dir = debugfs_create_dir(tty->name, debugfsdir); - debugfs_create_blob("last_rx_msg", 0400, - ser->debugfs_tty_dir, - &ser->rx_blob); + debugfs_create_blob("last_tx_msg", 0400, ser->debugfs_tty_dir, + &ser->tx_blob); - debugfs_create_x32("ser_state", 0400, - ser->debugfs_tty_dir, - (u32 *)&ser->state); + debugfs_create_blob("last_rx_msg", 0400, ser->debugfs_tty_dir, + &ser->rx_blob); - debugfs_create_x8("tty_status", 0400, - ser->debugfs_tty_dir, - &ser->tty_status); + debugfs_create_x32("ser_state", 0400, ser->debugfs_tty_dir, + (u32 *)&ser->state); + + debugfs_create_x8("tty_status", 0400, ser->debugfs_tty_dir, + &ser->tty_status); - } ser->tx_blob.data = ser->tx_data; ser->tx_blob.size = 0; ser->rx_blob.data = ser->rx_data; diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 27e93a438dd9..eb426822ad06 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -623,11 +623,7 @@ static void cfv_netdev_setup(struct net_device *netdev) /* Create debugfs counters for the device */ static inline void debugfs_init(struct cfv_info *cfv) { - cfv->debugfs = - debugfs_create_dir(netdev_name(cfv->ndev), NULL); - - if (IS_ERR(cfv->debugfs)) - return; + cfv->debugfs = debugfs_create_dir(netdev_name(cfv->ndev), NULL); debugfs_create_u32("rx-napi-complete", 0400, cfv->debugfs, &cfv->stats.rx_napi_complete); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index b6b93a2d93a5..483d270664cc 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1249,6 +1249,8 @@ int register_candev(struct net_device *dev) return -EINVAL; dev->rtnl_link_ops = &can_link_ops; + netif_carrier_off(dev); + return register_netdev(dev); } EXPORT_SYMBOL_GPL(register_candev); diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 09d8e623dcf6..dc5695dffc2e 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -404,9 +404,10 @@ static void flexcan_enable_wakeup_irq(struct flexcan_priv *priv, bool enable) priv->write(reg_mcr, ®s->mcr); } -static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv) +static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; + unsigned int ackval; u32 reg_mcr; reg_mcr = priv->read(®s->mcr); @@ -416,20 +417,37 @@ static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv) /* enable stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); + + /* get stop acknowledgment */ + if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, + ackval, ackval & (1 << priv->stm.ack_bit), + 0, FLEXCAN_TIMEOUT_US)) + return -ETIMEDOUT; + + return 0; } -static inline void flexcan_exit_stop_mode(struct flexcan_priv *priv) +static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; + unsigned int ackval; u32 reg_mcr; /* remove stop request */ regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 0); + /* get stop acknowledgment */ + if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr, + ackval, !(ackval & (1 << priv->stm.ack_bit)), + 0, FLEXCAN_TIMEOUT_US)) + return -ETIMEDOUT; + reg_mcr = priv->read(®s->mcr); reg_mcr &= ~FLEXCAN_MCR_SLF_WAK; priv->write(reg_mcr, ®s->mcr); + + return 0; } static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) @@ -1455,10 +1473,10 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) priv = netdev_priv(dev); priv->stm.gpr = syscon_node_to_regmap(gpr_np); - of_node_put(gpr_np); if (IS_ERR(priv->stm.gpr)) { dev_dbg(&pdev->dev, "could not find gpr regmap\n"); - return PTR_ERR(priv->stm.gpr); + ret = PTR_ERR(priv->stm.gpr); + goto out_put_node; } priv->stm.req_gpr = out_val[1]; @@ -1477,6 +1495,10 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) device_set_wakeup_enable(&pdev->dev, true); return 0; + +out_put_node: + of_node_put(gpr_np); + return ret; } static const struct of_device_id flexcan_of_match[] = { @@ -1644,7 +1666,9 @@ static int __maybe_unused flexcan_suspend(struct device *device) */ if (device_may_wakeup(device)) { enable_irq_wake(dev->irq); - flexcan_enter_stop_mode(priv); + err = flexcan_enter_stop_mode(priv); + if (err) + return err; } else { err = flexcan_chip_disable(priv); if (err) @@ -1717,10 +1741,13 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); + int err; if (netif_running(dev) && device_may_wakeup(device)) { flexcan_enable_wakeup_irq(priv, false); - flexcan_exit_stop_mode(priv); + err = flexcan_exit_stop_mode(priv); + if (err) + return err; } return 0; diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 51eecc7cdcdd..edaa1ca972c1 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1508,10 +1508,11 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota) /* All packets processed */ if (num_pkts < quota) { - napi_complete_done(napi, num_pkts); - /* Enable Rx FIFO interrupts */ - rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), - RCANFD_RFCC_RFIE); + if (napi_complete_done(napi, num_pkts)) { + /* Enable Rx FIFO interrupts */ + rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), + RCANFD_RFCC_RFIE); + } } return num_pkts; } diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c index 185c7f7d38a4..5e0d5e8101c8 100644 --- a/drivers/net/can/sja1000/peak_pcmcia.c +++ b/drivers/net/can/sja1000/peak_pcmcia.c @@ -479,7 +479,7 @@ static void pcan_free_channels(struct pcan_pccard *card) if (!netdev) continue; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ); unregister_sja1000dev(netdev); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 234cf1042df6..12358f06d194 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -664,17 +664,6 @@ static int mcp251x_power_enable(struct regulator *reg, int enable) return regulator_disable(reg); } -static void mcp251x_open_clean(struct net_device *net) -{ - struct mcp251x_priv *priv = netdev_priv(net); - struct spi_device *spi = priv->spi; - - free_irq(spi->irq, priv); - mcp251x_hw_sleep(spi); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); -} - static int mcp251x_stop(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); @@ -941,37 +930,43 @@ static int mcp251x_open(struct net_device *net) flags | IRQF_ONESHOT, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); - mcp251x_power_enable(priv->transceiver, 0); - close_candev(net); - goto open_unlock; + goto out_close; } priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!priv->wq) { + ret = -ENOMEM; + goto out_clean; + } INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler); INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler); ret = mcp251x_hw_reset(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_setup(net, spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; ret = mcp251x_set_normal_mode(spi); - if (ret) { - mcp251x_open_clean(net); - goto open_unlock; - } + if (ret) + goto out_free_wq; can_led_event(net, CAN_LED_EVENT_OPEN); netif_wake_queue(net); + mutex_unlock(&priv->mcp_lock); -open_unlock: + return 0; + +out_free_wq: + destroy_workqueue(priv->wq); +out_clean: + free_irq(spi->irq, priv); + mcp251x_hw_sleep(spi); +out_close: + mcp251x_power_enable(priv->transceiver, 0); + close_candev(net); mutex_unlock(&priv->mcp_lock); return ret; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 458154c9b482..65dce642b86b 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -568,16 +568,16 @@ static int peak_usb_ndo_stop(struct net_device *netdev) dev->state &= ~PCAN_USB_STATE_STARTED; netif_stop_queue(netdev); + close_candev(netdev); + + dev->can.state = CAN_STATE_STOPPED; + /* unlink all pending urbs and free used memory */ peak_usb_unlink_all_urbs(dev); if (dev->adapter->dev_stop) dev->adapter->dev_stop(dev); - close_candev(netdev); - - dev->can.state = CAN_STATE_STOPPED; - /* can set bus off now */ if (dev->adapter->dev_set_bus) { int err = dev->adapter->dev_set_bus(dev, 0); @@ -855,7 +855,7 @@ static void peak_usb_disconnect(struct usb_interface *intf) dev_prev_siblings = dev->prev_siblings; dev->state &= ~PCAN_USB_STATE_CONNECTED; - strncpy(name, netdev->name, IFNAMSIZ); + strlcpy(name, netdev->name, IFNAMSIZ); unregister_netdev(netdev); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 34761c3a6286..47cc1ff5b88e 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -841,7 +841,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) goto err_out; /* allocate command buffer once for all for the interface */ - pdev->cmd_buffer_addr = kmalloc(PCAN_UFD_CMD_BUFFER_SIZE, + pdev->cmd_buffer_addr = kzalloc(PCAN_UFD_CMD_BUFFER_SIZE, GFP_KERNEL); if (!pdev->cmd_buffer_addr) goto err_out_1; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 178bb7cff0c1..53cb2f72bdd0 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -494,7 +494,7 @@ static int pcan_usb_pro_drv_loaded(struct peak_usb_device *dev, int loaded) u8 *buffer; int err; - buffer = kmalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL); + buffer = kzalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL); if (!buffer) return -ENOMEM; diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig index 5e4f74286ea3..e1c23d1e91e6 100644 --- a/drivers/net/dsa/microchip/Kconfig +++ b/drivers/net/dsa/microchip/Kconfig @@ -5,7 +5,6 @@ config NET_DSA_MICROCHIP_KSZ_COMMON menuconfig NET_DSA_MICROCHIP_KSZ9477 tristate "Microchip KSZ9477 series switch support" depends on NET_DSA - select NET_DSA_TAG_KSZ9477 select NET_DSA_MICROCHIP_KSZ_COMMON help This driver adds support for Microchip KSZ9477 switch chips. diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index ae80b3c6dea2..a23d3ffdf0c4 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -18,7 +18,6 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" #include "ksz_common.h" #include "ksz8795_reg.h" diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index 50aa0d24effb..d0f8153e86b7 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -14,7 +14,6 @@ #include <linux/regmap.h> #include <linux/spi/spi.h> -#include "ksz_priv.h" #include "ksz_common.h" #define SPI_ADDR_SHIFT 12 diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index a8c97f7a79b7..187be42de5f1 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -14,7 +14,6 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" #include "ksz9477_reg.h" #include "ksz_common.h" diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index 5a9e27b337a8..a226b389e12d 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -13,7 +13,6 @@ #include <linux/regmap.h> #include <linux/spi/spi.h> -#include "ksz_priv.h" #include "ksz_common.h" #define SPI_ADDR_SHIFT 24 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index ce20cc90f9ef..b45c7b972cec 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -18,17 +18,7 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" - -void ksz_port_cleanup(struct ksz_device *dev, int port) -{ - /* Common code for port cleanup. */ - mutex_lock(&dev->dev_mutex); - dev->on_ports &= ~(1 << port); - dev->live_ports &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); -} -EXPORT_SYMBOL_GPL(ksz_port_cleanup); +#include "ksz_common.h" void ksz_update_port_member(struct ksz_device *dev, int port) { diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 84fed4a2578b..c44a8d23d973 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -7,9 +7,152 @@ #ifndef __KSZ_COMMON_H #define __KSZ_COMMON_H +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/phy.h> #include <linux/regmap.h> +#include <net/dsa.h> + +struct vlan_table { + u32 table[3]; +}; + +struct ksz_port_mib { + struct mutex cnt_mutex; /* structure access */ + u8 cnt_ptr; + u64 *counters; +}; + +struct ksz_port { + u16 member; + u16 vid_member; + int stp_state; + struct phy_device phydev; + + u32 on:1; /* port is not disabled by hardware */ + u32 phy:1; /* port has a PHY */ + u32 fiber:1; /* port is fiber */ + u32 sgmii:1; /* port is SGMII */ + u32 force:1; + u32 read:1; /* read MIB counters in background */ + u32 freeze:1; /* MIB counter freeze is enabled */ + + struct ksz_port_mib mib; +}; + +struct ksz_device { + struct dsa_switch *ds; + struct ksz_platform_data *pdata; + const char *name; + + struct mutex dev_mutex; /* device access */ + struct mutex stats_mutex; /* status access */ + struct mutex alu_mutex; /* ALU access */ + struct mutex vlan_mutex; /* vlan access */ + const struct ksz_dev_ops *dev_ops; + + struct device *dev; + struct regmap *regmap[3]; + + void *priv; + + struct gpio_desc *reset_gpio; /* Optional reset GPIO */ + + /* chip specific data */ + u32 chip_id; + int num_vlans; + int num_alus; + int num_statics; + int cpu_port; /* port connected to CPU */ + int cpu_ports; /* port bitmap can be cpu port */ + int phy_port_cnt; + int port_cnt; + int reg_mib_cnt; + int mib_cnt; + int mib_port_cnt; + int last_port; /* ports after that not used */ + phy_interface_t interface; + u32 regs_size; + bool phy_errata_9477; + bool synclko_125; + + struct vlan_table *vlan_cache; + + struct ksz_port *ports; + struct timer_list mib_read_timer; + struct work_struct mib_read; + unsigned long mib_read_interval; + u16 br_member; + u16 member; + u16 live_ports; + u16 on_ports; /* ports enabled by DSA */ + u16 rx_ports; + u16 tx_ports; + u16 mirror_rx; + u16 mirror_tx; + u32 features; /* chip specific features */ + u32 overrides; /* chip functions set by user */ + u16 host_mask; + u16 port_mask; +}; + +struct alu_struct { + /* entry 1 */ + u8 is_static:1; + u8 is_src_filter:1; + u8 is_dst_filter:1; + u8 prio_age:3; + u32 _reserv_0_1:23; + u8 mstp:3; + /* entry 2 */ + u8 is_override:1; + u8 is_use_fid:1; + u32 _reserv_1_1:23; + u8 port_forward:7; + /* entry 3 & 4*/ + u32 _reserv_2_1:9; + u8 fid:7; + u8 mac[ETH_ALEN]; +}; + +struct ksz_dev_ops { + u32 (*get_port_addr)(int port, int offset); + void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); + void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); + void (*phy_setup)(struct ksz_device *dev, int port, + struct phy_device *phy); + void (*port_cleanup)(struct ksz_device *dev, int port); + void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); + void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); + void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); + int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, + u8 *fid, u8 *src_port, u8 *timestamp, + u16 *entries); + int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, + u64 *cnt); + void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, + u64 *dropped, u64 *cnt); + void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); + void (*port_init_cnt)(struct ksz_device *dev, int port); + int (*shutdown)(struct ksz_device *dev); + int (*detect)(struct ksz_device *dev); + int (*init)(struct ksz_device *dev); + void (*exit)(struct ksz_device *dev); +}; + +struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); +int ksz_switch_register(struct ksz_device *dev, + const struct ksz_dev_ops *ops); +void ksz_switch_remove(struct ksz_device *dev); + +int ksz8795_switch_register(struct ksz_device *dev); +int ksz9477_switch_register(struct ksz_device *dev); -void ksz_port_cleanup(struct ksz_device *dev, int port); void ksz_update_port_member(struct ksz_device *dev, int port); void ksz_init_mib_timer(struct ksz_device *dev); diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h deleted file mode 100644 index 44c16aaf775c..000000000000 --- a/drivers/net/dsa/microchip/ksz_priv.h +++ /dev/null @@ -1,156 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * Microchip KSZ series switch common definitions - * - * Copyright (C) 2017-2019 Microchip Technology Inc. - */ - -#ifndef __KSZ_PRIV_H -#define __KSZ_PRIV_H - -#include <linux/kernel.h> -#include <linux/mutex.h> -#include <linux/phy.h> -#include <linux/etherdevice.h> -#include <net/dsa.h> - -struct vlan_table { - u32 table[3]; -}; - -struct ksz_port_mib { - struct mutex cnt_mutex; /* structure access */ - u8 cnt_ptr; - u64 *counters; -}; - -struct ksz_port { - u16 member; - u16 vid_member; - int stp_state; - struct phy_device phydev; - - u32 on:1; /* port is not disabled by hardware */ - u32 phy:1; /* port has a PHY */ - u32 fiber:1; /* port is fiber */ - u32 sgmii:1; /* port is SGMII */ - u32 force:1; - u32 read:1; /* read MIB counters in background */ - u32 freeze:1; /* MIB counter freeze is enabled */ - - struct ksz_port_mib mib; -}; - -struct ksz_device { - struct dsa_switch *ds; - struct ksz_platform_data *pdata; - const char *name; - - struct mutex dev_mutex; /* device access */ - struct mutex stats_mutex; /* status access */ - struct mutex alu_mutex; /* ALU access */ - struct mutex vlan_mutex; /* vlan access */ - const struct ksz_dev_ops *dev_ops; - - struct device *dev; - struct regmap *regmap[3]; - - void *priv; - - struct gpio_desc *reset_gpio; /* Optional reset GPIO */ - - /* chip specific data */ - u32 chip_id; - int num_vlans; - int num_alus; - int num_statics; - int cpu_port; /* port connected to CPU */ - int cpu_ports; /* port bitmap can be cpu port */ - int phy_port_cnt; - int port_cnt; - int reg_mib_cnt; - int mib_cnt; - int mib_port_cnt; - int last_port; /* ports after that not used */ - phy_interface_t interface; - u32 regs_size; - bool phy_errata_9477; - bool synclko_125; - - struct vlan_table *vlan_cache; - - struct ksz_port *ports; - struct timer_list mib_read_timer; - struct work_struct mib_read; - unsigned long mib_read_interval; - u16 br_member; - u16 member; - u16 live_ports; - u16 on_ports; /* ports enabled by DSA */ - u16 rx_ports; - u16 tx_ports; - u16 mirror_rx; - u16 mirror_tx; - u32 features; /* chip specific features */ - u32 overrides; /* chip functions set by user */ - u16 host_mask; - u16 port_mask; -}; - -struct alu_struct { - /* entry 1 */ - u8 is_static:1; - u8 is_src_filter:1; - u8 is_dst_filter:1; - u8 prio_age:3; - u32 _reserv_0_1:23; - u8 mstp:3; - /* entry 2 */ - u8 is_override:1; - u8 is_use_fid:1; - u32 _reserv_1_1:23; - u8 port_forward:7; - /* entry 3 & 4*/ - u32 _reserv_2_1:9; - u8 fid:7; - u8 mac[ETH_ALEN]; -}; - -struct ksz_dev_ops { - u32 (*get_port_addr)(int port, int offset); - void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); - void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); - void (*phy_setup)(struct ksz_device *dev, int port, - struct phy_device *phy); - void (*port_cleanup)(struct ksz_device *dev, int port); - void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); - void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); - void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); - int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, - u8 *fid, u8 *src_port, u8 *timestamp, - u16 *entries); - int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, - u64 *cnt); - void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, - u64 *dropped, u64 *cnt); - void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); - void (*port_init_cnt)(struct ksz_device *dev, int port); - int (*shutdown)(struct ksz_device *dev); - int (*detect)(struct ksz_device *dev); - int (*init)(struct ksz_device *dev); - void (*exit)(struct ksz_device *dev); -}; - -struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); -int ksz_switch_register(struct ksz_device *dev, - const struct ksz_dev_ops *ops); -void ksz_switch_remove(struct ksz_device *dev); - -int ksz8795_switch_register(struct ksz_device *dev); -int ksz9477_switch_register(struct ksz_device *dev); - -#endif diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 467e61ced82c..818a83eb2dcb 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -10,6 +10,7 @@ * Vivien Didelot <[email protected]> */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> @@ -27,7 +28,6 @@ #include <linux/platform_data/mv88e6xxx.h> #include <linux/netdevice.h> #include <linux/gpio/consumer.h> -#include <linux/phy.h> #include <linux/phylink.h> #include <net/dsa.h> @@ -81,6 +81,36 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val) return 0; } +int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, + u16 mask, u16 val) +{ + u16 data; + int err; + int i; + + /* There's no bus specific operation to wait for a mask */ + for (i = 0; i < 16; i++) { + err = mv88e6xxx_read(chip, addr, reg, &data); + if (err) + return err; + + if ((data & mask) == val) + return 0; + + usleep_range(1000, 2000); + } + + dev_err(chip->dev, "Timeout while waiting for switch\n"); + return -ETIMEDOUT; +} + +int mv88e6xxx_wait_bit(struct mv88e6xxx_chip *chip, int addr, int reg, + int bit, int val) +{ + return mv88e6xxx_wait_mask(chip, addr, reg, BIT(bit), + val ? BIT(bit) : 0x0000); +} + struct mii_bus *mv88e6xxx_default_mdio_bus(struct mv88e6xxx_chip *chip) { struct mv88e6xxx_mdio_bus *mdio_bus; @@ -364,45 +394,6 @@ static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) mv88e6xxx_reg_unlock(chip); } -int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) -{ - int i; - - for (i = 0; i < 16; i++) { - u16 val; - int err; - - err = mv88e6xxx_read(chip, addr, reg, &val); - if (err) - return err; - - if (!(val & mask)) - return 0; - - usleep_range(1000, 2000); - } - - dev_err(chip->dev, "Timeout while waiting for switch\n"); - return -ETIMEDOUT; -} - -/* Indirect write to single pointer-data register with an Update bit */ -int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, u16 update) -{ - u16 val; - int err; - - /* Wait until the previous operation is completed */ - err = mv88e6xxx_wait(chip, addr, reg, BIT(15)); - if (err) - return err; - - /* Set the Update bit to trigger a write operation */ - val = BIT(15) | update; - - return mv88e6xxx_write(chip, addr, reg, val); -} - int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, int speed, int duplex, int pause, phy_interface_t mode) @@ -430,7 +421,7 @@ int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, return 0; /* Port's MAC control must not be changed unless the link is down */ - err = chip->info->ops->port_set_link(chip, port, 0); + err = chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN); if (err) return err; @@ -482,30 +473,6 @@ static int mv88e6xxx_phy_is_internal(struct dsa_switch *ds, int port) return port < chip->info->num_internal_phys; } -/* We expect the switch to perform auto negotiation if there is a real - * phy. However, in the case of a fixed link phy, we force the port - * settings from the fixed link settings. - */ -static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - if (!phy_is_pseudo_fixed_link(phydev) && - mv88e6xxx_phy_is_internal(ds, port)) - return; - - mv88e6xxx_reg_lock(chip); - err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed, - phydev->duplex, phydev->pause, - phydev->interface); - mv88e6xxx_reg_unlock(chip); - - if (err && err != -EOPNOTSUPP) - dev_err(ds->dev, "p%d: failed to configure MAC\n", port); -} - static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port, unsigned long *mask, struct phylink_link_state *state) @@ -2379,8 +2346,10 @@ static int mv88e6390_hidden_write(struct mv88e6xxx_chip *chip, int port, static int mv88e6390_hidden_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_wait(chip, PORT_RESERVED_1A_CTRL_PORT, - PORT_RESERVED_1A, PORT_RESERVED_1A_BUSY); + int bit = __bf_shf(PORT_RESERVED_1A_BUSY); + + return mv88e6xxx_wait_bit(chip, PORT_RESERVED_1A_CTRL_PORT, + PORT_RESERVED_1A, bit, 0); } @@ -2747,6 +2716,7 @@ static int mv88e6xxx_mdios_register(struct mv88e6xxx_chip *chip, err = mv88e6xxx_mdio_register(chip, child, true); if (err) { mv88e6xxx_mdios_unregister(chip); + of_node_put(child); return err; } } @@ -4720,7 +4690,6 @@ static int mv88e6xxx_port_egress_floods(struct dsa_switch *ds, int port, static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_tag_protocol = mv88e6xxx_get_tag_protocol, .setup = mv88e6xxx_setup, - .adjust_link = mv88e6xxx_adjust_link, .phylink_validate = mv88e6xxx_validate, .phylink_mac_link_state = mv88e6xxx_link_state, .phylink_mac_config = mv88e6xxx_mac_config, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 8c6d3c906197..a406be2f5652 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -588,9 +588,10 @@ static inline bool mv88e6xxx_is_invalid_port(struct mv88e6xxx_chip *chip, int po int mv88e6xxx_read(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); -int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, - u16 update); -int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask); +int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, + u16 mask, u16 val); +int mv88e6xxx_wait_bit(struct mv88e6xxx_chip *chip, int addr, int reg, + int bit, int val); int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port, int link, int speed, int duplex, int pause, phy_interface_t mode); diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 1323ef30a5e9..25ec4c0ac589 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -27,100 +27,52 @@ int mv88e6xxx_g1_write(struct mv88e6xxx_chip *chip, int reg, u16 val) return mv88e6xxx_write(chip, addr, reg, val); } -int mv88e6xxx_g1_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +int mv88e6xxx_g1_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val) { - return mv88e6xxx_wait(chip, chip->info->global1_addr, reg, mask); + return mv88e6xxx_wait_bit(chip, chip->info->global1_addr, reg, + bit, val); +} + +int mv88e6xxx_g1_wait_mask(struct mv88e6xxx_chip *chip, int reg, + u16 mask, u16 val) +{ + return mv88e6xxx_wait_mask(chip, chip->info->global1_addr, reg, + mask, val); } /* Offset 0x00: Switch Global Status Register */ static int mv88e6185_g1_wait_ppu_disabled(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; - - for (i = 0; i < 16; i++) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState bits 15:14 */ - state &= MV88E6185_G1_STS_PPU_STATE_MASK; - if (state != MV88E6185_G1_STS_PPU_STATE_POLLING) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_mask(chip, MV88E6XXX_G1_STS, + MV88E6185_G1_STS_PPU_STATE_MASK, + MV88E6185_G1_STS_PPU_STATE_DISABLED); } static int mv88e6185_g1_wait_ppu_polling(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; - - for (i = 0; i < 16; ++i) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState bits 15:14 */ - state &= MV88E6185_G1_STS_PPU_STATE_MASK; - if (state == MV88E6185_G1_STS_PPU_STATE_POLLING) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_mask(chip, MV88E6XXX_G1_STS, + MV88E6185_G1_STS_PPU_STATE_MASK, + MV88E6185_G1_STS_PPU_STATE_POLLING); } static int mv88e6352_g1_wait_ppu_polling(struct mv88e6xxx_chip *chip) { - u16 state; - int i, err; + int bit = __bf_shf(MV88E6352_G1_STS_PPU_STATE); - for (i = 0; i < 16; ++i) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &state); - if (err) - return err; - - /* Check the value of the PPUState (or InitState) bit 15 */ - if (state & MV88E6352_G1_STS_PPU_STATE) - return 0; - - usleep_range(1000, 2000); - } - - return -ETIMEDOUT; + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } static int mv88e6xxx_g1_wait_init_ready(struct mv88e6xxx_chip *chip) { - const unsigned long timeout = jiffies + 1 * HZ; - u16 val; - int err; + int bit = __bf_shf(MV88E6XXX_G1_STS_INIT_READY); /* Wait up to 1 second for the switch to be ready. The InitReady bit 11 * is set to a one when all units inside the device (ATU, VTU, etc.) * have finished their initialization and are ready to accept frames. */ - while (time_before(jiffies, timeout)) { - err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val); - if (err) - return err; - - if (val & MV88E6XXX_G1_STS_INIT_READY) - break; - - usleep_range(1000, 2000); - } - - if (time_after(jiffies, timeout)) - return -ETIMEDOUT; - - return 0; + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1); } /* Offset 0x01: Switch MAC Address Register Bytes 0 & 1 @@ -476,8 +428,9 @@ int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index) static int mv88e6xxx_g1_stats_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_STATS_OP, - MV88E6XXX_G1_STATS_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_STATS_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STATS_OP, bit, 0); } int mv88e6095_g1_stats_set_histogram(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index d444266f7d78..78b9ae22d18c 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -249,7 +249,10 @@ int mv88e6xxx_g1_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); int mv88e6xxx_g1_write(struct mv88e6xxx_chip *chip, int reg, u16 val); -int mv88e6xxx_g1_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); +int mv88e6xxx_g1_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val); +int mv88e6xxx_g1_wait_mask(struct mv88e6xxx_chip *chip, int reg, + u16 mask, u16 val); int mv88e6xxx_g1_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr); diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 1cf388e9bd94..18b86515b6bc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -5,6 +5,8 @@ * Copyright (c) 2008 Marvell Semiconductor * Copyright (c) 2017 Savoir-faire Linux, Inc. */ + +#include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> @@ -75,8 +77,9 @@ int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g1_atu_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_ATU_OP, - MV88E6XXX_G1_ATU_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_ATU_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_ATU_OP, bit, 0); } static int mv88e6xxx_g1_atu_op(struct mv88e6xxx_chip *chip, u16 fid, u16 op) diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index 6cac997360e8..33056a609e96 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -7,6 +7,7 @@ * Copyright (c) 2017 Savoir-faire Linux, Inc. */ +#include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> @@ -67,8 +68,9 @@ static int mv88e6xxx_g1_vtu_sid_write(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g1_vtu_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g1_wait(chip, MV88E6XXX_G1_VTU_OP, - MV88E6XXX_G1_VTU_OP_BUSY); + int bit = __bf_shf(MV88E6XXX_G1_VTU_OP_BUSY); + + return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_VTU_OP, bit, 0); } static int mv88e6xxx_g1_vtu_op(struct mv88e6xxx_chip *chip, u16 op) diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 2305b94b3051..bdbb72fc20ed 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -26,14 +26,11 @@ int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val) return mv88e6xxx_write(chip, chip->info->global2_addr, reg, val); } -int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) +int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, int reg, int + bit, int val) { - return mv88e6xxx_update(chip, chip->info->global2_addr, reg, update); -} - -int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) -{ - return mv88e6xxx_wait(chip, chip->info->global2_addr, reg, mask); + return mv88e6xxx_wait_bit(chip, chip->info->global2_addr, reg, + bit, val); } /* Offset 0x00: Interrupt Source Register */ @@ -123,7 +120,8 @@ int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, * but bit 4 is reserved on older chips, so it is safe to use. */ - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_DEVICE_MAPPING, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_DEVICE_MAPPING, + MV88E6XXX_G2_DEVICE_MAPPING_UPDATE | val); } /* Offset 0x07: Trunk Mask Table register */ @@ -136,7 +134,8 @@ static int mv88e6xxx_g2_trunk_mask_write(struct mv88e6xxx_chip *chip, int num, if (hash) val |= MV88E6XXX_G2_TRUNK_MASK_HASH; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MASK, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_TRUNK_MASK, + MV88E6XXX_G2_TRUNK_MASK_UPDATE | val); } /* Offset 0x08: Trunk Mapping Table register */ @@ -147,7 +146,8 @@ static int mv88e6xxx_g2_trunk_mapping_write(struct mv88e6xxx_chip *chip, int id, const u16 port_mask = BIT(mv88e6xxx_num_ports(chip)) - 1; u16 val = (id << 11) | (map & port_mask); - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MAPPING, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_TRUNK_MAPPING, + MV88E6XXX_G2_TRUNK_MAPPING_UPDATE | val); } int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) @@ -178,8 +178,9 @@ int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) static int mv88e6xxx_g2_irl_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_IRL_CMD, - MV88E6XXX_G2_IRL_CMD_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_IRL_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_IRL_CMD, bit, 0); } static int mv88e6xxx_g2_irl_op(struct mv88e6xxx_chip *chip, u16 op, int port, @@ -214,8 +215,9 @@ int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port) static int mv88e6xxx_g2_pvt_op_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_PVT_ADDR, - MV88E6XXX_G2_PVT_ADDR_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_PVT_ADDR_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_PVT_ADDR, bit, 0); } static int mv88e6xxx_g2_pvt_op(struct mv88e6xxx_chip *chip, int src_dev, @@ -261,7 +263,8 @@ static int mv88e6xxx_g2_switch_mac_write(struct mv88e6xxx_chip *chip, { u16 val = (pointer << 8) | data; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SWITCH_MAC, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SWITCH_MAC, + MV88E6XXX_G2_SWITCH_MAC_UPDATE | val); } int mv88e6xxx_g2_set_switch_mac(struct mv88e6xxx_chip *chip, u8 *addr) @@ -284,7 +287,8 @@ static int mv88e6xxx_g2_pot_write(struct mv88e6xxx_chip *chip, int pointer, { u16 val = (pointer << 8) | (data & 0x7); - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_PRIO_OVERRIDE, val); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_PRIO_OVERRIDE, + MV88E6XXX_G2_PRIO_OVERRIDE_UPDATE | val); } int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) @@ -308,9 +312,16 @@ int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip) static int mv88e6xxx_g2_eeprom_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_EEPROM_CMD, - MV88E6XXX_G2_EEPROM_CMD_BUSY | - MV88E6XXX_G2_EEPROM_CMD_RUNNING); + int bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_BUSY); + int err; + + err = mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_EEPROM_CMD, bit, 0); + if (err) + return err; + + bit = __bf_shf(MV88E6XXX_G2_EEPROM_CMD_RUNNING); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_EEPROM_CMD, bit, 0); } static int mv88e6xxx_g2_eeprom_cmd(struct mv88e6xxx_chip *chip, u16 cmd) @@ -572,8 +583,9 @@ int mv88e6xxx_g2_set_eeprom16(struct mv88e6xxx_chip *chip, static int mv88e6xxx_g2_smi_phy_wait(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_wait(chip, MV88E6XXX_G2_SMI_PHY_CMD, - MV88E6XXX_G2_SMI_PHY_CMD_BUSY); + int bit = __bf_shf(MV88E6XXX_G2_SMI_PHY_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6XXX_G2_SMI_PHY_CMD, bit, 0); } static int mv88e6xxx_g2_smi_phy_cmd(struct mv88e6xxx_chip *chip, u16 cmd) @@ -840,12 +852,13 @@ const struct mv88e6xxx_irq_ops mv88e6250_watchdog_ops = { static int mv88e6390_watchdog_setup(struct mv88e6xxx_chip *chip) { - return mv88e6xxx_g2_update(chip, MV88E6390_G2_WDOG_CTL, - MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE | - MV88E6390_G2_WDOG_CTL_CUT_THROUGH | - MV88E6390_G2_WDOG_CTL_QUEUE_CONTROLLER | - MV88E6390_G2_WDOG_CTL_EGRESS | - MV88E6390_G2_WDOG_CTL_FORCE_IRQ); + return mv88e6xxx_g2_write(chip, MV88E6390_G2_WDOG_CTL, + MV88E6390_G2_WDOG_CTL_UPDATE | + MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE | + MV88E6390_G2_WDOG_CTL_CUT_THROUGH | + MV88E6390_G2_WDOG_CTL_QUEUE_CONTROLLER | + MV88E6390_G2_WDOG_CTL_EGRESS | + MV88E6390_G2_WDOG_CTL_FORCE_IRQ); } static int mv88e6390_watchdog_action(struct mv88e6xxx_chip *chip, int irq) @@ -878,8 +891,9 @@ static int mv88e6390_watchdog_action(struct mv88e6xxx_chip *chip, int irq) static void mv88e6390_watchdog_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g2_update(chip, MV88E6390_G2_WDOG_CTL, - MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE); + mv88e6xxx_g2_write(chip, MV88E6390_G2_WDOG_CTL, + MV88E6390_G2_WDOG_CTL_UPDATE | + MV88E6390_G2_WDOG_CTL_PTR_INT_ENABLE); } const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = { diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index a664fc25f132..42da4bca73e8 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -295,8 +295,8 @@ static inline int mv88e6xxx_g2_require(struct mv88e6xxx_chip *chip) int mv88e6xxx_g2_read(struct mv88e6xxx_chip *chip, int reg, u16 *val); int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 val); -int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update); -int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask); +int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, int reg, + int bit, int val); int mv88e6352_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g2_irl_init_all(struct mv88e6xxx_chip *chip, int port); @@ -376,12 +376,8 @@ static inline int mv88e6xxx_g2_write(struct mv88e6xxx_chip *chip, int reg, u16 v return -EOPNOTSUPP; } -static inline int mv88e6xxx_g2_update(struct mv88e6xxx_chip *chip, int reg, u16 update) -{ - return -EOPNOTSUPP; -} - -static inline int mv88e6xxx_g2_wait(struct mv88e6xxx_chip *chip, int reg, u16 mask) +static inline int mv88e6xxx_g2_wait_bit(struct mv88e6xxx_chip *chip, + int reg, int bit, int val) { return -EOPNOTSUPP; } diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c index 116b8cf5a6e3..657783e043ff 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_avb.c +++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c @@ -11,6 +11,8 @@ * Brandon Streiff <[email protected]> */ +#include <linux/bitfield.h> + #include "global2.h" /* Offset 0x16: AVB Command Register @@ -27,17 +29,33 @@ /* mv88e6xxx_g2_avb_read -- Read one or multiple 16-bit words. * The hardware supports snapshotting up to four contiguous registers. */ +static int mv88e6xxx_g2_avb_wait(struct mv88e6xxx_chip *chip) +{ + int bit = __bf_shf(MV88E6352_G2_AVB_CMD_BUSY); + + return mv88e6xxx_g2_wait_bit(chip, MV88E6352_G2_AVB_CMD, bit, 0); +} + static int mv88e6xxx_g2_avb_read(struct mv88e6xxx_chip *chip, u16 readop, u16 *data, int len) { int err; int i; + err = mv88e6xxx_g2_avb_wait(chip); + if (err) + return err; + /* Hardware can only snapshot four words. */ if (len > 4) return -E2BIG; - err = mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, readop); + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_CMD, + MV88E6352_G2_AVB_CMD_BUSY | readop); + if (err) + return err; + + err = mv88e6xxx_g2_avb_wait(chip); if (err) return err; @@ -57,11 +75,18 @@ static int mv88e6xxx_g2_avb_write(struct mv88e6xxx_chip *chip, u16 writeop, { int err; + err = mv88e6xxx_g2_avb_wait(chip); + if (err) + return err; + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_DATA, data); if (err) return err; - return mv88e6xxx_g2_update(chip, MV88E6352_G2_AVB_CMD, writeop); + err = mv88e6xxx_g2_write(chip, MV88E6352_G2_AVB_CMD, + MV88E6352_G2_AVB_CMD_BUSY | writeop); + + return mv88e6xxx_g2_avb_wait(chip); } static int mv88e6352_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip, diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c index baddecadd8be..33b7b9570d29 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -37,7 +37,8 @@ static int mv88e6xxx_g2_scratch_write(struct mv88e6xxx_chip *chip, int reg, { u16 value = (reg << 8) | data; - return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, value); + return mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SCRATCH_MISC_MISC, + MV88E6XXX_G2_SCRATCH_MISC_UPDATE | value); } /** diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 5fc78a063843..282fe08db050 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -64,8 +64,10 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, if (err) return err; - if (!!(data >> bit) == !!val) + if (!!(data & BIT(bit)) == !!val) return 0; + + usleep_range(1000, 2000); } return -ETIMEDOUT; diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 232e8cc96f6d..16f15c93a102 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2009 Felix Fietkau <[email protected]> * Copyright (C) 2011-2012 Gabor Juhos <[email protected]> - * Copyright (c) 2015, The Linux Foundation. All rights reserved. + * Copyright (c) 2015, 2019, The Linux Foundation. All rights reserved. * Copyright (c) 2016 John Crispin <[email protected]> */ @@ -583,8 +583,11 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); - if (err) + if (err) { + of_node_put(port); + of_node_put(ports); return err; + } if (!dsa_is_user_port(priv->ds, reg)) continue; @@ -595,6 +598,7 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) internal_mdio_mask |= BIT(reg); } + of_node_put(ports); if (!external_mdio_mask && !internal_mdio_mask) { dev_err(priv->dev, "no PHYs are defined.\n"); return -EINVAL; @@ -935,6 +939,8 @@ qca8k_port_enable(struct dsa_switch *ds, int port, qca8k_port_set_status(priv, port, 1); priv->port_sts[port].enabled = 1; + phy_support_asym_pause(phy); + return 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 6bfb1696a6f2..9988c9d18567 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -277,6 +277,18 @@ sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, SJA1105ET_SIZE_L2_LOOKUP_ENTRY, op); } +static size_t sja1105et_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_lookup_entry *entry = entry_ptr; + u8 *cmd = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(cmd, &entry->lockeds, 28, 28, size, op); + + return sja1105et_l2_lookup_entry_packing(buf, entry_ptr, op); +} + static void sja1105et_mgmt_route_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -477,7 +489,7 @@ sja1105et_general_params_entry_packing(void *buf, void *entry_ptr, /* SJA1105E/T: First generation */ struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_L2_LOOKUP] = { - .entry_packing = sja1105et_l2_lookup_entry_packing, + .entry_packing = sja1105et_dyn_l2_lookup_entry_packing, .cmd_packing = sja1105et_l2_lookup_cmd_packing, .access = (OP_READ | OP_WRITE | OP_DEL), .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 32bf3a7cc3b6..d073baffc20b 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -218,7 +218,7 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) /* This selects between Independent VLAN Learning (IVL) and * Shared VLAN Learning (SVL) */ - .shared_learn = false, + .shared_learn = true, /* Don't discard management traffic based on ENFPORT - * we don't perform SMAC port enforcement anyway, so * what we are setting here doesn't matter. @@ -625,6 +625,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (of_property_read_u32(child, "reg", &index) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); + of_node_put(child); return -ENODEV; } @@ -634,6 +635,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", index); + of_node_put(child); return -ENODEV; } ports[index].phy_mode = phy_mode; @@ -643,6 +645,7 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (!of_phy_is_fixed_link(child)) { dev_err(dev, "phy-handle or fixed-link " "properties missing!\n"); + of_node_put(child); return -ENODEV; } /* phy-handle is missing, but fixed-link isn't. @@ -1089,8 +1092,13 @@ int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); + if (dsa_port_is_vlan_filtering(&ds->ports[port])) { + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); + } else { + l2_lookup.mask_vlanid = 0; + l2_lookup.mask_iotag = 0; + } l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, @@ -1147,8 +1155,13 @@ int sja1105pqrs_fdb_del(struct dsa_switch *ds, int port, l2_lookup.vlanid = vid; l2_lookup.iotag = SJA1105_S_TAG; l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0); - l2_lookup.mask_vlanid = VLAN_VID_MASK; - l2_lookup.mask_iotag = BIT(0); + if (dsa_port_is_vlan_filtering(&ds->ports[port])) { + l2_lookup.mask_vlanid = VLAN_VID_MASK; + l2_lookup.mask_iotag = BIT(0); + } else { + l2_lookup.mask_vlanid = 0; + l2_lookup.mask_iotag = 0; + } l2_lookup.destports = BIT(port); rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP, @@ -1178,60 +1191,31 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { struct sja1105_private *priv = ds->priv; - u16 rx_vid, tx_vid; - int rc, i; - if (dsa_port_is_vlan_filtering(&ds->ports[port])) - return priv->info->fdb_add_cmd(ds, port, addr, vid); - - /* Since we make use of VLANs even when the bridge core doesn't tell us - * to, translate these FDB entries into the correct dsa_8021q ones. - * The basic idea (also repeats for removal below) is: - * - Each of the other front-panel ports needs to be able to forward a - * pvid-tagged (aka tagged with their rx_vid) frame that matches this - * DMAC. - * - The CPU port (aka the tx_vid of this port) needs to be able to - * send a frame matching this DMAC to the specified port. - * For a better picture see net/dsa/tag_8021q.c. + /* dsa_8021q is in effect when the bridge's vlan_filtering isn't, + * so the switch still does some VLAN processing internally. + * But Shared VLAN Learning (SVL) is also active, and it will take + * care of autonomous forwarding between the unique pvid's of each + * port. Here we just make sure that users can't add duplicate FDB + * entries when in this mode - the actual VID doesn't matter except + * for what gets printed in 'bridge fdb show'. In the case of zero, + * no VID gets printed at all. */ - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (i == port) - continue; - if (i == dsa_upstream_port(priv->ds, port)) - continue; + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + vid = 0; - rx_vid = dsa_8021q_rx_vid(ds, i); - rc = priv->info->fdb_add_cmd(ds, port, addr, rx_vid); - if (rc < 0) - return rc; - } - tx_vid = dsa_8021q_tx_vid(ds, port); - return priv->info->fdb_add_cmd(ds, port, addr, tx_vid); + return priv->info->fdb_add_cmd(ds, port, addr, vid); } static int sja1105_fdb_del(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid) { struct sja1105_private *priv = ds->priv; - u16 rx_vid, tx_vid; - int rc, i; - - if (dsa_port_is_vlan_filtering(&ds->ports[port])) - return priv->info->fdb_del_cmd(ds, port, addr, vid); - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (i == port) - continue; - if (i == dsa_upstream_port(priv->ds, port)) - continue; + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + vid = 0; - rx_vid = dsa_8021q_rx_vid(ds, i); - rc = priv->info->fdb_del_cmd(ds, port, addr, rx_vid); - if (rc < 0) - return rc; - } - tx_vid = dsa_8021q_tx_vid(ds, port); - return priv->info->fdb_del_cmd(ds, port, addr, tx_vid); + return priv->info->fdb_del_cmd(ds, port, addr, vid); } static int sja1105_fdb_dump(struct dsa_switch *ds, int port, @@ -1270,39 +1254,9 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, continue; u64_to_ether_addr(l2_lookup.macaddr, macaddr); - /* On SJA1105 E/T, the switch doesn't implement the LOCKEDS - * bit, so it doesn't tell us whether a FDB entry is static - * or not. - * But, of course, we can find out - we're the ones who added - * it in the first place. - */ - if (priv->info->device_id == SJA1105E_DEVICE_ID || - priv->info->device_id == SJA1105T_DEVICE_ID) { - int match; - - match = sja1105_find_static_fdb_entry(priv, port, - &l2_lookup); - l2_lookup.lockeds = (match >= 0); - } - - /* We need to hide the dsa_8021q VLANs from the user. This - * basically means hiding the duplicates and only showing - * the pvid that is supposed to be active in standalone and - * non-vlan_filtering modes (aka 1). - * - For statically added FDB entries (bridge fdb add), we - * can convert the TX VID (coming from the CPU port) into the - * pvid and ignore the RX VIDs of the other ports. - * - For dynamically learned FDB entries, a single entry with - * no duplicates is learned - that which has the real port's - * pvid, aka RX VID. - */ - if (!dsa_port_is_vlan_filtering(&ds->ports[port])) { - if (l2_lookup.vlanid == tx_vid || - l2_lookup.vlanid == rx_vid) - l2_lookup.vlanid = 1; - else - continue; - } + /* We need to hide the dsa_8021q VLANs from the user. */ + if (!dsa_port_is_vlan_filtering(&ds->ports[port])) + l2_lookup.vlanid = 0; cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); } return 0; @@ -1594,6 +1548,7 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port, */ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) { + struct sja1105_l2_lookup_params_entry *l2_lookup_params; struct sja1105_general_params_entry *general_params; struct sja1105_private *priv = ds->priv; struct sja1105_table *table; @@ -1622,6 +1577,28 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) general_params->incl_srcpt1 = enabled; general_params->incl_srcpt0 = enabled; + /* VLAN filtering => independent VLAN learning. + * No VLAN filtering => shared VLAN learning. + * + * In shared VLAN learning mode, untagged traffic still gets + * pvid-tagged, and the FDB table gets populated with entries + * containing the "real" (pvid or from VLAN tag) VLAN ID. + * However the switch performs a masked L2 lookup in the FDB, + * effectively only looking up a frame's DMAC (and not VID) for the + * forwarding decision. + * + * This is extremely convenient for us, because in modes with + * vlan_filtering=0, dsa_8021q actually installs unique pvid's into + * each front panel port. This is good for identification but breaks + * learning badly - the VID of the learnt FDB entry is unique, aka + * no frames coming from any other port are going to have it. So + * for forwarding purposes, this is as though learning was broken + * (all frames get flooded). + */ + table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; + l2_lookup_params = table->entries; + l2_lookup_params->shared_learn = !enabled; + rc = sja1105_static_config_reload(priv); if (rc) dev_err(ds->dev, "Failed to change VLAN Ethertype\n"); @@ -1751,6 +1728,8 @@ static void sja1105_teardown(struct dsa_switch *ds) cancel_work_sync(&priv->tagger_data.rxtstamp_work); skb_queue_purge(&priv->tagger_data.skb_rxtstamp_queue); + sja1105_ptp_clock_unregister(priv); + sja1105_static_config_free(&priv->static_config); } static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, @@ -2208,9 +2187,7 @@ static int sja1105_remove(struct spi_device *spi) { struct sja1105_private *priv = spi_get_drvdata(spi); - sja1105_ptp_clock_unregister(priv); dsa_unregister_switch(priv->ds); - sja1105_static_config_free(&priv->static_config); return 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index d19cfdf681af..d8e8dd59f3d1 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -369,16 +369,15 @@ int sja1105_ptp_clock_register(struct sja1105_private *priv) .mult = SJA1105_CC_MULT, }; mutex_init(&priv->ptp_lock); - INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check); - - schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL); - priv->ptp_caps = sja1105_ptp_caps; priv->clock = ptp_clock_register(&priv->ptp_caps, ds->dev); if (IS_ERR_OR_NULL(priv->clock)) return PTR_ERR(priv->clock); + INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check); + schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL); + return sja1105_ptp_reset(priv); } diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig index 2a3e2450968e..a9478577b495 100644 --- a/drivers/net/ethernet/8390/Kconfig +++ b/drivers/net/ethernet/8390/Kconfig @@ -12,8 +12,8 @@ config NET_VENDOR_8390 Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about Western Digital cards. If you say Y, you will be - asked for your specific card in the following questions. + the questions about National Semiconductor 8390 cards. If you say Y, + you will be asked for your specific card in the following questions. if NET_VENDOR_8390 diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index e43d922f043e..174344c450af 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2362,7 +2362,7 @@ static int et131x_tx_dma_memory_alloc(struct et131x_adapter *adapter) /* Allocate memory for the TCB's (Transmit Control Block) */ tx_ring->tcb_ring = kcalloc(NUM_TCB, sizeof(struct tcb), - GFP_ATOMIC | GFP_DMA); + GFP_KERNEL | GFP_DMA); if (!tx_ring->tcb_ring) return -ENOMEM; diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 3434730a7699..0537df06a9b5 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -860,7 +860,9 @@ static int emac_probe(struct platform_device *pdev) goto out_clk_disable_unprepare; } - db->phy_node = of_parse_phandle(np, "phy", 0); + db->phy_node = of_parse_phandle(np, "phy-handle", 0); + if (!db->phy_node) + db->phy_node = of_parse_phandle(np, "phy", 0); if (!db->phy_node) { dev_err(&pdev->dev, "no associated PHY\n"); ret = -ENODEV; diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index de4950d2022e..9f965cdfff5c 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -14,7 +14,7 @@ config NET_VENDOR_AMD say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all + the kernel: saying N will just cause the configurator to skip all the questions regarding AMD chipsets. If you say Y, you will be asked for your specific chipset/driver in the following questions. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index b91143947ed2..b0a6c96b6ef4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -438,7 +438,6 @@ static const struct file_operations xi2c_reg_value_fops = { void xgbe_debugfs_init(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; /* Set defaults */ @@ -451,88 +450,48 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) return; pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL); - if (!pdata->xgbe_debugfs) { - netdev_err(pdata->netdev, "debugfs_create_dir failed\n"); - kfree(buf); - return; - } - pfile = debugfs_create_file("xgmac_register", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register", 0600, pdata->xgbe_debugfs, pdata, + &xgmac_reg_addr_fops); - pfile = debugfs_create_file("xgmac_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xgmac_reg_value_fops); - pfile = debugfs_create_file("xpcs_mmd", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_mmd_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_mmd", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_mmd_fops); - pfile = debugfs_create_file("xpcs_register", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_reg_addr_fops); - pfile = debugfs_create_file("xpcs_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xpcs_reg_value_fops); if (pdata->xprop_regs) { - pfile = debugfs_create_file("xprop_register", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xprop_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xprop_register", 0600, pdata->xgbe_debugfs, + pdata, &xprop_reg_addr_fops); + + debugfs_create_file("xprop_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xprop_reg_value_fops); } if (pdata->xi2c_regs) { - pfile = debugfs_create_file("xi2c_register", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xi2c_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xi2c_register", 0600, pdata->xgbe_debugfs, + pdata, &xi2c_reg_addr_fops); + + debugfs_create_file("xi2c_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xi2c_reg_value_fops); } if (pdata->vdata->an_cdr_workaround) { - pfile = debugfs_create_bool("an_cdr_workaround", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_workaround); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); - - pfile = debugfs_create_bool("an_cdr_track_early", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_track_early); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); + debugfs_create_bool("an_cdr_workaround", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_workaround); + + debugfs_create_bool("an_cdr_track_early", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_track_early); } kfree(buf); @@ -546,7 +505,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; if (!pdata->xgbe_debugfs) @@ -559,11 +517,8 @@ void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf)) goto out; - pfile = debugfs_rename(pdata->xgbe_debugfs->d_parent, - pdata->xgbe_debugfs, - pdata->xgbe_debugfs->d_parent, buf); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_rename failed\n"); + debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs, + pdata->xgbe_debugfs->d_parent, buf); out: kfree(buf); diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig index fde7ae33e302..f78b9c841296 100644 --- a/drivers/net/ethernet/apple/Kconfig +++ b/drivers/net/ethernet/apple/Kconfig @@ -11,8 +11,8 @@ config NET_VENDOR_APPLE If you have a network (Ethernet) card belonging to this class, say Y. Note that the answer to this question doesn't directly affect the - kernel: saying N will just cause the configurator to skip all - the questions about IBM devices. If you say Y, you will be asked for + kernel: saying N will just cause the configurator to skip all the + questions about Apple devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_APPLE diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index c40daad515d5..a58185b1d8bf 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -815,8 +815,8 @@ static int reverse6[64] = { static unsigned int crc416(unsigned int curval, unsigned short nxtval) { - register unsigned int counter, cur = curval, next = nxtval; - register int high_crc_set, low_data_set; + unsigned int counter, cur = curval, next = nxtval; + int high_crc_set, low_data_set; /* Swap bytes */ next = ((next & 0x00FF) << 8) | (next >> 8); diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 40a8717f51b1..7548247455d7 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1141,7 +1141,7 @@ static int ag71xx_rings_init(struct ag71xx *ag) tx->descs_cpu = dma_alloc_coherent(&ag->pdev->dev, ring_size * AG71XX_DESC_SIZE, - &tx->descs_dma, GFP_ATOMIC); + &tx->descs_dma, GFP_KERNEL); if (!tx->descs_cpu) { kfree(tx->buf); tx->buf = NULL; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index e9017caf024d..e24f5d2b6afe 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -14,9 +14,9 @@ config NET_VENDOR_BROADCOM say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all - the questions regarding AMD chipsets. If you say Y, you will be asked - for your specific chipset/driver in the following questions. + the kernel: saying N will just cause the configurator to skip all + the questions regarding Broadcom chipsets. If you say Y, you will + be asked for your specific chipset/driver in the following questions. if NET_VENDOR_BROADCOM diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b9c5cea8db16..9483553ce444 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -992,7 +992,7 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget) { struct bcm_sysport_priv *priv = container_of(napi, struct bcm_sysport_priv, napi); - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; unsigned int work_done = 0; work_done = bcm_sysport_desc_rx(priv, budget); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e2be5a685130..e47ea92e2ae3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1934,8 +1934,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return netdev_pick_tx(dev, skb, NULL) % - (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); + return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp)); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c23fbb34f0e9..94be97b7952c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2267,7 +2267,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) } } if (bp->flags & BNXT_FLAG_DIM) { - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; dim_update_sample(cpr->event_ctr, cpr->rx_packets, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index e3262089b751..1b1610d5b573 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1724,7 +1724,6 @@ struct bnxt { u8 switch_id[8]; struct bnxt_tc_info *tc_info; struct dentry *debugfs_pdev; - struct dentry *debugfs_dim; struct device *hwmon_dev; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c index 61393f351a77..156c2404854f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -61,45 +61,30 @@ static const struct file_operations debugfs_dim_fops = { .read = debugfs_dim_read, }; -static struct dentry *debugfs_dim_ring_init(struct dim *dim, int ring_idx, - struct dentry *dd) +static void debugfs_dim_ring_init(struct dim *dim, int ring_idx, + struct dentry *dd) { static char qname[16]; snprintf(qname, 10, "%d", ring_idx); - return debugfs_create_file(qname, 0600, dd, - dim, &debugfs_dim_fops); + debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops); } void bnxt_debug_dev_init(struct bnxt *bp) { const char *pname = pci_name(bp->pdev); - struct dentry *pdevf; + struct dentry *dir; int i; bp->debugfs_pdev = debugfs_create_dir(pname, bnxt_debug_mnt); - if (bp->debugfs_pdev) { - pdevf = debugfs_create_dir("dim", bp->debugfs_pdev); - if (!pdevf) { - pr_err("failed to create debugfs entry %s/dim\n", - pname); - return; - } - bp->debugfs_dim = pdevf; - /* create files for each rx ring */ - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + dir = debugfs_create_dir("dim", bp->debugfs_pdev); - if (cpr && bp->bnapi[i]->rx_ring) { - pdevf = debugfs_dim_ring_init(&cpr->dim, i, - bp->debugfs_dim); - if (!pdevf) - pr_err("failed to create debugfs entry %s/dim/%d\n", - pname, i); - } - } - } else { - pr_err("failed to create debugfs entry %s\n", pname); + /* create files for each rx ring */ + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + + if (cpr && bp->bnapi[i]->rx_ring) + debugfs_dim_ring_init(&cpr->dim, i, dir); } } @@ -114,8 +99,6 @@ void bnxt_debug_dev_exit(struct bnxt *bp) void bnxt_debug_init(void) { bnxt_debug_mnt = debugfs_create_dir("bnxt_en", NULL); - if (!bnxt_debug_mnt) - pr_err("failed to init bnxt_en debugfs\n"); } void bnxt_debug_exit(void) diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 57dc3cbff36e..155599dcee76 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4096,12 +4096,16 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; u32 port_id; + int i; cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock), GFP_KERNEL); if (!cp->csk_tbl) return -ENOMEM; + for (i = 0; i < MAX_CM_SK_TBL_SZ; i++) + atomic_set(&cp->csk_tbl[i].ref_count, 0); + port_id = prandom_u32(); port_id %= CNIC_LOCAL_PORT_RANGE; if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE, @@ -5480,6 +5484,7 @@ static struct cnic_dev *cnic_alloc_dev(struct net_device *dev, cdev->unregister_device = cnic_unregister_device; cdev->iscsi_nl_msg_recv = cnic_iscsi_nl_msg_recv; cdev->get_fc_npiv_tbl = cnic_get_fc_npiv_tbl; + atomic_set(&cdev->ref_count, 0); cp = cdev->cnic_priv; cp->dev = cdev; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index a2b57807453b..d3a0b614dbfa 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1895,7 +1895,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget) { struct bcmgenet_rx_ring *ring = container_of(napi, struct bcmgenet_rx_ring, napi); - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; unsigned int work_done; work_done = bcmgenet_desc_rx(ring, budget); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index 021d99cd1665..614d07be7181 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -260,9 +260,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, dev_info(&oct->pci_dev->dev, "got a request for FLR from VF that owns DPI ring %u\n", mbox->q_no); - pcie_capability_set_word( - oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no], - PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); + pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]); break; case OCTEON_PF_CHANGED_VF_MACADDR: diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index ad22554857bf..acb016834f04 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1381,24 +1381,18 @@ static int acpi_get_mac_address(struct device *dev, struct acpi_device *adev, u8 *dst) { u8 mac[ETH_ALEN]; - int ret; + u8 *addr; - ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev), - "mac-address", mac, ETH_ALEN); - if (ret) - goto out; - - if (!is_valid_ether_addr(mac)) { + addr = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN); + if (!addr) { dev_err(dev, "MAC address invalid: %pM\n", mac); - ret = -EINVAL; - goto out; + return -EINVAL; } dev_info(dev, "MAC address set to: %pM\n", mac); - memcpy(dst, mac, ETH_ALEN); -out: - return ret; + ether_addr_copy(dst, mac); + return 0; } /* Currently only sets the MAC address. */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 1e82b9efe447..58f89f6a040f 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3269,7 +3269,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!adapter->regs) { dev_err(&pdev->dev, "cannot map device registers\n"); err = -ENOMEM; - goto out_free_adapter; + goto out_free_adapter_nofail; } adapter->pdev = pdev; @@ -3397,6 +3397,9 @@ out_free_dev: if (adapter->port[i]) free_netdev(adapter->port[i]); +out_free_adapter_nofail: + kfree_skb(adapter->nofail_skb); + out_free_adapter: kfree(adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 02959035ed3f..dd99c55d9a88 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3529,7 +3529,6 @@ int t4_setup_debugfs(struct adapter *adap) { int i; u32 size = 0; - struct dentry *de; static struct t4_debugfs_entry t4_debugfs_files[] = { { "cim_la", &cim_la_fops, 0400, 0 }, @@ -3640,8 +3639,8 @@ int t4_setup_debugfs(struct adapter *adap) } } - de = debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, - &flash_debugfs_fops, adap->params.sf_size); + debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, + &flash_debugfs_fops, adap->params.sf_size); debugfs_create_bool("use_backdoor", 0600, adap->debugfs_root, &adap->use_bd); debugfs_create_bool("trace_rss", 0600, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 4311ad9c84b2..71854a19cebe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6269,10 +6269,7 @@ static int __init cxgb4_init_module(void) { int ret; - /* Debugfs support is optional, just warn if this fails */ cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (!cxgb4_debugfs_root) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4_driver); if (ret < 0) diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c index eaf1fb74689c..01c65d13fc0e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.c +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -57,7 +57,7 @@ struct smt_data *t4_init_smt(void) s->smtab[i].state = SMT_STATE_UNUSED; memset(&s->smtab[i].src_mac, 0, ETH_ALEN); spin_lock_init(&s->smtab[i].lock); - atomic_set(&s->smtab[i].refcnt, 0); + s->smtab[i].refcnt = 0; } return s; } @@ -68,7 +68,7 @@ static struct smt_entry *find_or_alloc_smte(struct smt_data *s, u8 *smac) struct smt_entry *e, *end; for (e = &s->smtab[0], end = &s->smtab[s->smt_size]; e != end; ++e) { - if (atomic_read(&e->refcnt) == 0) { + if (e->refcnt == 0) { if (!first_free) first_free = e; } else { @@ -97,11 +97,9 @@ found_reuse: static void t4_smte_free(struct smt_entry *e) { - spin_lock_bh(&e->lock); - if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ + if (e->refcnt == 0) { /* hasn't been recycled */ e->state = SMT_STATE_UNUSED; } - spin_unlock_bh(&e->lock); } /** @@ -111,8 +109,10 @@ static void t4_smte_free(struct smt_entry *e) */ void cxgb4_smt_release(struct smt_entry *e) { - if (atomic_dec_and_test(&e->refcnt)) + spin_lock_bh(&e->lock); + if ((--e->refcnt) == 0) t4_smte_free(e); + spin_unlock_bh(&e->lock); } EXPORT_SYMBOL(cxgb4_smt_release); @@ -215,14 +215,14 @@ static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf, e = find_or_alloc_smte(s, smac); if (e) { spin_lock(&e->lock); - if (!atomic_read(&e->refcnt)) { - atomic_set(&e->refcnt, 1); + if (!e->refcnt) { + e->refcnt = 1; e->state = SMT_STATE_SWITCHING; e->pfvf = pfvf; memcpy(e->src_mac, smac, ETH_ALEN); write_smt_entry(adap, e); } else { - atomic_inc(&e->refcnt); + ++e->refcnt; } spin_unlock(&e->lock); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h index d6c2cc271398..1268d6e93a47 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.h +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -59,7 +59,7 @@ struct smt_entry { u16 idx; u16 pfvf; u8 src_mac[ETH_ALEN]; - atomic_t refcnt; + int refcnt; spinlock_t lock; /* protect smt entry add,removal */ }; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 6d4cf3d0b2f0..f6fc0875d5b0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2478,11 +2478,10 @@ static int setup_debugfs(struct adapter *adapter) * Debugfs support is best effort. */ for (i = 0; i < ARRAY_SIZE(debugfs_files); i++) - (void)debugfs_create_file(debugfs_files[i].name, - debugfs_files[i].mode, - adapter->debugfs_root, - (void *)adapter, - debugfs_files[i].fops); + debugfs_create_file(debugfs_files[i].name, + debugfs_files[i].mode, + adapter->debugfs_root, (void *)adapter, + debugfs_files[i].fops); return 0; } @@ -3257,11 +3256,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, adapter->debugfs_root = debugfs_create_dir(pci_name(pdev), cxgb4vf_debugfs_root); - if (IS_ERR_OR_NULL(adapter->debugfs_root)) - dev_warn(&pdev->dev, "could not create debugfs" - " directory"); - else - setup_debugfs(adapter); + setup_debugfs(adapter); } /* @@ -3486,13 +3481,11 @@ static int __init cxgb4vf_module_init(void) return -EINVAL; } - /* Debugfs support is optional, just warn if this fails */ + /* Debugfs support is optional, debugfs will warn if this fails */ cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4vf_driver); - if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) + if (ret < 0) debugfs_remove(cxgb4vf_debugfs_root); return ret; } diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index ef5d61d57597..323976c811e9 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -550,7 +550,7 @@ int be_process_mcc(struct be_adapter *adapter) int num = 0, status = 0; struct be_mcc_obj *mcc_obj = &adapter->mcc_obj; - spin_lock(&adapter->mcc_cq_lock); + spin_lock_bh(&adapter->mcc_cq_lock); while ((compl = be_mcc_compl_get(adapter))) { if (compl->flags & CQE_FLAGS_ASYNC_MASK) { @@ -566,7 +566,7 @@ int be_process_mcc(struct be_adapter *adapter) if (num) be_cq_notify(adapter, mcc_obj->cq.id, mcc_obj->rearm_cq, num); - spin_unlock(&adapter->mcc_cq_lock); + spin_unlock_bh(&adapter->mcc_cq_lock); return status; } @@ -581,9 +581,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter) if (be_check_error(adapter, BE_ERROR_ANY)) return -EIO; - local_bh_disable(); status = be_process_mcc(adapter); - local_bh_enable(); if (atomic_read(&mcc_obj->q.used) == 0) break; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 1c9883019767..314e9868b861 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5630,9 +5630,7 @@ static void be_worker(struct work_struct *work) * mcc completions */ if (!netif_running(adapter->netdev)) { - local_bh_disable(); be_process_mcc(adapter); - local_bh_enable(); goto reschedule; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 9c4d1afa34e5..b4b82b9c5cd6 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -485,7 +485,7 @@ static struct dpaa_bp *dpaa_bpid2pool(int bpid) static bool dpaa_bpid2pool_use(int bpid) { if (dpaa_bpid2pool(bpid)) { - atomic_inc(&dpaa_bp_array[bpid]->refs); + refcount_inc(&dpaa_bp_array[bpid]->refs); return true; } @@ -496,7 +496,7 @@ static bool dpaa_bpid2pool_use(int bpid) static void dpaa_bpid2pool_map(int bpid, struct dpaa_bp *dpaa_bp) { dpaa_bp_array[bpid] = dpaa_bp; - atomic_set(&dpaa_bp->refs, 1); + refcount_set(&dpaa_bp->refs, 1); } static int dpaa_bp_alloc_pool(struct dpaa_bp *dpaa_bp) @@ -584,7 +584,7 @@ static void dpaa_bp_free(struct dpaa_bp *dpaa_bp) if (!bp) return; - if (!atomic_dec_and_test(&bp->refs)) + if (!refcount_dec_and_test(&bp->refs)) return; if (bp->free_buf_cb) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index af320f83c742..f7e59e8db075 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -32,6 +32,7 @@ #define __DPAA_H #include <linux/netdevice.h> +#include <linux/refcount.h> #include <soc/fsl/qman.h> #include <soc/fsl/bman.h> @@ -99,7 +100,7 @@ struct dpaa_bp { int (*seed_cb)(struct dpaa_bp *); /* bpool can be emptied before freeing by this cb */ void (*free_buf_cb)(const struct dpaa_bp *, struct bm_buffer *); - atomic_t refs; + refcount_t refs; }; struct dpaa_rx_errors { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index a027f4a9d0cc..a9afe46b837f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -164,70 +164,30 @@ static const struct file_operations dpaa2_dbg_ch_ops = { void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) { - if (!dpaa2_dbg_root) - return; + struct dentry *dir; /* Create a directory for the interface */ - priv->dbg.dir = debugfs_create_dir(priv->net_dev->name, - dpaa2_dbg_root); - if (!priv->dbg.dir) { - netdev_err(priv->net_dev, "debugfs_create_dir() failed\n"); - return; - } + dir = debugfs_create_dir(priv->net_dev->name, dpaa2_dbg_root); + priv->dbg.dir = dir; /* per-cpu stats file */ - priv->dbg.cpu_stats = debugfs_create_file("cpu_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_cpu_ops); - if (!priv->dbg.cpu_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_cpu_stats; - } + debugfs_create_file("cpu_stats", 0444, dir, priv, &dpaa2_dbg_cpu_ops); /* per-fq stats file */ - priv->dbg.fq_stats = debugfs_create_file("fq_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_fq_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_fq_stats; - } + debugfs_create_file("fq_stats", 0444, dir, priv, &dpaa2_dbg_fq_ops); /* per-fq stats file */ - priv->dbg.ch_stats = debugfs_create_file("ch_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_ch_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_ch_stats; - } - - return; - -err_ch_stats: - debugfs_remove(priv->dbg.fq_stats); -err_fq_stats: - debugfs_remove(priv->dbg.cpu_stats); -err_cpu_stats: - debugfs_remove(priv->dbg.dir); + debugfs_create_file("ch_stats", 0444, dir, priv, &dpaa2_dbg_ch_ops); } void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) { - debugfs_remove(priv->dbg.fq_stats); - debugfs_remove(priv->dbg.ch_stats); - debugfs_remove(priv->dbg.cpu_stats); - debugfs_remove(priv->dbg.dir); + debugfs_remove_recursive(priv->dbg.dir); } void dpaa2_eth_dbg_init(void) { dpaa2_dbg_root = debugfs_create_dir(DPAA2_ETH_DBG_ROOT, NULL); - if (!dpaa2_dbg_root) { - pr_err("DPAA2-ETH: debugfs create failed\n"); - return; - } - pr_debug("DPAA2-ETH: debugfs created\n"); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h index 4f63de997a26..15598b28f03b 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h @@ -11,9 +11,6 @@ struct dpaa2_eth_priv; struct dpaa2_debugfs { struct dentry *dir; - struct dentry *fq_stats; - struct dentry *ch_stats; - struct dentry *cpu_stats; }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 9c530f75134f..c219587bd334 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -2,6 +2,7 @@ config FSL_ENETC tristate "ENETC PF driver" depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + select PHYLIB help This driver supports NXP ENETC gigabit ethernet controller PCIe physical function (PF) devices, managing ENETC Ports at a privileged @@ -12,6 +13,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + select PHYLIB help This driver supports NXP ENETC gigabit ethernet controller PCIe virtual function (VF) devices enabled by the ENETC PF driver. diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index e80fedb27cee..210749bf1eac 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2439,9 +2439,6 @@ MODULE_PARM_DESC(fsl_fm_rx_extra_headroom, "Extra headroom for Rx buffers"); * buffers when not using jumbo frames. * Must be large enough to accommodate the network MTU, but small enough * to avoid wasting skb memory. - * - * Could be overridden once, at boot-time, via the - * fm_set_max_frm() callback. */ static int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE; module_param(fsl_fm_max_frm, int, 0); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 92372dc43be8..ebc37e256922 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -31,9 +31,6 @@ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ dma_addr_t bus; /* the bus for the desc_ring */ - u32 cnt; /* free-running total number of completed packets */ - u32 fill_cnt; /* free-running total number of descriptors posted */ - u32 mask; /* masks the cnt to the size of the ring */ u8 seqno; /* the next expected seqno for this desc*/ }; @@ -60,8 +57,6 @@ struct gve_rx_data_queue { dma_addr_t data_bus; /* dma mapping of the slots */ struct gve_rx_slot_page_info *page_info; /* page info of the buffers */ struct gve_queue_page_list *qpl; /* qpl assigned to this queue */ - u32 mask; /* masks the cnt to the size of the ring */ - u32 cnt; /* free-running total number of completed packets */ }; struct gve_priv; @@ -73,6 +68,9 @@ struct gve_rx_ring { struct gve_rx_data_queue data; u64 rbytes; /* free-running bytes received */ u64 rpackets; /* free-running packets received */ + u32 cnt; /* free-running total number of completed packets */ + u32 fill_cnt; /* free-running total number of descs and buffs posted */ + u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ u32 q_num; /* queue index */ u32 ntfy_id; /* notification block index */ struct gve_queue_resources *q_resources; /* head and tail pointer idx */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 26540b856541..d8fa816f4473 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -138,8 +138,8 @@ gve_get_ethtool_stats(struct net_device *netdev, for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { struct gve_rx_ring *rx = &priv->rx[ring]; - data[i++] = rx->desc.cnt; - data[i++] = rx->desc.fill_cnt; + data[i++] = rx->cnt; + data[i++] = rx->fill_cnt; } } else { i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 1914b8350da7..59564ac99d2a 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -37,7 +37,7 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) rx->data.qpl = NULL; kvfree(rx->data.page_info); - slots = rx->data.mask + 1; + slots = rx->mask + 1; bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(dev, bytes, rx->data.data_ring, rx->data.data_bus); @@ -64,7 +64,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) /* Allocate one page per Rx queue slot. Each page is split into two * packet buffers, when possible we "page flip" between the two. */ - slots = rx->data.mask + 1; + slots = rx->mask + 1; rx->data.page_info = kvzalloc(slots * sizeof(*rx->data.page_info), GFP_KERNEL); @@ -111,7 +111,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) rx->q_num = idx; slots = priv->rx_pages_per_qpl; - rx->data.mask = slots - 1; + rx->mask = slots - 1; /* alloc rx data ring */ bytes = sizeof(*rx->data.data_ring) * slots; @@ -125,7 +125,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) err = -ENOMEM; goto abort_with_slots; } - rx->desc.fill_cnt = filled_pages; + rx->fill_cnt = filled_pages; /* Ensure data ring slots (packet buffers) are visible. */ dma_wmb(); @@ -156,8 +156,8 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) err = -ENOMEM; goto abort_with_q_resources; } - rx->desc.mask = slots - 1; - rx->desc.cnt = 0; + rx->mask = slots - 1; + rx->cnt = 0; rx->desc.seqno = 1; gve_rx_add_to_block(priv, idx); @@ -213,7 +213,7 @@ void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx) { u32 db_idx = be32_to_cpu(rx->q_resources->db_index); - iowrite32be(rx->desc.fill_cnt, &priv->db_bar2[db_idx]); + iowrite32be(rx->fill_cnt, &priv->db_bar2[db_idx]); } static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) @@ -273,7 +273,7 @@ static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, } static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, - netdev_features_t feat) + netdev_features_t feat, u32 idx) { struct gve_rx_slot_page_info *page_info; struct gve_priv *priv = rx->gve; @@ -282,14 +282,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, struct sk_buff *skb; int pagecount; u16 len; - u32 idx; /* drop this packet */ if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) return true; len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD; - idx = rx->data.cnt & rx->data.mask; page_info = &rx->data.page_info[idx]; /* gvnic can only receive into registered segments. If the buffer @@ -340,8 +338,6 @@ have_skb: if (!skb) return true; - rx->data.cnt++; - if (likely(feat & NETIF_F_RXCSUM)) { /* NIC passes up the partial sum */ if (rx_desc->csum) @@ -370,7 +366,7 @@ static bool gve_rx_work_pending(struct gve_rx_ring *rx) __be16 flags_seq; u32 next_idx; - next_idx = rx->desc.cnt & rx->desc.mask; + next_idx = rx->cnt & rx->mask; desc = rx->desc.desc_ring + next_idx; flags_seq = desc->flags_seq; @@ -385,8 +381,8 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, { struct gve_priv *priv = rx->gve; struct gve_rx_desc *desc; - u32 cnt = rx->desc.cnt; - u32 idx = cnt & rx->desc.mask; + u32 cnt = rx->cnt; + u32 idx = cnt & rx->mask; u32 work_done = 0; u64 bytes = 0; @@ -401,10 +397,10 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, rx->q_num, GVE_SEQNO(desc->flags_seq), rx->desc.seqno); bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; - if (!gve_rx(rx, desc, feat)) + if (!gve_rx(rx, desc, feat, idx)) gve_schedule_reset(priv); cnt++; - idx = cnt & rx->desc.mask; + idx = cnt & rx->mask; desc = rx->desc.desc_ring + idx; rx->desc.seqno = gve_next_seqno(rx->desc.seqno); work_done++; @@ -417,8 +413,8 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, rx->rpackets += work_done; rx->rbytes += bytes; u64_stats_update_end(&rx->statss); - rx->desc.cnt = cnt; - rx->desc.fill_cnt += work_done; + rx->cnt = cnt; + rx->fill_cnt += work_done; /* restock desc ring slots */ dma_wmb(); /* Ensure descs are visible before ringing doorbell */ diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index d60452845539..c84167447abe 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -220,6 +220,7 @@ struct hip04_priv { unsigned int reg_inten; struct napi_struct napi; + struct device *dev; struct net_device *ndev; struct tx_desc *tx_desc; @@ -248,7 +249,7 @@ struct hip04_priv { static inline unsigned int tx_count(unsigned int head, unsigned int tail) { - return (head - tail) % (TX_DESC_NUM - 1); + return (head - tail) % TX_DESC_NUM; } static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex) @@ -465,7 +466,7 @@ static int hip04_tx_reclaim(struct net_device *ndev, bool force) } if (priv->tx_phys[tx_tail]) { - dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail], + dma_unmap_single(priv->dev, priv->tx_phys[tx_tail], priv->tx_skb[tx_tail]->len, DMA_TO_DEVICE); priv->tx_phys[tx_tail] = 0; @@ -516,8 +517,8 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } - phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) { + phys = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, phys)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -585,6 +586,9 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) u16 len; u32 err; + /* clean up tx descriptors */ + tx_remaining = hip04_tx_reclaim(ndev, false); + while (cnt && !last) { buf = priv->rx_buf[priv->rx_head]; skb = build_skb(buf, priv->rx_buf_size); @@ -593,7 +597,7 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget) goto refill; } - dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head], + dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[priv->rx_head] = 0; @@ -622,9 +626,9 @@ refill: buf = netdev_alloc_frag(priv->rx_buf_size); if (!buf) goto done; - phys = dma_map_single(&ndev->dev, buf, + phys = dma_map_single(priv->dev, buf, RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) goto done; priv->rx_buf[priv->rx_head] = buf; priv->rx_phys[priv->rx_head] = phys; @@ -645,8 +649,7 @@ refill: } napi_complete_done(napi, rx); done: - /* clean up tx descriptors and start a new timer if necessary */ - tx_remaining = hip04_tx_reclaim(ndev, false); + /* start a new timer if necessary */ if (rx < budget && tx_remaining) hip04_start_tx_timer(priv); @@ -728,9 +731,9 @@ static int hip04_mac_open(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { dma_addr_t phys; - phys = dma_map_single(&ndev->dev, priv->rx_buf[i], + phys = dma_map_single(priv->dev, priv->rx_buf[i], RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, phys)) + if (dma_mapping_error(priv->dev, phys)) return -EIO; priv->rx_phys[i] = phys; @@ -764,7 +767,7 @@ static int hip04_mac_stop(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { if (priv->rx_phys[i]) { - dma_unmap_single(&ndev->dev, priv->rx_phys[i], + dma_unmap_single(priv->dev, priv->rx_phys[i], RX_BUF_SIZE, DMA_FROM_DEVICE); priv->rx_phys[i] = 0; } @@ -907,6 +910,7 @@ static int hip04_mac_probe(struct platform_device *pdev) return -ENOMEM; priv = netdev_priv(ndev); + priv->dev = d; priv->ndev = ndev; platform_set_drvdata(pdev, ndev); SET_NETDEV_DEV(ndev, &pdev->dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index a4624db3b5d5..6c9fd58c436f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -58,10 +58,10 @@ BIT(HNAE3_DEV_SUPPORT_ROCE_B)) #define hnae3_dev_roce_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) #define hnae3_dev_dcb_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) #define hnae3_dev_fd_supported(hdev) \ hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B) @@ -91,6 +91,11 @@ struct hnae3_queue { u16 rx_desc_num;/* total number of rx desc */ }; +struct hns3_mac_stats { + u64 tx_pause_cnt; + u64 rx_pause_cnt; +}; + /*hnae3 loop mode*/ enum hnae3_loop { HNAE3_LOOP_APP, @@ -298,6 +303,8 @@ struct hnae3_ae_dev { * Remove multicast address from mac table * update_stats() * Update Old network device statistics + * get_mac_stats() + * get mac pause statistics including tx_cnt and rx_cnt * get_ethtool_stats() * Get ethtool network device statistics * get_strings() @@ -426,8 +433,8 @@ struct hnae3_ae_ops { void (*update_stats)(struct hnae3_handle *handle, struct net_device_stats *net_stats); void (*get_stats)(struct hnae3_handle *handle, u64 *data); - void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt); + void (*get_mac_stats)(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats); void (*get_strings)(struct hnae3_handle *handle, u32 stringset, u8 *data); int (*get_sset_count)(struct hnae3_handle *handle, int stringset); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index a4b937286f55..7070d25ddb5b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -8,6 +8,7 @@ #include "hns3_enet.h" #define HNS3_DBG_READ_LEN 256 +#define HNS3_DBG_WRITE_LEN 1024 static struct dentry *hns3_dbgfs_root; @@ -322,6 +323,9 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer, test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) return 0; + if (count > HNS3_DBG_WRITE_LEN) + return -ENOSPC; + cmd_buf = kzalloc(count + 1, GFP_KERNEL); if (!cmd_buf) return count; @@ -372,20 +376,11 @@ static const struct file_operations hns3_dbg_cmd_fops = { void hns3_dbg_init(struct hnae3_handle *handle) { const char *name = pci_name(handle->pdev); - struct dentry *pfile; handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root); - if (!handle->hnae3_dbgfs) - return; - pfile = debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, - &hns3_dbg_cmd_fops); - if (!pfile) { - debugfs_remove_recursive(handle->hnae3_dbgfs); - handle->hnae3_dbgfs = NULL; - dev_warn(&handle->pdev->dev, "create file for %s fail\n", - name); - } + debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, + &hns3_dbg_cmd_fops); } void hns3_dbg_uninit(struct hnae3_handle *handle) @@ -397,10 +392,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) void hns3_dbg_register_debugfs(const char *debugfs_dir_name) { hns3_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (!hns3_dbgfs_root) { - pr_warn("Register debugfs for %s fail\n", debugfs_dir_name); - return; - } } void hns3_dbg_unregister_debugfs(void) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index ed05fb9f04ed..1750f80341e7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -28,6 +28,12 @@ #define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift))) #define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE) +#define hns3_rl_err(fmt, ...) \ + do { \ + if (net_ratelimit()) \ + netdev_err(fmt, ##__VA_ARGS__); \ + } while (0) + static void hns3_clear_all_ring(struct hnae3_handle *h, bool force); static void hns3_remove_hw_addr(struct net_device *netdev); @@ -45,6 +51,9 @@ MODULE_PARM_DESC(debug, " Network interface message level setting"); #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \ NETIF_MSG_IFDOWN | NETIF_MSG_IFUP) +#define HNS3_INNER_VLAN_TAG 1 +#define HNS3_OUTER_VLAN_TAG 2 + /* hns3_pci_tbl - PCI Device ID Table * * Last entry must be all 0s @@ -961,16 +970,16 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U); } -static int hns3_fill_desc_vtags(struct sk_buff *skb, - struct hns3_enet_ring *tx_ring, - u32 *inner_vlan_flag, - u32 *out_vlan_flag, - u16 *inner_vtag, - u16 *out_vtag) +static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring, + struct sk_buff *skb) { -#define HNS3_TX_VLAN_PRIO_SHIFT 13 - struct hnae3_handle *handle = tx_ring->tqp->handle; + struct vlan_ethhdr *vhdr; + int rc; + + if (!(skb->protocol == htons(ETH_P_8021Q) || + skb_vlan_tag_present(skb))) + return 0; /* Since HW limitation, if port based insert VLAN enabled, only one VLAN * header is allowed in skb, otherwise it will cause RAS error. @@ -981,8 +990,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, return -EINVAL; if (skb->protocol == htons(ETH_P_8021Q) && - !(tx_ring->tqp->handle->kinfo.netdev->features & - NETIF_F_HW_VLAN_CTAG_TX)) { + !(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) { /* When HW VLAN acceleration is turned off, and the stack * sets the protocol to 802.1q, the driver just need to * set the protocol to the encapsulated ethertype. @@ -992,45 +1000,107 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, } if (skb_vlan_tag_present(skb)) { - u16 vlan_tag; - - vlan_tag = skb_vlan_tag_get(skb); - vlan_tag |= (skb->priority & 0x7) << HNS3_TX_VLAN_PRIO_SHIFT; - /* Based on hw strategy, use out_vtag in two layer tag case, * and use inner_vtag in one tag case. */ - if (skb->protocol == htons(ETH_P_8021Q)) { - if (handle->port_base_vlan_state == - HNAE3_PORT_BASE_VLAN_DISABLE){ - hns3_set_field(*out_vlan_flag, - HNS3_TXD_OVLAN_B, 1); - *out_vtag = vlan_tag; - } else { - hns3_set_field(*inner_vlan_flag, - HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else { - hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else if (skb->protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *vhdr; - int rc; + if (skb->protocol == htons(ETH_P_8021Q) && + handle->port_base_vlan_state == + HNAE3_PORT_BASE_VLAN_DISABLE) + rc = HNS3_OUTER_VLAN_TAG; + else + rc = HNS3_INNER_VLAN_TAG; - rc = skb_cow_head(skb, 0); - if (unlikely(rc < 0)) - return rc; - vhdr = (struct vlan_ethhdr *)skb->data; - vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7) - << HNS3_TX_VLAN_PRIO_SHIFT); + skb->protocol = vlan_get_protocol(skb); + return rc; } + rc = skb_cow_head(skb, 0); + if (unlikely(rc < 0)) + return rc; + + vhdr = (struct vlan_ethhdr *)skb->data; + vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT) + & VLAN_PRIO_MASK); + skb->protocol = vlan_get_protocol(skb); return 0; } +static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, + struct sk_buff *skb, struct hns3_desc *desc) +{ + u32 ol_type_vlan_len_msec = 0; + u32 type_cs_vlan_tso = 0; + u32 paylen = skb->len; + u16 inner_vtag = 0; + u16 out_vtag = 0; + u16 mss = 0; + int ret; + + ret = hns3_handle_vtags(ring, skb); + if (unlikely(ret < 0)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_vlan_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } else if (ret == HNS3_INNER_VLAN_TAG) { + inner_vtag = skb_vlan_tag_get(skb); + inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1); + } else if (ret == HNS3_OUTER_VLAN_TAG) { + out_vtag = skb_vlan_tag_get(skb); + out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B, + 1); + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + u8 ol4_proto, il4_proto; + + skb_reset_mac_len(skb); + + ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l4_proto_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l2l3l4_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_tso(skb, &paylen, &mss, + &type_cs_vlan_tso); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_tso_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + } + + /* Set txbd */ + desc->tx.ol_type_vlan_len_msec = + cpu_to_le32(ol_type_vlan_len_msec); + desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); + desc->tx.paylen = cpu_to_le32(paylen); + desc->tx.mss = cpu_to_le16(mss); + desc->tx.vlan_tag = cpu_to_le16(inner_vtag); + desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); + + return 0; +} + static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, unsigned int size, int frag_end, enum hns_desc_type type) @@ -1045,50 +1115,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, if (type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; - u32 ol_type_vlan_len_msec = 0; - u32 type_cs_vlan_tso = 0; - u32 paylen = skb->len; - u16 inner_vtag = 0; - u16 out_vtag = 0; - u16 mss = 0; int ret; - ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso, - &ol_type_vlan_len_msec, - &inner_vtag, &out_vtag); + ret = hns3_fill_skb_desc(ring, skb, desc); if (unlikely(ret)) return ret; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - u8 ol4_proto, il4_proto; - - skb_reset_mac_len(skb); - - ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); - if (unlikely(ret)) - return ret; - - ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, - &type_cs_vlan_tso, - &ol_type_vlan_len_msec); - if (unlikely(ret)) - return ret; - - ret = hns3_set_tso(skb, &paylen, &mss, - &type_cs_vlan_tso); - if (unlikely(ret)) - return ret; - } - - /* Set txbd */ - desc->tx.ol_type_vlan_len_msec = - cpu_to_le32(ol_type_vlan_len_msec); - desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); - desc->tx.paylen = cpu_to_le32(paylen); - desc->tx.mss = cpu_to_le16(mss); - desc->tx.vlan_tag = cpu_to_le16(inner_vtag); - desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); } else { frag = (skb_frag_t *)priv; @@ -1096,7 +1128,9 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, } if (unlikely(dma_mapping_error(dev, dma))) { + u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); return -ENOMEM; } @@ -1152,28 +1186,20 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, return 0; } -static int hns3_nic_bd_num(struct sk_buff *skb) +static unsigned int hns3_nic_bd_num(struct sk_buff *skb) { - int size = skb_headlen(skb); - int i, bd_num; + unsigned int bd_num; + int i; /* if the total len is within the max bd limit */ if (likely(skb->len <= HNS3_MAX_BD_SIZE)) return skb_shinfo(skb)->nr_frags + 1; - bd_num = hns3_tx_bd_count(size); + bd_num = hns3_tx_bd_count(skb_headlen(skb)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - int frag_bd_num; - - size = skb_frag_size(frag); - frag_bd_num = hns3_tx_bd_count(size); - - if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG)) - return -ENOMEM; - - bd_num += frag_bd_num; + bd_num += hns3_tx_bd_count(skb_frag_size(frag)); } return bd_num; @@ -1194,7 +1220,7 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb) */ static bool hns3_skb_need_linearized(struct sk_buff *skb) { - int bd_limit = HNS3_MAX_BD_PER_FRAG - 1; + int bd_limit = HNS3_MAX_BD_NUM_NORMAL - 1; unsigned int tot_len = 0; int i; @@ -1224,21 +1250,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, struct sk_buff **out_skb) { struct sk_buff *skb = *out_skb; - int bd_num; + unsigned int bd_num; bd_num = hns3_nic_bd_num(skb); - if (bd_num < 0) - return bd_num; - - if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) { + if (unlikely(bd_num > HNS3_MAX_BD_NUM_NORMAL)) { struct sk_buff *new_skb; - if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb)) + if (skb_is_gso(skb) && bd_num <= HNS3_MAX_BD_NUM_TSO && + !hns3_skb_need_linearized(skb)) goto out; - bd_num = hns3_tx_bd_count(skb->len); - if (unlikely(ring_space(ring) < bd_num)) - return -EBUSY; /* manual split the send packet */ new_skb = skb_copy(skb, GFP_ATOMIC); if (!new_skb) @@ -1246,6 +1267,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, dev_kfree_skb_any(skb); *out_skb = new_skb; + bd_num = hns3_nic_bd_num(new_skb); + if ((skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_TSO) || + (!skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_NORMAL)) + return -ENOMEM; + u64_stats_update_begin(&ring->syncp); ring->stats.tx_copy++; u64_stats_update_end(&ring->syncp); @@ -1319,9 +1345,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) u64_stats_update_end(&ring->syncp); } - if (net_ratelimit()) - netdev_err(netdev, "xmit error: %d!\n", buf_num); - + hns3_rl_err(netdev, "xmit error: %d!\n", buf_num); goto out_err_tx_ok; } @@ -1487,7 +1511,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev, tx_bytes += ring->stats.tx_bytes; tx_pkts += ring->stats.tx_pkts; tx_drop += ring->stats.sw_err_cnt; + tx_drop += ring->stats.tx_vlan_err; + tx_drop += ring->stats.tx_l4_proto_err; + tx_drop += ring->stats.tx_l2l3l4_err; + tx_drop += ring->stats.tx_tso_err; tx_errors += ring->stats.sw_err_cnt; + tx_errors += ring->stats.tx_vlan_err; + tx_errors += ring->stats.tx_l4_proto_err; + tx_errors += ring->stats.tx_l2l3l4_err; + tx_errors += ring->stats.tx_tso_err; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); /* fetch the rx stats */ @@ -1694,15 +1726,12 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev) /* When mac received many pause frames continuous, it's unable to send * packets, which may cause tx timeout */ - if (h->ae_algo->ops->update_stats && - h->ae_algo->ops->get_mac_pause_stats) { - u64 tx_pause_cnt, rx_pause_cnt; + if (h->ae_algo->ops->get_mac_stats) { + struct hns3_mac_stats mac_stats; - h->ae_algo->ops->update_stats(h, &ndev->stats); - h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt, - &rx_pause_cnt); + h->ae_algo->ops->get_mac_stats(h, &mac_stats); netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n", - tx_pause_cnt, rx_pause_cnt); + mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt); } hw_head = readl_relaxed(tx_ring->tqp->io_base + @@ -2371,8 +2400,9 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, ring->stats.sw_err_cnt++; u64_stats_update_end(&ring->syncp); - netdev_err(ring->tqp->handle->kinfo.netdev, - "hnae reserve buffer map failed.\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx buffer failed: %d\n", + ret); break; } hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); @@ -2457,9 +2487,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info) th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr, &iph->daddr, 0); } else { - netdev_err(skb->dev, - "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", - be16_to_cpu(type), depth); + hns3_rl_err(skb->dev, + "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", + be16_to_cpu(type), depth); return -EFAULT; } @@ -2601,7 +2631,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length, ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); skb = ring->skb; if (unlikely(!skb)) { - netdev_err(netdev, "alloc rx skb fail\n"); + hns3_rl_err(netdev, "alloc rx skb fail\n"); u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; @@ -2676,8 +2706,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, new_skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); if (unlikely(!new_skb)) { - netdev_err(ring->tqp->handle->kinfo.netdev, - "alloc rx skb frag fail\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx fraglist skb fail\n"); return -ENXIO; } ring->frag_num = 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 0a970f5fed10..5b0ee1fe40f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -195,7 +195,8 @@ enum hns3_nic_state { #define HNS3_VECTOR_INITED 1 #define HNS3_MAX_BD_SIZE 65535 -#define HNS3_MAX_BD_PER_FRAG 8 +#define HNS3_MAX_BD_NUM_NORMAL 8 +#define HNS3_MAX_BD_NUM_TSO 63 #define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS #define HNS3_VECTOR_GL0_OFFSET 0x100 @@ -377,6 +378,10 @@ struct ring_stats { u64 restart_queue; u64 tx_busy; u64 tx_copy; + u64 tx_vlan_err; + u64 tx_l4_proto_err; + u64 tx_l2l3l4_err; + u64 tx_tso_err; }; struct { u64 rx_pkts; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 02f46c73ac3b..185ff32262e4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -30,6 +30,10 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("wake", restart_queue), HNS3_TQP_STAT("busy", tx_busy), HNS3_TQP_STAT("copy", tx_copy), + HNS3_TQP_STAT("vlan_err", tx_vlan_err), + HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err), + HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err), + HNS3_TQP_STAT("tso_err", tx_tso_err), }; #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index dade20a37d40..29979be9e33a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -87,6 +87,7 @@ enum hclge_opcode_type { HCLGE_OPC_QUERY_VF_RSRC = 0x0024, HCLGE_OPC_GET_CFG_PARAM = 0x0025, HCLGE_OPC_PF_RST_DONE = 0x0026, + HCLGE_OPC_QUERY_VF_RST_RDY = 0x0027, HCLGE_OPC_STATS_64_BIT = 0x0030, HCLGE_OPC_STATS_32_BIT = 0x0031, @@ -588,6 +589,12 @@ struct hclge_config_mac_mode_cmd { u8 rsv[20]; }; +struct hclge_pf_rst_sync_cmd { +#define HCLGE_PF_RST_ALL_VF_RDY_B 0 + u8 all_vf_ready; + u8 rsv[23]; +}; + #define HCLGE_CFG_SPEED_S 0 #define HCLGE_CFG_SPEED_M GENMASK(5, 0) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index f16bfc67412a..f0295d12a1b6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -14,16 +14,8 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset) struct hclge_desc desc[4]; int ret; - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); - desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); - desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); - desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); - - ret = hclge_cmd_send(&hdev->hw, desc, 4); - if (ret != HCLGE_CMD_EXEC_SUCCESS) { + ret = hclge_query_bd_num_cmd_send(hdev, desc); + if (ret) { dev_err(&hdev->pdev->dev, "get dfx bdnum fail, status is %d.\n", ret); return ret; @@ -1003,6 +995,33 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) kfree(desc_src); } +#define HCLGE_CMD_NCL_CONFIG_BD_NUM 5 + +static void hclge_ncl_config_data_print(struct hclge_dev *hdev, + struct hclge_desc *desc, int *offset, + int *length) +{ +#define HCLGE_CMD_DATA_NUM 6 + + int i; + int j; + + for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) { + for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { + if (i == 0 && j == 0) + continue; + + dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", + *offset, + le32_to_cpu(desc[i].data[j])); + *offset += sizeof(u32); + *length -= sizeof(u32); + if (*length <= 0) + return; + } + } +} + /* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file * @hdev: pointer to struct hclge_dev * @cmd_buf: string that contains offset and length @@ -1012,17 +1031,13 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, { #define HCLGE_MAX_NCL_CONFIG_OFFSET 4096 #define HCLGE_MAX_NCL_CONFIG_LENGTH (20 + 24 * 4) -#define HCLGE_CMD_DATA_NUM 6 - struct hclge_desc desc[5]; - u32 byte_offset; - int bd_num = 5; + struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM]; + int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM; int offset; int length; int data0; int ret; - int i; - int j; ret = sscanf(cmd_buf, "%x %x", &offset, &length); if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET || @@ -1048,22 +1063,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, if (ret) return; - byte_offset = offset; - for (i = 0; i < bd_num; i++) { - for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { - if (i == 0 && j == 0) - continue; - - dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", - byte_offset, - le32_to_cpu(desc[i].data[j])); - byte_offset += sizeof(u32); - length -= sizeof(u32); - if (length <= 0) - return; - } - } - offset += HCLGE_MAX_NCL_CONFIG_LENGTH; + hclge_ncl_config_data_print(hdev, desc, &offset, &length); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index b7399f5ba2c3..a3ca0e6e1e30 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -35,6 +35,23 @@ #define BUF_RESERVE_PERCENT 90 #define HCLGE_RESET_MAX_FAIL_CNT 5 +#define HCLGE_RESET_SYNC_TIME 100 +#define HCLGE_PF_RESET_SYNC_TIME 20 +#define HCLGE_PF_RESET_SYNC_CNT 1500 + +/* Get DFX BD number offset */ +#define HCLGE_DFX_BIOS_BD_OFFSET 1 +#define HCLGE_DFX_SSU_0_BD_OFFSET 2 +#define HCLGE_DFX_SSU_1_BD_OFFSET 3 +#define HCLGE_DFX_IGU_BD_OFFSET 4 +#define HCLGE_DFX_RPU_0_BD_OFFSET 5 +#define HCLGE_DFX_RPU_1_BD_OFFSET 6 +#define HCLGE_DFX_NCSI_BD_OFFSET 7 +#define HCLGE_DFX_RTC_BD_OFFSET 8 +#define HCLGE_DFX_PPP_BD_OFFSET 9 +#define HCLGE_DFX_RCB_BD_OFFSET 10 +#define HCLGE_DFX_TQP_BD_OFFSET 11 +#define HCLGE_DFX_SSU_2_BD_OFFSET 12 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps); static int hclge_init_vlan_config(struct hclge_dev *hdev); @@ -317,6 +334,36 @@ static const u8 hclge_hash_key[] = { 0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA }; +static const u32 hclge_dfx_bd_offset_list[] = { + HCLGE_DFX_BIOS_BD_OFFSET, + HCLGE_DFX_SSU_0_BD_OFFSET, + HCLGE_DFX_SSU_1_BD_OFFSET, + HCLGE_DFX_IGU_BD_OFFSET, + HCLGE_DFX_RPU_0_BD_OFFSET, + HCLGE_DFX_RPU_1_BD_OFFSET, + HCLGE_DFX_NCSI_BD_OFFSET, + HCLGE_DFX_RTC_BD_OFFSET, + HCLGE_DFX_PPP_BD_OFFSET, + HCLGE_DFX_RCB_BD_OFFSET, + HCLGE_DFX_TQP_BD_OFFSET, + HCLGE_DFX_SSU_2_BD_OFFSET +}; + +static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = { + HCLGE_OPC_DFX_BIOS_COMMON_REG, + HCLGE_OPC_DFX_SSU_REG_0, + HCLGE_OPC_DFX_SSU_REG_1, + HCLGE_OPC_DFX_IGU_EGU_REG, + HCLGE_OPC_DFX_RPU_REG_0, + HCLGE_OPC_DFX_RPU_REG_1, + HCLGE_OPC_DFX_NCSI_REG, + HCLGE_OPC_DFX_RTC_REG, + HCLGE_OPC_DFX_PPP_REG, + HCLGE_OPC_DFX_RCB_REG, + HCLGE_OPC_DFX_TQP_REG, + HCLGE_OPC_DFX_SSU_REG_2 +}; + static int hclge_mac_update_stats_defective(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -364,9 +411,13 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num) u16 i, k, n; int ret; - desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL); + /* This may be called inside atomic sections, + * so GFP_ATOMIC is more suitalbe here + */ + desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC); if (!desc) return -ENOMEM; + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true); ret = hclge_cmd_send(&hdev->hw, desc, desc_num); if (ret) { @@ -702,14 +753,16 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) p = hclge_tqps_get_stats(handle, p); } -static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt) +static void hclge_get_mac_stat(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - *tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; - *rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; + hclge_update_stats(handle, NULL); + + mac_stats->tx_pause_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; + mac_stats->rx_pause_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; } static int hclge_parse_func_status(struct hclge_dev *hdev, @@ -3134,6 +3187,39 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) return 0; } +static int hclge_func_reset_sync_vf(struct hclge_dev *hdev) +{ + struct hclge_pf_rst_sync_cmd *req; + struct hclge_desc desc; + int cnt = 0; + int ret; + + req = (struct hclge_pf_rst_sync_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_VF_RST_RDY, true); + + do { + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + /* for compatible with old firmware, wait + * 100 ms for VF to stop IO + */ + if (ret == -EOPNOTSUPP) { + msleep(HCLGE_RESET_SYNC_TIME); + return 0; + } else if (ret) { + dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n", + ret); + return ret; + } else if (req->all_vf_ready) { + return 0; + } + msleep(HCLGE_PF_RESET_SYNC_TIME); + hclge_cmd_reuse_desc(&desc, true); + } while (cnt++ < HCLGE_PF_RESET_SYNC_CNT); + + dev_err(&hdev->pdev->dev, "sync with VF timeout!\n"); + return -ETIME; +} + int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id) { struct hclge_desc desc; @@ -3300,17 +3386,18 @@ static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable) static int hclge_reset_prepare_wait(struct hclge_dev *hdev) { -#define HCLGE_RESET_SYNC_TIME 100 - u32 reg_val; int ret = 0; switch (hdev->reset_type) { case HNAE3_FUNC_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + ret = hclge_func_reset_cmd(hdev, 0); if (ret) { dev_err(&hdev->pdev->dev, @@ -3327,10 +3414,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) hdev->rst_stats.pf_rst_cnt++; break; case HNAE3_FLR_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); set_bit(HNAE3_FLR_DOWN, &hdev->flr_state); hdev->rst_stats.flr_rst_cnt++; @@ -8203,28 +8293,15 @@ static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) { int ret; - if (rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_FULL; - else if (rx_en && !tx_en) - hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; - else if (!rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; - else - hdev->fc_mode_last_time = HCLGE_FC_NONE; - if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) return 0; ret = hclge_mac_pause_en_cfg(hdev, tx_en, rx_en); - if (ret) { - dev_err(&hdev->pdev->dev, "configure pauseparam error, ret = %d.\n", - ret); - return ret; - } - - hdev->tm_info.fc_mode = hdev->fc_mode_last_time; + if (ret) + dev_err(&hdev->pdev->dev, + "configure pauseparam error, ret = %d.\n", ret); - return 0; + return ret; } int hclge_cfg_flowctrl(struct hclge_dev *hdev) @@ -8289,6 +8366,21 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg, } } +static void hclge_record_user_pauseparam(struct hclge_dev *hdev, + u32 rx_en, u32 tx_en) +{ + if (rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_FULL; + else if (rx_en && !tx_en) + hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; + else if (!rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; + else + hdev->fc_mode_last_time = HCLGE_FC_NONE; + + hdev->tm_info.fc_mode = hdev->fc_mode_last_time; +} + static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, u32 rx_en, u32 tx_en) { @@ -8314,6 +8406,8 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, hclge_set_flowctrl_adv(hdev, rx_en, tx_en); + hclge_record_user_pauseparam(hdev, rx_en, tx_en); + if (!auto_neg) return hclge_cfg_pauseparam(hdev, rx_en, tx_en); @@ -9324,106 +9418,314 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, } #define MAX_SEPARATE_NUM 4 -#define SEPARATOR_VALUE 0xFFFFFFFF +#define SEPARATOR_VALUE 0xFDFCFBFA #define REG_NUM_PER_LINE 4 #define REG_LEN_PER_LINE (REG_NUM_PER_LINE * sizeof(u32)) +#define REG_SEPARATOR_LINE 1 +#define REG_NUM_REMAIN_MASK 3 +#define BD_LIST_MAX_NUM 30 -static int hclge_get_regs_len(struct hnae3_handle *handle) +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc) { - int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; + /*prepare 4 commands to query DFX BD number*/ + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); + desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); + desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); + + return hclge_cmd_send(&hdev->hw, desc, 4); +} + +static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev, + int *bd_num_list, + u32 type_num) +{ +#define HCLGE_DFX_REG_BD_NUM 4 + + u32 entries_per_desc, desc_index, index, offset, i; + struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM]; int ret; - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + ret = hclge_query_bd_num_cmd_send(hdev, desc); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return -EOPNOTSUPP; + "Get dfx bd num fail, status is %d.\n", ret); + return ret; } - cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1; - common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1; - ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1; - tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1; + entries_per_desc = ARRAY_SIZE(desc[0].data); + for (i = 0; i < type_num; i++) { + offset = hclge_dfx_bd_offset_list[i]; + index = offset % entries_per_desc; + desc_index = offset / entries_per_desc; + bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]); + } - return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + - tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE + - regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64); + return ret; } -static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, - void *data) +static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc_src, int bd_num, + enum hclge_opcode_type cmd) { - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; - int i, j, reg_um, separator_num; + struct hclge_desc *desc = desc_src; + int i, ret; + + hclge_cmd_setup_basic_desc(desc, cmd, true); + for (i = 0; i < bd_num - 1; i++) { + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + desc++; + hclge_cmd_setup_basic_desc(desc, cmd, true); + } + + desc = desc_src; + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(&hdev->pdev->dev, + "Query dfx reg cmd(0x%x) send fail, status is %d.\n", + cmd, ret); + + return ret; +} + +static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num, + void *data) +{ + int entries_per_desc, reg_num, separator_num, desc_index, index, i; + struct hclge_desc *desc = desc_src; u32 *reg = data; + + entries_per_desc = ARRAY_SIZE(desc->data); + reg_num = entries_per_desc * bd_num; + separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) { + index = i % entries_per_desc; + desc_index = i / entries_per_desc; + *reg++ = le32_to_cpu(desc[desc_index].data[index]); + } + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + return reg_num + separator_num; +} + +static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int data_len_per_desc, data_len, bd_num, i; + int bd_num_list[BD_LIST_MAX_NUM]; int ret; - *version = hdev->fw_version; + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; + } - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + *len = 0; + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + data_len = data_len_per_desc * bd_num; + *len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE; + } + + return ret; +} + +static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int bd_num, bd_num_max, buf_len, i; + int bd_num_list[BD_LIST_MAX_NUM]; + struct hclge_desc *desc_src; + u32 *reg = data; + int ret; + + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return; + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; } + bd_num_max = bd_num_list[0]; + for (i = 1; i < dfx_reg_type_num; i++) + bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); + + buf_len = sizeof(*desc_src) * bd_num_max; + desc_src = kzalloc(buf_len, GFP_KERNEL); + if (!desc_src) { + dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__); + return -ENOMEM; + } + + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num, + hclge_dfx_reg_opcode_list[i]); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg fail, status is %d.\n", ret); + break; + } + + reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); + } + + kfree(desc_src); + return ret; +} + +static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, + struct hnae3_knic_private_info *kinfo) +{ +#define HCLGE_RING_REG_OFFSET 0x200 +#define HCLGE_RING_INT_REG_OFFSET 0x4 + + int i, j, reg_num, separator_num; + int data_num_sum; + u32 *reg = data; + /* fetching per-PF registers valus from PF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(cmdq_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum = reg_num + separator_num; - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(common_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum += reg_num + separator_num; - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(ring_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < kinfo->num_tqps; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, ring_reg_addr_list[i] + - 0x200 * j); + HCLGE_RING_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * kinfo->num_tqps; - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < hdev->num_msi_used - 1; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, tqp_intr_reg_addr_list[i] + - 4 * j); + HCLGE_RING_INT_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1); + + return data_num_sum; +} + +static int hclge_get_regs_len(struct hnae3_handle *handle) +{ + int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int regs_num_32_bit, regs_num_64_bit, dfx_regs_len; + int regs_lines_32_bit, regs_lines_64_bit; + int ret; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return ret; + } + + ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg len failed, ret = %d.\n", ret); + return ret; + } + + cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + + return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + + tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit + + regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len; +} + +static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + int i, reg_num, separator_num, ret; + u32 *reg = data; + + *version = hdev->fw_version; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return; + } + + reg += hclge_fetch_pf_reg(hdev, reg, kinfo); - /* fetching PF common registers values from firmware */ ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg); if (ret) { dev_err(&hdev->pdev->dev, "Get 32 bit register failed, ret = %d.\n", ret); return; } + reg_num = regs_num_32_bit; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; - reg += regs_num_32_bit; ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "Get 64 bit register failed, ret = %d.\n", ret); + return; + } + reg_num = regs_num_64_bit * 2; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + ret = hclge_get_dfx_reg(hdev, reg); + if (ret) + dev_err(&hdev->pdev->dev, + "Get dfx register failed, ret = %d.\n", ret); } static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status) @@ -9538,7 +9840,7 @@ static const struct hnae3_ae_ops hclge_ops = { .set_mtu = hclge_set_mtu, .reset_queue = hclge_reset_tqp, .get_stats = hclge_get_stats, - .get_mac_pause_stats = hclge_get_mac_pause_stat, + .get_mac_stats = hclge_get_mac_stat, .update_stats = hclge_update_stats, .get_strings = hclge_get_strings, .get_sset_count = hclge_get_sset_count, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index c9b9867fc226..f6d9b57830fb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -1029,4 +1029,6 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, u16 state, u16 vlan_tag, u16 qos, u16 vlan_proto); void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time); +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index ce82b2b0f8f5..d8b828180aa8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1889,21 +1889,20 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr) static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, u32 *clearval) { - u32 val, cmdq_src_reg, rst_ing_reg; + u32 val, cmdq_stat_reg, rst_ing_reg; /* fetch the events from their corresponding regs */ - cmdq_src_reg = hclgevf_read_dev(&hdev->hw, - HCLGEVF_VECTOR0_CMDQ_SRC_REG); + cmdq_stat_reg = hclgevf_read_dev(&hdev->hw, + HCLGEVF_VECTOR0_CMDQ_STAT_REG); - if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) { + if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) { rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); set_bit(HNAE3_VF_RESET, &hdev->reset_pending); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B); - *clearval = cmdq_src_reg; + *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); hdev->rst_stats.vf_rst_cnt++; /* set up VF hardware reset status, its PF will clear * this status when PF has initialized done. @@ -1915,9 +1914,20 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, } /* check for vector0 mailbox(=CMDQ RX) event source */ - if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) { - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); - *clearval = cmdq_src_reg; + if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_stat_reg) { + /* for revision 0x21, clearing interrupt is writing bit 0 + * to the clear register, writing bit 1 means to keep the + * old value. + * for revision 0x20, the clear register is a read & write + * register, so we should just write 0 to the bit we are + * handling, and keep other bits as cmdq_stat_reg. + */ + if (hdev->pdev->revision >= 0x21) + *clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + else + *clearval = cmdq_stat_reg & + ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + return HCLGEVF_VECTOR0_EVENT_MBX; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index f0736b060884..bdde3afc286b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -87,6 +87,8 @@ /* Vector0 interrupt CMDQ event source register(RW) */ #define HCLGEVF_VECTOR0_CMDQ_SRC_REG 0x27100 +/* Vector0 interrupt CMDQ event status register(RO) */ +#define HCLGEVF_VECTOR0_CMDQ_STAT_REG 0x27104 /* CMDQ register bits for RX event(=MBX event) */ #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B 1 /* RST register bits for RESET event */ @@ -123,7 +125,7 @@ #define HCLGEVF_S_IP_BIT BIT(3) #define HCLGEVF_V_TAG_BIT BIT(4) -#define HCLGEVF_STATS_TIMER_INTERVAL (36) +#define HCLGEVF_STATS_TIMER_INTERVAL 36U enum hclgevf_evt_cause { HCLGEVF_VECTOR0_EVENT_RST, diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 4138a8480347..cca71ba7a74a 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3251,7 +3251,7 @@ static int ehea_mem_notifier(struct notifier_block *nb, switch (action) { case MEM_CANCEL_OFFLINE: pr_info("memory offlining canceled"); - /* Fall through: re-add canceled memory block */ + /* Fall through - re-add canceled memory block */ case MEM_ONLINE: pr_info("memory is going online"); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 7d42582ed48d..b14441944b4b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_H_ #define _FM10K_H_ @@ -177,14 +177,10 @@ static inline struct netdev_queue *txring_txq(const struct fm10k_ring *ring) #define MIN_Q_VECTORS 1 enum fm10k_non_q_vectors { FM10K_MBX_VECTOR, -#define NON_Q_VECTORS_VF NON_Q_VECTORS_PF - NON_Q_VECTORS_PF + NON_Q_VECTORS }; -#define NON_Q_VECTORS(hw) (((hw)->mac.type == fm10k_mac_pf) ? \ - NON_Q_VECTORS_PF : \ - NON_Q_VECTORS_VF) -#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS(hw)) +#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS) struct fm10k_q_vector { struct fm10k_intfc *interface; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index 20768ac7f17e..c45315472245 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" @@ -36,7 +36,7 @@ static int fm10k_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets) static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) { u8 num_tc = 0; - int i, err; + int i; /* verify type and determine num_tcs needed */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { @@ -57,7 +57,7 @@ static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) /* update TC hardware mapping if necessary */ if (num_tc != netdev_get_num_tc(dev)) { - err = fm10k_setup_tc(dev, num_tc); + int err = fm10k_setup_tc(dev, num_tc); if (err) return err; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index dca104121c05..1d27b2fb23af 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -160,8 +160,6 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx); q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc); - if (!q_vector->dbg_q_vector) - return; /* Generate a file for each rx ring in the q_vector */ for (i = 0; i < q_vector->tx.count; i++) { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 4895dd83dd08..c681d2d28107 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/vmalloc.h> @@ -222,7 +222,6 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, const unsigned int size) { unsigned int i; - char *p; if (!pointer) { /* memory is not zero allocated so we have to clear it */ @@ -232,7 +231,7 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, } for (i = 0; i < size; i++) { - p = (char *)pointer + stats[i].stat_offset; + char *p = (char *)pointer + stats[i].stat_offset; switch (stats[i].sizeof_stat) { case sizeof(u64): @@ -651,7 +650,6 @@ static int fm10k_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_q_vector *qv; u16 tx_itr, rx_itr; int i; @@ -677,7 +675,8 @@ static int fm10k_set_coalesce(struct net_device *dev, /* update q_vectors */ for (i = 0; i < interface->num_q_vectors; i++) { - qv = interface->q_vector[i]; + struct fm10k_q_vector *qv = interface->q_vector[i]; + qv->tx.itr = tx_itr; qv->rx.itr = rx_itr; } @@ -1115,13 +1114,12 @@ static void fm10k_get_channels(struct net_device *dev, struct ethtool_channels *ch) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; /* report maximum channels */ ch->max_combined = fm10k_max_channels(dev); /* report info for other vector */ - ch->max_other = NON_Q_VECTORS(hw); + ch->max_other = NON_Q_VECTORS; ch->other_count = ch->max_other; /* record RSS queues */ @@ -1133,14 +1131,13 @@ static int fm10k_set_channels(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); unsigned int count = ch->combined_count; - struct fm10k_hw *hw = &interface->hw; /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; /* verify other_count has not changed */ - if (ch->other_count != NON_Q_VECTORS(hw)) + if (ch->other_count != NON_Q_VECTORS) return -EINVAL; /* verify the number of channels does not exceed hardware limits */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 8de77155f2e7..afe1fafd2447 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include "fm10k_vf.h" @@ -426,7 +426,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) struct fm10k_iov_data *iov_data = interface->iov_data; struct fm10k_hw *hw = &interface->hw; size_t size; - int i, err; + int i; /* return error if iov_data is already populated */ if (iov_data) @@ -452,6 +452,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) /* loop through vf_info structures initializing each entry */ for (i = 0; i < num_vfs; i++) { struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; + int err; /* Record VF VSI value */ vf_info->vsi = i + 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9ffff7886085..e0a2be534b20 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -17,7 +17,7 @@ const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright(c) 2013 - 2018 Intel Corporation."; + "Copyright(c) 2013 - 2019 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <[email protected]>"); MODULE_DESCRIPTION(DRV_SUMMARY); @@ -315,7 +315,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, /* prefetch first cache line of first page */ prefetch(page_addr); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); #endif /* allocate a skb to store the frags */ @@ -1824,7 +1824,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) v_budget = min_t(u16, v_budget, num_online_cpus()); /* account for vectors not related to queues */ - v_budget += NON_Q_VECTORS(hw); + v_budget += NON_Q_VECTORS; /* At the same time, hardware can only support a maximum of * hw.mac->max_msix_vectors vectors. With features @@ -1856,7 +1856,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) } /* record the number of queues available for q_vectors */ - interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw); + interface->num_q_vectors = v_budget - NON_Q_VECTORS; return 0; } @@ -1870,7 +1870,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) { struct net_device *dev = interface->netdev; - int pc, offset, rss_i, i, q_idx; + int pc, offset, rss_i, i; u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1; u8 num_pcs = netdev_get_num_tc(dev); @@ -1880,7 +1880,8 @@ static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) rss_i = interface->ring_feature[RING_F_RSS].indices; for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) { - q_idx = pc; + int q_idx = pc; + for (i = 0; i < rss_i; i++) { interface->tx_ring[offset + i]->reg_idx = q_idx; interface->tx_ring[offset + i]->qos_pc = pc; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 21021fe4f1c3..75e51f91036c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_common.h" @@ -297,13 +297,14 @@ static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len) { struct fm10k_mbx_fifo *fifo = &mbx->rx; u16 total_len = 0, msg_len; - u32 *msg; /* length should include previous amounts pushed */ len += mbx->pushed; /* offset in message is based off of current message size */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len); msg_len = FM10K_TLV_DWORD_LEN(*msg); total_len += msg_len; @@ -1920,7 +1921,6 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* reduce length by 1 to convert to a mask */ u16 mbmem_len = mbx->mbmem_len - 1; u16 tail_len, len = 0; - u32 *msg; /* push head behind tail */ if (mbx->tail < head) @@ -1930,6 +1930,8 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* determine msg aligned offset for end of buffer */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len); tail_len = len; len += FM10K_TLV_DWORD_LEN(*msg); @@ -2132,7 +2134,8 @@ fifo_err: * DWORDs, not bytes. Any invalid values will cause the mailbox to return * error. **/ -s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, +s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw, + struct fm10k_mbx_info *mbx, const struct fm10k_msg_data *msg_data) { mbx->mbx_reg = FM10K_GMBX; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 538a8467f434..d3e85480f46d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include <linux/vmalloc.h> @@ -54,7 +54,7 @@ err: **/ static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_tx_queues; i++) { err = fm10k_setup_tx_resources(interface->tx_ring[i]); @@ -121,7 +121,7 @@ err: **/ static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_rx_queues; i++) { err = fm10k_setup_rx_resources(interface->rx_ring[i]); @@ -169,7 +169,6 @@ void fm10k_unmap_and_free_tx_resource(struct fm10k_ring *ring, **/ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) { - struct fm10k_tx_buffer *tx_buffer; unsigned long size; u16 i; @@ -179,7 +178,8 @@ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) /* Free all the Tx ring sk_buffs */ for (i = 0; i < tx_ring->count; i++) { - tx_buffer = &tx_ring->tx_buffer[i]; + struct fm10k_tx_buffer *tx_buffer = &tx_ring->tx_buffer[i]; + fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer); } @@ -871,7 +871,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -891,7 +891,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -1444,11 +1444,11 @@ static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type, static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, struct fm10k_l2_accel *l2_accel) { - struct fm10k_ring *ring; int i; for (i = 0; i < interface->num_rx_queues; i++) { - ring = interface->rx_ring[i]; + struct fm10k_ring *ring = interface->rx_ring[i]; + rcu_assign_pointer(ring->l2_accel, l2_accel); } @@ -1463,7 +1463,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, struct fm10k_l2_accel *old_l2_accel = NULL; struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; - int size = 0, i; + int size, i; u16 vid, glort; /* The hardware supported by fm10k only filters on the destination MAC diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 7bfc8a5b6f55..bb236fa44048 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/module.h> #include <linux/interrupt.h> @@ -344,7 +344,6 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; u32 __iomem *hw_addr; u32 value; - int err; /* do nothing if netdev is still present or hw_addr is set */ if (netif_device_present(netdev) || interface->hw.hw_addr) @@ -362,6 +361,8 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) hw_addr = READ_ONCE(interface->uc_addr); value = readl(hw_addr); if (~value) { + int err; + /* Make sure the reset was initiated because we detached, * otherwise we might race with a different reset flow. */ @@ -697,8 +698,6 @@ static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) */ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) { - int i; - /* If we're down or resetting, just bail */ if (test_bit(__FM10K_DOWN, interface->state) || test_bit(__FM10K_RESETTING, interface->state)) @@ -710,6 +709,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) interface->next_tx_hang_check = jiffies + (2 * HZ); if (netif_carrier_ok(interface->netdev)) { + int i; + /* Force detection of hung controller */ for (i = 0; i < interface->num_tx_queues; i++) set_check_for_tx_hang(interface->tx_ring[i]); @@ -897,7 +898,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - txint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + txint = ring->q_vector->v_idx + NON_Q_VECTORS; txint |= FM10K_INT_MAP_TIMER0; } @@ -1036,7 +1037,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + rxint = ring->q_vector->v_idx + NON_Q_VECTORS; rxint |= FM10K_INT_MAP_TIMER1; } @@ -1719,10 +1720,9 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface) void fm10k_qv_free_irq(struct fm10k_intfc *interface) { int vector = interface->num_q_vectors; - struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - entry = &interface->msix_entries[NON_Q_VECTORS(hw) + vector]; + entry = &interface->msix_entries[NON_Q_VECTORS + vector]; while (vector) { struct fm10k_q_vector *q_vector; @@ -1759,7 +1759,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) unsigned int ri = 0, ti = 0; int vector, err; - entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; + entry = &interface->msix_entries[NON_Q_VECTORS]; for (vector = 0; vector < interface->num_q_vectors; vector++) { struct fm10k_q_vector *q_vector = interface->q_vector[vector]; @@ -2339,7 +2339,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* Restart the MAC/VLAN request queue in-case of outstanding events */ fm10k_macvlan_schedule(interface); - return err; + return 0; } /** diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index cb4d02629b86..be07bfdb0bb4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_pf.h" #include "fm10k_vf.h" @@ -1152,7 +1152,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw, * assumption is that in this case it is acceptable to just directly * hand off the message from the VF to the underlying shared code. **/ -s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, +s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; @@ -1352,7 +1352,6 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - u32 *result; s32 err = 0; u32 msg[2]; u8 mode = 0; @@ -1362,7 +1361,7 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, return FM10K_ERR_PARAM; if (!!results[FM10K_LPORT_STATE_MSG_XCAST_MODE]) { - result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; + u32 *result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; /* XCAST mode update requested */ err = fm10k_tlv_attr_get_u8(result, &mode); @@ -1566,7 +1565,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type, /* read remaining fields */ fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI); fault->address <<= 32; - fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); + fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO); /* clear valid bit to allow for next error */ @@ -1642,7 +1641,7 @@ const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[] = { * switch API. **/ s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, mask; u32 dglort_map; @@ -1685,7 +1684,7 @@ const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = { * This handler configures the default VLAN for the PF **/ static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, pvid; u32 pvid_update; @@ -1746,7 +1745,7 @@ const struct fm10k_tlv_attr fm10k_err_msg_attr[] = { * messages that the PF has sent. **/ s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { struct fm10k_swapi_error err_msg; s32 err; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 2a7a40bf2b1c..21eff0895a7a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_tlv.h" @@ -472,7 +472,7 @@ static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, const struct fm10k_tlv_attr *tlv_attr) { u32 i, attr_id, offset = 0; - s32 err = 0; + s32 err; u16 len; /* verify pointers are not NULL */ @@ -587,8 +587,9 @@ s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg, * a minimum it just indicates that the message requested was * unimplemented. **/ -s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) +s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw, + u32 __always_unused **results, + struct fm10k_mbx_info __always_unused *mbx) { return FM10K_NOT_IMPLEMENTED; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 9fb9fca375e3..15ac1c7885bc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_TYPE_H_ #define _FM10K_TYPE_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index a8519c1f0406..dc8ccd378ec9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_vf.h" @@ -198,7 +198,7 @@ static s32 fm10k_update_vlan_vf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set) * This function should determine the MAC address for the VF **/ s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u8 perm_addr[ETH_ALEN]; u16 vid; @@ -267,8 +267,10 @@ static s32 fm10k_read_mac_addr_vf(struct fm10k_hw *hw) * This function is used to add or remove unicast MAC addresses for * the VF. **/ -static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, - const u8 *mac, u16 vid, bool add, u8 flags) +static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + const u8 *mac, u16 vid, bool add, + u8 __always_unused flags) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[7]; @@ -309,7 +311,8 @@ static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, * This function is used to add or remove multicast MAC addresses for * the VF. **/ -static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, u16 glort, +static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, const u8 *mac, u16 vid, bool add) { struct fm10k_mbx_info *mbx = &hw->mbx; @@ -373,7 +376,7 @@ const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[] = { * are ready to bring up the interface. **/ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ? FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO; @@ -392,8 +395,9 @@ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, * enabled we can add filters, if it is disabled all filters for this * logical port are flushed. **/ -static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, - u16 count, bool enable) +static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + u16 __always_unused count, bool enable) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[2]; @@ -420,7 +424,8 @@ static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, * so that it can enable either multicast, multicast promiscuous, or * promiscuous mode of operation. **/ -static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode) +static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, + u16 __always_unused glort, u8 mode) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[3]; @@ -475,7 +480,7 @@ static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw, * that information to then populate a DGLORTMAP/DEC entry and the queues * to which it has been assigned. **/ -static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw *hw, +static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw, struct fm10k_dglort_cfg *dglort) { /* verify the dglort pointer */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 84bd06901014..3e535d3263b3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1021,6 +1021,7 @@ i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type) return NULL; } void i40e_update_stats(struct i40e_vsi *vsi); +void i40e_update_veb_stats(struct i40e_veb *veb); void i40e_update_eth_stats(struct i40e_vsi *vsi); struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi); int i40e_fetch_switch_configuration(struct i40e_pf *pf, diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 55d20acfcf70..41232898d8ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1732,29 +1732,15 @@ static const struct file_operations i40e_dbg_netdev_ops_fops = { **/ void i40e_dbg_pf_init(struct i40e_pf *pf) { - struct dentry *pfile; const char *name = pci_name(pf->pdev); - const struct device *dev = &pf->pdev->dev; pf->i40e_dbg_pf = debugfs_create_dir(name, i40e_dbg_root); - if (!pf->i40e_dbg_pf) - return; - - pfile = debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_command_fops); - if (!pfile) - goto create_failed; - pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_netdev_ops_fops); - if (!pfile) - goto create_failed; + debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_command_fops); - return; - -create_failed: - dev_info(dev, "debugfs dir/file for %s failed\n", name); - debugfs_remove_recursive(pf->i40e_dbg_pf); + debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_netdev_ops_fops); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 527eb52c5401..01e4615b1b4b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -711,6 +711,35 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, } /** + * i40e_get_settings_link_up_fec - Get the FEC mode encoding from mask + * @req_fec_info: mask request FEC info + * @ks: ethtool ksettings to fill in + **/ +static void i40e_get_settings_link_up_fec(u8 req_fec_info, + struct ethtool_link_ksettings *ks) +{ + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + + if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } else { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_NONE); + if (I40E_AQ_SET_FEC_AUTO & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } + } +} + +/** * i40e_get_settings_link_up - Get the Link settings for when link is up * @hw: hw structure * @ks: ethtool ksettings to fill in @@ -769,13 +798,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseSR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -892,9 +915,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, supported, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); ethtool_link_ksettings_add_link_mode(ks, supported, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, supported, @@ -908,10 +928,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, advertising, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -929,13 +946,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + break; case I40E_PHY_TYPE_25GBASE_AOC: case I40E_PHY_TYPE_25GBASE_ACC: @@ -945,13 +957,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -2250,7 +2257,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - struct i40e_veb *veb = pf->veb[pf->lan_veb]; + struct i40e_veb *veb = NULL; unsigned int i; bool veb_stats; u64 *p = data; @@ -2273,8 +2280,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, goto check_data_pointer; veb_stats = ((pf->lan_veb != I40E_NO_VEB) && + (pf->lan_veb < I40E_MAX_VEB) && (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)); + if (veb_stats) { + veb = pf->veb[pf->lan_veb]; + i40e_update_veb_stats(veb); + } + /* If veb stats aren't enabled, pass NULL instead of the veb so that * we initialize stats to zero and update the data pointer * intelligently @@ -2329,7 +2342,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) } if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) - return; + goto check_data_pointer; i40e_add_stat_strings(&data, i40e_gstrings_veb_stats); @@ -2341,6 +2354,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i); +check_data_pointer: WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN, "stat strings count mismatch!"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 44da407e0bf9..6d456e579314 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -677,7 +677,7 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi) * i40e_update_veb_stats - Update Switch component statistics * @veb: the VEB being updated **/ -static void i40e_update_veb_stats(struct i40e_veb *veb) +void i40e_update_veb_stats(struct i40e_veb *veb) { struct i40e_pf *pf = veb->pf; struct i40e_hw *hw = &pf->hw; @@ -2530,6 +2530,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi_name, i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); + } else { + dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", + vsi->netdev->name, + cur_multipromisc ? "entering" : "leaving"); } } @@ -8486,6 +8490,11 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); + dev_info(&pf->pdev->dev, + pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? + "FW LLDP is disabled\n" : + "FW LLDP is enabled\n"); + } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 02b09a8ad54c..4601f9e4e998 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -55,7 +55,12 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - if (vf->link_forced) { + + /* Always report link is down if the VF queues aren't enabled */ + if (!vf->queues_enabled) { + pfe.event_data.link_event.link_status = false; + pfe.event_data.link_event.link_speed = 0; + } else if (vf->link_forced) { pfe.event_data.link_event.link_status = vf->link_up; pfe.event_data.link_event.link_speed = (vf->link_up ? VIRTCHNL_LINK_SPEED_40GB : 0); @@ -65,6 +70,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed); } + i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, sizeof(pfe), NULL); } @@ -2037,30 +2043,33 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) alluni = true; aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti, alluni); - if (!aq_ret) { - if (allmulti) { + if (aq_ret) + goto err_out; + + if (allmulti) { + if (!test_and_set_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set multicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset multicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } - if (alluni) { + } else if (test_and_clear_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset multicast promiscuous mode\n", + vf->vf_id); + + if (alluni) { + if (!test_and_set_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set unicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset unicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } - } + } else if (test_and_clear_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset unicast promiscuous mode\n", + vf->vf_id); + err_out: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, @@ -2153,7 +2162,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) * VF does not know about these additional VSIs and all * it cares is about its own queues. PF configures these queues * to its appropriate VSIs based on TC mapping - **/ + */ if (vf->adq_enabled) { if (idx >= ARRAY_SIZE(vf->ch)) { aq_ret = I40E_ERR_NO_AVAILABLE_VSI; @@ -2364,6 +2373,8 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) } } + vf->queues_enabled = true; + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2385,6 +2396,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; + /* Immediately mark queues as disabled */ + vf->queues_enabled = false; + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index f65cc0c16550..7164b9bb294f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -99,6 +99,7 @@ struct i40e_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ bool link_forced; bool link_up; /* only valid if VF link is forced */ + bool queues_enabled; /* true if the VF queues are enabled */ bool spoofchk; u16 num_mac; u16 num_vlan; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 50dfb02fa34c..171cdc552961 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -190,22 +190,12 @@ static const struct file_operations ixgbe_dbg_netdev_ops_fops = { void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) { const char *name = pci_name(adapter->pdev); - struct dentry *pfile; + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); - if (adapter->ixgbe_dbg_adapter) { - pfile = debugfs_create_file("reg_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_reg_ops_fops); - if (!pfile) - e_dev_err("debugfs reg_ops for %s failed\n", name); - pfile = debugfs_create_file("netdev_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_netdev_ops_fops); - if (!pfile) - e_dev_err("debugfs netdev_ops for %s failed\n", name); - } else { - e_dev_err("debugfs entry for %s failed\n", name); - } + debugfs_create_file("reg_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_reg_ops_fops); + debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_netdev_ops_fops); } /** @@ -224,8 +214,6 @@ void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) void ixgbe_dbg_init(void) { ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); - if (ixgbe_dbg_root == NULL) - pr_err("init of debugfs failed\n"); } /** diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index f660cc2b8258..0b9e851f3da4 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -319,20 +319,33 @@ static int orion_mdio_probe(struct platform_device *pdev) init_waitqueue_head(&dev->smi_busy_wait); - for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { - dev->clk[i] = of_clk_get(pdev->dev.of_node, i); - if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) { + if (pdev->dev.of_node) { + for (i = 0; i < ARRAY_SIZE(dev->clk); i++) { + dev->clk[i] = of_clk_get(pdev->dev.of_node, i); + if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_clk; + } + if (IS_ERR(dev->clk[i])) + break; + clk_prepare_enable(dev->clk[i]); + } + + if (!IS_ERR(of_clk_get(pdev->dev.of_node, + ARRAY_SIZE(dev->clk)))) + dev_warn(&pdev->dev, + "unsupported number of clocks, limiting to the first " + __stringify(ARRAY_SIZE(dev->clk)) "\n"); + } else { + dev->clk[0] = clk_get(&pdev->dev, NULL); + if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto out_clk; } - if (IS_ERR(dev->clk[i])) - break; - clk_prepare_enable(dev->clk[i]); + if (!IS_ERR(dev->clk[0])) + clk_prepare_enable(dev->clk[0]); } - if (!IS_ERR(of_clk_get(pdev->dev.of_node, ARRAY_SIZE(dev->clk)))) - dev_warn(&pdev->dev, "unsupported number of clocks, limiting to the first " - __stringify(ARRAY_SIZE(dev->clk)) "\n"); dev->err_interrupt = platform_get_irq(pdev, 0); if (dev->err_interrupt > 0 && diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c index 274fb07362cb..4a3baa7e0142 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -452,8 +452,6 @@ static int mvpp2_dbgfs_flow_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); port_entry = &port->priv->dbgfs_entries->port_flow_entries[port->id]; @@ -480,8 +478,6 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent, sprintf(flow_entry_name, "%02d", flow); flow_entry_dir = debugfs_create_dir(flow_entry_name, parent); - if (!flow_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->flow_entries[flow]; @@ -514,8 +510,6 @@ static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; flow_dir = debugfs_create_dir("flows", parent); - if (!flow_dir) - return -ENOMEM; for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) { ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i); @@ -539,8 +533,6 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent, sprintf(prs_entry_name, "%03d", tid); prs_entry_dir = debugfs_create_dir(prs_entry_name, parent); - if (!prs_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->prs_entries[tid]; @@ -578,8 +570,6 @@ static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; prs_dir = debugfs_create_dir("parser", parent); - if (!prs_dir) - return -ENOMEM; for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) { ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i); @@ -688,8 +678,6 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); debugfs_create_file("parser_entries", 0444, port_dir, port, &mvpp2_dbgfs_port_parser_fops); @@ -716,15 +704,10 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) int ret, i; mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); - if (!mvpp2_root) { + if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL); - if (IS_ERR(mvpp2_root)) - return; - } mvpp2_dir = debugfs_create_dir(name, mvpp2_root); - if (IS_ERR(mvpp2_dir)) - return; priv->dbgfs_dir = mvpp2_dir; priv->dbgfs_entries = kzalloc(sizeof(*priv->dbgfs_entries), GFP_KERNEL); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e9d8ffe897e9..74fd9e171865 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -811,6 +811,26 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) return 0; } +static void mvpp2_set_hw_csum(struct mvpp2_port *port, + enum mvpp2_bm_pool_log_num new_long_pool) +{ + const netdev_features_t csums = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + + /* Update L4 checksum when jumbo enable/disable on port. + * Only port 0 supports hardware checksum offload due to + * the Tx FIFO size limitation. + * Also, don't set NETIF_F_HW_CSUM because L3_offset in TX descriptor + * has 7 bits, so the maximum L3 offset is 128. + */ + if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) { + port->dev->features &= ~csums; + port->dev->hw_features &= ~csums; + } else { + port->dev->features |= csums; + port->dev->hw_features |= csums; + } +} + static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); @@ -843,15 +863,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) /* Add port to new short & long pool */ mvpp2_swf_bm_pool_init(port); - /* Update L4 checksum when jumbo enable/disable on port */ - if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) { - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - dev->hw_features &= ~(NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM); - } else { - dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - } + mvpp2_set_hw_csum(port, new_long_pool); } dev->mtu = mtu; @@ -3701,6 +3713,7 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) static int mvpp2_change_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); + bool running = netif_running(dev); int err; if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) { @@ -3709,40 +3722,24 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } - if (!netif_running(dev)) { - err = mvpp2_bm_update_mtu(dev, mtu); - if (!err) { - port->pkt_size = MVPP2_RX_PKT_SIZE(mtu); - return 0; - } - - /* Reconfigure BM to the original MTU */ - err = mvpp2_bm_update_mtu(dev, dev->mtu); - if (err) - goto log_error; - } - - mvpp2_stop_dev(port); + if (running) + mvpp2_stop_dev(port); err = mvpp2_bm_update_mtu(dev, mtu); - if (!err) { + if (err) { + netdev_err(dev, "failed to change MTU\n"); + /* Reconfigure BM to the original MTU */ + mvpp2_bm_update_mtu(dev, dev->mtu); + } else { port->pkt_size = MVPP2_RX_PKT_SIZE(mtu); - goto out_start; } - /* Reconfigure BM to the original MTU */ - err = mvpp2_bm_update_mtu(dev, dev->mtu); - if (err) - goto log_error; - -out_start: - mvpp2_start_dev(port); - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); + if (running) { + mvpp2_start_dev(port); + mvpp2_egress_enable(port); + mvpp2_ingress_enable(port); + } - return 0; -log_error: - netdev_err(dev, "failed to change MTU\n"); return err; } @@ -4740,9 +4737,9 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, else ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; - ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; - ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | - MVPP22_XLG_CTRL4_EN_IDLE_CHECK; + ctrl4 &= ~(MVPP22_XLG_CTRL4_MACMODSELECT_GMAC | + MVPP22_XLG_CTRL4_EN_IDLE_CHECK); + ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC; if (old_ctrl0 != ctrl0) writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG); @@ -5207,10 +5204,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->features |= NETIF_F_NTUPLE; } - if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) { - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } + mvpp2_set_hw_csum(port, port->pool_long->id); dev->vlan_features |= features; dev->gso_max_segs = MVPP2_MAX_TSO_SEGS; @@ -5756,9 +5750,6 @@ static int mvpp2_remove(struct platform_device *pdev) mvpp2_dbgfs_cleanup(priv); - flush_workqueue(priv->stats_queue); - destroy_workqueue(priv->stats_queue); - fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) { mutex_destroy(&priv->port_list[i]->gather_stats_lock); @@ -5767,6 +5758,8 @@ static int mvpp2_remove(struct platform_device *pdev) i++; } + destroy_workqueue(priv->stats_queue); + for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i]; diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 06dffee81e02..0a2ec387a482 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3731,7 +3731,6 @@ static int skge_device_event(struct notifier_block *unused, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct skge_port *skge; - struct dentry *d; if (dev->netdev_ops->ndo_open != &skge_up || !skge_debug) goto done; @@ -3739,33 +3738,20 @@ static int skge_device_event(struct notifier_block *unused, skge = netdev_priv(dev); switch (event) { case NETDEV_CHANGENAME: - if (skge->debugfs) { - d = debugfs_rename(skge_debug, skge->debugfs, - skge_debug, dev->name); - if (d) - skge->debugfs = d; - else { - netdev_info(dev, "rename failed\n"); - debugfs_remove(skge->debugfs); - } - } + if (skge->debugfs) + skge->debugfs = debugfs_rename(skge_debug, + skge->debugfs, + skge_debug, dev->name); break; case NETDEV_GOING_DOWN: - if (skge->debugfs) { - debugfs_remove(skge->debugfs); - skge->debugfs = NULL; - } + debugfs_remove(skge->debugfs); + skge->debugfs = NULL; break; case NETDEV_UP: - d = debugfs_create_file(dev->name, 0444, - skge_debug, dev, - &skge_debug_fops); - if (!d || IS_ERR(d)) - netdev_info(dev, "debugfs create failed\n"); - else - skge->debugfs = d; + skge->debugfs = debugfs_create_file(dev->name, 0444, skge_debug, + dev, &skge_debug_fops); break; } @@ -3780,15 +3766,8 @@ static struct notifier_block skge_notifier = { static __init void skge_debug_init(void) { - struct dentry *ent; - - ent = debugfs_create_dir("skge", NULL); - if (!ent || IS_ERR(ent)) { - pr_info("debugfs create directory failed\n"); - return; - } + skge_debug = debugfs_create_dir("skge", NULL); - skge_debug = ent; register_netdevice_notifier(&skge_notifier); } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 762fe0821923..c2e00bb587cd 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4924,6 +4924,13 @@ static const struct dmi_system_id msi_blacklist[] = { DMI_MATCH(DMI_PRODUCT_NAME, "P5W DH Deluxe"), }, }, + { + .ident = "ASUS P6T", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P6T"), + }, + }, {} }; diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 263cd0909fe0..1f7fff81f24d 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -9,7 +9,6 @@ if NET_VENDOR_MEDIATEK config NET_MEDIATEK_SOC tristate "MediaTek SoC Gigabit Ethernet support" - depends on NET_VENDOR_MEDIATEK select PHYLIB ---help--- This driver supports the gigabit ethernet MACs in the diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index 88316c743820..eaf08f7ad128 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -99,8 +99,7 @@ static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev, readl(cr_space + offset); err = devlink_region_snapshot_create(crdump->region_crspace, - cr_res_size, crspace_data, - id, &kvfree); + crspace_data, id, &kvfree); if (err) { kvfree(crspace_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", @@ -139,9 +138,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev, readl(health_buf_start + offset); err = devlink_region_snapshot_create(crdump->region_fw_health, - HEALTH_BUFFER_SIZE, - health_data, - id, &kvfree); + health_data, id, &kvfree); if (err) { kvfree(health_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..973f90888b1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1368,49 +1368,19 @@ static void clean_debug_files(struct mlx5_core_dev *dev) debugfs_remove_recursive(dbg->dbg_root); } -static int create_debugfs_files(struct mlx5_core_dev *dev) +static void create_debugfs_files(struct mlx5_core_dev *dev) { struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - int err = -ENOMEM; - - if (!mlx5_debugfs_root) - return 0; dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root); - if (!dbg->dbg_root) - return err; - - dbg->dbg_in = debugfs_create_file("in", 0400, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_in) - goto err_dbg; - dbg->dbg_out = debugfs_create_file("out", 0200, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_out) - goto err_dbg; - - dbg->dbg_outlen = debugfs_create_file("out_len", 0600, dbg->dbg_root, - dev, &olfops); - if (!dbg->dbg_outlen) - goto err_dbg; - - dbg->dbg_status = debugfs_create_u8("status", 0600, dbg->dbg_root, - &dbg->status); - if (!dbg->dbg_status) - goto err_dbg; - - dbg->dbg_run = debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); - if (!dbg->dbg_run) - goto err_dbg; + debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out_len", 0600, dbg->dbg_root, dev, &olfops); + debugfs_create_u8("status", 0600, dbg->dbg_root, &dbg->status); + debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); mlx5_cmdif_debugfs_init(dev); - - return 0; - -err_dbg: - clean_debug_files(dev); - return err; } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -2007,17 +1977,10 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_cache; } - err = create_debugfs_files(dev); - if (err) { - err = -ENOMEM; - goto err_wq; - } + create_debugfs_files(dev); return 0; -err_wq: - destroy_workqueue(cmd->wq); - err_cache: destroy_msg_cache(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index a11e22d0b0cc..04854e5fbcd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -92,8 +92,6 @@ EXPORT_SYMBOL(mlx5_debugfs_root); void mlx5_register_debugfs(void) { mlx5_debugfs_root = debugfs_create_dir("mlx5", NULL); - if (IS_ERR_OR_NULL(mlx5_debugfs_root)) - mlx5_debugfs_root = NULL; } void mlx5_unregister_debugfs(void) @@ -101,45 +99,25 @@ void mlx5_unregister_debugfs(void) debugfs_remove(mlx5_debugfs_root); } -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - atomic_set(&dev->num_qps, 0); dev->priv.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg_root); - if (!dev->priv.qp_debugfs) - return -ENOMEM; - - return 0; } void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.qp_debugfs); } -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg_root); - if (!dev->priv.eq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.eq_debugfs); } @@ -183,85 +161,41 @@ static const struct file_operations stats_fops = { .write = average_write, }; -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) { struct mlx5_cmd_stats *stats; struct dentry **cmd; const char *namep; - int err; int i; - if (!mlx5_debugfs_root) - return 0; - cmd = &dev->priv.cmdif_debugfs; *cmd = debugfs_create_dir("commands", dev->priv.dbg_root); - if (!*cmd) - return -ENOMEM; for (i = 0; i < ARRAY_SIZE(dev->cmd.stats); i++) { stats = &dev->cmd.stats[i]; namep = mlx5_command_str(i); if (strcmp(namep, "unknown command opcode")) { stats->root = debugfs_create_dir(namep, *cmd); - if (!stats->root) { - mlx5_core_warn(dev, "failed adding command %d\n", - i); - err = -ENOMEM; - goto out; - } - - stats->avg = debugfs_create_file("average", 0400, - stats->root, stats, - &stats_fops); - if (!stats->avg) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } - - stats->count = debugfs_create_u64("n", 0400, - stats->root, - &stats->n); - if (!stats->count) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } + + debugfs_create_file("average", 0400, stats->root, stats, + &stats_fops); + debugfs_create_u64("n", 0400, stats->root, &stats->n); } } - - return 0; -out: - debugfs_remove_recursive(dev->priv.cmdif_debugfs); - return err; } void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cmdif_debugfs); } -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg_root); - if (!dev->priv.cq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cq_debugfs); } @@ -484,7 +418,6 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, { struct mlx5_rsc_debug *d; char resn[32]; - int err; int i; d = kzalloc(struct_size(d, fields, nfile), GFP_KERNEL); @@ -496,30 +429,15 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, d->type = type; sprintf(resn, "0x%x", rsn); d->root = debugfs_create_dir(resn, root); - if (!d->root) { - err = -ENOMEM; - goto out_free; - } for (i = 0; i < nfile; i++) { d->fields[i].i = i; - d->fields[i].dent = debugfs_create_file(field[i], 0400, - d->root, &d->fields[i], - &fops); - if (!d->fields[i].dent) { - err = -ENOMEM; - goto out_rem; - } + debugfs_create_file(field[i], 0400, d->root, &d->fields[i], + &fops); } *dbg = d; return 0; -out_rem: - debugfs_remove_recursive(d->root); - -out_free: - kfree(d); - return err; } static void rem_res_tree(struct mlx5_rsc_debug *d) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 5bb6a26ea267..50862275544e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -213,7 +213,7 @@ void mlx5_unregister_device(struct mlx5_core_dev *dev) struct mlx5_interface *intf; mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) + list_for_each_entry_reverse(intf, &intf_list, list) mlx5_remove_device(intf, priv); list_del(&priv->dev_list); mutex_unlock(&mlx5_intf_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 79d93d6c7d7a..0807992090b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -159,7 +159,7 @@ do { \ enum mlx5e_rq_group { MLX5E_RQ_GROUP_REGULAR, MLX5E_RQ_GROUP_XSK, - MLX5E_NUM_RQ_GROUPS /* Keep last. */ +#define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g) }; static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) @@ -182,14 +182,6 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS); } -/* Use this function to get max num channels after netdev was created */ -static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev) -{ - return min_t(unsigned int, - netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS, - netdev->num_tx_queues); -} - struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; @@ -359,6 +351,7 @@ enum { MLX5E_SQ_STATE_IPSEC, MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, + MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, }; struct mlx5e_sq_wqe_info { @@ -483,8 +476,6 @@ struct mlx5e_xdp_mpwqe { struct mlx5e_tx_wqe *wqe; u8 ds_count; u8 pkt_count; - u8 max_ds_count; - u8 complete; u8 inline_on; }; @@ -830,6 +821,7 @@ struct mlx5e_priv { struct net_device *netdev; struct mlx5e_stats stats; struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS]; + u16 max_nch; u8 max_opened_tc; struct hwtstamp_config tstamp; u16 q_counter; @@ -871,6 +863,7 @@ struct mlx5e_profile { mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; } rx_handlers; int max_tc; + u8 rq_groups; }; void mlx5e_build_ptys2ethtool_map(void); @@ -1134,7 +1127,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, u16 num_channels); -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 4518ce19112e..ca2161b42c7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -16,7 +16,8 @@ struct mlx5e_tc_table { struct rhashtable ht; - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; + struct mutex hairpin_tbl_lock; /* protects hairpin_tbl */ DECLARE_HASHTABLE(hairpin_tbl, 8); struct notifier_block netdevice_nb; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index bd882b5ee9a7..3a615d663d84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -66,9 +66,10 @@ static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params, *group = qid / nch; } -static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid) +static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile, + struct mlx5e_params *params, u64 qid) { - return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS; + return qid < params->num_channels * profile->rq_groups; } /* Parameter calculations */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index d5e5afbdca6d..f777994f3005 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -78,9 +78,10 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { }; static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, - const u32 **arr, u32 *size) + const u32 **arr, u32 *size, + bool force_legacy) { - bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : ARRAY_SIZE(mlx5e_link_speed); @@ -152,7 +153,8 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, sizeof(out), MLX5_REG_PTYS, 0, 1); } -u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy) { unsigned long temp = eth_proto_oper; const u32 *table; @@ -160,7 +162,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) u32 max_size; int i; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy); i = find_first_bit(&temp, max_size); if (i < max_size) speed = table[i]; @@ -170,6 +172,7 @@ u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { struct mlx5e_port_eth_proto eproto; + bool force_legacy = false; bool ext; int err; @@ -177,8 +180,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) goto out; - - *speed = mlx5e_port_ptys2speed(mdev, eproto.oper); + if (ext && !eproto.admin) { + force_legacy = true; + err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto); + if (err) + goto out; + } + *speed = mlx5e_port_ptys2speed(mdev, eproto.oper, force_legacy); if (!(*speed)) err = -EINVAL; @@ -201,7 +209,7 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) if (err) return err; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, false); for (i = 0; i < max_size; ++i) if (eproto.cap & MLX5E_PROT_MASK(i)) max_speed = max(max_speed, table[i]); @@ -210,14 +218,15 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) return 0; } -u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed) +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy) { u32 link_modes = 0; const u32 *table; u32 max_size; int i; - mlx5e_port_get_speed_arr(mdev, &table, &max_size); + mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy); for (i = 0; i < max_size; ++i) { if (table[i] == speed) link_modes |= MLX5E_PROT_MASK(i); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index 70f536ec51c4..4a7f4497692b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -48,10 +48,12 @@ void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, u32 proto_admin, bool ext); -u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper); +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, + bool force_legacy); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); -u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed); +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, + bool force_legacy); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h index e78e92753d73..ed7a3881d2c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -4,7 +4,6 @@ #ifndef __MLX5E_EN_REPORTER_H #define __MLX5E_EN_REPORTER_H -#include <linux/mlx5/driver.h> #include "en.h" int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index f3d98748b211..6e54fefea410 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2019 Mellanox Technologies. */ -#include <net/devlink.h> #include "reporter.h" #include "lib/eq.h" @@ -117,7 +116,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter, char *err_str, struct mlx5e_tx_err_ctx *err_ctx) { - if (IS_ERR_OR_NULL(tx_reporter)) { + if (!tx_reporter) { netdev_err(err_ctx->sq->channel->netdev, err_str); return err_ctx->recover(err_ctx->sq); } @@ -289,23 +288,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *mdev = priv->mdev; struct devlink *devlink = priv_to_devlink(mdev); - priv->tx_reporter = + reporter = devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, MLX5_REPORTER_TX_GRACEFUL_PERIOD, true, priv); - if (IS_ERR(priv->tx_reporter)) + if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n", - PTR_ERR(priv->tx_reporter)); - return IS_ERR_OR_NULL(priv->tx_reporter); + PTR_ERR(reporter)); + return PTR_ERR(reporter); + } + priv->tx_reporter = reporter; + return 0; } void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->tx_reporter)) + if (!priv->tx_reporter) return; devlink_health_reporter_destroy(priv->tx_reporter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index ddfe19adb3d9..87be96747902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -6,7 +6,7 @@ #include "en.h" -#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS +#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1) #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) @@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map, mlx5_write64((__be32 *)ctrl, uar_map); } -static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe) +static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg) { - return !!wqe->ctrl.tisn; + return cseg && !!cseg->tisn; +} + +static inline u8 +mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg, + struct sk_buff *skb) +{ + u8 mode; + + if (mlx5e_transport_inline_tx_wqe(cseg)) + return MLX5_INLINE_MODE_TCP_UDP; + + mode = sq->min_inline_mode; + + if (skb_vlan_tag_present(skb) && + test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state)) + mode = max_t(u8, MLX5_INLINE_MODE_L2, mode); + + return mode; } static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index b0b982cf69bb..1ed5c33e022f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -179,33 +179,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; struct mlx5_wq_cyc *wq = &sq->wq; - u8 wqebbs; - u16 pi; - - mlx5e_xdpsq_fetch_wqe(sq, &session->wqe); - - prefetchw(session->wqe->data); - session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; - session->pkt_count = 0; - session->complete = 0; + u16 pi, contig_wqebbs; pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); -/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS - * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. - * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a - * full-session WQE be cache-aligned. - */ -#if L1_CACHE_BYTES < 128 -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) -#else -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) -#endif + if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) + mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs); - wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi), - MLX5E_XDP_MPW_MAX_WQEBBS); + session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi); - session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs; + prefetchw(session->wqe->data); + session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->pkt_count = 0; mlx5e_xdp_update_inline_state(sq); @@ -244,7 +230,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) { if (unlikely(!sq->mpwqe.wqe)) { if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { + MLX5E_XDPSQ_STOP_ROOM))) { /* SQ is full, ring doorbell */ mlx5e_xmit_xdp_doorbell(sq); sq->stats->full++; @@ -285,8 +271,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); - if (unlikely(session->complete || - session->ds_count == session->max_ds_count)) + if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) || + session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS)) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index b90923932668..36ac1e3816b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -40,6 +40,26 @@ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM) + +#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) +#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \ + DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS) + +/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS + * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. + * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a + * full-session WQE be cache-aligned. + */ +#if L1_CACHE_BYTES < 128 +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) +#else +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) +#endif + +#define MLX5E_XDP_MPW_MAX_NUM_DS \ + (MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS) + struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, @@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) session->inline_on = 1; } +static inline bool +mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session) +{ + return session->inline_on && + session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS; +} + +static inline void +mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq, + u16 pi, u16 nnops) +{ + struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi]; + + edge_wi = wi + nnops; + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->num_wqebbs = 1; + wi->num_pkts = 0; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } + + sq->stats->nops += nnops; +} + static inline void mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, @@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, session->pkt_count++; -#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) - if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) { struct mlx5_wqe_inline_seg *inline_dseg = (struct mlx5_wqe_inline_seg *)dseg; u16 ds_len = sizeof(*inline_dseg) + dma_len; u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS); - if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) { - /* Not enough space for inline wqe, send with memory pointer */ - session->complete = true; - goto no_inline; - } - inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); memcpy(inline_dseg->data, xdptxd->data, dma_len); @@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, return; } -no_inline: dseg->addr = cpu_to_be64(xdptxd->dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; session->ds_count++; } -static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, - struct mlx5e_tx_wqe **wqe) +static inline struct mlx5e_tx_wqe * +mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe *wqe; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(wqe, 0, sizeof(*wqe)); - *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - memset(*wqe, 0, sizeof(**wqe)); + return wqe; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index ea032f54197e..3766545ce259 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -412,7 +412,7 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, goto out; tls_ctx = tls_get_ctx(skb->sk); - if (unlikely(tls_ctx->netdev != netdev)) + if (unlikely(WARN_ON_ONCE(tls_ctx->netdev != netdev))) goto err_out; priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1539cf3de5dc..f7890e0ce96c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -180,15 +180,3 @@ out: return err; } - -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev) -{ - u8 min_inline_mode; - - mlx5_query_min_inline(mdev, &min_inline_mode); - if (min_inline_mode == MLX5_INLINE_MODE_NONE && - !MLX5_CAP_ETH(mdev, wqe_vlan_insert)) - min_inline_mode = MLX5_INLINE_MODE_L2; - - return min_inline_mode; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 8dd31b5c740c..01f2918063af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, struct mlx5e_params *params) { - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev); + mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index a6b0eda0bd1a..02530b50609c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -391,7 +391,7 @@ void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, { mutex_lock(&priv->state_lock); - ch->max_combined = mlx5e_get_netdev_max_channels(priv->netdev); + ch->max_combined = priv->max_nch; ch->combined_count = priv->channels.params.num_channels; if (priv->xsk.refcnt) { /* The upper half are XSK queues. */ @@ -785,7 +785,7 @@ static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings } static void get_speed_duplex(struct net_device *netdev, - u32 eth_proto_oper, + u32 eth_proto_oper, bool force_legacy, struct ethtool_link_ksettings *link_ksettings) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -795,7 +795,7 @@ static void get_speed_duplex(struct net_device *netdev, if (!netif_carrier_ok(netdev)) goto out; - speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper); + speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy); if (!speed) { speed = SPEED_UNKNOWN; goto out; @@ -914,8 +914,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, /* Fields: eth_proto_admin and ext_eth_proto_admin are * mutually exclusive. Hence try reading legacy advertising * when extended advertising is zero. - * admin_ext indicates how eth_proto_admin should be - * interpreted + * admin_ext indicates which proto_admin (ext vs. legacy) + * should be read and interpreted */ admin_ext = ext; if (ext && !eth_proto_admin) { @@ -924,7 +924,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, admin_ext = false; } - eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, admin_ext, eth_proto_oper); eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); @@ -939,7 +939,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, get_supported(mdev, eth_proto_cap, link_ksettings); get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings, admin_ext); - get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings); + get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext, + link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; @@ -1016,45 +1017,69 @@ static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) return ptys_modes; } +static bool ext_link_mode_requested(const unsigned long *adver) +{ +#define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT + int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT; + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes); + + bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size); + return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static bool ext_speed_requested(u32 speed) +{ +#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000 + return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED); +} + +static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed) +{ + bool ext_link_mode = ext_link_mode_requested(adver); + bool ext_speed = ext_speed_requested(speed); + + return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed; +} + int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_port_eth_proto eproto; + const unsigned long *adver; bool an_changes = false; u8 an_disable_admin; bool ext_supported; - bool ext_requested; u8 an_disable_cap; bool an_disable; u32 link_modes; u8 an_status; + u8 autoneg; u32 speed; + bool ext; int err; u32 (*ethtool2ptys_adver_func)(const unsigned long *adver); -#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1) + adver = link_ksettings->link_modes.advertising; + autoneg = link_ksettings->base.autoneg; + speed = link_ksettings->base.speed; - ext_requested = !!(link_ksettings->link_modes.advertising[0] > - MLX5E_PTYS_EXT || - link_ksettings->link_modes.advertising[1]); + ext = ext_requested(autoneg, adver, speed), ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); - ext_requested &= ext_supported; + if (!ext_supported && ext) + return -EOPNOTSUPP; - speed = link_ksettings->base.speed; - ethtool2ptys_adver_func = ext_requested ? - mlx5e_ethtool2ptys_ext_adver_link : + ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link : mlx5e_ethtool2ptys_adver_link; - err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) { netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); goto out; } - link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? - ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) : - mlx5e_port_speed2linkmodes(mdev, speed); + link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) : + mlx5e_port_speed2linkmodes(mdev, speed, !ext); link_modes = link_modes & eproto.cap; if (!link_modes) { @@ -1067,14 +1092,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap, &an_disable_admin); - an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE; + an_disable = autoneg == AUTONEG_DISABLE; an_changes = ((!an_disable && an_disable_admin) || (an_disable && !an_disable_admin)); if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index a66589816e21..eed7101e8bb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -611,7 +611,8 @@ static int validate_flow(struct mlx5e_priv *priv, return -ENOSPC; if (fs->ring_cookie != RX_CLS_FLOW_DISC) - if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie)) + if (!mlx5e_qid_validate(priv->profile, &priv->channels.params, + fs->ring_cookie)) return -EINVAL; switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b2618dd6dd10..9a2fcef6e7f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -331,12 +331,11 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) { - struct mlx5e_wqe_frag_info next_frag, *prev; + struct mlx5e_wqe_frag_info next_frag = {}; + struct mlx5e_wqe_frag_info *prev = NULL; int i; next_frag.di = &rq->wqe.di[0]; - next_frag.offset = 0; - prev = NULL; for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) { struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0]; @@ -1131,6 +1130,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; sq->stop_room = MLX5E_SQ_STOP_ROOM; INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert)) + set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) { @@ -1677,10 +1678,10 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, struct mlx5e_channel_param *cparam) { struct mlx5e_priv *priv = c->priv; - int err, tc, max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + int err, tc; for (tc = 0; tc < params->num_tc; tc++) { - int txq_ix = c->ix + tc * max_nch; + int txq_ix = c->ix + tc * priv->max_nch; err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix, params, &cparam->sq, &c->sq[tc], tc); @@ -2323,7 +2324,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } - if (!IS_ERR_OR_NULL(priv->tx_reporter)) + if (priv->tx_reporter) devlink_health_reporter_state_update(priv->tx_reporter, DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); @@ -2438,11 +2439,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv) int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int err; int ix; - for (ix = 0; ix < max_nch; ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt); if (unlikely(err)) goto err_destroy_rqts; @@ -2460,10 +2460,9 @@ err_destroy_rqts: void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) mlx5e_destroy_rqt(priv, &tirs[i].rqt); } @@ -2557,7 +2556,7 @@ static void mlx5e_redirect_rqts(struct mlx5e_priv *priv, mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp); } - for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { struct mlx5e_redirect_rqt_param direct_rrp = { .is_rss = false, { @@ -2758,7 +2757,7 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) goto free_in; } - for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn, in, inlen); if (err) @@ -2858,12 +2857,11 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i, tc; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) for (tc = 0; tc < priv->profile->max_tc; tc++) - priv->channel_tc2txq[i][tc] = i + tc * max_nch; + priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch; } static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) @@ -2884,7 +2882,7 @@ static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { int num_txqs = priv->channels.num * priv->channels.params.num_tc; - int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS; + int num_rxqs = priv->channels.num * priv->profile->rq_groups; struct net_device *netdev = priv->netdev; mlx5e_netdev_set_tcs(netdev); @@ -3306,7 +3304,6 @@ err_destroy_inner_tirs: int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); struct mlx5e_tir *tir; void *tirc; int inlen; @@ -3319,7 +3316,7 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) if (!in) return -ENOMEM; - for (ix = 0; ix < max_nch; ix++) { + for (ix = 0; ix < priv->max_nch; ix++) { memset(in, 0, inlen); tir = &tirs[ix]; tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); @@ -3358,10 +3355,9 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < max_nch; i++) + for (i = 0; i < priv->max_nch; i++) mlx5e_destroy_tir(priv->mdev, &tirs[i]); } @@ -3487,7 +3483,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) { int i; - for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; @@ -4777,7 +4773,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); /* TX inline */ - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev); + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); /* RSS */ mlx5e_build_rss_params(rss_params, params->num_channels); @@ -4962,8 +4958,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, return err; mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params, - mlx5e_get_netdev_max_channels(netdev), - netdev->mtu); + priv->max_nch, netdev->mtu); mlx5e_timestamp_init(priv); @@ -5166,6 +5161,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = MLX5E_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(XSK), }; /* mlx5e generic netdev management API (move to en_common.c) */ @@ -5183,6 +5179,7 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->profile = profile; priv->ppriv = ppriv; priv->msglevel = MLX5E_MSG_LEVEL; + priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); priv->max_opened_tc = 1; mutex_init(&priv->state_lock); @@ -5220,7 +5217,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), nch * profile->max_tc, - nch * MLX5E_NUM_RQ_GROUPS); + nch * profile->rq_groups); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 6edf0aeb1e26..7ce5cb6e527e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -389,24 +389,17 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = { .set_pauseparam = mlx5e_uplink_rep_set_pauseparam, }; -static int mlx5e_rep_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid) +static void mlx5e_rep_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { - struct mlx5_eswitch *esw; struct mlx5e_priv *priv; u64 parent_id; priv = netdev_priv(dev); - esw = priv->mdev->priv.eswitch; - - if (esw->mode == MLX5_ESWITCH_NONE) - return -EOPNOTSUPP; parent_id = mlx5_query_nic_system_image_guid(priv->mdev); ppid->id_len = sizeof(parent_id); memcpy(ppid->id, &parent_id, sizeof(parent_id)); - - return 0; } static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, @@ -613,12 +606,17 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) neigh_connected = (nud_state & NUD_VALID) && !dead; list_for_each_entry(e, &nhe->encap_list, encap_list) { + if (!mlx5e_encap_take(e)) + continue; + encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); priv = netdev_priv(e->out_dev); if (encap_connected != neigh_connected || !ether_addr_equal(e->h_dest, ha)) mlx5e_rep_update_flows(priv, e, neigh_connected, ha); + + mlx5e_encap_put(priv, e); } mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); @@ -781,9 +779,9 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, { int err; - err = __tc_indr_block_cb_register(netdev, rpriv, - mlx5e_rep_indr_setup_tc_cb, - rpriv); + err = __flow_indr_block_cb_register(netdev, rpriv, + mlx5e_rep_indr_setup_tc_cb, + rpriv); if (err) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); @@ -796,8 +794,8 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv, struct net_device *netdev) { - __tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, - rpriv); + __flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, + rpriv); } static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, @@ -1156,6 +1154,23 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, } } +static +int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + switch (ma->command) { + case TC_CLSMATCHALL_REPLACE: + return mlx5e_tc_configure_matchall(priv, ma); + case TC_CLSMATCHALL_DESTROY: + return mlx5e_tc_delete_matchall(priv, ma); + case TC_CLSMATCHALL_STATS: + mlx5e_tc_stats_matchall(priv, ma); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { @@ -1165,6 +1180,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags); + case TC_SETUP_CLSMATCHALL: + return mlx5e_rep_setup_tc_cls_matchall(priv, type_data); default: return -EOPNOTSUPP; } @@ -1699,6 +1716,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = 1, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; static const struct mlx5e_profile mlx5e_uplink_rep_profile = { @@ -1716,6 +1734,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, .rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, .max_tc = MLX5E_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; static bool @@ -1727,37 +1746,46 @@ is_devlink_port_supported(const struct mlx5_core_dev *dev, mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport); } +static unsigned int +vport_to_devlink_port_index(const struct mlx5_core_dev *dev, u16 vport_num) +{ + return (MLX5_CAP_GEN(dev, vhca_id) << 16) | vport_num; +} + static int register_devlink_port(struct mlx5_core_dev *dev, struct mlx5e_rep_priv *rpriv) { struct devlink *devlink = priv_to_devlink(dev); struct mlx5_eswitch_rep *rep = rpriv->rep; struct netdev_phys_item_id ppid = {}; - int ret; + unsigned int dl_port_index = 0; if (!is_devlink_port_supported(dev, rpriv)) return 0; - ret = mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (ret) - return ret; + mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (rep->vport == MLX5_VPORT_UPLINK) + if (rep->vport == MLX5_VPORT_UPLINK) { devlink_port_attrs_set(&rpriv->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, PCI_FUNC(dev->pdev->devfn), false, 0, &ppid.id[0], ppid.id_len); - else if (rep->vport == MLX5_VPORT_PF) + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } else if (rep->vport == MLX5_VPORT_PF) { devlink_port_attrs_pci_pf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn); - else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) + dl_port_index = rep->vport; + } else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, + rpriv->rep->vport)) { devlink_port_attrs_pci_vf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn, rep->vport - 1); + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } - return devlink_port_register(devlink, &rpriv->dl_port, rep->vport); + return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index); } static void unregister_devlink_port(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 10fafd5fa17b..8ac96727cad8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -88,6 +88,7 @@ struct mlx5e_rep_priv { struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */ + struct rtnl_link_stats64 prev_vf_vport_stats; struct devlink_port dl_port; }; @@ -163,6 +164,9 @@ struct mlx5e_encap_entry { u8 flags; char *encap_header; int encap_size; + refcount_t refcnt; + struct completion res_ready; + int compl_result; }; struct mlx5e_rep_sq { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ac6e586d403d..60570b442fff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -859,13 +859,24 @@ tail_padding_csum(struct sk_buff *skb, int offset, } static void -mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto, - struct mlx5e_rq_stats *stats) +mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto, + struct mlx5e_rq_stats *stats) { struct ipv6hdr *ip6; struct iphdr *ip4; int pkt_len; + /* Fixup vlan headers, if any */ + if (network_depth > ETH_HLEN) + /* CQE csum is calculated from the IP header and does + * not cover VLAN headers (if present). This will add + * the checksum manually. + */ + skb->csum = csum_partial(skb->data + ETH_HLEN, + network_depth - ETH_HLEN, + skb->csum); + + /* Fixup tail padding, if any */ switch (proto) { case htons(ETH_P_IP): ip4 = (struct iphdr *)(skb->data + network_depth); @@ -931,16 +942,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; /* CQE csum covers all received bytes */ /* csum might need some fixups ...*/ - if (network_depth > ETH_HLEN) - /* CQE csum is calculated from the IP header and does - * not cover VLAN headers (if present). This will add - * the checksum manually. - */ - skb->csum = csum_partial(skb->data + ETH_HLEN, - network_depth - ETH_HLEN, - skb->csum); - - mlx5e_skb_padding_csum(skb, network_depth, proto, stats); + mlx5e_skb_csum_fixup(skb, network_depth, proto, stats); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 539b4d3656da..94a32c76c182 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, @@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, @@ -172,7 +174,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) memset(s, 0, sizeof(*s)); - for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq; @@ -200,6 +202,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_xdp_tx_xmit += xdpsq_stats->xmit; s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; + s->rx_xdp_tx_nops += xdpsq_stats->nops; s->rx_xdp_tx_full += xdpsq_stats->full; s->rx_xdp_tx_err += xdpsq_stats->err; s->rx_xdp_tx_cqe += xdpsq_stats->cqes; @@ -227,6 +230,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_xdp_xmit += xdpsq_red_stats->xmit; s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; + s->tx_xdp_nops += xdpsq_red_stats->nops; s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; @@ -1331,6 +1335,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = { { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1340,6 +1345,7 @@ static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1395,7 +1401,7 @@ static const struct counter_desc ch_stats_desc[] = { static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + int max_nch = priv->max_nch; return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + @@ -1409,8 +1415,8 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); bool is_xsk = priv->xsk.ever_used; + int max_nch = priv->max_nch; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -1452,8 +1458,8 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); bool is_xsk = priv->xsk.ever_used; + int max_nch = priv->max_nch; int i, j, tc; for (i = 0; i < max_nch; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 76ac111e14d0..bf645d42c833 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -81,6 +81,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_mpwqe; u64 rx_xdp_tx_inlnw; + u64 rx_xdp_tx_nops; u64 rx_xdp_tx_full; u64 rx_xdp_tx_err; u64 rx_xdp_tx_cqe; @@ -97,6 +98,7 @@ struct mlx5e_sw_stats { u64 tx_xdp_xmit; u64 tx_xdp_mpwqe; u64 tx_xdp_inlnw; + u64 tx_xdp_nops; u64 tx_xdp_full; u64 tx_xdp_err; u64 tx_xdp_cqes; @@ -288,6 +290,7 @@ struct mlx5e_xdpsq_stats { u64 xmit; u64 mpwqe; u64 inlnw; + u64 nops; u64 full; u64 err; /* dirtied @completion */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f3ed028d5017..5be3da621499 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -39,6 +39,7 @@ #include <linux/mlx5/device.h> #include <linux/rhashtable.h> #include <linux/refcount.h> +#include <linux/completion.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -102,6 +103,7 @@ enum { * container_of(helper item, containing struct type, helper field[index]) */ struct encap_flow_item { + struct mlx5e_encap_entry *e; /* attached encap instance */ struct list_head list; int index; }; @@ -118,7 +120,9 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; + struct mlx5e_mod_hdr_entry *mh; /* attached mod header instance */ struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ + struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ struct list_head unready; /* flows not ready to be offloaded (e.g due to missing route) */ @@ -161,12 +165,20 @@ struct mlx5e_hairpin_entry { /* a node of a hash table which keeps all the hairpin entries */ struct hlist_node hairpin_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same hairpin */ struct list_head flows; + /* hpe's that were not fully initialized when dead peer update event + * function traversed them. + */ + struct list_head dead_peer_wait_list; u16 peer_vhca_id; u8 prio; struct mlx5e_hairpin *hp; + refcount_t refcnt; + struct completion res_ready; }; struct mod_hdr_key { @@ -178,12 +190,18 @@ struct mlx5e_mod_hdr_entry { /* a node of a hash table which keeps all the mod_hdr entries */ struct hlist_node mod_hdr_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same mod_hdr entry */ struct list_head flows; struct mod_hdr_key key; u32 mod_hdr_id; + + refcount_t refcnt; + struct completion res_ready; + int compl_result; }; #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) @@ -274,14 +292,61 @@ static inline int cmp_mod_hdr_info(struct mod_hdr_key *a, return memcmp(a->actions, b->actions, a->num_actions * MLX5_MH_ACT_SZ); } +static struct mod_hdr_tbl * +get_mod_hdr_table(struct mlx5e_priv *priv, int namespace) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + return namespace == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : + &priv->fs.tc.mod_hdr; +} + +static struct mlx5e_mod_hdr_entry * +mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key) +{ + struct mlx5e_mod_hdr_entry *mh, *found = NULL; + + hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { + if (!cmp_mod_hdr_info(&mh->key, key)) { + refcount_inc(&mh->refcnt); + found = mh; + break; + } + } + + return found; +} + +static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, + struct mlx5e_mod_hdr_entry *mh, + int namespace) +{ + struct mod_hdr_tbl *tbl = get_mod_hdr_table(priv, namespace); + + if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) + return; + hash_del(&mh->mod_hdr_hlist); + mutex_unlock(&tbl->lock); + + WARN_ON(!list_empty(&mh->flows)); + if (mh->compl_result > 0) + mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); + + kfree(mh); +} + +static int get_flow_name_space(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; +} static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int num_actions, actions_size, namespace, err; - bool found = false, is_eswitch_flow; struct mlx5e_mod_hdr_entry *mh; + struct mod_hdr_tbl *tbl; struct mod_hdr_key key; u32 hash_key; @@ -293,85 +358,82 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_key = hash_mod_hdr_info(&key); - is_eswitch_flow = mlx5e_is_eswitch_flow(flow); - if (is_eswitch_flow) { - namespace = MLX5_FLOW_NAMESPACE_FDB; - hash_for_each_possible(esw->offloads.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } else { - namespace = MLX5_FLOW_NAMESPACE_KERNEL; - hash_for_each_possible(priv->fs.tc.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } + namespace = get_flow_name_space(flow); + tbl = get_mod_hdr_table(priv, namespace); - if (found) + mutex_lock(&tbl->lock); + mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); + if (mh) { + mutex_unlock(&tbl->lock); + wait_for_completion(&mh->res_ready); + + if (mh->compl_result < 0) { + err = -EREMOTEIO; + goto attach_header_err; + } goto attach_flow; + } mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); - if (!mh) + if (!mh) { + mutex_unlock(&tbl->lock); return -ENOMEM; + } mh->key.actions = (void *)mh + sizeof(*mh); memcpy(mh->key.actions, key.actions, actions_size); mh->key.num_actions = num_actions; + spin_lock_init(&mh->flows_lock); INIT_LIST_HEAD(&mh->flows); + refcount_set(&mh->refcnt, 1); + init_completion(&mh->res_ready); + + hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); + mutex_unlock(&tbl->lock); err = mlx5_modify_header_alloc(priv->mdev, namespace, mh->key.num_actions, mh->key.actions, &mh->mod_hdr_id); - if (err) - goto out_err; - - if (is_eswitch_flow) - hash_add(esw->offloads.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); - else - hash_add(priv->fs.tc.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); + if (err) { + mh->compl_result = err; + goto alloc_header_err; + } + mh->compl_result = 1; + complete_all(&mh->res_ready); attach_flow: + flow->mh = mh; + spin_lock(&mh->flows_lock); list_add(&flow->mod_hdr, &mh->flows); - if (is_eswitch_flow) + spin_unlock(&mh->flows_lock); + if (mlx5e_is_eswitch_flow(flow)) flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; else flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; return 0; -out_err: - kfree(mh); +alloc_header_err: + complete_all(&mh->res_ready); +attach_header_err: + mlx5e_mod_hdr_put(priv, mh, namespace); return err; } static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->mod_hdr.next; - /* flow wasn't fully initialized */ - if (list_empty(&flow->mod_hdr)) + if (!flow->mh) return; + spin_lock(&flow->mh->flows_lock); list_del(&flow->mod_hdr); + spin_unlock(&flow->mh->flows_lock); - if (list_empty(next)) { - struct mlx5e_mod_hdr_entry *mh; - - mh = list_entry(next, struct mlx5e_mod_hdr_entry, flows); - - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); - hash_del(&mh->mod_hdr_hlist); - kfree(mh); - } + mlx5e_mod_hdr_put(priv, flow->mh, get_flow_name_space(flow)); + flow->mh = NULL; } static @@ -635,13 +697,35 @@ static struct mlx5e_hairpin_entry *mlx5e_hairpin_get(struct mlx5e_priv *priv, hash_for_each_possible(priv->fs.tc.hairpin_tbl, hpe, hairpin_hlist, hash_key) { - if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) + if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) { + refcount_inc(&hpe->refcnt); return hpe; + } } return NULL; } +static void mlx5e_hairpin_put(struct mlx5e_priv *priv, + struct mlx5e_hairpin_entry *hpe) +{ + /* no more hairpin flows for us, release the hairpin pair */ + if (!refcount_dec_and_mutex_lock(&hpe->refcnt, &priv->fs.tc.hairpin_tbl_lock)) + return; + hash_del(&hpe->hairpin_hlist); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + if (!IS_ERR_OR_NULL(hpe->hp)) { + netdev_dbg(priv->netdev, "del hairpin: peer %s\n", + dev_name(hpe->hp->pair->peer_mdev->device)); + + mlx5e_hairpin_destroy(hpe->hp); + } + + WARN_ON(!list_empty(&hpe->flows)); + kfree(hpe); +} + #define UNKNOWN_MATCH_PRIO 8 static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, @@ -707,17 +791,37 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, extack); if (err) return err; + + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); hpe = mlx5e_hairpin_get(priv, peer_id, match_prio); - if (hpe) + if (hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + wait_for_completion(&hpe->res_ready); + + if (IS_ERR(hpe->hp)) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } hpe = kzalloc(sizeof(*hpe), GFP_KERNEL); - if (!hpe) + if (!hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); return -ENOMEM; + } + spin_lock_init(&hpe->flows_lock); INIT_LIST_HEAD(&hpe->flows); + INIT_LIST_HEAD(&hpe->dead_peer_wait_list); hpe->peer_vhca_id = peer_id; hpe->prio = match_prio; + refcount_set(&hpe->refcnt, 1); + init_completion(&hpe->res_ready); + + hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, + hash_hairpin_info(peer_id, match_prio)); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); params.log_data_size = 15; params.log_data_size = min_t(u8, params.log_data_size, @@ -739,9 +843,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, params.num_channels = link_speed64; hp = mlx5e_hairpin_create(priv, ¶ms, peer_ifindex); + hpe->hp = hp; + complete_all(&hpe->res_ready); if (IS_ERR(hp)) { err = PTR_ERR(hp); - goto create_hairpin_err; + goto out_err; } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", @@ -749,10 +855,6 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); - hpe->hp = hp; - hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, - hash_hairpin_info(peer_id, match_prio)); - attach_flow: if (hpe->hp->num_channels > 1) { flow_flag_set(flow, HAIRPIN_RSS); @@ -760,39 +862,32 @@ attach_flow: } else { flow->nic_attr->hairpin_tirn = hpe->hp->tirn; } + + flow->hpe = hpe; + spin_lock(&hpe->flows_lock); list_add(&flow->hairpin, &hpe->flows); + spin_unlock(&hpe->flows_lock); return 0; -create_hairpin_err: - kfree(hpe); +out_err: + mlx5e_hairpin_put(priv, hpe); return err; } static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->hairpin.next; - /* flow wasn't fully initialized */ - if (list_empty(&flow->hairpin)) + if (!flow->hpe) return; + spin_lock(&flow->hpe->flows_lock); list_del(&flow->hairpin); + spin_unlock(&flow->hpe->flows_lock); - /* no more hairpin flows for us, release the hairpin pair */ - if (list_empty(next)) { - struct mlx5e_hairpin_entry *hpe; - - hpe = list_entry(next, struct mlx5e_hairpin_entry, flows); - - netdev_dbg(priv->netdev, "del hairpin: peer %s\n", - dev_name(hpe->hp->pair->peer_mdev->device)); - - mlx5e_hairpin_destroy(hpe->hp); - hash_del(&hpe->hairpin_hlist); - kfree(hpe); - } + mlx5e_hairpin_put(priv, flow->hpe); + flow->hpe = NULL; } static int @@ -1320,13 +1415,13 @@ static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; - u64 bytes, packets, lastuse = 0; struct mlx5e_tc_flow *flow; struct mlx5e_encap_entry *e; struct mlx5_fc *counter; struct neigh_table *tbl; bool neigh_used = false; struct neighbour *n; + u64 lastuse; if (m_neigh->family == AF_INET) tbl = &arp_tbl; @@ -1339,8 +1434,11 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) list_for_each_entry(e, &nhe->encap_list, encap_list) { struct encap_flow_item *efi, *tmp; - if (!(e->flags & MLX5_ENCAP_ENTRY_VALID)) + + if (!(e->flags & MLX5_ENCAP_ENTRY_VALID) || + !mlx5e_encap_take(e)) continue; + list_for_each_entry_safe(efi, tmp, &e->flows, list) { flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); @@ -1349,7 +1447,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) if (mlx5e_is_offloaded_flow(flow)) { counter = mlx5e_tc_get_counter(flow); - mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); + lastuse = mlx5_fc_query_lastuse(counter); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { mlx5e_flow_put(netdev_priv(e->out_dev), flow); neigh_used = true; @@ -1359,6 +1457,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) mlx5e_flow_put(netdev_priv(e->out_dev), flow); } + + mlx5e_encap_put(netdev_priv(e->out_dev), e); if (neigh_used) break; } @@ -1378,29 +1478,51 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) } } +static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + WARN_ON(!list_empty(&e->flows)); + mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); + + if (e->flags & MLX5_ENCAP_ENTRY_VALID) + mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + + kfree(e->encap_header); + kfree(e); +} + +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (!refcount_dec_and_mutex_lock(&e->refcnt, &esw->offloads.encap_tbl_lock)) + return; + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); +} + static void mlx5e_detach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, int out_index) { - struct list_head *next = flow->encaps[out_index].list.next; + struct mlx5e_encap_entry *e = flow->encaps[out_index].e; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; /* flow wasn't fully initialized */ - if (list_empty(&flow->encaps[out_index].list)) + if (!e) return; + mutex_lock(&esw->offloads.encap_tbl_lock); list_del(&flow->encaps[out_index].list); - if (list_empty(next)) { - struct mlx5e_encap_entry *e; - - e = list_entry(next, struct mlx5e_encap_entry, flows); - mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); - - if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); - - hash_del_rcu(&e->encap_hlist); - kfree(e->encap_header); - kfree(e); + flow->encaps[out_index].e = NULL; + if (!refcount_dec_and_test(&e->refcnt)) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + return; } + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); } static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) @@ -2485,7 +2607,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv, if (flow_flag_test(flow, EGRESS) && !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) || - (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP))) + (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || + (actions & MLX5_FLOW_CONTEXT_ACTION_DROP))) return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) @@ -2722,6 +2845,31 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, +bool mlx5e_encap_take(struct mlx5e_encap_entry *e) +{ + return refcount_inc_not_zero(&e->refcnt); +} + +static struct mlx5e_encap_entry * +mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, + uintptr_t hash_key) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_encap_entry *e; + struct encap_key e_key; + + hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, + encap_hlist, hash_key) { + e_key.ip_tun_key = &e->tun_info->key; + e_key.tc_tunnel = e->tunnel; + if (!cmp_encap_info(&e_key, key) && + mlx5e_encap_take(e)) + return e; + } + + return NULL; +} + static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct net_device *mirred_dev, @@ -2734,11 +2882,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; const struct ip_tunnel_info *tun_info; - struct encap_key key, e_key; + struct encap_key key; struct mlx5e_encap_entry *e; unsigned short family; uintptr_t hash_key; - bool found = false; int err = 0; parse_attr = attr->parse_attr; @@ -2753,42 +2900,59 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, - encap_hlist, hash_key) { - e_key.ip_tun_key = &e->tun_info->key; - e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, &key)) { - found = true; - break; - } - } + mutex_lock(&esw->offloads.encap_tbl_lock); + e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ - if (found) + if (e) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + wait_for_completion(&e->res_ready); + + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + if (e->compl_result) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - return -ENOMEM; + if (!e) { + err = -ENOMEM; + goto out_err; + } + + refcount_set(&e->refcnt, 1); + init_completion(&e->res_ready); e->tun_info = tun_info; err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); - if (err) + if (err) { + kfree(e); + e = NULL; goto out_err; + } INIT_LIST_HEAD(&e->flows); + hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - if (err) + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + complete_all(&e->res_ready); + if (err) { + e->compl_result = err; goto out_err; - - hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + } attach_flow: + flow->encaps[out_index].e = e; list_add(&flow->encaps[out_index].list, &e->flows); flow->encaps[out_index].index = out_index; *encap_dev = e->out_dev; @@ -2799,11 +2963,14 @@ attach_flow: } else { *encap_valid = false; } + mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - kfree(e); + mutex_unlock(&esw->offloads.encap_tbl_lock); + if (e) + mlx5e_encap_put(priv, e); return err; } @@ -3638,11 +3805,112 @@ errout: return err; } +static int apply_police_params(struct mlx5e_priv *priv, u32 rate, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch *esw; + u16 vport_num; + u32 rate_mbps; + int err; + + esw = priv->mdev->priv.eswitch; + /* rate is given in bytes/sec. + * First convert to bits/sec and then round to the nearest mbit/secs. + * mbit means million bits. + * Moreover, if rate is non zero we choose to configure to a minimum of + * 1 mbit/sec. + */ + rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + vport_num = rpriv->rep->vport; + + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + if (err) + NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); + + return err; +} + +static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + const struct flow_action_entry *act; + int err; + int i; + + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall called with no action"); + return -EINVAL; + } + + if (!flow_offload_has_one_action(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action"); + return -EOPNOTSUPP; + } + + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_POLICE: + err = apply_police_params(priv, act->police.rate_bytes_ps, extack); + if (err) + return err; + + rpriv->prev_vf_vport_stats = priv->stats.vf_vport; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall"); + return -EOPNOTSUPP; + } + } + + return 0; +} + +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + int prio = TC_H_MAJ(ma->common.prio) >> 16; + + if (prio != 1) { + NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); + return -EINVAL; + } + + return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack); +} + +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + + return apply_police_params(priv, 0, extack); +} + +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct rtnl_link_stats64 cur_stats; + u64 dbytes; + u64 dpkts; + + cur_stats = priv->stats.vf_vport; + dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; + dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; + rpriv->prev_vf_vport_stats = cur_stats; + flow_stats_update(&ma->stats, dpkts, dbytes, jiffies); +} + static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *peer_mdev = peer_priv->mdev; - struct mlx5e_hairpin_entry *hpe; + struct mlx5e_hairpin_entry *hpe, *tmp; + LIST_HEAD(init_wait_list); u16 peer_vhca_id; int bkt; @@ -3651,9 +3919,18 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); - hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) { - if (hpe->peer_vhca_id == peer_vhca_id) + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); + hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) + if (refcount_inc_not_zero(&hpe->refcnt)) + list_add(&hpe->dead_peer_wait_list, &init_wait_list); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { + wait_for_completion(&hpe->res_ready); + if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) hpe->hp->pair->peer_gone = true; + + mlx5e_hairpin_put(priv, hpe); } } @@ -3690,7 +3967,9 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) int err; mutex_init(&tc->t_lock); - hash_init(tc->mod_hdr_tbl); + mutex_init(&tc->mod_hdr.lock); + hash_init(tc->mod_hdr.hlist); + mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); err = rhashtable_init(&tc->ht, &tc_ht_params); @@ -3722,6 +4001,9 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) if (tc->netdevice_nb.notifier_call) unregister_netdevice_notifier(&tc->netdevice_nb); + mutex_destroy(&tc->mod_hdr.lock); + mutex_destroy(&tc->hairpin_tbl_lock); + rhashtable_destroy(&tc->ht); if (!IS_ERR_OR_NULL(tc->t)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 1cb66bf76997..ea2072e2fe84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -63,11 +63,20 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags); +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma); + struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); +bool mlx5e_encap_take(struct mlx5e_encap_entry *e); +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); struct mlx5e_neigh_hash_entry; void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index acf25cc38fa1..d3a67a9b4eba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { - u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ? - MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode; + u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb); opcode = MLX5_OPCODE_SEND; mss = 0; @@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { + u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb); + opcode = MLX5_OPCODE_SEND; mss = 0; - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + ihs = mlx5e_calc_min_inline(mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); stats->packets++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index c50b6f0769c8..49b06b256c92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -49,7 +49,7 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) { struct mlx5e_sq_stats *stats = sq->stats; - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state))) return; @@ -61,7 +61,7 @@ static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) { struct mlx5e_rq_stats *stats = rq->stats; - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state))) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 41f25ea2e8d9..09d4c64b6e73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -215,11 +215,7 @@ static int mlx5_eq_async_int(struct notifier_block *nb, */ dma_rmb(); - if (likely(eqe->type < MLX5_EVENT_TYPE_MAX)) - atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); - else - mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type); - + atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe); ++eq->cons_index; @@ -415,7 +411,7 @@ void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) int mlx5_eq_table_init(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table; - int i, err; + int i; eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL); if (!eq_table) @@ -423,9 +419,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) dev->priv.eq_table = eq_table; - err = mlx5_eq_debugfs_init(dev); - if (err) - goto kvfree_eq_table; + mlx5_eq_debugfs_init(dev); mutex_init(&eq_table->lock); for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++) @@ -433,11 +427,6 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) eq_table->irq_table = dev->priv.irq_table; return 0; - -kvfree_eq_table: - kvfree(eq_table); - dev->priv.eq_table = NULL; - return err; } void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev) @@ -945,9 +934,6 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_register); @@ -956,9 +942,6 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_unregister); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7a0888470fae..f0692407f617 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -58,20 +58,9 @@ struct vport_addr { bool mc_promisc; }; -enum { - UC_ADDR_CHANGE = BIT(0), - MC_ADDR_CHANGE = BIT(1), - PROMISC_CHANGE = BIT(3), -}; - static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw); static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw); -/* Vport context events */ -#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \ - MC_ADDR_CHANGE | \ - PROMISC_CHANGE) - struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { @@ -108,13 +97,13 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1); - if (events_mask & UC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_uc_address_change, 1); - if (events_mask & MC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_mc_address_change, 1); - if (events_mask & PROMISC_CHANGE) + if (events_mask & MLX5_VPORT_PROMISC_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_promisc_change, 1); @@ -463,6 +452,22 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) return err; } +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +static int esw_legacy_enable(struct mlx5_eswitch *esw) +{ + int ret; + + ret = esw_create_legacy_table(esw); + if (ret) + return ret; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); + return 0; +} + static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) { esw_cleanup_vepa_rules(esw); @@ -470,6 +475,19 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) esw_destroy_legacy_vepa_table(esw); } +static void esw_legacy_disable(struct mlx5_eswitch *esw) +{ + struct esw_mc_addr *mc_promisc; + + mlx5_eswitch_disable_pf_vf_vports(esw); + + mc_promisc = &esw->mc_promisc; + if (mc_promisc->uplink_rule) + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_legacy_table(esw); +} + /* E-Switch vport UC/MC lists management */ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, struct vport_addr *vaddr); @@ -901,21 +919,21 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport) esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); - if (vport->enabled_events & UC_ADDR_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) { esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); } - if (vport->enabled_events & MC_ADDR_CHANGE) + if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE) esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); - if (vport->enabled_events & PROMISC_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) { esw_update_vport_rx_mode(esw, vport); if (!IS_ERR_OR_NULL(vport->allmulti_rule)) esw_update_vport_mc_promisc(esw, vport); } - if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) + if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE)) esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport); @@ -1393,18 +1411,49 @@ out: return err; } +static bool element_type_supported(struct mlx5_eswitch *esw, int type) +{ + struct mlx5_core_dev *dev = esw->dev = esw->dev; + + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + /* Vport QoS management */ -static int esw_create_tsar(struct mlx5_eswitch *esw) +static void esw_create_tsar(struct mlx5_eswitch *esw) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; int err; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return 0; + return; + + if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return; if (esw->qos.enabled) - return -EEXIST; + return; + + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -1412,11 +1461,10 @@ static int esw_create_tsar(struct mlx5_eswitch *esw) &esw->qos.root_tsar_id); if (err) { esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); - return err; + return; } esw->qos.enabled = true; - return 0; } static void esw_destroy_tsar(struct mlx5_eswitch *esw) @@ -1537,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, return 0; } +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps) +{ + u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + + return mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW); +} + static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN]) { ((u8 *)node_guid)[7] = mac[0]; @@ -1619,7 +1683,7 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) } static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - int enable_events) + enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; @@ -1641,7 +1705,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num); /* Sync with current vport context */ - vport->enabled_events = enable_events; + vport->enabled_events = enabled_events; vport->enabled = true; /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well @@ -1770,11 +1834,46 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) /* Public E-Switch API */ #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) -int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs + * whichever are present on the eswitch. + */ +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; + int i; + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + esw_enable_vport(esw, vport, enabled_events); +} + +/* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs + * whichever are previously enabled on the eswitch. + */ +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + int i; + + mlx5_esw_for_all_vports_reverse(esw, i, vport) + esw_disable_vport(esw, vport); +} + +int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +{ int err; - int i, enabled_events; if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { @@ -1788,44 +1887,23 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support)) esw_warn(esw->dev, "engress ACL is not supported by FW\n"); + esw_create_tsar(esw); + esw->mode = mode; mlx5_lag_update(esw->dev); if (mode == MLX5_ESWITCH_LEGACY) { - err = esw_create_legacy_table(esw); - if (err) - goto abort; + err = esw_legacy_enable(esw); } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw); + err = esw_offloads_enable(esw); } if (err) goto abort; - err = esw_create_tsar(esw); - if (err) - esw_warn(esw->dev, "Failed to create eswitch TSAR"); - - enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS : - UC_ADDR_CHANGE; - - /* Enable PF vport */ - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_enable_vport(esw, vport, enabled_events); - - /* Enable ECPF vports */ - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - esw_enable_vport(esw, vport, enabled_events); - } - - /* Enable VF vports */ - mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) - esw_enable_vport(esw, vport, enabled_events); - mlx5_eswitch_event_handlers_register(esw); esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n", @@ -1847,10 +1925,7 @@ abort: void mlx5_eswitch_disable(struct mlx5_eswitch *esw) { - struct esw_mc_addr *mc_promisc; - struct mlx5_vport *vport; int old_mode; - int i; if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE) return; @@ -1859,21 +1934,14 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); - mc_promisc = &esw->mc_promisc; mlx5_eswitch_event_handlers_unregister(esw); - mlx5_esw_for_all_vports(esw, i, vport) - esw_disable_vport(esw, vport); - - if (mc_promisc && mc_promisc->uplink_rule) - mlx5_del_flow_rules(mc_promisc->uplink_rule); - - esw_destroy_tsar(esw); - if (esw->mode == MLX5_ESWITCH_LEGACY) - esw_destroy_legacy_table(esw); + esw_legacy_disable(esw); else if (esw->mode == MLX5_ESWITCH_OFFLOADS) - esw_offloads_cleanup(esw); + esw_offloads_disable(esw); + + esw_destroy_tsar(esw); old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1931,8 +1999,10 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto abort; + mutex_init(&esw->offloads.encap_tbl_lock); hash_init(esw->offloads.encap_tbl); - hash_init(esw->offloads.mod_hdr_tbl); + mutex_init(&esw->offloads.mod_hdr.lock); + hash_init(esw->offloads.mod_hdr.hlist); atomic64_set(&esw->offloads.num_flows, 0); mutex_init(&esw->state_lock); @@ -1969,6 +2039,8 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); esw_offloads_cleanup_reps(esw); + mutex_destroy(&esw->offloads.mod_hdr.lock); + mutex_destroy(&esw->offloads.encap_tbl_lock); kfree(esw->vports); kfree(esw); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 60f0c62b447b..86db0e9776da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -102,6 +102,13 @@ struct mlx5_vport_info { bool trusted; }; +/* Vport context events */ +enum mlx5_eswitch_vport_event { + MLX5_VPORT_UC_ADDR_CHANGE = BIT(0), + MLX5_VPORT_MC_ADDR_CHANGE = BIT(1), + MLX5_VPORT_PROMISC_CHANGE = BIT(3), +}; + struct mlx5_vport { struct mlx5_core_dev *dev; int vport; @@ -123,7 +130,7 @@ struct mlx5_vport { } qos; bool enabled; - u16 enabled_events; + enum mlx5_eswitch_vport_event enabled_events; }; enum offloads_fdb_flags { @@ -174,8 +181,9 @@ struct mlx5_esw_offload { struct mlx5_eswitch_rep *vport_reps; struct list_head peer_flows; struct mutex peer_mutex; + struct mutex encap_tbl_lock; /* protects encap_tbl */ DECLARE_HASHTABLE(encap_tbl, 8); - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; DECLARE_HASHTABLE(termtbl_tbl, 8); struct mutex termtbl_mutex; /* protects termtbl hash */ const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES]; @@ -208,8 +216,11 @@ enum { struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; + /* legacy data structures */ struct mlx5_eswitch_fdb fdb_table; struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; + struct esw_mc_addr mc_promisc; + /* end of legacy */ struct workqueue_struct *work_queue; struct mlx5_vport *vports; u32 flags; @@ -219,7 +230,6 @@ struct mlx5_eswitch { * and async SRIOV admin state changes */ struct mutex state_lock; - struct esw_mc_addr mc_promisc; struct { bool enabled; @@ -234,8 +244,8 @@ struct mlx5_eswitch { struct mlx5_esw_functions esw_funcs; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw); -int esw_offloads_init(struct mlx5_eswitch *esw); +void esw_offloads_disable(struct mlx5_eswitch *esw); +int esw_offloads_enable(struct mlx5_eswitch *esw); void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, @@ -252,6 +262,8 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -514,6 +526,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); (vport) = &(esw)->vports[i], \ (i) < (esw)->total_vports; (i)++) +#define mlx5_esw_for_all_vports_reverse(esw, i, vport) \ + for ((i) = (esw)->total_vports - 1; \ + (vport) = &(esw)->vports[i], \ + (i) >= MLX5_VPORT_PF; (i)--) + #define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ for ((i) = MLX5_VPORT_FIRST_VF; \ (vport) = &(esw)->vports[(i)], \ @@ -575,6 +592,11 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num); void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs); int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data); +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events); +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d502c91c148c..42cc5001255b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -594,38 +594,15 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) mlx5_del_flow_rules(rule); } -static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw) +static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) { u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; u8 fdb_to_vport_reg_c_id; int err; - err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, - out, sizeof(out)); - if (err) - return err; - - fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, - esw_vport_context.fdb_to_vport_reg_c_id); - - fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; - MLX5_SET(modify_esw_vport_context_in, in, - esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); - - MLX5_SET(modify_esw_vport_context_in, in, - field_select.fdb_to_vport_reg_c_id, 1); - - return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport, - in, sizeof(in)); -} - -static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) -{ - u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; - u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; - u8 fdb_to_vport_reg_c_id; - int err; + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return 0; err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, out, sizeof(out)); @@ -635,7 +612,10 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, esw_vport_context.fdb_to_vport_reg_c_id); - fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; + if (enable) + fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; + else + fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; MLX5_SET(modify_esw_vport_context_in, in, esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); @@ -1413,10 +1393,9 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw) int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vports = esw->total_vports; - struct mlx5_core_dev *dev = esw->dev; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN], rep_type; int vport_index; + u8 rep_type; esw->offloads.vport_reps = kcalloc(total_vports, sizeof(struct mlx5_eswitch_rep), @@ -1424,12 +1403,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - mlx5_query_mac_address(dev, hw_id); - mlx5_esw_for_all_reps(esw, vport_index, rep) { rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index); rep->vport_index = vport_index; - ether_addr_copy(rep->hw_id, hw_id); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) atomic_set(&rep->rep_data[rep_type].state, @@ -2131,7 +2107,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type return NOTIFY_OK; } -int esw_offloads_init(struct mlx5_eswitch *esw) +int esw_offloads_enable(struct mlx5_eswitch *esw) { int err; @@ -2145,11 +2121,11 @@ int esw_offloads_init(struct mlx5_eswitch *esw) if (err) return err; - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { - err = mlx5_eswitch_enable_passing_vport_metadata(esw); - if (err) - goto err_vport_metadata; - } + err = esw_set_passing_vport_metadata(esw, true); + if (err) + goto err_vport_metadata; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); err = esw_offloads_load_all_reps(esw); if (err) @@ -2163,8 +2139,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw) return 0; err_reps: - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); return err; @@ -2189,13 +2165,13 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw) +void esw_offloads_disable(struct mlx5_eswitch *esw) { mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw); - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7ac1249eadc3..b84a225bbe86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,7 +566,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -574,6 +576,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) MLX5_SET(alloc_flow_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_FLOW_COUNTER); + MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (!err) @@ -581,6 +584,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) return err; } +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +{ + return mlx5_cmd_fc_bulk_alloc(dev, 0, id); +} + int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; @@ -615,67 +623,24 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, return 0; } -struct mlx5_cmd_fc_bulk { - u32 id; - int num; - int outlen; - u32 out[0]; -}; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) -{ - struct mlx5_cmd_fc_bulk *b; - int outlen = - MLX5_ST_SZ_BYTES(query_flow_counter_out) + - MLX5_ST_SZ_BYTES(traffic_counter) * num; - - b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); - if (!b) - return NULL; - - b->id = id; - b->num = num; - b->outlen = outlen; - - return b; -} - -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len) { - kfree(b); + return MLX5_ST_SZ_BYTES(query_flow_counter_out) + + MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len; } -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out) { + int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len); u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0}; MLX5_SET(query_flow_counter_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_COUNTER); MLX5_SET(query_flow_counter_in, in, op_mod, 0); - MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id); - MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num); - return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen); -} - -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes) -{ - int index = id - b->id; - void *stats; - - if (index < 0 || index >= b->num) { - mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n", - id, b->id, b->id + b->num - 1); - return; - } - - stats = MLX5_ADDR_OF(query_flow_counter_out, b->out, - flow_statistics[index]); - *packets = MLX5_GET64(traffic_counter, stats, packets); - *bytes = MLX5_GET64(traffic_counter, stats, octets); + MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id); + MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len); + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index e340f9af2f5a..bc4606306009 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -78,20 +78,16 @@ struct mlx5_flow_cmds { }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); -struct mlx5_cmd_fc_bulk; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes); +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len); +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c48c382f926f..c1252d6be0ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -68,7 +68,7 @@ enum fs_flow_table_type { FS_FT_SNIFFER_RX = 0X5, FS_FT_SNIFFER_TX = 0X6, FS_FT_RDMA_RX = 0X7, - FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX, + FS_FT_MAX_TYPE = FS_FT_RDMA_RX, }; enum fs_flow_table_op_mod { @@ -275,7 +275,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); (type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ (type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) : \ (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\ + (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_RDMA_RX != FS_FT_MAX_TYPE))\ ) #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index b3762123a69c..1804cf3c3814 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,8 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FC_POOL_USED_BUFF_RATIO 10 struct mlx5_fc_cache { u64 packets; @@ -58,12 +60,18 @@ struct mlx5_fc { u64 lastpackets; u64 lastbytes; + struct mlx5_fc_bulk *bulk; u32 id; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); + /* locking scheme: * * It is the responsibility of the user to prevent concurrent calls or bad @@ -75,7 +83,7 @@ struct mlx5_fc { * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * mlx5_fc_stats_work(). addlist is a lockless single linked list * that doesn't require any additional synchronization when adding single * node. * - spawn thread to do the actual destroy @@ -136,81 +144,87 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -/* The function returns the last counter that was queried so the caller - * function can continue calling it till all counters are queried. - */ -static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, - struct mlx5_fc *first, - u32 last_id) +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - struct mlx5_fc *counter = NULL; - struct mlx5_cmd_fc_bulk *b; - bool more = false; - u32 afirst_id; - int num; - int err; + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +static void update_counter_cache(int index, u32 *bulk_raw_data, + struct mlx5_fc_cache *cache) +{ + void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data, + flow_statistics[index]); + u64 packets = MLX5_GET64(traffic_counter, stats, packets); + u64 bytes = MLX5_GET64(traffic_counter, stats, octets); - /* first id must be aligned to 4 when using bulk query */ - afirst_id = first->id & ~0x3; + if (cache->packets == packets) + return; - /* number of counters to query inc. the last counter */ - num = ALIGN(last_id - afirst_id + 1, 4); - if (num > max_bulk) { - num = max_bulk; - last_id = afirst_id + num - 1; - } + cache->packets = packets; + cache->bytes = bytes; + cache->lastuse = jiffies; +} - b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num); - if (!b) { - mlx5_core_err(dev, "Error allocating resources for bulk query\n"); - return NULL; - } +static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, + struct mlx5_fc *first, + u32 last_id) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + bool query_more_counters = (first->id <= last_id); + int max_bulk_len = get_max_bulk_query_len(dev); + u32 *data = fc_stats->bulk_query_out; + struct mlx5_fc *counter = first; + u32 bulk_base_id; + int bulk_len; + int err; - err = mlx5_cmd_fc_bulk_query(dev, b); - if (err) { - mlx5_core_err(dev, "Error doing bulk query: %d\n", err); - goto out; - } + while (query_more_counters) { + /* first id must be aligned to 4 when using bulk query */ + bulk_base_id = counter->id & ~0x3; - counter = first; - list_for_each_entry_from(counter, &fc_stats->counters, list) { - struct mlx5_fc_cache *c = &counter->cache; - u64 packets; - u64 bytes; + /* number of counters to query inc. the last counter */ + bulk_len = min_t(int, max_bulk_len, + ALIGN(last_id - bulk_base_id + 1, 4)); - if (counter->id > last_id) { - more = true; - break; + err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, + data); + if (err) { + mlx5_core_err(dev, "Error doing bulk query: %d\n", err); + return; } + query_more_counters = false; - mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &packets, &bytes); + list_for_each_entry_from(counter, &fc_stats->counters, list) { + int counter_index = counter->id - bulk_base_id; + struct mlx5_fc_cache *cache = &counter->cache; - if (c->packets == packets) - continue; + if (counter->id >= bulk_base_id + bulk_len) { + query_more_counters = true; + break; + } - c->packets = packets; - c->bytes = bytes; - c->lastuse = jiffies; + update_counter_cache(counter_index, data, cache); + } } - -out: - mlx5_cmd_fc_bulk_free(b); - - return more ? counter : NULL; } -static void mlx5_free_fc(struct mlx5_core_dev *dev, - struct mlx5_fc *counter) +static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { mlx5_cmd_fc_free(dev, counter->id); kfree(counter); } +static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (counter->bulk) + mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); + else + mlx5_fc_free(dev, counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -234,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } if (time_before(now, fc_stats->next_query) || @@ -244,32 +258,62 @@ static void mlx5_fc_stats_work(struct work_struct *work) counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, list); - while (counter) - counter = mlx5_fc_stats_query(dev, counter, last->id); + if (counter) + mlx5_fc_stats_query_counter_range(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct mlx5_fc *counter; int err; counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); - if (err) - goto err_out; + if (err) { + kfree(counter); + return ERR_PTR(err); + } + + return counter; +} + +static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) { + counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool); + if (!IS_ERR(counter)) + return counter; + } + + return mlx5_fc_single_alloc(dev); +} + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int err; + + if (IS_ERR(counter)) + return counter; + + INIT_LIST_HEAD(&counter->list); + counter->aging = aging; if (aging) { u32 id = counter->id; counter->cache.lastuse = jiffies; - counter->aging = true; + counter->lastbytes = counter->cache.bytes; + counter->lastpackets = counter->cache.packets; idr_preload(GFP_KERNEL); spin_lock(&fc_stats->counters_idr_lock); @@ -290,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; err_out_alloc: - mlx5_cmd_fc_free(dev, counter->id); -err_out: - kfree(counter); - + mlx5_fc_release(dev, counter); return ERR_PTR(err); } EXPORT_SYMBOL(mlx5_fc_create); @@ -317,13 +358,15 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; } - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len; + int max_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -331,14 +374,25 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); + max_bulk_len = get_max_bulk_query_len(dev); + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + if (!fc_stats->bulk_query_out) + return -ENOMEM; + fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) - return -ENOMEM; + goto err_wq_create; fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); + mlx5_fc_pool_init(&fc_stats->fc_pool, dev); return 0; + +err_wq_create: + kfree(fc_stats->bulk_query_out); + return -ENOMEM; } void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) @@ -348,18 +402,21 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) struct mlx5_fc *counter; struct mlx5_fc *tmp; + mlx5_fc_pool_cleanup(&fc_stats->fc_pool); cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; + kfree(fc_stats->bulk_query_out); + idr_destroy(&fc_stats->counters_idr); tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, @@ -369,6 +426,11 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, } EXPORT_SYMBOL(mlx5_fc_query); +u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter) +{ + return counter->cache.lastuse; +} + void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse) { @@ -401,3 +463,243 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval = min_t(unsigned long, interval, fc_stats->sampling_interval); } + +/* Flow counter bluks */ + +struct mlx5_fc_bulk { + struct list_head pool_list; + u32 base_id; + int bulk_len; + unsigned long *bitmask; + struct mlx5_fc fcs[0]; +}; + +static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, + u32 id) +{ + counter->bulk = bulk; + counter->id = id; +} + +static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) +{ + return bitmap_weight(bulk->bitmask, bulk->bulk_len); +} + +static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +{ + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; + struct mlx5_fc_bulk *bulk; + int err = -ENOMEM; + int bulk_len; + u32 base_id; + int i; + + alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); + bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; + + bulk = kzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc), + GFP_KERNEL); + if (!bulk) + goto err_alloc_bulk; + + bulk->bitmask = kcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), + GFP_KERNEL); + if (!bulk->bitmask) + goto err_alloc_bitmask; + + err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id); + if (err) + goto err_mlx5_cmd_bulk_alloc; + + bulk->base_id = base_id; + bulk->bulk_len = bulk_len; + for (i = 0; i < bulk_len; i++) { + mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i); + set_bit(i, bulk->bitmask); + } + + return bulk; + +err_mlx5_cmd_bulk_alloc: + kfree(bulk->bitmask); +err_alloc_bitmask: + kfree(bulk); +err_alloc_bulk: + return ERR_PTR(err); +} + +static int +mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) +{ + if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all counters were released\n"); + return -EBUSY; + } + + mlx5_cmd_fc_free(dev, bulk->base_id); + kfree(bulk->bitmask); + kfree(bulk); + + return 0; +} + +static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +{ + int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); + + if (free_fc_index >= bulk->bulk_len) + return ERR_PTR(-ENOSPC); + + clear_bit(free_fc_index, bulk->bitmask); + return &bulk->fcs[free_fc_index]; +} + +static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) +{ + int fc_index = fc->id - bulk->base_id; + + if (test_bit(fc_index, bulk->bitmask)) + return -EINVAL; + + set_bit(fc_index, bulk->bitmask); + return 0; +} + +/* Flow counters pool API */ + +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) +{ + fc_pool->dev = dev; + mutex_init(&fc_pool->pool_lock); + INIT_LIST_HEAD(&fc_pool->fully_used); + INIT_LIST_HEAD(&fc_pool->partially_used); + INIT_LIST_HEAD(&fc_pool->unused); + fc_pool->available_fcs = 0; + fc_pool->used_fcs = 0; + fc_pool->threshold = 0; +} + +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); +} + +static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) +{ + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); +} + +static struct mlx5_fc_bulk * +mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *new_bulk; + + new_bulk = mlx5_fc_bulk_create(dev); + if (!IS_ERR(new_bulk)) + fc_pool->available_fcs += new_bulk->bulk_len; + mlx5_fc_pool_update_threshold(fc_pool); + return new_bulk; +} + +static void +mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + + fc_pool->available_fcs -= bulk->bulk_len; + mlx5_fc_bulk_destroy(dev, bulk); + mlx5_fc_pool_update_threshold(fc_pool); +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk) +{ + struct mlx5_fc_bulk *bulk; + struct mlx5_fc *fc; + + if (list_empty(src_list)) + return ERR_PTR(-ENODATA); + + bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); + fc = mlx5_fc_bulk_acquire_fc(bulk); + if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) + list_move(&bulk->pool_list, next_list); + return fc; +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_fc_bulk *new_bulk; + struct mlx5_fc *fc; + + mutex_lock(&fc_pool->pool_lock); + + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, + &fc_pool->fully_used, false); + if (IS_ERR(fc)) + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, + &fc_pool->partially_used, + true); + if (IS_ERR(fc)) { + new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); + if (IS_ERR(new_bulk)) { + fc = ERR_CAST(new_bulk); + goto out; + } + fc = mlx5_fc_bulk_acquire_fc(new_bulk); + list_add(&new_bulk->pool_list, &fc_pool->partially_used); + } + fc_pool->available_fcs--; + fc_pool->used_fcs++; + +out: + mutex_unlock(&fc_pool->pool_lock); + return fc; +} + +static void +mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk = fc->bulk; + int bulk_free_fcs_amount; + + mutex_lock(&fc_pool->pool_lock); + + if (mlx5_fc_bulk_release_fc(bulk, fc)) { + mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); + goto unlock; + } + + fc_pool->available_fcs++; + fc_pool->used_fcs--; + + bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); + if (bulk_free_fcs_amount == 1) + list_move_tail(&bulk->pool_list, &fc_pool->partially_used); + if (bulk_free_fcs_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fc_pool->available_fcs > fc_pool->threshold) + mlx5_fc_pool_free_bulk(fc_pool, bulk); + else + list_add(&bulk->pool_list, &fc_pool->unused); + } + +unlock: + mutex_unlock(&fc_pool->pool_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 6bfaaab362dc..1a2560e3bf7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -88,8 +88,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev, netdev->mtu = netdev->max_mtu; mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params, - mlx5e_get_netdev_max_channels(netdev), - netdev->mtu); + priv->max_nch, netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); mlx5e_timestamp_init(priv); @@ -118,11 +117,10 @@ void mlx5i_cleanup(struct mlx5e_priv *priv) static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) { - int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); struct mlx5e_sw_stats s = { 0 }; int i, j; - for (i = 0; i < max_nch; i++) { + for (i = 0; i < priv->max_nch; i++) { struct mlx5e_channel_stats *channel_stats; struct mlx5e_rq_stats *rq_stats; @@ -436,6 +434,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ .max_tc = MLX5I_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; /* mlx5i netdev NDos */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 6e56fa769d2e..c5a491e22e55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -355,6 +355,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = { .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ .max_tc = MLX5I_MAX_NUM_TC, + .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), }; const struct mlx5e_profile *mlx5i_pkey_get_profile(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 3dfab91ae5f2..4be4d2d36218 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -87,7 +87,7 @@ void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); /* This function should only be called after mlx5_cmd_force_teardown_hca */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index b9d4f4e19ff9..148b55c3db7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/refcount.h> #include <linux/mlx5/driver.h> #include <net/vxlan.h> #include "mlx5_core.h" @@ -48,7 +49,7 @@ struct mlx5_vxlan { struct mlx5_vxlan_port { struct hlist_node hlist; - atomic_t refcount; + refcount_t refcount; u16 udp_port; }; @@ -113,7 +114,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) vxlanp = mlx5_vxlan_lookup_port(vxlan, port); if (vxlanp) { - atomic_inc(&vxlanp->refcount); + refcount_inc(&vxlanp->refcount); return 0; } @@ -137,7 +138,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) } vxlanp->udp_port = port; - atomic_set(&vxlanp->refcount, 1); + refcount_set(&vxlanp->refcount, 1); spin_lock_bh(&vxlan->lock); hash_add(vxlan->htable, &vxlanp->hlist, port); @@ -170,7 +171,7 @@ int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) goto out_unlock; } - if (atomic_dec_and_test(&vxlanp->refcount)) { + if (refcount_dec_and_test(&vxlanp->refcount)) { hash_del(&vxlanp->hlist); remove = true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b15b27a497fc..0b70b1d6338d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -826,11 +826,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eq_cleanup; } - err = mlx5_cq_debugfs_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize cq debugfs\n"); - goto err_events_cleanup; - } + mlx5_cq_debugfs_init(dev); mlx5_init_qp_table(dev); @@ -891,7 +887,6 @@ err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); -err_events_cleanup: mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); @@ -1217,8 +1212,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { int err = 0; - if (cleanup) + if (cleanup) { + mlx5_unregister_device(dev); mlx5_drain_health_wq(dev); + } mutex_lock(&dev->intf_state_mutex); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1369,7 +1366,6 @@ static void remove_one(struct pci_dev *pdev) mlx5_crdump_disable(dev); mlx5_devlink_unregister(devlink); - mlx5_unregister_device(dev); if (mlx5_unload_one(dev, true)) { mlx5_core_err(dev, "mlx5_unload_one failed\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 471bbc48bc1f..87b75b2207c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -146,7 +146,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); void mlx5_cmd_flush(struct mlx5_core_dev *dev); -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index c912d82ca64b..30f7848a6f88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline_mode) { switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode)) + break; + /* fall through */ case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; - case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: - mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode); - break; case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: *min_inline_mode = MLX5_INLINE_MODE_NONE; break; diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 06c80343d9ed..f458fd1ce9f8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -71,7 +71,7 @@ config MLXSW_SWITCHX2 module will be called mlxsw_switchx2. config MLXSW_SPECTRUM - tristate "Mellanox Technologies Spectrum support" + tristate "Mellanox Technologies Spectrum family support" depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q depends on PSAMPLE || PSAMPLE=n depends on BRIDGE || BRIDGE=n @@ -87,8 +87,8 @@ config MLXSW_SPECTRUM select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m ---help--- - This driver supports Mellanox Technologies Spectrum Ethernet - Switch ASICs. + This driver supports Mellanox Technologies + Spectrum/Spectrum-2/Spectrum-3 Ethernet Switch ASICs. To compile this driver as a module, choose M here: the module will be called mlxsw_spectrum. diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 946339e13eb9..5b1323645a5d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -9,6 +9,7 @@ #define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM2 0xcf6c +#define PCI_DEVICE_ID_MELLANOX_SPECTRUM3 0xcf70 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB 0xcb20 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB2 0xcf08 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9277b3f125e8..389861ece418 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -65,6 +65,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2"; +static const char mlxsw_sp3_driver_name[] = "mlxsw_spectrum3"; static const char mlxsw_sp_driver_version[] = "1.0"; static const unsigned char mlxsw_sp1_mac_mask[ETH_ALEN] = { @@ -5290,6 +5291,35 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .res_query_enabled = true, }; +static struct mlxsw_driver mlxsw_sp3_driver = { + .kind = mlxsw_sp3_driver_name, + .priv_size = sizeof(struct mlxsw_sp), + .init = mlxsw_sp2_init, + .fini = mlxsw_sp_fini, + .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, + .port_split = mlxsw_sp_port_split, + .port_unsplit = mlxsw_sp_port_unsplit, + .sb_pool_get = mlxsw_sp_sb_pool_get, + .sb_pool_set = mlxsw_sp_sb_pool_set, + .sb_port_pool_get = mlxsw_sp_sb_port_pool_get, + .sb_port_pool_set = mlxsw_sp_sb_port_pool_set, + .sb_tc_pool_bind_get = mlxsw_sp_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = mlxsw_sp_sb_tc_pool_bind_set, + .sb_occ_snapshot = mlxsw_sp_sb_occ_snapshot, + .sb_occ_max_clear = mlxsw_sp_sb_occ_max_clear, + .sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, + .flash_update = mlxsw_sp_flash_update, + .txhdr_construct = mlxsw_sp_txhdr_construct, + .resources_register = mlxsw_sp2_resources_register, + .params_register = mlxsw_sp2_params_register, + .params_unregister = mlxsw_sp2_params_unregister, + .ptp_transmitted = mlxsw_sp_ptp_transmitted, + .txhdr_len = MLXSW_TXHDR_LEN, + .profile = &mlxsw_sp2_config_profile, + .res_query_enabled = true, +}; + bool mlxsw_sp_port_dev_check(const struct net_device *dev) { return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; @@ -6324,6 +6354,16 @@ static struct pci_driver mlxsw_sp2_pci_driver = { .id_table = mlxsw_sp2_pci_id_table, }; +static const struct pci_device_id mlxsw_sp3_pci_id_table[] = { + {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM3), 0}, + {0, }, +}; + +static struct pci_driver mlxsw_sp3_pci_driver = { + .name = mlxsw_sp3_driver_name, + .id_table = mlxsw_sp3_pci_id_table, +}; + static int __init mlxsw_sp_module_init(void) { int err; @@ -6339,6 +6379,10 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_core_driver_register; + err = mlxsw_core_driver_register(&mlxsw_sp3_driver); + if (err) + goto err_sp3_core_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp1_pci_driver); if (err) goto err_sp1_pci_driver_register; @@ -6347,11 +6391,19 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_pci_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp3_pci_driver); + if (err) + goto err_sp3_pci_driver_register; + return 0; -err_sp2_pci_driver_register: +err_sp3_pci_driver_register: mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); +err_sp2_pci_driver_register: + mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); err_sp1_pci_driver_register: + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); +err_sp3_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp2_driver); err_sp2_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp1_driver); @@ -6363,8 +6415,10 @@ err_sp1_core_driver_register: static void __exit mlxsw_sp_module_exit(void) { + mlxsw_pci_driver_unregister(&mlxsw_sp3_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); mlxsw_core_driver_unregister(&mlxsw_sp2_driver); mlxsw_core_driver_unregister(&mlxsw_sp1_driver); unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); @@ -6379,4 +6433,5 @@ MODULE_AUTHOR("Jiri Pirko <[email protected]>"); MODULE_DESCRIPTION("Mellanox Spectrum driver"); MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table); MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table); +MODULE_DEVICE_TABLE(pci, mlxsw_sp3_pci_id_table); MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index c78d93afbb9d..db17ba35ec84 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -954,4 +954,8 @@ void mlxsw_sp_port_nve_fini(struct mlxsw_sp_port *mlxsw_sp_port); int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp); +/* spectrum_nve_vxlan.c */ +int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp); + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 1537f70bc26d..888ba4300bcc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -437,8 +437,8 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { MLXSW_SP1_SB_PR_CPU_SIZE, true, false), }; -#define MLXSW_SP2_SB_PR_INGRESS_SIZE 38128752 -#define MLXSW_SP2_SB_PR_EGRESS_SIZE 38128752 +#define MLXSW_SP2_SB_PR_INGRESS_SIZE 35297568 +#define MLXSW_SP2_SB_PR_EGRESS_SIZE 35297568 #define MLXSW_SP2_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp2_sb_pool_dess */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 1df164a4b06d..17f334b46c40 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -775,6 +775,7 @@ static void mlxsw_sp_nve_tunnel_fini(struct mlxsw_sp *mlxsw_sp) ops->fini(nve); mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, nve->tunnel_index); + memset(&nve->config, 0, sizeof(nve->config)); } nve->num_nve_tunnels--; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h index 0035640156a1..12f664f42f21 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h @@ -29,6 +29,7 @@ struct mlxsw_sp_nve { unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX]; u32 tunnel_index; u16 ul_rif_index; /* Reserved for Spectrum */ + unsigned int inc_parsing_depth_refs; }; struct mlxsw_sp_nve_ops { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index 93ccd9fc2266..05517c7feaa5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -103,9 +103,9 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, config->udp_dport = cfg->dst_port; } -static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, - unsigned int parsing_depth, - __be16 udp_dport) +static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, + unsigned int parsing_depth, + __be16 udp_dport) { char mprs_pl[MLXSW_REG_MPRS_LEN]; @@ -113,6 +113,56 @@ static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl); } +static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + int parsing_depth = mlxsw_sp->nve->inc_parsing_depth_refs ? + MLXSW_SP_NVE_VXLAN_PARSING_DEPTH : + MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH; + + return __mlxsw_sp_nve_parsing_set(mlxsw_sp, parsing_depth, udp_dport); +} + +static int +__mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + int err; + + mlxsw_sp->nve->inc_parsing_depth_refs++; + + err = mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); + if (err) + goto err_nve_parsing_set; + return 0; + +err_nve_parsing_set: + mlxsw_sp->nve->inc_parsing_depth_refs--; + return err; +} + +static void +__mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp, + __be16 udp_dport) +{ + mlxsw_sp->nve->inc_parsing_depth_refs--; + mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport); +} + +int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp) +{ + __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; + + return __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, udp_dport); +} + +void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp) +{ + __be16 udp_dport = mlxsw_sp->nve->config.udp_dport; + + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, udp_dport); +} + static void mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl, const struct mlxsw_sp_nve_config *config) @@ -176,9 +226,7 @@ static int mlxsw_sp1_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = mlxsw_sp_nve_parsing_set(mlxsw_sp, - MLXSW_SP_NVE_VXLAN_PARSING_DEPTH, - config->udp_dport); + err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); if (err) return err; @@ -203,8 +251,7 @@ err_promote_decap: err_rtdp_set: mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); return err; } @@ -216,8 +263,7 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp); - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); } static int @@ -320,9 +366,7 @@ static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve, struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp; int err; - err = mlxsw_sp_nve_parsing_set(mlxsw_sp, - MLXSW_SP_NVE_VXLAN_PARSING_DEPTH, - config->udp_dport); + err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport); if (err) return err; @@ -348,8 +392,7 @@ err_promote_decap: err_rtdp_set: mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); err_config_set: - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); return err; } @@ -361,8 +404,7 @@ static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve) mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id, config->ul_proto, &config->ul_sip); mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp); - mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH, - config->udp_dport); + __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0); } const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index bd9c2bc2d5d6..63b07edd9d81 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -979,6 +979,9 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port *tmp; + u16 orig_ing_types = 0; + u16 orig_egr_types = 0; + int err; int i; /* MTPPPC configures timestamping globally, not per port. Find the @@ -986,12 +989,26 @@ static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port, */ for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) { tmp = mlxsw_sp->ports[i]; + if (tmp) { + orig_ing_types |= tmp->ptp.ing_types; + orig_egr_types |= tmp->ptp.egr_types; + } if (tmp && tmp != mlxsw_sp_port) { ing_types |= tmp->ptp.ing_types; egr_types |= tmp->ptp.egr_types; } } + if ((ing_types || egr_types) && !(orig_ing_types || orig_egr_types)) { + err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth"); + return err; + } + } + if (!(ing_types || egr_types) && (orig_ing_types || orig_egr_types)) + mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp); + return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp, ing_types, egr_types); } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index b71e4ecbe469..6932e615d4b0 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1818,6 +1818,7 @@ EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { + cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); ocelot_ace_deinit(); diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index ff2f419ae352..1b019fdfcd97 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -173,7 +173,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, struct nfp_fl_payload *nfp_flow, bool last, struct net_device *in_dev, enum nfp_flower_tun_type tun_type, int *tun_out_cnt, - struct netlink_ext_ack *extack) + bool pkt_host, struct netlink_ext_ack *extack) { size_t act_size = sizeof(struct nfp_fl_output); struct nfp_flower_priv *priv = app->priv; @@ -218,6 +218,20 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, return gid; } output->port = cpu_to_be32(NFP_FL_LAG_OUT | gid); + } else if (nfp_flower_internal_port_can_offload(app, out_dev)) { + if (!(priv->flower_ext_feats & NFP_FL_FEATS_PRE_TUN_RULES)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules not supported in loaded firmware"); + return -EOPNOTSUPP; + } + + if (nfp_flow->pre_tun_rule.dev || !pkt_host) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules require single egress dev and ptype HOST action"); + return -EOPNOTSUPP; + } + + nfp_flow->pre_tun_rule.dev = out_dev; + + return 0; } else { /* Set action output parameters. */ output->flags = cpu_to_be16(tmp_flags); @@ -885,7 +899,7 @@ nfp_flower_output_action(struct nfp_app *app, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt, u32 *csum_updated, + int *out_cnt, u32 *csum_updated, bool pkt_host, struct netlink_ext_ack *extack) { struct nfp_flower_priv *priv = app->priv; @@ -907,7 +921,7 @@ nfp_flower_output_action(struct nfp_app *app, output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type, - tun_out_cnt, extack); + tun_out_cnt, pkt_host, extack); if (err) return err; @@ -939,7 +953,7 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, struct net_device *netdev, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, int *out_cnt, u32 *csum_updated, - struct nfp_flower_pedit_acts *set_act, + struct nfp_flower_pedit_acts *set_act, bool *pkt_host, struct netlink_ext_ack *extack, int act_idx) { struct nfp_fl_set_ipv4_tun *set_tun; @@ -955,17 +969,21 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, case FLOW_ACTION_DROP: nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP); break; + case FLOW_ACTION_REDIRECT_INGRESS: case FLOW_ACTION_REDIRECT: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; + case FLOW_ACTION_MIRRED_INGRESS: case FLOW_ACTION_MIRRED: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; @@ -1095,6 +1113,13 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, nfp_fl_set_mpls(set_m, act); *a_len += sizeof(struct nfp_fl_set_mpls); break; + case FLOW_ACTION_PTYPE: + /* TC ptype skbedit sets PACKET_HOST for ingress redirect. */ + if (act->ptype != PACKET_HOST) + return -EOPNOTSUPP; + + *pkt_host = true; + break; default: /* Currently we do not handle any other actions. */ NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported action in action list"); @@ -1150,6 +1175,7 @@ int nfp_flower_compile_action(struct nfp_app *app, struct nfp_flower_pedit_acts set_act; enum nfp_flower_tun_type tun_type; struct flow_action_entry *act; + bool pkt_host = false; u32 csum_updated = 0; memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -1166,7 +1192,7 @@ int nfp_flower_compile_action(struct nfp_app *app, err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated, - &set_act, extack, i); + &set_act, &pkt_host, extack, i); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 332439400d85..7eb2ec8969c3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -220,7 +220,8 @@ struct nfp_fl_set_ipv4_tun { __be16 tun_flags; u8 ttl; u8 tos; - __be32 extra; + __be16 outer_vlan_tpid; + __be16 outer_vlan_tci; u8 tun_len; u8 res2; __be16 tun_proto; @@ -483,6 +484,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_QOS_MOD = 18, NFP_FLOWER_CMSG_TYPE_QOS_DEL = 19, NFP_FLOWER_CMSG_TYPE_QOS_STATS = 20, + NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE = 21, NFP_FLOWER_CMSG_TYPE_MAX = 32, }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index eb846133943b..7a20447cca19 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -781,6 +781,7 @@ static int nfp_flower_init(struct nfp_app *app) INIT_LIST_HEAD(&app_priv->indr_block_cb_priv); INIT_LIST_HEAD(&app_priv->non_repr_priv); + app_priv->pre_tun_rule_cnt = 0; return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index af9441d5787f..31d94592a7c0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -42,6 +42,7 @@ struct nfp_app; #define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_VF_RLIM BIT(4) #define NFP_FL_FEATS_FLOW_MOD BIT(5) +#define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_FLOW_MERGE BIT(30) #define NFP_FL_FEATS_LAG BIT(31) @@ -162,6 +163,7 @@ struct nfp_fl_internal_ports { * @qos_stats_work: Workqueue for qos stats processing * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates + * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded */ struct nfp_flower_priv { struct nfp_app *app; @@ -193,6 +195,7 @@ struct nfp_flower_priv { struct delayed_work qos_stats_work; unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ + int pre_tun_rule_cnt; }; /** @@ -218,6 +221,7 @@ struct nfp_fl_qos { * @block_shared: Flag indicating if offload applies to shared blocks * @mac_list: List entry of reprs that share the same offloaded MAC * @qos_table: Stored info on filters implementing qos + * @on_bridge: Indicates if the repr is attached to a bridge */ struct nfp_flower_repr_priv { struct nfp_repr *nfp_repr; @@ -227,6 +231,7 @@ struct nfp_flower_repr_priv { bool block_shared; struct list_head mac_list; struct nfp_fl_qos qos_table; + bool on_bridge; }; /** @@ -280,6 +285,11 @@ struct nfp_fl_payload { char *action_data; struct list_head linked_flows; bool in_hw; + struct { + struct net_device *dev; + __be16 vlan_tci; + __be16 port_idx; + } pre_tun_rule; }; struct nfp_fl_payload_link { @@ -333,6 +343,11 @@ static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay) return flow_pay->tc_flower_cookie == (unsigned long)flow_pay; } +static inline bool nfp_flower_is_supported_bridge(struct net_device *netdev) +{ + return netif_is_ovs_master(netdev); +} + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_ctx_split); void nfp_flower_metadata_cleanup(struct nfp_app *app); @@ -415,4 +430,8 @@ void nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev); u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, struct net_device *netdev); +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index e209f150c5f2..3a4f4f042ae7 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -61,6 +61,11 @@ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) +#define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ + (NFP_FLOWER_LAYER_PORT | \ + NFP_FLOWER_LAYER_MAC | \ + NFP_FLOWER_LAYER_IPV4) + struct nfp_flower_merge_check { union { struct { @@ -489,6 +494,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; INIT_LIST_HEAD(&flow_pay->linked_flows); flow_pay->in_hw = false; + flow_pay->pre_tun_rule.dev = NULL; return flow_pay; @@ -732,28 +738,62 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len, return act_off; } -static int nfp_fl_verify_post_tun_acts(char *acts, int len) +static int +nfp_fl_verify_post_tun_acts(char *acts, int len, struct nfp_fl_push_vlan **vlan) { struct nfp_fl_act_head *a; unsigned int act_off = 0; while (act_off < len) { a = (struct nfp_fl_act_head *)&acts[act_off]; - if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) + + if (a->jump_id == NFP_FL_ACTION_OPCODE_PUSH_VLAN && !act_off) + *vlan = (struct nfp_fl_push_vlan *)a; + else if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) return -EOPNOTSUPP; act_off += a->len_lw << NFP_FL_LW_SIZ; } + /* Ensure any VLAN push also has an egress action. */ + if (*vlan && act_off <= sizeof(struct nfp_fl_push_vlan)) + return -EOPNOTSUPP; + return 0; } static int +nfp_fl_push_vlan_after_tun(char *acts, int len, struct nfp_fl_push_vlan *vlan) +{ + struct nfp_fl_set_ipv4_tun *tun; + struct nfp_fl_act_head *a; + unsigned int act_off = 0; + + while (act_off < len) { + a = (struct nfp_fl_act_head *)&acts[act_off]; + + if (a->jump_id == NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL) { + tun = (struct nfp_fl_set_ipv4_tun *)a; + tun->outer_vlan_tpid = vlan->vlan_tpid; + tun->outer_vlan_tci = vlan->vlan_tci; + + return 0; + } + + act_off += a->len_lw << NFP_FL_LW_SIZ; + } + + /* Return error if no tunnel action is found. */ + return -EOPNOTSUPP; +} + +static int nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, struct nfp_fl_payload *sub_flow2, struct nfp_fl_payload *merge_flow) { unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2; + struct nfp_fl_push_vlan *post_tun_push_vlan = NULL; bool tunnel_act = false; char *merge_act; int err; @@ -790,18 +830,36 @@ nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, sub2_act_len -= pre_off2; /* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes - * a tunnel, sub_flow 2 can only have output actions for a valid merge. + * a tunnel, there are restrictions on what sub_flow 2 actions lead to a + * valid merge. */ if (tunnel_act) { char *post_tun_acts = &sub_flow2->action_data[pre_off2]; - err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len); + err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len, + &post_tun_push_vlan); if (err) return err; + + if (post_tun_push_vlan) { + pre_off2 += sizeof(*post_tun_push_vlan); + sub2_act_len -= sizeof(*post_tun_push_vlan); + } } /* Copy remaining actions from sub_flows 1 and 2. */ memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len); + + if (post_tun_push_vlan) { + /* Update tunnel action in merge to include VLAN push. */ + err = nfp_fl_push_vlan_after_tun(merge_act, sub1_act_len, + post_tun_push_vlan); + if (err) + return err; + + merge_flow->meta.act_len -= sizeof(*post_tun_push_vlan); + } + merge_act += sub1_act_len; memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len); @@ -945,6 +1003,106 @@ err_destroy_merge_flow: } /** + * nfp_flower_validate_pre_tun_rule() + * @app: Pointer to the APP handle + * @flow: Pointer to NFP flow representation of rule + * @extack: Netlink extended ACK report + * + * Verifies the flow as a pre-tunnel rule. + * + * Return: negative value on error, 0 if verified. + */ +static int +nfp_flower_validate_pre_tun_rule(struct nfp_app *app, + struct nfp_fl_payload *flow, + struct netlink_ext_ack *extack) +{ + struct nfp_flower_meta_tci *meta_tci; + struct nfp_flower_mac_mpls *mac; + struct nfp_fl_act_head *act; + u8 *mask = flow->mask_data; + bool vlan = false; + int act_offset; + u8 key_layer; + + meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } + + key_layer = meta_tci->nfp_flow_key_layer; + if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); + return -EOPNOTSUPP; + } + + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MAC fields match required"); + return -EOPNOTSUPP; + } + + /* Skip fields known to exist. */ + mask += sizeof(struct nfp_flower_meta_tci); + mask += sizeof(struct nfp_flower_in_port); + + /* Ensure destination MAC address is fully matched. */ + mac = (struct nfp_flower_mac_mpls *)mask; + if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC field must not be masked"); + return -EOPNOTSUPP; + } + + if (key_layer & NFP_FLOWER_LAYER_IPV4) { + int ip_flags = offsetof(struct nfp_flower_ipv4, ip_ext.flags); + int ip_proto = offsetof(struct nfp_flower_ipv4, ip_ext.proto); + int i; + + mask += sizeof(struct nfp_flower_mac_mpls); + + /* Ensure proto and flags are the only IP layer fields. */ + for (i = 0; i < sizeof(struct nfp_flower_ipv4); i++) + if (mask[i] && i != ip_flags && i != ip_proto) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); + return -EOPNOTSUPP; + } + } + + /* Action must be a single egress or pop_vlan and egress. */ + act_offset = 0; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + if (vlan) { + if (act->jump_id != NFP_FL_ACTION_OPCODE_POP_VLAN) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on VLAN must have VLAN pop as first action"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + } + + if (act->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non egress action detected where egress was expected"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + + /* Ensure there are no more actions after egress. */ + if (act_offset != flow->meta.act_len) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: egress is not the last action"); + return -EOPNOTSUPP; + } + + return 0; +} + +/** * nfp_flower_add_offload() - Adds a new flow to hardware. * @app: Pointer to the APP handle * @netdev: netdev structure. @@ -994,6 +1152,12 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; + if (flow_pay->pre_tun_rule.dev) { + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + if (err) + goto err_destroy_flow; + } + err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack); if (err) goto err_destroy_flow; @@ -1006,8 +1170,11 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_release_metadata; } - err = nfp_flower_xmit_flow(app, flow_pay, - NFP_FLOWER_CMSG_TYPE_FLOW_ADD); + if (flow_pay->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_flow(app, flow_pay); + else + err = nfp_flower_xmit_flow(app, flow_pay, + NFP_FLOWER_CMSG_TYPE_FLOW_ADD); if (err) goto err_remove_rhash; @@ -1149,8 +1316,11 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, goto err_free_merge_flow; } - err = nfp_flower_xmit_flow(app, nfp_flow, - NFP_FLOWER_CMSG_TYPE_FLOW_DEL); + if (nfp_flow->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_del_flow(app, nfp_flow); + else + err = nfp_flower_xmit_flow(app, nfp_flow, + NFP_FLOWER_CMSG_TYPE_FLOW_DEL); /* Fall through on error. */ err_free_merge_flow: @@ -1479,16 +1649,17 @@ int nfp_flower_reg_indir_block_handler(struct nfp_app *app, return NOTIFY_OK; if (event == NETDEV_REGISTER) { - err = __tc_indr_block_cb_register(netdev, app, - nfp_flower_indr_setup_tc_cb, - app); + err = __flow_indr_block_cb_register(netdev, app, + nfp_flower_indr_setup_tc_cb, + app); if (err) nfp_flower_cmsg_warn(app, "Indirect block reg failed - %s\n", netdev->name); } else if (event == NETDEV_UNREGISTER) { - __tc_indr_block_cb_unregister(netdev, - nfp_flower_indr_setup_tc_cb, app); + __flow_indr_block_cb_unregister(netdev, + nfp_flower_indr_setup_tc_cb, + app); } return NOTIFY_OK; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a7a80f4b722a..def8c198b016 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -15,6 +15,24 @@ #define NFP_FL_MAX_ROUTES 32 +#define NFP_TUN_PRE_TUN_RULE_LIMIT 32 +#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 +#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 + +/** + * struct nfp_tun_pre_run_rule - rule matched before decap + * @flags: options for the rule offset + * @port_idx: index of destination MAC address for the rule + * @vlan_tci: VLAN info associated with MAC + * @host_ctx_id: stats context of rule to update + */ +struct nfp_tun_pre_tun_rule { + __be32 flags; + __be16 port_idx; + __be16 vlan_tci; + __be32 host_ctx_id; +}; + /** * struct nfp_tun_active_tuns - periodic message of active tunnels * @seq: sequence number of the message @@ -124,11 +142,12 @@ enum nfp_flower_mac_offload_cmd { /** * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC - * @ht_node: Hashtable entry - * @addr: Offloaded MAC address - * @index: Offloaded index for given MAC address - * @ref_count: Number of devs using this MAC address - * @repr_list: List of reprs sharing this MAC address + * @ht_node: Hashtable entry + * @addr: Offloaded MAC address + * @index: Offloaded index for given MAC address + * @ref_count: Number of devs using this MAC address + * @repr_list: List of reprs sharing this MAC address + * @bridge_count: Number of bridge/internal devs with MAC */ struct nfp_tun_offloaded_mac { struct rhash_head ht_node; @@ -136,6 +155,7 @@ struct nfp_tun_offloaded_mac { u16 index; int ref_count; struct list_head repr_list; + int bridge_count; }; static const struct rhashtable_params offloaded_macs_params = { @@ -556,6 +576,8 @@ nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry, list_del(&repr_priv->mac_list); list_add_tail(&repr_priv->mac_list, &entry->repr_list); + } else if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count++; } entry->ref_count++; @@ -572,20 +594,35 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { - nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod); - return 0; + if (entry->bridge_count || + !nfp_flower_is_supported_bridge(netdev)) { + nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, + netdev, mod); + return 0; + } + + /* MAC is global but matches need to go to pre_tun table. */ + nfp_mac_idx = entry->index | NFP_TUN_PRE_TUN_IDX_BIT; } - /* Assign a global index if non-repr or MAC address is now shared. */ - if (entry || !port) { - ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, - NFP_MAX_MAC_INDEX, GFP_KERNEL); - if (ida_idx < 0) - return ida_idx; + if (!nfp_mac_idx) { + /* Assign a global index if non-repr or MAC is now shared. */ + if (entry || !port) { + ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, + NFP_MAX_MAC_INDEX, GFP_KERNEL); + if (ida_idx < 0) + return ida_idx; - nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); - } else { - nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port); + nfp_mac_idx = + nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); + + if (nfp_flower_is_supported_bridge(netdev)) + nfp_mac_idx |= NFP_TUN_PRE_TUN_IDX_BIT; + + } else { + nfp_mac_idx = + nfp_tunnel_get_mac_idx_from_phy_port_id(port); + } } if (!entry) { @@ -654,6 +691,25 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, list_del(&repr_priv->mac_list); } + if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count--; + + if (!entry->bridge_count && entry->ref_count) { + u16 nfp_mac_idx; + + nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; + if (__nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, + false)) { + nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n", + netdev_name(netdev)); + return 0; + } + + entry->index = nfp_mac_idx; + return 0; + } + } + /* If MAC is now used by 1 repr set the offloaded MAC index to port. */ if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) { u16 nfp_mac_idx; @@ -713,6 +769,9 @@ nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev, return 0; repr_priv = repr->app_priv; + if (repr_priv->on_bridge) + return 0; + mac_offloaded = &repr_priv->mac_offloaded; off_mac = &repr_priv->offloaded_mac_addr[0]; port = nfp_repr_get_port_id(netdev); @@ -828,10 +887,119 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app, if (err) nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n", netdev_name(netdev)); + } else if (event == NETDEV_CHANGEUPPER) { + /* If a repr is attached to a bridge then tunnel packets + * entering the physical port are directed through the bridge + * datapath and cannot be directly detunneled. Therefore, + * associated offloaded MACs and indexes should not be used + * by fw for detunneling. + */ + struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev; + struct nfp_flower_repr_priv *repr_priv; + struct nfp_repr *repr; + + if (!nfp_netdev_is_nfp_repr(netdev) || + !nfp_flower_is_supported_bridge(upper)) + return NOTIFY_OK; + + repr = netdev_priv(netdev); + if (repr->app != app) + return NOTIFY_OK; + + repr_priv = repr->app_priv; + + if (info->linking) { + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_DEL)) + nfp_flower_cmsg_warn(app, "Failed to delete offloaded MAC on %s.\n", + netdev_name(netdev)); + repr_priv->on_bridge = true; + } else { + repr_priv->on_bridge = false; + + if (!(netdev->flags & IFF_UP)) + return NOTIFY_OK; + + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_ADD)) + nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n", + netdev_name(netdev)); + } } return NOTIFY_OK; } +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_tun_pre_tun_rule payload; + struct net_device *internal_dev; + int err; + + if (app_priv->pre_tun_rule_cnt == NFP_TUN_PRE_TUN_RULE_LIMIT) + return -ENOSPC; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + internal_dev = flow->pre_tun_rule.dev; + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.host_ctx_id = flow->meta.host_ctx_id; + + /* Lookup MAC index for the pre-tunnel rule egress device. + * Note that because the device is always an internal port, it will + * have a constant global index so does not need to be tracked. + */ + mac_entry = nfp_tunnel_lookup_offloaded_macs(app, + internal_dev->dev_addr); + if (!mac_entry) + return -ENOENT; + + payload.port_idx = cpu_to_be16(mac_entry->index); + + /* Copy mac id and vlan to flow - dev may not exist at delete time. */ + flow->pre_tun_rule.vlan_tci = payload.vlan_tci; + flow->pre_tun_rule.port_idx = payload.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt++; + + return 0; +} + +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_pre_tun_rule payload; + u32 tmp_flags = 0; + int err; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + tmp_flags |= NFP_TUN_PRE_TUN_RULE_DEL; + payload.flags = cpu_to_be32(tmp_flags); + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.port_idx = flow->pre_tun_rule.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt--; + + return 0; +} + int nfp_tunnel_config_start(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index ab7f2498e1c4..553c708694e8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -159,19 +159,13 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) else strcpy(name, "ctrl-vnic"); nn->debugfs_dir = debugfs_create_dir(name, ddir); - if (IS_ERR_OR_NULL(nn->debugfs_dir)) - return; /* Create queue debugging sub-tree */ queues = debugfs_create_dir("queue", nn->debugfs_dir); - if (IS_ERR_OR_NULL(queues)) - return; rx = debugfs_create_dir("rx", queues); tx = debugfs_create_dir("tx", queues); xdp = debugfs_create_dir("xdp", queues); - if (IS_ERR_OR_NULL(rx) || IS_ERR_OR_NULL(tx) || IS_ERR_OR_NULL(xdp)) - return; for (i = 0; i < min(nn->max_rx_rings, nn->max_r_vecs); i++) { sprintf(name, "%d", i); @@ -190,16 +184,7 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) struct dentry *nfp_net_debugfs_device_add(struct pci_dev *pdev) { - struct dentry *dev_dir; - - if (IS_ERR_OR_NULL(nfp_dir)) - return NULL; - - dev_dir = debugfs_create_dir(pci_name(pdev), nfp_dir); - if (IS_ERR_OR_NULL(dev_dir)) - return NULL; - - return dev_dir; + return debugfs_create_dir(pci_name(pdev), nfp_dir); } void nfp_net_debugfs_dir_clean(struct dentry **dir) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index d9cbe84ac6ad..1b840ee47339 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -444,12 +444,12 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data) data = nfp_pr_et(data, "hw_rx_csum_complete"); data = nfp_pr_et(data, "hw_rx_csum_err"); data = nfp_pr_et(data, "rx_replace_buf_alloc_fail"); - data = nfp_pr_et(data, "rx_tls_decrypted"); + data = nfp_pr_et(data, "rx_tls_decrypted_packets"); data = nfp_pr_et(data, "hw_tx_csum"); data = nfp_pr_et(data, "hw_tx_inner_csum"); data = nfp_pr_et(data, "tx_gather"); data = nfp_pr_et(data, "tx_lso"); - data = nfp_pr_et(data, "tx_tls_encrypted"); + data = nfp_pr_et(data, "tx_tls_encrypted_packets"); data = nfp_pr_et(data, "tx_tls_ooo"); data = nfp_pr_et(data, "tx_tls_drop_no_sync_data"); diff --git a/drivers/net/ethernet/ni/Kconfig b/drivers/net/ethernet/ni/Kconfig index 70b1a03c0953..01229190132d 100644 --- a/drivers/net/ethernet/ni/Kconfig +++ b/drivers/net/ethernet/ni/Kconfig @@ -11,7 +11,7 @@ config NET_VENDOR_NI Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about National Instrument devices. + the questions about National Instruments devices. If you say Y, you will be asked for your specific device in the following questions. diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig index 8161e308e64b..ead3750b4489 100644 --- a/drivers/net/ethernet/packetengines/Kconfig +++ b/drivers/net/ethernet/packetengines/Kconfig @@ -1,10 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only # -# Packet engine device configuration +# Packet Engines device configuration # config NET_VENDOR_PACKET_ENGINES - bool "Packet Engine devices" + bool "Packet Engines devices" default y depends on PCI ---help--- @@ -12,7 +12,7 @@ config NET_VENDOR_PACKET_ENGINES Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about packet engine devices. If you say Y, you will + the questions about Packet Engines devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_PACKET_ENGINES diff --git a/drivers/net/ethernet/packetengines/Makefile b/drivers/net/ethernet/packetengines/Makefile index 1553c9cfc254..cf054b796d11 100644 --- a/drivers/net/ethernet/packetengines/Makefile +++ b/drivers/net/ethernet/packetengines/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only # -# Makefile for the Packet Engine network device drivers. +# Makefile for the Packet Engines network device drivers. # obj-$(CONFIG_HAMACHI) += hamachi.o diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 4e8118a08654..9f5113639eaf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -1093,7 +1093,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, snprintf(bit_name, 30, p_aeu->bit_name, num); else - strncpy(bit_name, + strlcpy(bit_name, p_aeu->bit_name, 30); /* We now need to pass bitmask in its diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 829dd60ab937..e5ac8bd4fd14 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1688,6 +1688,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, switch (media_type) { case MEDIA_DA_TWINAX: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; /* For DAC media multiple speed capabilities are supported*/ @@ -1707,6 +1708,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, *if_capability |= QED_LM_100000baseCR4_Full_BIT; break; case MEDIA_BASE_T: + *if_capability |= QED_LM_TP_BIT; if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) { if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { @@ -1718,6 +1720,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, } } if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) { + *if_capability |= QED_LM_FIBRE_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET) *if_capability |= QED_LM_1000baseT_Full_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET) @@ -1728,6 +1731,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, case MEDIA_SFPP_10G_FIBER: case MEDIA_XFP_FIBER: case MEDIA_MODULE_FIBER: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) || @@ -1770,6 +1774,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, break; case MEDIA_KR: + *if_capability |= QED_LM_Backplane_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; if (capability & @@ -1821,7 +1826,6 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->link_up = true; /* TODO - at the moment assume supported and advertised speed equal */ - if_link->supported_caps = QED_LM_FIBRE_BIT; if (link_caps.default_speed_autoneg) if_link->supported_caps |= QED_LM_Autoneg_BIT; if (params.pause.autoneg || diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 17c64e43d6c3..158ac0738911 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -442,7 +442,7 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, /* Vendor specific information */ dev->vendor_id = cdev->vendor_id; dev->vendor_part_id = cdev->device_id; - dev->hw_ver = 0; + dev->hw_ver = cdev->chip_rev; dev->fw_ver = (FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) | (FW_REVISION_VERSION << 8) | (FW_ENGINEERING_VERSION); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e85f9fef930c..abcee474909a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -424,12 +424,13 @@ struct qede_link_mode_mapping { }; static const struct qede_link_mode_mapping qed_lm_map[] = { + {QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, {QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, {QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT}, {QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, {QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT}, - {QED_LM_2500baseX_Full_BIT, ETHTOOL_LINK_MODE_2500baseX_Full_BIT}, + {QED_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT}, {QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, {QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, {QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT}, diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index bcb890b18a94..702aa217a27a 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -131,17 +131,10 @@ DEFINE_SHOW_ATTRIBUTE(qcaspi_info); void qcaspi_init_device_debugfs(struct qcaspi *qca) { - struct dentry *device_root; + qca->device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), + NULL); - device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), NULL); - qca->device_root = device_root; - - if (IS_ERR(device_root) || !device_root) { - pr_warn("failed to create debugfs directory for %s\n", - dev_name(&qca->net_dev->dev)); - return; - } - debugfs_create_file("info", S_IFREG | 0444, device_root, qca, + debugfs_create_file("info", S_IFREG | 0444, qca->device_root, qca, &qcaspi_info_fops); } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 60189923737a..21d38167f961 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -206,9 +206,9 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr, ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; if (ip4h->protocol == IPPROTO_UDP) - ul_header->udp_ip4_ind = 1; + ul_header->udp_ind = 1; else - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0; /* Changing remaining fields to network order */ hdr++; @@ -239,6 +239,7 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr, struct rmnet_map_ul_csum_header *ul_header, struct sk_buff *skb) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr; __be16 *hdr = (__be16 *)ul_header, offset; offset = htons((__force u16)(skb_transport_header(skb) - @@ -246,7 +247,11 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr, ul_header->csum_start_offset = offset; ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; - ul_header->udp_ip4_ind = 0; + + if (ip6h->nexthdr == IPPROTO_UDP) + ul_header->udp_ind = 1; + else + ul_header->udp_ind = 0; /* Changing remaining fields to network order */ hdr++; @@ -419,7 +424,7 @@ sw_csum: ul_header->csum_start_offset = 0; ul_header->csum_insert_offset = 0; ul_header->csum_enabled = 0; - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0; priv->stats.csum_sw++; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 109779e449cd..a4233ace21ca 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -271,7 +271,6 @@ enum rtl_registers { Config3 = 0x54, Config4 = 0x55, Config5 = 0x56, - MultiIntr = 0x5c, PHYAR = 0x60, PHYstatus = 0x6c, RxMaxSize = 0xda, @@ -643,7 +642,7 @@ struct rtl8169_private { struct RxDesc *RxDescArray; /* 256-aligned Rx descriptor ring */ dma_addr_t TxPhyAddr; dma_addr_t RxPhyAddr; - void *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ + struct page *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ struct ring_info tx_skb[NUM_TX_DESC]; /* Tx data buffers */ u16 cp_cmd; u16 irq_mask; @@ -851,6 +850,14 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) return RTL_R32(tp, OCPDR); } +static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, + u16 set) +{ + u16 data = r8168_mac_ocp_read(tp, reg); + + r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); +} + #define OCP_STD_PHY_BASE 0xa400 static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) @@ -4408,7 +4415,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168c_2[] = { { 0x01, 0, 0x0001 }, - { 0x03, 0x0400, 0x0220 } + { 0x03, 0x0400, 0x0020 } }; rtl_set_def_aspm_entry_latency(tp); @@ -4455,7 +4462,8 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) static const struct ephy_info e_info_8168d_4[] = { { 0x0b, 0x0000, 0x0048 }, { 0x19, 0x0020, 0x0050 }, - { 0x0c, 0x0100, 0x0020 } + { 0x0c, 0x0100, 0x0020 }, + { 0x10, 0x0004, 0x0000 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4505,7 +4513,9 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168e_2[] = { { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4567,7 +4577,9 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4582,8 +4594,9 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static const struct ephy_info e_info_8168f_1[] = { { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, - { 0x1e, 0x0000, 0x4000 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4622,8 +4635,8 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_1[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x37d0, 0x0820 }, + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, { 0x1e, 0x0000, 0x0001 }, { 0x19, 0x8000, 0x0000 } }; @@ -4639,10 +4652,15 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x19, 0xffff, 0xfc00 }, - { 0x1e, 0xffff, 0x20eb } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, + { 0x19, 0xffff, 0x7c00 }, + { 0x1e, 0xffff, 0x20eb }, + { 0x0d, 0xffff, 0x1666 }, + { 0x00, 0xffff, 0x10a3 }, + { 0x06, 0xffff, 0xf050 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x4000, 0x0000 }, }; rtl_hw_start_8168g(tp); @@ -4656,11 +4674,16 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) static void rtl_hw_start_8411_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8411_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x0f, 0xffff, 0x5200 }, - { 0x19, 0x0020, 0x0000 }, - { 0x1e, 0x0000, 0x2000 } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x37d0, 0x0820 }, + { 0x1e, 0x0000, 0x0001 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x00, 0x0000, 0x0080 }, + { 0x06, 0x0000, 0x0010 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x0000, 0x4000 }, }; rtl_hw_start_8168g(tp); @@ -4810,16 +4833,15 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { - int rg_saw_cnt; - u32 data; static const struct ephy_info e_info_8168h_1[] = { { 0x1e, 0x0800, 0x0001 }, { 0x1d, 0x0000, 0x0800 }, { 0x05, 0xffff, 0x2089 }, { 0x06, 0xffff, 0x5881 }, - { 0x04, 0xffff, 0x154a }, + { 0x04, 0xffff, 0x854a }, { 0x01, 0xffff, 0x068b } }; + int rg_saw_cnt; /* disable aspm and clock request before access ephy */ rtl_hw_aspm_clkreq_enable(tp, false); @@ -4864,31 +4886,13 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) sw_cnt_1ms_ini = 16000000/rg_saw_cnt; sw_cnt_1ms_ini &= 0x0fff; - data = r8168_mac_ocp_read(tp, 0xd412); - data &= ~0x0fff; - data |= sw_cnt_1ms_ini; - r8168_mac_ocp_write(tp, 0xd412, data); + r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini); } - data = r8168_mac_ocp_read(tp, 0xe056); - data &= ~0xf0; - data |= 0x70; - r8168_mac_ocp_write(tp, 0xe056, data); - - data = r8168_mac_ocp_read(tp, 0xe052); - data &= ~0x6000; - data |= 0x8008; - r8168_mac_ocp_write(tp, 0xe052, data); - - data = r8168_mac_ocp_read(tp, 0xe0d6); - data &= ~0x01ff; - data |= 0x017f; - r8168_mac_ocp_write(tp, 0xe0d6, data); - - data = r8168_mac_ocp_read(tp, 0xd420); - data &= ~0x0fff; - data |= 0x047f; - r8168_mac_ocp_write(tp, 0xd420, data); + r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0070); + r8168_mac_ocp_modify(tp, 0xe052, 0x6000, 0x8008); + r8168_mac_ocp_modify(tp, 0xe0d6, 0x01ff, 0x017f); + r8168_mac_ocp_modify(tp, 0xd420, 0x0fff, 0x047f); r8168_mac_ocp_write(tp, 0xe63e, 0x0001); r8168_mac_ocp_write(tp, 0xe63e, 0x0000); @@ -4970,12 +4974,11 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) { - u32 data; static const struct ephy_info e_info_8168ep_3[] = { - { 0x00, 0xffff, 0x10a3 }, - { 0x19, 0xffff, 0x7c00 }, - { 0x1e, 0xffff, 0x20eb }, - { 0x0d, 0xffff, 0x1666 } + { 0x00, 0x0000, 0x0080 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, }; /* disable aspm and clock request before access ephy */ @@ -4987,18 +4990,9 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); - data = r8168_mac_ocp_read(tp, 0xd3e2); - data &= 0xf000; - data |= 0x0271; - r8168_mac_ocp_write(tp, 0xd3e2, data); - - data = r8168_mac_ocp_read(tp, 0xd3e4); - data &= 0xff00; - r8168_mac_ocp_write(tp, 0xd3e4, data); - - data = r8168_mac_ocp_read(tp, 0xe860); - data |= 0x0080; - r8168_mac_ocp_write(tp, 0xe860, data); + r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x0271); + r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000); + r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080); rtl_hw_aspm_clkreq_enable(tp, true); } @@ -5241,10 +5235,7 @@ static void rtl_hw_start(struct rtl8169_private *tp) RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); rtl_set_tx_config_registers(tp); - rtl_set_rx_mode(tp->dev); - /* no early-rx interrupts */ - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); rtl_irq_enable(tp); } @@ -5269,17 +5260,6 @@ static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc) desc->opts1 &= ~cpu_to_le32(DescOwn | RsvdMask); } -static void rtl8169_free_rx_databuff(struct rtl8169_private *tp, - void **data_buff, struct RxDesc *desc) -{ - dma_unmap_single(tp_to_dev(tp), le64_to_cpu(desc->addr), - R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); - - kfree(*data_buff); - *data_buff = NULL; - rtl8169_make_unusable_by_asic(desc); -} - static inline void rtl8169_mark_to_asic(struct RxDesc *desc) { u32 eor = le32_to_cpu(desc->opts1) & RingEnd; @@ -5290,49 +5270,43 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc) desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE); } -static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp, - struct RxDesc *desc) +static struct page *rtl8169_alloc_rx_data(struct rtl8169_private *tp, + struct RxDesc *desc) { - void *data; - dma_addr_t mapping; struct device *d = tp_to_dev(tp); int node = dev_to_node(d); + dma_addr_t mapping; + struct page *data; - data = kmalloc_node(R8169_RX_BUF_SIZE, GFP_KERNEL, node); + data = alloc_pages_node(node, GFP_KERNEL, get_order(R8169_RX_BUF_SIZE)); if (!data) return NULL; - /* Memory should be properly aligned, but better check. */ - if (!IS_ALIGNED((unsigned long)data, 8)) { - netdev_err_once(tp->dev, "RX buffer not 8-byte-aligned\n"); - goto err_out; - } - - mapping = dma_map_single(d, data, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + mapping = dma_map_page(d, data, 0, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(d, mapping))) { if (net_ratelimit()) netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n"); - goto err_out; + __free_pages(data, get_order(R8169_RX_BUF_SIZE)); + return NULL; } desc->addr = cpu_to_le64(mapping); rtl8169_mark_to_asic(desc); - return data; -err_out: - kfree(data); - return NULL; + return data; } static void rtl8169_rx_clear(struct rtl8169_private *tp) { unsigned int i; - for (i = 0; i < NUM_RX_DESC; i++) { - if (tp->Rx_databuff[i]) { - rtl8169_free_rx_databuff(tp, tp->Rx_databuff + i, - tp->RxDescArray + i); - } + for (i = 0; i < NUM_RX_DESC && tp->Rx_databuff[i]; i++) { + dma_unmap_page(tp_to_dev(tp), + le64_to_cpu(tp->RxDescArray[i].addr), + R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + __free_pages(tp->Rx_databuff[i], get_order(R8169_RX_BUF_SIZE)); + tp->Rx_databuff[i] = NULL; + rtl8169_make_unusable_by_asic(tp->RxDescArray + i); } } @@ -5346,7 +5320,7 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp) unsigned int i; for (i = 0; i < NUM_RX_DESC; i++) { - void *data; + struct page *data; data = rtl8169_alloc_rx_data(tp, tp->RxDescArray + i); if (!data) { @@ -5901,6 +5875,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget for (rx_left = min(budget, NUM_RX_DESC); rx_left > 0; rx_left--, cur_rx++) { unsigned int entry = cur_rx % NUM_RX_DESC; + const void *rx_buf = page_address(tp->Rx_databuff[entry]); struct RxDesc *desc = tp->RxDescArray + entry; u32 status; @@ -5955,9 +5930,8 @@ process_pkt: goto release_descriptor; } - prefetch(tp->Rx_databuff[entry]); - skb_copy_to_linear_data(skb, tp->Rx_databuff[entry], - pkt_size); + prefetch(rx_buf); + skb_copy_to_linear_data(skb, rx_buf, pkt_size); skb->tail += pkt_size; skb->len = pkt_size; @@ -6107,10 +6081,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp) if (ret) return ret; - if (tp->supports_gmii) - phy_remove_link_mode(phydev, - ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - else + if (!tp->supports_gmii) phy_set_max_speed(phydev, SPEED_100); phy_support_asym_pause(phydev); @@ -6561,13 +6532,18 @@ static int rtl_alloc_irq(struct rtl8169_private *tp) { unsigned int flags; - if (tp->mac_version <= RTL_GIGA_MAC_VER_06) { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: rtl_unlock_config_regs(tp); RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable); rtl_lock_config_regs(tp); + /* fall through */ + case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24: flags = PCI_IRQ_LEGACY; - } else { + break; + default: flags = PCI_IRQ_ALL_TYPES; + break; } return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags); @@ -6661,8 +6637,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp) static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - u32 data; - tp->ocp_base = OCP_STD_PHY_BASE; RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); @@ -6677,16 +6651,12 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) msleep(1); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); - data = r8168_mac_ocp_read(tp, 0xe8de); - data &= ~(1 << 14); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0); if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42)) return; - data = r8168_mac_ocp_read(tp, 0xe8de); - data |= (1 << 15); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15)); rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42); } @@ -6918,9 +6888,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* RTL8168e-vl has a HW issue with TSO */ if (tp->mac_version == RTL_GIGA_MAC_VER_34) { - dev->vlan_features &= ~NETIF_F_ALL_TSO; - dev->hw_features &= ~NETIF_F_ALL_TSO; - dev->features &= ~NETIF_F_ALL_TSO; + dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); } dev->hw_features |= NETIF_F_RXALL; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 079f459c73a5..2c5d3f5b84dd 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2208,10 +2208,12 @@ static int rocker_router_fib_event(struct notifier_block *nb, if (fen_info->fi->fib_nh_is_v6) { NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported"); + kfree(fib_work); return notifier_from_errno(-EINVAL); } if (fen_info->fi->nh) { NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); + kfree(fib_work); return notifier_from_errno(-EINVAL); } } diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig index 027938017579..e92a178a76df 100644 --- a/drivers/net/ethernet/samsung/Kconfig +++ b/drivers/net/ethernet/samsung/Kconfig @@ -11,7 +11,7 @@ config NET_VENDOR_SAMSUNG say Y. Note that the answer to this question does not directly affect - the kernel: saying N will just case the configurator to skip all + the kernel: saying N will just cause the configurator to skip all the questions about Samsung chipsets. If you say Y, you will be asked for your specific chipset/driver in the following questions. diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c index fd850d3d8ec0..05ea3523890a 100644 --- a/drivers/net/ethernet/sfc/falcon/rx.c +++ b/drivers/net/ethernet/sfc/falcon/rx.c @@ -424,7 +424,6 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct ef4_nic *efx = channel->efx; struct sk_buff *skb; @@ -460,9 +459,7 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index d5db045535d3..85ec07f5a674 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -412,7 +412,6 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct efx_nic *efx = channel->efx; struct sk_buff *skb; @@ -449,9 +448,7 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index bd14803545de..8d88e4083456 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -712,6 +712,7 @@ static void smc911x_phy_detect(struct net_device *dev) /* Found an external PHY */ break; } + /* Else, fall through */ default: /* Internal media only */ SMC_GET_PHY_ID1(lp, 1, id1); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ed872eed1cab..e1e6f67041ec 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -354,6 +354,8 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int rssen; + unsigned int vlhash; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -381,6 +383,10 @@ struct dma_features { #define JUMBO_LEN 9000 +/* Receive Side Scaling */ +#define STMMAC_RSS_HASH_KEY_SIZE 40 +#define STMMAC_RSS_MAX_TABLE_SIZE 256 + extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 01c2e2d83e76..fc9954e4a772 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -85,6 +85,8 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 value; base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + base_register); @@ -102,6 +104,8 @@ static void dwmac4_tx_queue_priority(struct mac_device_info *hw, u32 value; base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + base_register); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 7f86dffb264d..429c94e40c73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -44,11 +44,22 @@ #define XGMAC_CORE_INIT_RX 0 #define XGMAC_PACKET_FILTER 0x00000008 #define XGMAC_FILTER_RA BIT(31) +#define XGMAC_FILTER_VTFE BIT(16) +#define XGMAC_FILTER_HPF BIT(10) #define XGMAC_FILTER_PCF BIT(7) #define XGMAC_FILTER_PM BIT(4) #define XGMAC_FILTER_HMC BIT(2) #define XGMAC_FILTER_PR BIT(0) #define XGMAC_HASH_TABLE(x) (0x00000010 + (x) * 4) +#define XGMAC_MAX_HASH_TABLE 8 +#define XGMAC_VLAN_TAG 0x00000050 +#define XGMAC_VLAN_EDVLP BIT(26) +#define XGMAC_VLAN_VTHM BIT(25) +#define XGMAC_VLAN_DOVLTC BIT(20) +#define XGMAC_VLAN_ESVL BIT(18) +#define XGMAC_VLAN_ETV BIT(16) +#define XGMAC_VLAN_VID GENMASK(15, 0) +#define XGMAC_VLAN_HASH_TABLE 0x00000058 #define XGMAC_RXQ_CTRL0 0x000000a0 #define XGMAC_RXQEN(x) GENMASK((x) * 2 + 1, (x) * 2) #define XGMAC_RXQEN_SHIFT(x) ((x) * 2) @@ -82,10 +93,13 @@ #define XGMAC_HWFEAT_AVSEL BIT(11) #define XGMAC_HWFEAT_RAVSEL BIT(10) #define XGMAC_HWFEAT_ARPOFFSEL BIT(9) +#define XGMAC_HWFEAT_MMCSEL BIT(8) #define XGMAC_HWFEAT_MGKSEL BIT(7) #define XGMAC_HWFEAT_RWKSEL BIT(6) +#define XGMAC_HWFEAT_VLHASH BIT(4) #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 +#define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) #define XGMAC_HWFEAT_ADDR64 GENMASK(15, 14) #define XGMAC_HWFEAT_TXFIFOSIZE GENMASK(10, 6) @@ -96,15 +110,36 @@ #define XGMAC_HWFEAT_RXCHCNT GENMASK(15, 12) #define XGMAC_HWFEAT_TXQCNT GENMASK(9, 6) #define XGMAC_HWFEAT_RXQCNT GENMASK(3, 0) +#define XGMAC_HW_FEATURE3 0x00000128 +#define XGMAC_HWFEAT_ASP GENMASK(15, 14) +#define XGMAC_HWFEAT_FRPES GENMASK(12, 11) +#define XGMAC_HWFEAT_FRPPB GENMASK(10, 9) +#define XGMAC_HWFEAT_FRPSEL BIT(3) +#define XGMAC_MAC_DPP_FSM_INT_STATUS 0x00000150 +#define XGMAC_MAC_FSM_CONTROL 0x00000158 +#define XGMAC_PRTYEN BIT(1) +#define XGMAC_TMOUTEN BIT(0) #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 -#define XGMAC_ADDR0_HIGH 0x00000300 +#define XGMAC_ADDRx_HIGH(x) (0x00000300 + (x) * 0x8) +#define XGMAC_ADDR_MAX 32 #define XGMAC_AE BIT(31) #define XGMAC_DCS GENMASK(19, 16) #define XGMAC_DCS_SHIFT 16 -#define XGMAC_ADDR0_LOW 0x00000304 +#define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8) #define XGMAC_ARP_ADDR 0x00000c10 +#define XGMAC_RSS_CTRL 0x00000c80 +#define XGMAC_UDP4TE BIT(3) +#define XGMAC_TCP4TE BIT(2) +#define XGMAC_IP2TE BIT(1) +#define XGMAC_RSSE BIT(0) +#define XGMAC_RSS_ADDR 0x00000c88 +#define XGMAC_RSSIA_SHIFT 8 +#define XGMAC_ADDRT BIT(2) +#define XGMAC_CT BIT(1) +#define XGMAC_OB BIT(0) +#define XGMAC_RSS_DATA 0x00000c8c #define XGMAC_TIMESTAMP_STATUS 0x00000d20 #define XGMAC_TXTSC BIT(15) #define XGMAC_TXTIMESTAMP_NSEC 0x00000d30 @@ -113,6 +148,7 @@ /* MTL Registers */ #define XGMAC_MTL_OPMODE 0x00001000 +#define XGMAC_FRPE BIT(15) #define XGMAC_ETSALG GENMASK(6, 5) #define XGMAC_WRR (0x0 << 5) #define XGMAC_WFQ (0x1 << 5) @@ -121,8 +157,32 @@ #define XGMAC_MTL_INT_STATUS 0x00001020 #define XGMAC_MTL_RXQ_DMA_MAP0 0x00001030 #define XGMAC_MTL_RXQ_DMA_MAP1 0x00001034 -#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 3, (x) * 8) +#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_QxMDMACH_SHIFT(x) ((x) * 8) +#define XGMAC_QDDMACH BIT(7) +#define XGMAC_TC_PRTY_MAP0 0x00001040 +#define XGMAC_TC_PRTY_MAP1 0x00001044 +#define XGMAC_PSTC(x) GENMASK((x) * 8 + 7, (x) * 8) +#define XGMAC_PSTC_SHIFT(x) ((x) * 8) +#define XGMAC_MTL_RXP_CONTROL_STATUS 0x000010a0 +#define XGMAC_RXPI BIT(31) +#define XGMAC_NPE GENMASK(23, 16) +#define XGMAC_NVE GENMASK(7, 0) +#define XGMAC_MTL_RXP_IACC_CTRL_ST 0x000010b0 +#define XGMAC_STARTBUSY BIT(31) +#define XGMAC_WRRDN BIT(16) +#define XGMAC_ADDR GENMASK(9, 0) +#define XGMAC_MTL_RXP_IACC_DATA 0x000010b4 +#define XGMAC_MTL_ECC_CONTROL 0x000010c0 +#define XGMAC_MTL_SAFETY_INT_STATUS 0x000010c4 +#define XGMAC_MEUIS BIT(1) +#define XGMAC_MECIS BIT(0) +#define XGMAC_MTL_ECC_INT_ENABLE 0x000010c8 +#define XGMAC_RPCEIE BIT(12) +#define XGMAC_ECEIE BIT(8) +#define XGMAC_RXCEIE BIT(4) +#define XGMAC_TXCEIE BIT(0) +#define XGMAC_MTL_ECC_INT_STATUS 0x000010cc #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -187,6 +247,16 @@ #define XGMAC_TDPS GENMASK(29, 0) #define XGMAC_RX_EDMA_CTRL 0x00003044 #define XGMAC_RDPS GENMASK(29, 0) +#define XGMAC_DMA_SAFETY_INT_STATUS 0x00003064 +#define XGMAC_MCSIS BIT(31) +#define XGMAC_MSUIS BIT(29) +#define XGMAC_MSCIS BIT(28) +#define XGMAC_DEUIS BIT(1) +#define XGMAC_DECIS BIT(0) +#define XGMAC_DMA_ECC_INT_ENABLE 0x00003068 +#define XGMAC_DCEIE BIT(1) +#define XGMAC_TCEIE BIT(0) +#define XGMAC_DMA_ECC_INT_STATUS 0x0000306c #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) #define XGMAC_PBLx8 BIT(16) #define XGMAC_DMA_CH_TX_CONTROL(x) (0x00003104 + (0x80 * (x))) @@ -253,6 +323,13 @@ #define XGMAC_RDES3_IOC BIT(30) #define XGMAC_RDES3_LD BIT(28) #define XGMAC_RDES3_CDA BIT(27) +#define XGMAC_RDES3_RSV BIT(26) +#define XGMAC_RDES3_L34T GENMASK(23, 20) +#define XGMAC_RDES3_L34T_SHIFT 20 +#define XGMAC_L34T_IP4TCP 0x1 +#define XGMAC_L34T_IP4UDP 0x2 +#define XGMAC_L34T_IP6TCP 0x9 +#define XGMAC_L34T_IP6UDP 0xA #define XGMAC_RDES3_ES BIT(15) #define XGMAC_RDES3_PL GENMASK(13, 0) #define XGMAC_RDES3_TSD BIT(6) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 0a32c96a7854..767f3fe5efaa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -4,6 +4,9 @@ * stmmac XGMAC support. */ +#include <linux/bitrev.h> +#include <linux/crc32.h> +#include <linux/iopoll.h> #include "stmmac.h" #include "dwxgmac2.h" @@ -106,6 +109,8 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 value, reg; reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + reg); value &= ~XGMAC_PSRQ(queue); @@ -114,6 +119,23 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, writel(value, ioaddr + reg); } +static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, + u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value, reg; + + reg = (queue < 4) ? XGMAC_TC_PRTY_MAP0 : XGMAC_TC_PRTY_MAP1; + if (queue >= 4) + queue -= 4; + + value = readl(ioaddr + reg); + value &= ~XGMAC_PSTC(queue); + value |= (prio << XGMAC_PSTC_SHIFT(queue)) & XGMAC_PSTC(queue); + + writel(value, ioaddr + reg); +} + static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw, u32 rx_alg) { @@ -140,7 +162,9 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, u32 tx_alg) { void __iomem *ioaddr = hw->pcsr; + bool ets = true; u32 value; + int i; value = readl(ioaddr + XGMAC_MTL_OPMODE); value &= ~XGMAC_ETSALG; @@ -156,10 +180,28 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, value |= XGMAC_DWRR; break; default: + ets = false; break; } writel(value, ioaddr + XGMAC_MTL_OPMODE); + + /* Set ETS if desired */ + for (i = 0; i < MTL_MAX_TX_QUEUES; i++) { + value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + value &= ~XGMAC_TSA; + if (ets) + value |= XGMAC_ETS; + writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + } +} + +static void dwxgmac2_set_mtl_tx_queue_weight(struct mac_device_info *hw, + u32 weight, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(weight, ioaddr + XGMAC_MTL_TCx_QUANTUM_WEIGHT(queue)); } static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, @@ -169,6 +211,8 @@ static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, u32 value, reg; reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1; + if (queue >= 4) + queue -= 4; value = readl(ioaddr + reg); value &= ~XGMAC_QxMDMACH(queue); @@ -278,10 +322,10 @@ static void dwxgmac2_set_umac_addr(struct mac_device_info *hw, u32 value; value = (addr[5] << 8) | addr[4]; - writel(value | XGMAC_AE, ioaddr + XGMAC_ADDR0_HIGH); + writel(value | XGMAC_AE, ioaddr + XGMAC_ADDRx_HIGH(reg_n)); value = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0]; - writel(value, ioaddr + XGMAC_ADDR0_LOW); + writel(value, ioaddr + XGMAC_ADDRx_LOW(reg_n)); } static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, @@ -291,8 +335,8 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, u32 hi_addr, lo_addr; /* Read the MAC address from the hardware */ - hi_addr = readl(ioaddr + XGMAC_ADDR0_HIGH); - lo_addr = readl(ioaddr + XGMAC_ADDR0_LOW); + hi_addr = readl(ioaddr + XGMAC_ADDRx_HIGH(reg_n)); + lo_addr = readl(ioaddr + XGMAC_ADDRx_LOW(reg_n)); /* Extract the MAC address from the high and low words */ addr[0] = lo_addr & 0xff; @@ -303,19 +347,82 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, addr[5] = (hi_addr >> 8) & 0xff; } +static void dwxgmac2_set_mchash(void __iomem *ioaddr, u32 *mcfilterbits, + int mcbitslog2) +{ + int numhashregs, regs; + + switch (mcbitslog2) { + case 6: + numhashregs = 2; + break; + case 7: + numhashregs = 4; + break; + case 8: + numhashregs = 8; + break; + default: + return; + } + + for (regs = 0; regs < numhashregs; regs++) + writel(mcfilterbits[regs], ioaddr + XGMAC_HASH_TABLE(regs)); +} + static void dwxgmac2_set_filter(struct mac_device_info *hw, struct net_device *dev) { void __iomem *ioaddr = (void __iomem *)dev->base_addr; - u32 value = XGMAC_FILTER_RA; + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + int mcbitslog2 = hw->mcast_bits_log2; + u32 mc_filter[8]; + int i; + + value &= ~(XGMAC_FILTER_PR | XGMAC_FILTER_HMC | XGMAC_FILTER_PM); + value |= XGMAC_FILTER_HPF; + + memset(mc_filter, 0, sizeof(mc_filter)); if (dev->flags & IFF_PROMISC) { - value |= XGMAC_FILTER_PR | XGMAC_FILTER_PCF; + value |= XGMAC_FILTER_PR; + value |= XGMAC_FILTER_PCF; } else if ((dev->flags & IFF_ALLMULTI) || - (netdev_mc_count(dev) > HASH_TABLE_SIZE)) { + (netdev_mc_count(dev) > hw->multicast_filter_bins)) { value |= XGMAC_FILTER_PM; - writel(~0x0, ioaddr + XGMAC_HASH_TABLE(0)); - writel(~0x0, ioaddr + XGMAC_HASH_TABLE(1)); + + for (i = 0; i < XGMAC_MAX_HASH_TABLE; i++) + writel(~0x0, ioaddr + XGMAC_HASH_TABLE(i)); + } else if (!netdev_mc_empty(dev)) { + struct netdev_hw_addr *ha; + + value |= XGMAC_FILTER_HMC; + + netdev_for_each_mc_addr(ha, dev) { + int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >> + (32 - mcbitslog2)); + mc_filter[nr >> 5] |= (1 << (nr & 0x1F)); + } + } + + dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2); + + /* Handle multiple unicast addresses */ + if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) { + value |= XGMAC_FILTER_PR; + } else { + struct netdev_hw_addr *ha; + int reg = 1; + + netdev_for_each_uc_addr(ha, dev) { + dwxgmac2_set_umac_addr(hw, ha->addr, reg); + reg++; + } + + for ( ; reg < XGMAC_ADDR_MAX; reg++) { + writel(0, ioaddr + XGMAC_ADDRx_HIGH(reg)); + writel(0, ioaddr + XGMAC_ADDRx_LOW(reg)); + } } writel(value, ioaddr + XGMAC_PACKET_FILTER); @@ -333,17 +440,574 @@ static void dwxgmac2_set_mac_loopback(void __iomem *ioaddr, bool enable) writel(value, ioaddr + XGMAC_RX_CONFIG); } +static int dwxgmac2_rss_write_reg(void __iomem *ioaddr, bool is_key, int idx, + u32 val) +{ + u32 ctrl = 0; + + writel(val, ioaddr + XGMAC_RSS_DATA); + ctrl |= idx << XGMAC_RSSIA_SHIFT; + ctrl |= is_key ? XGMAC_ADDRT : 0x0; + ctrl |= XGMAC_OB; + writel(ctrl, ioaddr + XGMAC_RSS_ADDR); + + return readl_poll_timeout(ioaddr + XGMAC_RSS_ADDR, ctrl, + !(ctrl & XGMAC_OB), 100, 10000); +} + +static int dwxgmac2_rss_configure(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq) +{ + void __iomem *ioaddr = hw->pcsr; + u32 *key = (u32 *)cfg->key; + int i, ret; + u32 value; + + value = readl(ioaddr + XGMAC_RSS_CTRL); + if (!cfg->enable) { + value &= ~XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; + } + + for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, *key++); + if (ret) + return ret; + } + + for (i = 0; i < ARRAY_SIZE(cfg->table); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, false, i, cfg->table[i]); + if (ret) + return ret; + } + + for (i = 0; i < num_rxq; i++) + dwxgmac2_map_mtl_to_dma(hw, i, XGMAC_QDDMACH); + + value |= XGMAC_UDP4TE | XGMAC_TCP4TE | XGMAC_IP2TE | XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; +} + +static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, + bool is_double) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(hash, ioaddr + XGMAC_VLAN_HASH_TABLE); + + if (hash) { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value |= XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value |= XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV; + if (is_double) { + value |= XGMAC_VLAN_EDVLP; + value |= XGMAC_VLAN_ESVL; + value |= XGMAC_VLAN_DOVLTC; + } + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } else { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value &= ~XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value = readl(ioaddr + XGMAC_VLAN_TAG); + + value &= ~(XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV); + value &= ~(XGMAC_VLAN_EDVLP | XGMAC_VLAN_ESVL); + value &= ~XGMAC_VLAN_DOVLTC; + value &= ~XGMAC_VLAN_VID; + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } +} + +struct dwxgmac3_error_desc { + bool valid; + const char *desc; + const char *detailed_desc; +}; + +#define STAT_OFF(field) offsetof(struct stmmac_safety_stats, field) + +static void dwxgmac3_log_error(struct net_device *ndev, u32 value, bool corr, + const char *module_name, + const struct dwxgmac3_error_desc *desc, + unsigned long field_offset, + struct stmmac_safety_stats *stats) +{ + unsigned long loc, mask; + u8 *bptr = (u8 *)stats; + unsigned long *ptr; + + ptr = (unsigned long *)(bptr + field_offset); + + mask = value; + for_each_set_bit(loc, &mask, 32) { + netdev_err(ndev, "Found %s error in %s: '%s: %s'\n", corr ? + "correctable" : "uncorrectable", module_name, + desc[loc].desc, desc[loc].detailed_desc); + + /* Update counters */ + ptr[loc]++; + } +} + +static const struct dwxgmac3_error_desc dwxgmac3_mac_errors[32]= { + { true, "ATPES", "Application Transmit Interface Parity Check Error" }, + { true, "DPES", "Descriptor Cache Data Path Parity Check Error" }, + { true, "TPES", "TSO Data Path Parity Check Error" }, + { true, "TSOPES", "TSO Header Data Path Parity Check Error" }, + { true, "MTPES", "MTL Data Path Parity Check Error" }, + { true, "MTSPES", "MTL TX Status Data Path Parity Check Error" }, + { true, "MTBUPES", "MAC TBU Data Path Parity Check Error" }, + { true, "MTFCPES", "MAC TFC Data Path Parity Check Error" }, + { true, "ARPES", "Application Receive Interface Data Path Parity Check Error" }, + { true, "MRWCPES", "MTL RWC Data Path Parity Check Error" }, + { true, "MRRCPES", "MTL RCC Data Path Parity Check Error" }, + { true, "CWPES", "CSR Write Data Path Parity Check Error" }, + { true, "ASRPES", "AXI Slave Read Data Path Parity Check Error" }, + { true, "TTES", "TX FSM Timeout Error" }, + { true, "RTES", "RX FSM Timeout Error" }, + { true, "CTES", "CSR FSM Timeout Error" }, + { true, "ATES", "APP FSM Timeout Error" }, + { true, "PTES", "PTP FSM Timeout Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { true, "MSTTES", "Master Read/Write Timeout Error" }, + { true, "SLVTES", "Slave Read/Write Timeout Error" }, + { true, "ATITES", "Application Timeout on ATI Interface Error" }, + { true, "ARITES", "Application Timeout on ARI Interface Error" }, + { true, "FSMPES", "FSM State Parity Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { true, "CPI", "Control Register Parity Check Error" }, +}; + +static void dwxgmac3_handle_mac_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + writel(value, ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MAC", + dwxgmac3_mac_errors, STAT_OFF(mac_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_mtl_errors[32]= { + { true, "TXCES", "MTL TX Memory Error" }, + { true, "TXAMS", "MTL TX Memory Address Mismatch Error" }, + { true, "TXUES", "MTL TX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "RXCES", "MTL RX Memory Error" }, + { true, "RXAMS", "MTL RX Memory Address Mismatch Error" }, + { true, "RXUES", "MTL RX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { true, "ECES", "MTL EST Memory Error" }, + { true, "EAMS", "MTL EST Memory Address Mismatch Error" }, + { true, "EUES", "MTL EST Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { true, "RPCES", "MTL RX Parser Memory Error" }, + { true, "RPAMS", "MTL RX Parser Memory Address Mismatch Error" }, + { true, "RPUES", "MTL RX Parser Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_mtl_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MTL_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_MTL_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MTL", + dwxgmac3_mtl_errors, STAT_OFF(mtl_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { + { true, "TCES", "DMA TSO Memory Error" }, + { true, "TAMS", "DMA TSO Memory Address Mismatch Error" }, + { true, "TUES", "DMA TSO Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "DCES", "DMA DCACHE Memory Error" }, + { true, "DAMS", "DMA DCACHE Address Mismatch Error" }, + { true, "DUES", "DMA DCACHE Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { false, "UNKNOWN", "Unknown Error" }, /* 8 */ + { false, "UNKNOWN", "Unknown Error" }, /* 9 */ + { false, "UNKNOWN", "Unknown Error" }, /* 10 */ + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { false, "UNKNOWN", "Unknown Error" }, /* 12 */ + { false, "UNKNOWN", "Unknown Error" }, /* 13 */ + { false, "UNKNOWN", "Unknown Error" }, /* 14 */ + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_dma_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_DMA_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "DMA", + dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); +} + +static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +{ + u32 value; + + if (!asp) + return -EINVAL; + + /* 1. Enable Safety Features */ + writel(0x0, ioaddr + XGMAC_MTL_ECC_CONTROL); + + /* 2. Enable MTL Safety Interrupts */ + value = readl(ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + value |= XGMAC_RPCEIE; /* RX Parser Memory Correctable Error */ + value |= XGMAC_ECEIE; /* EST Memory Correctable Error */ + value |= XGMAC_RXCEIE; /* RX Memory Correctable Error */ + value |= XGMAC_TXCEIE; /* TX Memory Correctable Error */ + writel(value, ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + + /* 3. Enable DMA Safety Interrupts */ + value = readl(ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + value |= XGMAC_DCEIE; /* Descriptor Cache Memory Correctable Error */ + value |= XGMAC_TCEIE; /* TSO Memory Correctable Error */ + writel(value, ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + + /* Only ECC Protection for External Memory feature is selected */ + if (asp <= 0x1) + return 0; + + /* 4. Enable Parity and Timeout for FSM */ + value = readl(ioaddr + XGMAC_MAC_FSM_CONTROL); + value |= XGMAC_PRTYEN; /* FSM Parity Feature */ + value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ + writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + + return 0; +} + +static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, + void __iomem *ioaddr, + unsigned int asp, + struct stmmac_safety_stats *stats) +{ + bool err, corr; + u32 mtl, dma; + int ret = 0; + + if (!asp) + return -EINVAL; + + mtl = readl(ioaddr + XGMAC_MTL_SAFETY_INT_STATUS); + dma = readl(ioaddr + XGMAC_DMA_SAFETY_INT_STATUS); + + err = (mtl & XGMAC_MCSIS) || (dma & XGMAC_MCSIS); + corr = false; + if (err) { + dwxgmac3_handle_mac_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = (mtl & (XGMAC_MEUIS | XGMAC_MECIS)) || + (dma & (XGMAC_MSUIS | XGMAC_MSCIS)); + corr = (mtl & XGMAC_MECIS) || (dma & XGMAC_MSCIS); + if (err) { + dwxgmac3_handle_mtl_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + corr = dma & XGMAC_DECIS; + if (err) { + dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + return ret; +} + +static const struct dwxgmac3_error { + const struct dwxgmac3_error_desc *desc; +} dwxgmac3_all_errors[] = { + { dwxgmac3_mac_errors }, + { dwxgmac3_mtl_errors }, + { dwxgmac3_dma_errors }, +}; + +static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, + int index, unsigned long *count, + const char **desc) +{ + int module = index / 32, offset = index % 32; + unsigned long *ptr = (unsigned long *)stats; + + if (module >= ARRAY_SIZE(dwxgmac3_all_errors)) + return -EINVAL; + if (!dwxgmac3_all_errors[module].desc[offset].valid) + return -EINVAL; + if (count) + *count = *(ptr + index); + if (desc) + *desc = dwxgmac3_all_errors[module].desc[offset].desc; + return 0; +} + +static int dwxgmac3_rxp_disable(void __iomem *ioaddr) +{ + u32 val = readl(ioaddr + XGMAC_MTL_OPMODE); + + val &= ~XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); + + return 0; +} + +static void dwxgmac3_rxp_enable(void __iomem *ioaddr) +{ + u32 val; + + val = readl(ioaddr + XGMAC_MTL_OPMODE); + val |= XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); +} + +static int dwxgmac3_rxp_update_single_entry(void __iomem *ioaddr, + struct stmmac_tc_entry *entry, + int pos) +{ + int ret, i; + + for (i = 0; i < (sizeof(entry->val) / sizeof(u32)); i++) { + int real_pos = pos * (sizeof(entry->val) / sizeof(u32)) + i; + u32 val; + + /* Wait for ready */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + + /* Write data */ + val = *((u32 *)&entry->val + i); + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_DATA); + + /* Write pos */ + val = real_pos & XGMAC_ADDR; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Write OP */ + val |= XGMAC_WRRDN; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Start Write */ + val |= XGMAC_STARTBUSY; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Wait for done */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + } + + return 0; +} + +static struct stmmac_tc_entry * +dwxgmac3_rxp_get_next_entry(struct stmmac_tc_entry *entries, + unsigned int count, u32 curr_prio) +{ + struct stmmac_tc_entry *entry; + u32 min_prio = ~0x0; + int i, min_prio_idx; + bool found = false; + + for (i = count - 1; i >= 0; i--) { + entry = &entries[i]; + + /* Do not update unused entries */ + if (!entry->in_use) + continue; + /* Do not update already updated entries (i.e. fragments) */ + if (entry->in_hw) + continue; + /* Let last entry be updated last */ + if (entry->is_last) + continue; + /* Do not return fragments */ + if (entry->is_frag) + continue; + /* Check if we already checked this prio */ + if (entry->prio < curr_prio) + continue; + /* Check if this is the minimum prio */ + if (entry->prio < min_prio) { + min_prio = entry->prio; + min_prio_idx = i; + found = true; + } + } + + if (found) + return &entries[min_prio_idx]; + return NULL; +} + +static int dwxgmac3_rxp_config(void __iomem *ioaddr, + struct stmmac_tc_entry *entries, + unsigned int count) +{ + struct stmmac_tc_entry *entry, *frag; + int i, ret, nve = 0; + u32 curr_prio = 0; + u32 old_val, val; + + /* Force disable RX */ + old_val = readl(ioaddr + XGMAC_RX_CONFIG); + val = old_val & ~XGMAC_CONFIG_RE; + writel(val, ioaddr + XGMAC_RX_CONFIG); + + /* Disable RX Parser */ + ret = dwxgmac3_rxp_disable(ioaddr); + if (ret) + goto re_enable; + + /* Set all entries as NOT in HW */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + entry->in_hw = false; + } + + /* Update entries by reverse order */ + while (1) { + entry = dwxgmac3_rxp_get_next_entry(entries, count, curr_prio); + if (!entry) + break; + + curr_prio = entry->prio; + frag = entry->frag_ptr; + + /* Set special fragment requirements */ + if (frag) { + entry->val.af = 0; + entry->val.rf = 0; + entry->val.nc = 1; + entry->val.ok_index = nve + 2; + } + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + entry->in_hw = true; + + if (frag && !frag->in_hw) { + ret = dwxgmac3_rxp_update_single_entry(ioaddr, frag, nve); + if (ret) + goto re_enable; + frag->table_pos = nve++; + frag->in_hw = true; + } + } + + if (!nve) + goto re_enable; + + /* Update all pass entry */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + if (!entry->is_last) + continue; + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + } + + /* Assume n. of parsable entries == n. of valid entries */ + val = (nve << 16) & XGMAC_NPE; + val |= nve & XGMAC_NVE; + writel(val, ioaddr + XGMAC_MTL_RXP_CONTROL_STATUS); + + /* Enable RX Parser */ + dwxgmac3_rxp_enable(ioaddr); + +re_enable: + /* Re-enable RX */ + writel(old_val, ioaddr + XGMAC_RX_CONFIG); + return ret; +} + const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, .rx_queue_prio = dwxgmac2_rx_queue_prio, - .tx_queue_prio = NULL, + .tx_queue_prio = dwxgmac2_tx_queue_prio, .rx_queue_routing = NULL, .prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms, - .set_mtl_tx_queue_weight = NULL, + .set_mtl_tx_queue_weight = dwxgmac2_set_mtl_tx_queue_weight, .map_mtl_to_dma = dwxgmac2_map_mtl_to_dma, .config_cbs = dwxgmac2_config_cbs, .dump_regs = NULL, @@ -362,7 +1026,13 @@ const struct stmmac_ops dwxgmac210_ops = { .pcs_get_adv_lp = NULL, .debug = NULL, .set_filter = dwxgmac2_set_filter, + .safety_feat_config = dwxgmac3_safety_feat_config, + .safety_feat_irq_status = dwxgmac3_safety_feat_irq_status, + .safety_feat_dump = dwxgmac3_safety_feat_dump, .set_mac_loopback = dwxgmac2_set_mac_loopback, + .rss_configure = dwxgmac2_rss_configure, + .update_vlan_hash = dwxgmac2_update_vlan_hash, + .rxp_config = dwxgmac3_rxp_config, }; int dwxgmac2_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index c4c45402b8f8..8c5dd6a36157 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -254,6 +254,34 @@ static void dwxgmac2_clear(struct dma_desc *p) p->des3 = 0; } +static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type) +{ + unsigned int rdes3 = le32_to_cpu(p->des3); + u32 ptype; + + if (rdes3 & XGMAC_RDES3_RSV) { + ptype = (rdes3 & XGMAC_RDES3_L34T) >> XGMAC_RDES3_L34T_SHIFT; + + switch (ptype) { + case XGMAC_L34T_IP4TCP: + case XGMAC_L34T_IP4UDP: + case XGMAC_L34T_IP6TCP: + case XGMAC_L34T_IP6UDP: + *type = PKT_HASH_TYPE_L4; + break; + default: + *type = PKT_HASH_TYPE_L3; + break; + } + + *hash = le32_to_cpu(p->des1); + return 0; + } + + return -EINVAL; +} + const struct stmmac_desc_ops dwxgmac210_desc_ops = { .tx_status = dwxgmac2_get_tx_status, .rx_status = dwxgmac2_get_rx_status, @@ -277,4 +305,5 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = { .get_addr = dwxgmac2_get_addr, .set_addr = dwxgmac2_set_addr, .clear = dwxgmac2_clear, + .get_rx_hash = dwxgmac2_get_rx_hash, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index a4f236e3593e..18cbf4ab4ad2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -356,12 +356,15 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12; dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11; dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6; + dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4; dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1; /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); + dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14; @@ -396,6 +399,13 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, ((hw_cap & XGMAC_HWFEAT_TXQCNT) >> 6) + 1; dma_cap->number_rx_queues = ((hw_cap & XGMAC_HWFEAT_RXQCNT) >> 0) + 1; + + /* MAC HW feature 3 */ + hw_cap = readl(ioaddr + XGMAC_HW_FEATURE3); + dma_cap->asp = (hw_cap & XGMAC_HWFEAT_ASP) >> 14; + dma_cap->frpes = (hw_cap & XGMAC_HWFEAT_FRPES) >> 11; + dma_cap->frpbs = (hw_cap & XGMAC_HWFEAT_FRPPB) >> 9; + dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3; } static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 6c61b753b55e..3af2e5015245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -201,7 +201,7 @@ static const struct stmmac_hwif_entry { .min_id = DWXGMAC_CORE_2_10, .regs = { .ptp_off = PTP_XGMAC_OFFSET, - .mmc_off = 0, + .mmc_off = MMC_XGMAC_OFFSET, }, .desc = &dwxgmac210_desc_ops, .dma = &dwxgmac210_dma_ops, @@ -209,7 +209,7 @@ static const struct stmmac_hwif_entry { .hwtimestamp = &stmmac_ptp, .mode = NULL, .tc = &dwmac510_tc_ops, - .mmc = NULL, + .mmc = &dwxgmac_mmc_ops, .setup = dwxgmac2_setup, .quirks = NULL, }, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 278c0dbec9d9..52fc2344b066 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -86,6 +86,9 @@ struct stmmac_desc_ops { void (*set_addr)(struct dma_desc *p, dma_addr_t addr); /* clear descriptor */ void (*clear)(struct dma_desc *p); + /* RSS */ + int (*get_rx_hash)(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type); }; #define stmmac_init_rx_desc(__priv, __args...) \ @@ -136,6 +139,8 @@ struct stmmac_desc_ops { stmmac_do_void_callback(__priv, desc, set_addr, __args) #define stmmac_clear_desc(__priv, __args...) \ stmmac_do_void_callback(__priv, desc, clear, __args) +#define stmmac_get_rx_hash(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_hash, __args) struct stmmac_dma_cfg; struct dma_features; @@ -249,6 +254,7 @@ struct rgmii_adv; struct stmmac_safety_stats; struct stmmac_tc_entry; struct stmmac_pps_cfg; +struct stmmac_rss; /* Helpers to program the MAC core */ struct stmmac_ops { @@ -327,6 +333,12 @@ struct stmmac_ops { u32 sub_second_inc, u32 systime_flags); /* Loopback for selftests */ void (*set_mac_loopback)(void __iomem *ioaddr, bool enable); + /* RSS */ + int (*rss_configure)(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq); + /* VLAN */ + void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash, + bool is_double); }; #define stmmac_core_init(__priv, __args...) \ @@ -397,6 +409,10 @@ struct stmmac_ops { stmmac_do_callback(__priv, mac, flex_pps_config, __args) #define stmmac_set_mac_loopback(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args) +#define stmmac_rss_configure(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rss_configure, __args) +#define stmmac_update_vlan_hash(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args) /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { @@ -503,6 +519,7 @@ extern const struct stmmac_ops dwxgmac210_ops; extern const struct stmmac_dma_ops dwxgmac210_dma_ops; extern const struct stmmac_desc_ops dwxgmac210_desc_ops; extern const struct stmmac_mmc_ops dwmac_mmc_ops; +extern const struct stmmac_mmc_ops dwxgmac_mmc_ops; #define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index 3587ceb9faf5..a0c05925883e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -24,6 +24,7 @@ #define MMC_GMAC4_OFFSET 0x700 #define MMC_GMAC3_X_OFFSET 0x100 +#define MMC_XGMAC_OFFSET 0x800 struct stmmac_counters { unsigned int mmc_tx_octetcount_gb; @@ -116,6 +117,14 @@ struct stmmac_counters { unsigned int mmc_rx_tcp_err_octets; unsigned int mmc_rx_icmp_gd_octets; unsigned int mmc_rx_icmp_err_octets; + + /* FPE */ + unsigned int mmc_tx_fpe_fragment_cntr; + unsigned int mmc_tx_hold_req_cntr; + unsigned int mmc_rx_packet_assembly_err_cntr; + unsigned int mmc_rx_packet_smd_err_cntr; + unsigned int mmc_rx_packet_assembly_ok_cntr; + unsigned int mmc_rx_fpe_fragment_cntr; }; #endif /* __MMC_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index a471db6d7b11..a223584f5f9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -119,6 +119,64 @@ #define MMC_RX_ICMP_GD_OCTETS 0x180 #define MMC_RX_ICMP_ERR_OCTETS 0x184 +/* XGMAC MMC Registers */ +#define MMC_XGMAC_TX_OCTET_GB 0x14 +#define MMC_XGMAC_TX_PKT_GB 0x1c +#define MMC_XGMAC_TX_BROAD_PKT_G 0x24 +#define MMC_XGMAC_TX_MULTI_PKT_G 0x2c +#define MMC_XGMAC_TX_64OCT_GB 0x34 +#define MMC_XGMAC_TX_65OCT_GB 0x3c +#define MMC_XGMAC_TX_128OCT_GB 0x44 +#define MMC_XGMAC_TX_256OCT_GB 0x4c +#define MMC_XGMAC_TX_512OCT_GB 0x54 +#define MMC_XGMAC_TX_1024OCT_GB 0x5c +#define MMC_XGMAC_TX_UNI_PKT_GB 0x64 +#define MMC_XGMAC_TX_MULTI_PKT_GB 0x6c +#define MMC_XGMAC_TX_BROAD_PKT_GB 0x74 +#define MMC_XGMAC_TX_UNDER 0x7c +#define MMC_XGMAC_TX_OCTET_G 0x84 +#define MMC_XGMAC_TX_PKT_G 0x8c +#define MMC_XGMAC_TX_PAUSE 0x94 +#define MMC_XGMAC_TX_VLAN_PKT_G 0x9c +#define MMC_XGMAC_TX_LPI_USEC 0xa4 +#define MMC_XGMAC_TX_LPI_TRAN 0xa8 + +#define MMC_XGMAC_RX_PKT_GB 0x100 +#define MMC_XGMAC_RX_OCTET_GB 0x108 +#define MMC_XGMAC_RX_OCTET_G 0x110 +#define MMC_XGMAC_RX_BROAD_PKT_G 0x118 +#define MMC_XGMAC_RX_MULTI_PKT_G 0x120 +#define MMC_XGMAC_RX_CRC_ERR 0x128 +#define MMC_XGMAC_RX_RUNT_ERR 0x130 +#define MMC_XGMAC_RX_JABBER_ERR 0x134 +#define MMC_XGMAC_RX_UNDER 0x138 +#define MMC_XGMAC_RX_OVER 0x13c +#define MMC_XGMAC_RX_64OCT_GB 0x140 +#define MMC_XGMAC_RX_65OCT_GB 0x148 +#define MMC_XGMAC_RX_128OCT_GB 0x150 +#define MMC_XGMAC_RX_256OCT_GB 0x158 +#define MMC_XGMAC_RX_512OCT_GB 0x160 +#define MMC_XGMAC_RX_1024OCT_GB 0x168 +#define MMC_XGMAC_RX_UNI_PKT_G 0x170 +#define MMC_XGMAC_RX_LENGTH_ERR 0x178 +#define MMC_XGMAC_RX_RANGE 0x180 +#define MMC_XGMAC_RX_PAUSE 0x188 +#define MMC_XGMAC_RX_FIFOOVER_PKT 0x190 +#define MMC_XGMAC_RX_VLAN_PKT_GB 0x198 +#define MMC_XGMAC_RX_WATCHDOG_ERR 0x1a0 +#define MMC_XGMAC_RX_LPI_USEC 0x1a4 +#define MMC_XGMAC_RX_LPI_TRAN 0x1a8 +#define MMC_XGMAC_RX_DISCARD_PKT_GB 0x1ac +#define MMC_XGMAC_RX_DISCARD_OCT_GB 0x1b4 +#define MMC_XGMAC_RX_ALIGN_ERR_PKT 0x1bc + +#define MMC_XGMAC_TX_FPE_FRAG 0x208 +#define MMC_XGMAC_TX_HOLD_REQ 0x20c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR 0x228 +#define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 +#define MMC_XGMAC_RX_FPE_FRAG 0x234 + static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) { u32 value = readl(mmcaddr + MMC_CNTRL); @@ -263,3 +321,137 @@ const struct stmmac_mmc_ops dwmac_mmc_ops = { .intr_all_mask = dwmac_mmc_intr_all_mask, .read = dwmac_mmc_read, }; + +static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) +{ + u32 value = readl(mmcaddr + MMC_CNTRL); + + value |= (mode & 0x3F); + + writel(value, mmcaddr + MMC_CNTRL); +} + +static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) +{ + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK); +} + +static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest) +{ + u64 tmp = 0; + + tmp += readl(addr + reg); + tmp += ((u64 )readl(addr + reg + 0x4)) << 32; + if (tmp > GENMASK(31, 0)) + *dest = ~0x0; + else + *dest = *dest + tmp; +} + +/* This reads the MAC core counters (if actaully supported). + * by default the MMC core is programmed to reset each + * counter after a read. So all the field of the mmc struct + * have to be incremented. + */ +static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc) +{ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_GB, + &mmc->mmc_tx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_GB, + &mmc->mmc_tx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_G, + &mmc->mmc_tx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_G, + &mmc->mmc_tx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_64OCT_GB, + &mmc->mmc_tx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_65OCT_GB, + &mmc->mmc_tx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_128OCT_GB, + &mmc->mmc_tx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_256OCT_GB, + &mmc->mmc_tx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_512OCT_GB, + &mmc->mmc_tx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_1024OCT_GB, + &mmc->mmc_tx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNI_PKT_GB, + &mmc->mmc_tx_unicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_GB, + &mmc->mmc_tx_multicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_GB, + &mmc->mmc_tx_broadcast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNDER, + &mmc->mmc_tx_underflow_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_G, + &mmc->mmc_tx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_G, + &mmc->mmc_tx_framecount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PAUSE, + &mmc->mmc_tx_pause_frame); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_VLAN_PKT_G, + &mmc->mmc_tx_vlan_frame_g); + + /* MMC RX counter registers */ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PKT_GB, + &mmc->mmc_rx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_GB, + &mmc->mmc_rx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_G, + &mmc->mmc_rx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_BROAD_PKT_G, + &mmc->mmc_rx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_MULTI_PKT_G, + &mmc->mmc_rx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + mmc->mmc_rx_run_error += readl(mmcaddr + MMC_XGMAC_RX_RUNT_ERR); + mmc->mmc_rx_jabber_error += readl(mmcaddr + MMC_XGMAC_RX_JABBER_ERR); + mmc->mmc_rx_undersize_g += readl(mmcaddr + MMC_XGMAC_RX_UNDER); + mmc->mmc_rx_oversize_g += readl(mmcaddr + MMC_XGMAC_RX_OVER); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_64OCT_GB, + &mmc->mmc_rx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_65OCT_GB, + &mmc->mmc_rx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_128OCT_GB, + &mmc->mmc_rx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_256OCT_GB, + &mmc->mmc_rx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_512OCT_GB, + &mmc->mmc_rx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_1024OCT_GB, + &mmc->mmc_rx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UNI_PKT_G, + &mmc->mmc_rx_unicast_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_LENGTH_ERR, + &mmc->mmc_rx_length_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_RANGE, + &mmc->mmc_rx_autofrangetype); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PAUSE, + &mmc->mmc_rx_pause_frames); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_FIFOOVER_PKT, + &mmc->mmc_rx_fifo_overflow); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_VLAN_PKT_GB, + &mmc->mmc_rx_vlan_frames_gb); + mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_XGMAC_RX_WATCHDOG_ERR); + + mmc->mmc_tx_fpe_fragment_cntr += readl(mmcaddr + MMC_XGMAC_TX_FPE_FRAG); + mmc->mmc_tx_hold_req_cntr += readl(mmcaddr + MMC_XGMAC_TX_HOLD_REQ); + mmc->mmc_rx_packet_assembly_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_ERR); + mmc->mmc_rx_packet_smd_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_SMD_ERR); + mmc->mmc_rx_packet_assembly_ok_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_OK); + mmc->mmc_rx_fpe_fragment_cntr += + readl(mmcaddr + MMC_XGMAC_RX_FPE_FRAG); +} + +const struct stmmac_mmc_ops dwxgmac_mmc_ops = { + .ctrl = dwxgmac_mmc_ctrl, + .intr_all_mask = dwxgmac_mmc_intr_all_mask, + .read = dwxgmac_mmc_read, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5cd966c154f3..80276587048a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -13,6 +13,7 @@ #define DRV_MODULE_VERSION "Jan_2016" #include <linux/clk.h> +#include <linux/if_vlan.h> #include <linux/stmmac.h> #include <linux/phylink.h> #include <linux/pci.h> @@ -113,6 +114,12 @@ struct stmmac_pps_cfg { struct timespec64 period; }; +struct stmmac_rss { + int enable; + u8 key[STMMAC_RSS_HASH_KEY_SIZE]; + u32 table[STMMAC_RSS_MAX_TABLE_SIZE]; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames; @@ -185,11 +192,10 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; - struct dentry *dbgfs_rings_status; - struct dentry *dbgfs_dma_cap; #endif unsigned long state; @@ -203,6 +209,9 @@ struct stmmac_priv { /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; + + /* Receive Side Scaling */ + struct stmmac_rss rss; }; enum stmmac_state { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 6efb66820d4c..2423160ab582 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -243,6 +243,12 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_rx_tcp_err_octets), STMMAC_MMC_STAT(mmc_rx_icmp_gd_octets), STMMAC_MMC_STAT(mmc_rx_icmp_err_octets), + STMMAC_MMC_STAT(mmc_tx_fpe_fragment_cntr), + STMMAC_MMC_STAT(mmc_tx_hold_req_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_smd_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_ok_cntr), + STMMAC_MMC_STAT(mmc_rx_fpe_fragment_cntr), }; #define STMMAC_MMC_STATS_LEN ARRAY_SIZE(stmmac_mmc) @@ -758,6 +764,76 @@ static int stmmac_set_coalesce(struct net_device *dev, return 0; } +static int stmmac_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *rxnfc, u32 *rule_locs) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + switch (rxnfc->cmd) { + case ETHTOOL_GRXRINGS: + rxnfc->data = priv->plat->rx_queues_to_use; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static u32 stmmac_get_rxfh_key_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return sizeof(priv->rss.key); +} + +static u32 stmmac_get_rxfh_indir_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return ARRAY_SIZE(priv->rss.table); +} + +static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + indir[i] = priv->rss.table[i]; + } + + if (key) + memcpy(key, priv->rss.key, sizeof(priv->rss.key)); + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = indir[i]; + } + + if (key) + memcpy(priv->rss.key, key, sizeof(priv->rss.key)); + + return stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + static int stmmac_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { @@ -849,6 +925,11 @@ static const struct ethtool_ops stmmac_ethtool_ops = { .get_eee = stmmac_ethtool_op_get_eee, .set_eee = stmmac_ethtool_op_set_eee, .get_sset_count = stmmac_get_sset_count, + .get_rxnfc = stmmac_get_rxnfc, + .get_rxfh_key_size = stmmac_get_rxfh_key_size, + .get_rxfh_indir_size = stmmac_get_rxfh_indir_size, + .get_rxfh = stmmac_get_rxfh, + .set_rxfh = stmmac_set_rxfh, .get_ts_info = stmmac_get_ts_info, .get_coalesce = stmmac_get_coalesce, .set_coalesce = stmmac_set_coalesce, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c7c9e5f162e6..06a63df1c2c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -105,7 +105,7 @@ MODULE_PARM_DESC(chain_mode, "To use chain instead of ring mode"); static irqreturn_t stmmac_interrupt(int irq, void *dev_id); #ifdef CONFIG_DEBUG_FS -static int stmmac_init_fs(struct net_device *dev); +static void stmmac_init_fs(struct net_device *dev); static void stmmac_exit_fs(struct net_device *dev); #endif @@ -814,20 +814,15 @@ static void stmmac_validate(struct phylink_config *config, phylink_set(mac_supported, 10baseT_Full); phylink_set(mac_supported, 100baseT_Half); phylink_set(mac_supported, 100baseT_Full); + phylink_set(mac_supported, 1000baseT_Half); + phylink_set(mac_supported, 1000baseT_Full); + phylink_set(mac_supported, 1000baseKX_Full); phylink_set(mac_supported, Autoneg); phylink_set(mac_supported, Pause); phylink_set(mac_supported, Asym_Pause); phylink_set_port_modes(mac_supported); - if (priv->plat->has_gmac || - priv->plat->has_gmac4 || - priv->plat->has_xgmac) { - phylink_set(mac_supported, 1000baseT_Half); - phylink_set(mac_supported, 1000baseT_Full); - phylink_set(mac_supported, 1000baseKX_Full); - } - /* Cut down 1G if asked to */ if ((max_speed > 0) && (max_speed < 1000)) { phylink_set(mask, 1000baseT_Full); @@ -1295,6 +1290,8 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) "(%s) dma_rx_phy=0x%08x\n", __func__, (u32)rx_q->dma_rx_phy); + stmmac_clear_rx_descriptors(priv, queue); + for (i = 0; i < DMA_RX_SIZE; i++) { struct dma_desc *p; @@ -1312,8 +1309,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) rx_q->cur_rx = 0; rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE); - stmmac_clear_rx_descriptors(priv, queue); - /* Setup the chained descriptor addresses */ if (priv->mode == STMMAC_CHAIN_MODE) { if (priv->extend_desc) @@ -1555,9 +1550,8 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv) goto err_dma; } - rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE, - sizeof(*rx_q->buf_pool), - GFP_KERNEL); + rx_q->buf_pool = kcalloc(DMA_RX_SIZE, sizeof(*rx_q->buf_pool), + GFP_KERNEL); if (!rx_q->buf_pool) goto err_dma; @@ -1608,15 +1602,15 @@ static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv) tx_q->queue_index = queue; tx_q->priv_data = priv; - tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE, - sizeof(*tx_q->tx_skbuff_dma), - GFP_KERNEL); + tx_q->tx_skbuff_dma = kcalloc(DMA_TX_SIZE, + sizeof(*tx_q->tx_skbuff_dma), + GFP_KERNEL); if (!tx_q->tx_skbuff_dma) goto err_dma; - tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE, - sizeof(struct sk_buff *), - GFP_KERNEL); + tx_q->tx_skbuff = kcalloc(DMA_TX_SIZE, + sizeof(struct sk_buff *), + GFP_KERNEL); if (!tx_q->tx_skbuff) goto err_dma; @@ -2423,6 +2417,22 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) } } +static void stmmac_mac_config_rss(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.rssen || !priv->plat->rss_en) { + priv->rss.enable = false; + return; + } + + if (priv->dev->features & NETIF_F_RXHASH) + priv->rss.enable = true; + else + priv->rss.enable = false; + + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2467,6 +2477,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set RX routing */ if (rx_queues_count > 1) stmmac_mac_config_rx_queues_routing(priv); + + /* Receive Side Scaling */ + if (rx_queues_count > 1) + stmmac_mac_config_rss(priv); } static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) @@ -3277,9 +3291,11 @@ static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q) static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - int dirty = stmmac_rx_dirty(priv, queue); + int len, dirty = stmmac_rx_dirty(priv, queue); unsigned int entry = rx_q->dirty_rx; + len = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; + while (dirty-- > 0) { struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry]; struct dma_desc *p; @@ -3297,6 +3313,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) } buf->addr = page_pool_get_dma_addr(buf->page); + + /* Sync whole allocation to device. This will invalidate old + * data. + */ + dma_sync_single_for_device(priv->device, buf->addr, len, + DMA_FROM_DEVICE); + stmmac_set_desc_addr(priv, p, buf->addr); stmmac_refill_desc3(priv, rx_q, p); @@ -3382,9 +3405,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) priv->dev->stats.rx_errors++; buf->page = NULL; } else { + enum pkt_hash_types hash_type; struct sk_buff *skb; - int frame_len; unsigned int des; + int frame_len; + u32 hash; stmmac_get_desc_addr(priv, p, &des); frame_len = stmmac_get_rx_frame_len(priv, p, coe); @@ -3431,8 +3456,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) skb_copy_to_linear_data(skb, page_address(buf->page), frame_len); skb_put(skb, frame_len); - dma_sync_single_for_device(priv->device, buf->addr, - frame_len, DMA_FROM_DEVICE); if (netif_msg_pktdata(priv)) { netdev_dbg(priv->dev, "frame received (%dbytes)", @@ -3451,6 +3474,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else skb->ip_summed = CHECKSUM_UNNECESSARY; + if (!stmmac_get_rx_hash(priv, p, &hash, &hash_type)) + skb_set_hash(skb, hash, hash_type); + + skb_record_rx_queue(skb, queue); napi_gro_receive(&ch->rx_napi, skb); /* Data payload copied into SKB, page ready for recycle */ @@ -3961,54 +3988,102 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) } DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap); -static int stmmac_init_fs(struct net_device *dev) +static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); - if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) { - netdev_err(priv->dev, "ERROR failed to create debugfs directory\n"); + /* Entry to report DMA RX/TX rings */ + debugfs_create_file("descriptors_status", 0444, priv->dbgfs_dir, dev, + &stmmac_rings_status_fops); - return -ENOMEM; + /* Entry to report the DMA HW features */ + debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, + &stmmac_dma_cap_fops); +} + +static void stmmac_exit_fs(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + debugfs_remove_recursive(priv->dbgfs_dir); +} +#endif /* CONFIG_DEBUG_FS */ + +static u32 stmmac_vid_crc32_le(__le16 vid_le) +{ + unsigned char *data = (unsigned char *)&vid_le; + unsigned char data_byte = 0; + u32 crc = ~0x0; + u32 temp = 0; + int i, bits; + + bits = get_bitmask_order(VLAN_VID_MASK); + for (i = 0; i < bits; i++) { + if ((i % 8) == 0) + data_byte = data[i / 8]; + + temp = ((crc & 1) ^ data_byte) & 1; + crc >>= 1; + data_byte >>= 1; + + if (temp) + crc ^= 0xedb88320; } - /* Entry to report DMA RX/TX rings */ - priv->dbgfs_rings_status = - debugfs_create_file("descriptors_status", 0444, - priv->dbgfs_dir, dev, - &stmmac_rings_status_fops); + return crc; +} - if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) { - netdev_err(priv->dev, "ERROR creating stmmac ring debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); +static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) +{ + u32 crc, hash = 0; + u16 vid; - return -ENOMEM; + for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) { + __le16 vid_le = cpu_to_le16(vid); + crc = bitrev32(~stmmac_vid_crc32_le(vid_le)) >> 28; + hash |= (1 << crc); } - /* Entry to report the DMA HW features */ - priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", 0444, - priv->dbgfs_dir, - dev, &stmmac_dma_cap_fops); + return stmmac_update_vlan_hash(priv, priv->hw, hash, is_double); +} - if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) { - netdev_err(priv->dev, "ERROR creating stmmac MMC debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); +static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) +{ + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; + int ret; - return -ENOMEM; + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; + + set_bit(vid, priv->active_vlans); + ret = stmmac_vlan_update(priv, is_double); + if (ret) { + clear_bit(vid, priv->active_vlans); + return ret; } - return 0; + return ret; } -static void stmmac_exit_fs(struct net_device *dev) +static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { - struct stmmac_priv *priv = netdev_priv(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; - debugfs_remove_recursive(priv->dbgfs_dir); + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; + + clear_bit(vid, priv->active_vlans); + return stmmac_vlan_update(priv, is_double); } -#endif /* CONFIG_DEBUG_FS */ static const struct net_device_ops stmmac_netdev_ops = { .ndo_open = stmmac_open, @@ -4026,6 +4101,8 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_poll_controller = stmmac_poll_controller, #endif .ndo_set_mac_address = stmmac_set_mac_address, + .ndo_vlan_rx_add_vid = stmmac_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = stmmac_vlan_rx_kill_vid, }; static void stmmac_reset_subtask(struct stmmac_priv *priv) @@ -4174,8 +4251,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; - u32 queue, maxq; - int ret = 0; + u32 queue, rxq, maxq; + int i, ret = 0; ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES); @@ -4280,9 +4357,22 @@ int stmmac_dvr_probe(struct device *device, #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; + if (priv->dma_cap.vlhash) { + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER; + } #endif priv->msg_enable = netif_msg_init(debug, default_msg_level); + /* Initialize RSS */ + rxq = priv->plat->rx_queues_to_use; + netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key)); + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq); + + if (priv->dma_cap.rssen && priv->plat->rss_en) + ndev->features |= NETIF_F_RXHASH; + /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) @@ -4319,8 +4409,9 @@ int stmmac_dvr_probe(struct device *device, NAPI_POLL_WEIGHT); } if (queue < priv->plat->tx_queues_to_use) { - netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx, - NAPI_POLL_WEIGHT); + netif_tx_napi_add(ndev, &ch->tx_napi, + stmmac_napi_poll_tx, + NAPI_POLL_WEIGHT); } } @@ -4366,10 +4457,7 @@ int stmmac_dvr_probe(struct device *device, } #ifdef CONFIG_DEBUG_FS - ret = stmmac_init_fs(ndev); - if (ret < 0) - netdev_warn(priv->dev, "%s: failed debugFS registration\n", - __func__); + stmmac_init_fs(ndev); #endif return ret; @@ -4615,16 +4703,8 @@ static int __init stmmac_init(void) { #ifdef CONFIG_DEBUG_FS /* Create debugfs main directory if it doesn't exist yet */ - if (!stmmac_fs_dir) { + if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); - - if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) { - pr_err("ERROR %s, debugfs create directory failed\n", - STMMAC_RESOURCE_NAME); - - return -ENOMEM; - } - } #endif return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0f3e6ce7f6ec..eaf8f08f2e91 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -376,6 +376,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) return ERR_PTR(-ENOMEM); *mac = of_get_mac_address(np); + if (IS_ERR(*mac)) { + if (PTR_ERR(*mac) == -EPROBE_DEFER) + return ERR_CAST(*mac); + + *mac = NULL; + } + plat->interface = of_get_phy_mode(np); /* Some wrapper drivers still rely on phy_node. Let's save it while diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index a97b1ea76438..abab84f2ef8b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -11,8 +11,10 @@ #include <linux/ip.h> #include <linux/phy.h> #include <linux/udp.h> +#include <net/pkt_cls.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> #include "stmmac.h" struct stmmachdr { @@ -229,7 +231,7 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, goto out; } if (tpriv->packet->src) { - if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr)) + if (!ether_addr_equal(ehdr->h_source, tpriv->packet->src)) goto out; } @@ -700,6 +702,308 @@ cleanup: return ret; } +static int stmmac_test_rss(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + + if (!priv->dma_cap.rssen || !priv->rss.enable) + return -EOPNOTSUPP; + + attr.dst = priv->dev->dev_addr; + attr.exp_hash = true; + attr.sport = 0x321; + attr.dport = 0x123; + + return __stmmac_test_loopback(priv, &attr); +} + +static int stmmac_test_vlan_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct stmmac_test_priv *tpriv = pt->af_packet_priv; + struct stmmachdr *shdr; + struct ethhdr *ehdr; + struct udphdr *uhdr; + struct iphdr *ihdr; + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + goto out; + + if (skb_linearize(skb)) + goto out; + if (skb_headlen(skb) < (STMMAC_TEST_PKT_SIZE - ETH_HLEN)) + goto out; + + ehdr = (struct ethhdr *)skb_mac_header(skb); + if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst)) + goto out; + + ihdr = ip_hdr(skb); + if (tpriv->double_vlan) + ihdr = (struct iphdr *)(skb_network_header(skb) + 4); + if (ihdr->protocol != IPPROTO_UDP) + goto out; + + uhdr = (struct udphdr *)((u8 *)ihdr + 4 * ihdr->ihl); + if (uhdr->dest != htons(tpriv->packet->dport)) + goto out; + + shdr = (struct stmmachdr *)((u8 *)uhdr + sizeof(*uhdr)); + if (shdr->magic != cpu_to_be64(STMMAC_TEST_PKT_MAGIC)) + goto out; + + tpriv->ok = true; + complete(&tpriv->comp); + +out: + kfree_skb(skb); + return 0; +} + +static int stmmac_test_vlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_IP); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 1; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = !tpriv->ok; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -1; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int stmmac_test_dvlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + tpriv->double_vlan = true; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_8021Q); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 2; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = !tpriv->ok; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -1; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +#ifdef CONFIG_NET_CLS_ACT +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + unsigned char addr[ETH_ALEN] = {0xde, 0xad, 0xbe, 0xef, 0x00, 0x00}; + struct tc_cls_u32_offload cls_u32 = { }; + struct stmmac_packet_attrs attr = { }; + struct tc_action **actions, *act; + struct tc_u32_sel *sel; + struct tcf_exts *exts; + int ret, i, nk = 1; + + if (!tc_can_offload(priv->dev)) + return -EOPNOTSUPP; + if (!priv->dma_cap.frpsel) + return -EOPNOTSUPP; + + sel = kzalloc(sizeof(*sel) + nk * sizeof(struct tc_u32_key), GFP_KERNEL); + if (!sel) + return -ENOMEM; + + exts = kzalloc(sizeof(*exts), GFP_KERNEL); + if (!exts) { + ret = -ENOMEM; + goto cleanup_sel; + } + + actions = kzalloc(nk * sizeof(*actions), GFP_KERNEL); + if (!actions) { + ret = -ENOMEM; + goto cleanup_exts; + } + + act = kzalloc(nk * sizeof(*act), GFP_KERNEL); + if (!act) { + ret = -ENOMEM; + goto cleanup_actions; + } + + cls_u32.command = TC_CLSU32_NEW_KNODE; + cls_u32.common.chain_index = 0; + cls_u32.common.protocol = htons(ETH_P_ALL); + cls_u32.knode.exts = exts; + cls_u32.knode.sel = sel; + cls_u32.knode.handle = 0x123; + + exts->nr_actions = nk; + exts->actions = actions; + for (i = 0; i < nk; i++) { + struct tcf_gact *gact = to_gact(&act[i]); + + actions[i] = &act[i]; + gact->tcf_action = TC_ACT_SHOT; + } + + sel->nkeys = nk; + sel->offshift = 0; + sel->keys[0].off = 6; + sel->keys[0].val = htonl(0xdeadbeef); + sel->keys[0].mask = ~0x0; + + ret = stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + if (ret) + goto cleanup_act; + + attr.dst = priv->dev->dev_addr; + attr.src = addr; + + ret = __stmmac_test_loopback(priv, &attr); + ret = !ret; /* Shall NOT receive packet */ + + cls_u32.command = TC_CLSU32_DELETE_KNODE; + stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + +cleanup_act: + kfree(act); +cleanup_actions: + kfree(actions); +cleanup_exts: + kfree(exts); +cleanup_sel: + kfree(sel); + return ret; +} +#else +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + return -EOPNOTSUPP; +} +#endif + #define STMMAC_LOOPBACK_NONE 0 #define STMMAC_LOOPBACK_MAC 1 #define STMMAC_LOOPBACK_PHY 2 @@ -745,6 +1049,22 @@ static const struct stmmac_test { .name = "Flow Control ", .lb = STMMAC_LOOPBACK_PHY, .fn = stmmac_test_flowctrl, + }, { + .name = "RSS ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rss, + }, { + .name = "VLAN Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_vlanfilt, + }, { + .name = "Double VLAN Filtering", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_dvlanfilt, + }, { + .name = "Flexible RX Parser ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rxp, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 58ea18af9813..37c0bc699cd9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -37,7 +37,7 @@ static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv, entry = &priv->tc_entries[i]; if (!entry->in_use && !first && free) first = entry; - if (entry->handle == loc && !free) + if ((entry->handle == loc) && !free && !entry->is_frag) dup = entry; } diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 5b196ebfed49..0f346761a2b2 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -788,6 +788,7 @@ spider_net_release_tx_chain(struct spider_net_card *card, int brutal) /* fallthrough, if we release the descriptors * brutally (then we don't care about * SPIDER_NET_DESCR_CARDOWNED) */ + /* Fall through */ case SPIDER_NET_DESCR_RESPONSE_ERROR: case SPIDER_NET_DESCR_PROTECTION_ERROR: diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig index 2f354ba029a6..cd0a8f46e7c6 100644 --- a/drivers/net/ethernet/xscale/Kconfig +++ b/drivers/net/ethernet/xscale/Kconfig @@ -13,7 +13,7 @@ config NET_VENDOR_XSCALE Note that the answer to this question does not directly affect the kernel: saying N will just cause the configurator to skip all - the questions about XSacle IXP devices. If you say Y, you will be + the questions about XScale IXP devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_XSCALE diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index daab2c07d891..9303aeb2595f 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -500,8 +500,9 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat) } break; } + /* fall through */ - default: /* fall through */ + default: if (bc->hdlctx.calibrate <= 0) return 0; i = min_t(int, cnt, bc->hdlctx.calibrate); diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 442018ccd65e..c5bfa19ddb93 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -25,6 +25,7 @@ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/jiffies.h> +#include <linux/refcount.h> #include <net/ax25.h> @@ -70,7 +71,7 @@ struct mkiss { #define CRC_MODE_FLEX_TEST 3 #define CRC_MODE_SMACK_TEST 4 - atomic_t refcnt; + refcount_t refcnt; struct completion dead; }; @@ -668,7 +669,7 @@ static struct mkiss *mkiss_get(struct tty_struct *tty) read_lock(&disc_data_lock); ax = tty->disc_data; if (ax) - atomic_inc(&ax->refcnt); + refcount_inc(&ax->refcnt); read_unlock(&disc_data_lock); return ax; @@ -676,7 +677,7 @@ static struct mkiss *mkiss_get(struct tty_struct *tty) static void mkiss_put(struct mkiss *ax) { - if (atomic_dec_and_test(&ax->refcnt)) + if (refcount_dec_and_test(&ax->refcnt)) complete(&ax->dead); } @@ -704,7 +705,7 @@ static int mkiss_open(struct tty_struct *tty) ax->dev = dev; spin_lock_init(&ax->buflock); - atomic_set(&ax->refcnt, 1); + refcount_set(&ax->refcnt, 1); init_completion(&ax->dead); ax->tty = tty; @@ -784,7 +785,7 @@ static void mkiss_close(struct tty_struct *tty) * We have now ensured that nobody can start using ap from now on, but * we have to wait for all existing users to finish. */ - if (!atomic_dec_and_test(&ax->refcnt)) + if (!refcount_dec_and_test(&ax->refcnt)) wait_for_completion(&ax->dead); /* * Halt the transmit queue so that a new transmit cannot scribble diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index c9392d70e639..5a37514e4234 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1158,23 +1158,16 @@ static int adf7242_stats_show(struct seq_file *file, void *offset) return 0; } -static int adf7242_debugfs_init(struct adf7242_local *lp) +static void adf7242_debugfs_init(struct adf7242_local *lp) { char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "adf7242-"; - struct dentry *stats; strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); lp->debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (IS_ERR_OR_NULL(lp->debugfs_root)) - return PTR_ERR_OR_ZERO(lp->debugfs_root); - stats = debugfs_create_devm_seqfile(&lp->spi->dev, "status", - lp->debugfs_root, - adf7242_stats_show); - return PTR_ERR_OR_ZERO(stats); - - return 0; + debugfs_create_devm_seqfile(&lp->spi->dev, "status", lp->debugfs_root, + adf7242_stats_show); } static const s32 adf7242_powers[] = { diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 595cf7e2a651..7d67f41387f5 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -1626,24 +1626,16 @@ static int at86rf230_stats_show(struct seq_file *file, void *offset) } DEFINE_SHOW_ATTRIBUTE(at86rf230_stats); -static int at86rf230_debugfs_init(struct at86rf230_local *lp) +static void at86rf230_debugfs_init(struct at86rf230_local *lp) { char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "at86rf230-"; - struct dentry *stats; strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); at86rf230_debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (!at86rf230_debugfs_root) - return -ENOMEM; - - stats = debugfs_create_file("trac_stats", 0444, - at86rf230_debugfs_root, lp, - &at86rf230_stats_fops); - if (!stats) - return -ENOMEM; - return 0; + debugfs_create_file("trac_stats", 0444, at86rf230_debugfs_root, lp, + &at86rf230_stats_fops); } static void at86rf230_debugfs_remove(void) @@ -1651,7 +1643,7 @@ static void at86rf230_debugfs_remove(void) debugfs_remove_recursive(at86rf230_debugfs_root); } #else -static int at86rf230_debugfs_init(struct at86rf230_local *lp) { return 0; } +static void at86rf230_debugfs_init(struct at86rf230_local *lp) { } static void at86rf230_debugfs_remove(void) { } #endif @@ -1751,9 +1743,7 @@ static int at86rf230_probe(struct spi_device *spi) /* going into sleep by default */ at86rf230_sleep(lp); - rc = at86rf230_debugfs_init(lp); - if (rc) - goto free_dev; + at86rf230_debugfs_init(lp); rc = ieee802154_register_hw(lp->hw); if (rc) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index b188fce3f641..11402dc347db 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -3019,14 +3019,7 @@ static int ca8210_test_interface_init(struct ca8210_priv *priv) priv, &test_int_fops ); - if (IS_ERR(test->ca8210_dfs_spi_int)) { - dev_err( - &priv->spi->dev, - "Error %ld when creating debugfs node\n", - PTR_ERR(test->ca8210_dfs_spi_int) - ); - return PTR_ERR(test->ca8210_dfs_spi_int); - } + debugfs_create_symlink("ca8210", NULL, node_name); init_waitqueue_head(&test->readq); return kfifo_alloc( diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index c5c417a3c0ce..08ca59fc189b 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -40,6 +40,10 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) return PTR_ERR_OR_ZERO(nsim_dev->ports_ddir) ?: -EINVAL; debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir, &nsim_dev->fw_update_status); + debugfs_create_u32("max_macs", 0600, nsim_dev->ddir, + &nsim_dev->max_macs); + debugfs_create_bool("test1", 0600, nsim_dev->ddir, + &nsim_dev->test1); return 0; } @@ -196,6 +200,54 @@ out: return err; } +enum nsim_devlink_param_id { + NSIM_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + NSIM_DEVLINK_PARAM_ID_TEST1, +}; + +static const struct devlink_param nsim_devlink_params[] = { + DEVLINK_PARAM_GENERIC(MAX_MACS, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), + DEVLINK_PARAM_DRIVER(NSIM_DEVLINK_PARAM_ID_TEST1, + "test1", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, NULL), +}; + +static void nsim_devlink_set_params_init_values(struct nsim_dev *nsim_dev, + struct devlink *devlink) +{ + union devlink_param_value value; + + value.vu32 = nsim_dev->max_macs; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + value); + value.vbool = nsim_dev->test1; + devlink_param_driverinit_value_set(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + value); +} + +static void nsim_devlink_param_load_driverinit_values(struct devlink *devlink) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + union devlink_param_value saved_value; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + &saved_value); + if (!err) + nsim_dev->max_macs = saved_value.vu32; + err = devlink_param_driverinit_value_get(devlink, + NSIM_DEVLINK_PARAM_ID_TEST1, + &saved_value); + if (!err) + nsim_dev->test1 = saved_value.vbool; +} + static int nsim_dev_reload(struct devlink *devlink, struct netlink_ext_ack *extack) { @@ -218,6 +270,7 @@ static int nsim_dev_reload(struct devlink *devlink, return err; } } + nsim_devlink_param_load_driverinit_values(devlink); return 0; } @@ -267,6 +320,9 @@ static const struct devlink_ops nsim_dev_devlink_ops = { .flash_update = nsim_dev_flash_update, }; +#define NSIM_DEV_MAX_MACS_DEFAULT 32 +#define NSIM_DEV_TEST1_DEFAULT true + static struct nsim_dev * nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) { @@ -284,6 +340,8 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) INIT_LIST_HEAD(&nsim_dev->port_list); mutex_init(&nsim_dev->port_list_lock); nsim_dev->fw_update_status = true; + nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; + nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; nsim_dev->fib_data = nsim_fib_create(); if (IS_ERR(nsim_dev->fib_data)) { @@ -299,18 +357,28 @@ nsim_dev_create(struct nsim_bus_dev *nsim_bus_dev, unsigned int port_count) if (err) goto err_resources_unregister; - err = nsim_dev_debugfs_init(nsim_dev); + err = devlink_params_register(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); if (err) goto err_dl_unregister; + nsim_devlink_set_params_init_values(nsim_dev, devlink); + + err = nsim_dev_debugfs_init(nsim_dev); + if (err) + goto err_params_unregister; err = nsim_bpf_dev_init(nsim_dev); if (err) goto err_debugfs_exit; + devlink_params_publish(devlink); return nsim_dev; err_debugfs_exit: nsim_dev_debugfs_exit(nsim_dev); +err_params_unregister: + devlink_params_unregister(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); err_dl_unregister: devlink_unregister(devlink); err_resources_unregister: @@ -328,6 +396,8 @@ static void nsim_dev_destroy(struct nsim_dev *nsim_dev) nsim_bpf_dev_exit(nsim_dev); nsim_dev_debugfs_exit(nsim_dev); + devlink_params_unregister(devlink, nsim_devlink_params, + ARRAY_SIZE(nsim_devlink_params)); devlink_unregister(devlink); devlink_resources_unregister(devlink, NULL); nsim_fib_destroy(nsim_dev->fib_data); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 79c05af2a7c0..95751a817508 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -158,6 +158,8 @@ struct nsim_dev { struct list_head port_list; struct mutex port_list_lock; /* protects port list */ bool fw_update_status; + u32 max_macs; + bool test1; }; int nsim_dev_init(void); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 206d8650ee7f..48ca213c0ada 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -172,8 +172,8 @@ config MDIO_MSCC_MIIM config MDIO_OCTEON tristate "Octeon and some ThunderX SOCs MDIO buses" - depends on 64BIT - depends on HAS_IOMEM && OF_MDIO + depends on (64BIT && OF_MDIO) || COMPILE_TEST + depends on HAS_IOMEM select MDIO_CAVIUM help This module provides a driver for the Octeon and ThunderX MDIO diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 3ffe46df249e..7c5265fd2b94 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -216,8 +216,10 @@ static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) if (IS_ERR(gpiod)) { if (PTR_ERR(gpiod) == -EPROBE_DEFER) return gpiod; - pr_err("error getting GPIO for fixed link %pOF, proceed without\n", - fixed_link_node); + + if (PTR_ERR(gpiod) != -ENOENT) + pr_err("error getting GPIO for fixed link %pOF, proceed without\n", + fixed_link_node); gpiod = NULL; } diff --git a/drivers/net/phy/mdio-cavium.h b/drivers/net/phy/mdio-cavium.h index ed5f9bb5448d..b7f89ad27465 100644 --- a/drivers/net/phy/mdio-cavium.h +++ b/drivers/net/phy/mdio-cavium.h @@ -108,6 +108,8 @@ static inline u64 oct_mdio_readq(u64 addr) return cvmx_read_csr(addr); } #else +#include <linux/io-64-nonatomic-lo-hi.h> + #define oct_mdio_writeq(val, addr) writeq(val, (void *)addr) #define oct_mdio_readq(addr) readq((void *)addr) #endif diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 28676af97b42..645d354ffb48 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -2226,8 +2226,8 @@ static int vsc8514_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; vsc8531->hw_stats = vsc85xx_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2251,8 +2251,8 @@ static int vsc8574_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; vsc8531->hw_stats = vsc8584_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2281,8 +2281,8 @@ static int vsc8584_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; vsc8531->hw_stats = vsc8584_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; @@ -2311,8 +2311,8 @@ static int vsc85xx_probe(struct phy_device *phydev) vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; vsc8531->hw_stats = vsc85xx_hw_stats; vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); + vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, + sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 16667fbac8bf..369903d9b6ec 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -207,14 +207,14 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) { const struct phy_setting *p; int i; for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) { if (p->speed > max_speed) - linkmode_clear_bit(p->bit, phydev->supported); + linkmode_clear_bit(p->bit, addr); else break; } @@ -222,6 +222,11 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) return 0; } +static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +{ + return __set_linkmode_max_speed(max_speed, phydev->supported); +} + int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) { int err; @@ -310,6 +315,34 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode); +static int phy_resolve_min_speed(struct phy_device *phydev, bool fdx_only) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + int i = ARRAY_SIZE(settings); + + linkmode_and(common, phydev->lp_advertising, phydev->advertising); + + while (--i >= 0) { + if (test_bit(settings[i].bit, common)) { + if (fdx_only && settings[i].duplex != DUPLEX_FULL) + continue; + return settings[i].speed; + } + } + + return SPEED_UNKNOWN; +} + +int phy_speed_down_core(struct phy_device *phydev) +{ + int min_common_speed = phy_resolve_min_speed(phydev, true); + + if (min_common_speed == SPEED_UNKNOWN) + return -EINVAL; + + return __set_linkmode_max_speed(min_common_speed, phydev->advertising); +} + static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, u16 regnum) { @@ -783,24 +816,43 @@ int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val) EXPORT_SYMBOL(phy_write_paged); /** - * phy_modify_paged() - Convenience function for modifying a paged register + * phy_modify_paged_changed() - Function for modifying a paged register * @phydev: a pointer to a &struct phy_device * @page: the page for the phy * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * - * Same rules as for phy_read() and phy_write(). + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, - u16 mask, u16 set) +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) { int ret = 0, oldpage; oldpage = phy_select_page(phydev, page); if (oldpage >= 0) - ret = __phy_modify(phydev, regnum, mask, set); + ret = __phy_modify_changed(phydev, regnum, mask, set); return phy_restore_page(phydev, oldpage, ret); } +EXPORT_SYMBOL(phy_modify_paged_changed); + +/** + * phy_modify_paged() - Convenience function for modifying a paged register + * @phydev: a pointer to a &struct phy_device + * @page: the page for the phy + * @regnum: register number + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + * + * Same rules as for phy_read() and phy_write(). + */ +int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set) +{ + int ret = phy_modify_paged_changed(phydev, page, regnum, mask, set); + + return ret < 0 ? ret : 0; +} EXPORT_SYMBOL(phy_modify_paged); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index ef7aa738e0dc..f3adea9ef400 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -608,38 +608,21 @@ static int phy_poll_aneg_done(struct phy_device *phydev) */ int phy_speed_down(struct phy_device *phydev, bool sync) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); int ret; if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_copy(adv_old, phydev->advertising); - linkmode_copy(adv, phydev->lp_advertising); - linkmode_and(adv, adv, phydev->supported); - - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - adv) || - linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - adv)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->advertising); - } + linkmode_copy(adv_tmp, phydev->advertising); + + ret = phy_speed_down_core(phydev); + if (ret) + return ret; - if (linkmode_equal(phydev->advertising, adv_old)) + linkmode_copy(phydev->adv_old, adv_tmp); + + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; ret = phy_config_aneg(phydev); @@ -658,30 +641,19 @@ EXPORT_SYMBOL_GPL(phy_speed_down); */ int phy_speed_up(struct phy_device *phydev) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(all_speeds) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(not_speeds); - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - __ETHTOOL_DECLARE_LINK_MODE_MASK(speeds); - - linkmode_copy(adv_old, phydev->advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_tmp); if (phydev->autoneg != AUTONEG_ENABLE) return 0; - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, all_speeds); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, all_speeds); + if (linkmode_empty(phydev->adv_old)) + return 0; - linkmode_andnot(not_speeds, adv_old, all_speeds); - linkmode_copy(supported, phydev->supported); - linkmode_and(speeds, supported, all_speeds); - linkmode_or(phydev->advertising, not_speeds, speeds); + linkmode_copy(adv_tmp, phydev->advertising); + linkmode_copy(phydev->advertising, phydev->adv_old); + linkmode_zero(phydev->adv_old); - if (linkmode_equal(phydev->advertising, adv_old)) + if (linkmode_equal(phydev->advertising, adv_tmp)) return 0; return phy_config_aneg(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 6b5cb87f3866..b039632de73a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1564,24 +1564,20 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); */ static int genphy_config_advert(struct phy_device *phydev) { - u32 advertise; - int bmsr, adv; - int err, changed = 0; + int err, bmsr, changed = 0; + u32 adv; /* Only allow advertising what this PHY supports */ linkmode_and(phydev->advertising, phydev->advertising, phydev->supported); - if (!ethtool_convert_link_mode_to_legacy_u32(&advertise, - phydev->advertising)) - phydev_warn(phydev, "PHY advertising (%*pb) more modes than genphy supports, some modes not advertised.\n", - __ETHTOOL_LINK_MODE_MASK_NBITS, - phydev->advertising); + + adv = linkmode_adv_to_mii_adv_t(phydev->advertising); /* Setup standard advertisement */ err = phy_modify_changed(phydev, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, - ethtool_adv_to_mii_adv_t(advertise)); + adv); if (err < 0) return err; if (err > 0) @@ -1598,13 +1594,7 @@ static int genphy_config_advert(struct phy_device *phydev) if (!(bmsr & BMSR_ESTATEN)) return changed; - /* Configure gigabit if it's supported */ - adv = 0; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->supported) || - linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->supported)) - adv = ethtool_adv_to_mii_ctrl1000_t(advertise); + adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); err = phy_modify_changed(phydev, MII_CTRL1000, ADVERTISE_1000FULL | ADVERTISE_1000HALF, @@ -1681,18 +1671,20 @@ int genphy_restart_aneg(struct phy_device *phydev) EXPORT_SYMBOL(genphy_restart_aneg); /** - * genphy_config_aneg - restart auto-negotiation or write BMCR + * __genphy_config_aneg - restart auto-negotiation or write BMCR * @phydev: target phy_device struct + * @changed: whether autoneg is requested * * Description: If auto-negotiation is enabled, we configure the * advertising, and then restart auto-negotiation. If it is not * enabled, then we write the BMCR. */ -int genphy_config_aneg(struct phy_device *phydev) +int __genphy_config_aneg(struct phy_device *phydev, bool changed) { - int err, changed; + int err; - changed = genphy_config_eee_advert(phydev); + if (genphy_config_eee_advert(phydev)) + changed = true; if (AUTONEG_ENABLE != phydev->autoneg) return genphy_setup_forced(phydev); @@ -1700,10 +1692,10 @@ int genphy_config_aneg(struct phy_device *phydev) err = genphy_config_advert(phydev); if (err < 0) /* error */ return err; + else if (err) + changed = true; - changed |= err; - - if (changed == 0) { + if (!changed) { /* Advertisement hasn't changed, but maybe aneg was never on to * begin with? Or maybe phy was isolated? */ @@ -1713,18 +1705,15 @@ int genphy_config_aneg(struct phy_device *phydev) return ctl; if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE)) - changed = 1; /* do restart aneg */ + changed = true; /* do restart aneg */ } /* Only restart aneg if we are advertising something different * than we were before. */ - if (changed > 0) - return genphy_restart_aneg(phydev); - - return 0; + return changed ? genphy_restart_aneg(phydev) : 0; } -EXPORT_SYMBOL(genphy_config_aneg); +EXPORT_SYMBOL(__genphy_config_aneg); /** * genphy_aneg_done - return auto-negotiation status @@ -1774,6 +1763,12 @@ done: phydev->link = status & BMSR_LSTATUS ? 1 : 0; phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0; + /* Consider the case that autoneg was started and "aneg complete" + * bit has been reset, but "link up" bit not yet. + */ + if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete) + phydev->link = 0; + return 0; } EXPORT_SYMBOL(genphy_update_link); @@ -1805,8 +1800,6 @@ int genphy_read_status(struct phy_device *phydev) phydev->pause = 0; phydev->asym_pause = 0; - linkmode_zero(phydev->lp_advertising); - if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { if (phydev->is_gigabit_capable) { lpagb = phy_read(phydev, MII_STAT1000); diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index b86a4b2116f8..59a94e07e7c5 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -48,8 +48,9 @@ void phy_led_trigger_change_speed(struct phy_device *phy) if (!phy->last_triggered) led_trigger_event(&phy->led_link_trigger->trigger, LED_FULL); + else + led_trigger_event(&phy->last_triggered->trigger, LED_OFF); - led_trigger_event(&phy->last_triggered->trigger, LED_OFF); led_trigger_event(&plt->trigger, LED_FULL); phy->last_triggered = plt; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 5d0af041b8f9..a45c5de96ab1 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -216,6 +216,8 @@ static int phylink_parse_fixedlink(struct phylink *pl, pl->supported, true); linkmode_zero(pl->supported); phylink_set(pl->supported, MII); + phylink_set(pl->supported, Pause); + phylink_set(pl->supported, Asym_Pause); if (s) { __set_bit(s->bit, pl->supported); } else { @@ -990,10 +992,10 @@ void phylink_start(struct phylink *pl) } if (pl->link_an_mode == MLO_AN_FIXED && pl->get_fixed_state) mod_timer(&pl->link_poll, jiffies + HZ); - if (pl->sfp_bus) - sfp_upstream_start(pl->sfp_bus); if (pl->phydev) phy_start(pl->phydev); + if (pl->sfp_bus) + sfp_upstream_start(pl->sfp_bus); } EXPORT_SYMBOL_GPL(phylink_start); @@ -1010,10 +1012,10 @@ void phylink_stop(struct phylink *pl) { ASSERT_RTNL(); - if (pl->phydev) - phy_stop(pl->phydev); if (pl->sfp_bus) sfp_upstream_stop(pl->sfp_bus); + if (pl->phydev) + phy_stop(pl->phydev); del_timer_sync(&pl->link_poll); if (pl->link_irq) { free_irq(pl->link_irq, pl); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index a669945eb829..5b466e80d956 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -39,6 +39,11 @@ #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) +#define RTL_ADV_2500FULL BIT(7) +#define RTL_LPADV_10000FULL BIT(11) +#define RTL_LPADV_5000FULL BIT(6) +#define RTL_LPADV_2500FULL BIT(5) + MODULE_DESCRIPTION("Realtek PHY driver"); MODULE_AUTHOR("Johnson Leung"); MODULE_LICENSE("GPL"); @@ -256,6 +261,53 @@ static int rtl8366rb_config_init(struct phy_device *phydev) return ret; } +static int rtl8125_get_features(struct phy_device *phydev) +{ + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->supported); + + return genphy_read_abilities(phydev); +} + +static int rtl8125_config_aneg(struct phy_device *phydev) +{ + int ret = 0; + + if (phydev->autoneg == AUTONEG_ENABLE) { + u16 adv2500 = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->advertising)) + adv2500 = RTL_ADV_2500FULL; + + ret = phy_modify_paged_changed(phydev, 0xa5d, 0x12, + RTL_ADV_2500FULL, adv2500); + if (ret < 0) + return ret; + } + + return __genphy_config_aneg(phydev, ret); +} + +static int rtl8125_read_status(struct phy_device *phydev) +{ + if (phydev->autoneg == AUTONEG_ENABLE) { + int lpadv = phy_read_paged(phydev, 0xa5d, 0x13); + + if (lpadv < 0) + return lpadv; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_10000FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_5000FULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->lp_advertising, lpadv & RTL_LPADV_2500FULL); + } + + return genphy_read_status(phydev); +} + static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), @@ -333,6 +385,16 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { + PHY_ID_MATCH_EXACT(0x001cca50), + .name = "RTL8125 2.5Gbps internal", + .get_features = rtl8125_get_features, + .config_aneg = rtl8125_config_aneg, + .read_status = rtl8125_read_status, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", .config_init = &rtl8366rb_config_init, diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 1d902ecb4aa8..a44dd3c8af63 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1115,6 +1115,9 @@ static const struct proto_ops pppoe_ops = { .recvmsg = pppoe_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppoe_proto = { diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c index 5ef422a43d70..08364f10a43f 100644 --- a/drivers/net/ppp/pppox.c +++ b/drivers/net/ppp/pppox.c @@ -17,6 +17,7 @@ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/compat.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> @@ -98,6 +99,18 @@ int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) EXPORT_SYMBOL(pppox_ioctl); +#ifdef CONFIG_COMPAT +int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == PPPOEIOCSFWD32) + cmd = PPPOEIOCSFWD; + + return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} + +EXPORT_SYMBOL(pppox_compat_ioctl); +#endif + static int pppox_create(struct net *net, struct socket *sock, int protocol, int kern) { diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index a8e52c8e4128..734de7de03f7 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -623,6 +623,9 @@ static const struct proto_ops pptp_ops = { .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppox_pptp_proto = { diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index ea90db3c7705..58a69f830d29 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -91,8 +91,8 @@ static unsigned short pull16(unsigned char **cpp); struct slcompress * slhc_init(int rslots, int tslots) { - register short i; - register struct cstate *ts; + short i; + struct cstate *ts; struct slcompress *comp; if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255) @@ -206,7 +206,7 @@ pull16(unsigned char **cpp) static long decode(unsigned char **cpp) { - register int x; + int x; x = *(*cpp)++; if(x == 0){ @@ -227,14 +227,14 @@ int slhc_compress(struct slcompress *comp, unsigned char *icp, int isize, unsigned char *ocp, unsigned char **cpp, int compress_cid) { - register struct cstate *ocs = &(comp->tstate[comp->xmit_oldest]); - register struct cstate *lcs = ocs; - register struct cstate *cs = lcs->next; - register unsigned long deltaS, deltaA; - register short changes = 0; + struct cstate *ocs = &(comp->tstate[comp->xmit_oldest]); + struct cstate *lcs = ocs; + struct cstate *cs = lcs->next; + unsigned long deltaS, deltaA; + short changes = 0; int hlen; unsigned char new_seq[16]; - register unsigned char *cp = new_seq; + unsigned char *cp = new_seq; struct iphdr *ip; struct tcphdr *th, *oth; __sum16 csum; @@ -486,11 +486,11 @@ uncompressed: int slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) { - register int changes; + int changes; long x; - register struct tcphdr *thp; - register struct iphdr *ip; - register struct cstate *cs; + struct tcphdr *thp; + struct iphdr *ip; + struct cstate *cs; int len, hdrlen; unsigned char *cp = icp; @@ -543,7 +543,7 @@ slhc_uncompress(struct slcompress *comp, unsigned char *icp, int isize) switch(changes & SPECIALS_MASK){ case SPECIAL_I: /* Echoed terminal traffic */ { - register short i; + short i; i = ntohs(ip->tot_len) - hdrlen; thp->ack_seq = htonl( ntohl(thp->ack_seq) + i); thp->seq = htonl( ntohl(thp->seq) + i); @@ -637,7 +637,7 @@ bad: int slhc_remember(struct slcompress *comp, unsigned char *icp, int isize) { - register struct cstate *cs; + struct cstate *cs; unsigned ihl; unsigned char index; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3d443597bd04..db16d7a13e00 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1599,7 +1599,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, return true; } -static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, +static struct sk_buff *__tun_build_skb(struct tun_file *tfile, + struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad) { struct sk_buff *skb = build_skb(buf, buflen); @@ -1609,6 +1610,7 @@ static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, skb_reserve(skb, pad); skb_put(skb, len); + skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; @@ -1686,7 +1688,8 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; - return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, + pad); } *skb_xdp = 0; @@ -1723,7 +1726,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, rcu_read_unlock(); local_bh_enable(); - return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad); err_xdp: put_page(alloc_frag->page); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 6d25dea5ad4b..f7d117d80cfb 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -282,7 +282,7 @@ static void mdio_write(struct net_device *dev, int phy_id, int loc, int val) static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata) { int i; - __u8 tmp; + __u8 tmp = 0; __le16 retdatai; int ret; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 69e0a2acfcb0..b6dc5d714b5e 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1295,6 +1295,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ + {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 39e0768d734d..40d18e866269 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -22,10 +22,11 @@ #include <linux/mdio.h> #include <linux/usb/cdc.h> #include <linux/suspend.h> +#include <linux/atomic.h> #include <linux/acpi.h> /* Information for net-next */ -#define NETNEXT_VERSION "09" +#define NETNEXT_VERSION "10" /* Information for net */ #define NET_VERSION "10" @@ -50,7 +51,7 @@ #define PLA_TEREDO_WAKE_BASE 0xc0c4 #define PLA_MAR 0xcd00 #define PLA_BACKUP 0xd000 -#define PAL_BDC_CR 0xd1a0 +#define PLA_BDC_CR 0xd1a0 #define PLA_TEREDO_TIMER 0xd2cc #define PLA_REALWOW_TIMER 0xd2e8 #define PLA_SUSPEND_FLAG 0xd38a @@ -274,7 +275,7 @@ #define TEREDO_RS_EVENT_MASK 0x00fe #define OOB_TEREDO_EN 0x0001 -/* PAL_BDC_CR */ +/* PLA_BDC_CR */ #define ALDPS_PROXY_MODE 0x0001 /* PLA_EFUSE_CMD */ @@ -583,6 +584,9 @@ enum rtl_register_content { #define TX_ALIGN 4 #define RX_ALIGN 8 +#define RTL8152_RX_MAX_PENDING 4096 +#define RTL8152_RXFG_HEADSZ 256 + #define INTR_LINK 0x0004 #define RTL8152_REQT_READ 0xc0 @@ -694,11 +698,11 @@ struct tx_desc { struct r8152; struct rx_agg { - struct list_head list; + struct list_head list, info_list; struct urb *urb; struct r8152 *context; + struct page *page; void *buffer; - void *head; }; struct tx_agg { @@ -719,7 +723,7 @@ struct r8152 { struct net_device *netdev; struct urb *intr_urb; struct tx_agg tx_info[RTL8152_MAX_TX]; - struct rx_agg rx_info[RTL8152_MAX_RX]; + struct list_head rx_info, rx_used; struct list_head rx_done, tx_free; struct sk_buff_head tx_queue, rx_queue; spinlock_t rx_lock, tx_lock; @@ -744,11 +748,17 @@ struct r8152 { void (*autosuspend_en)(struct r8152 *tp, bool enable); } rtl_ops; + atomic_t rx_count; + int intr_interval; u32 saved_wolopts; u32 msg_enable; u32 tx_qlen; u32 coalesce; + u32 rx_buf_sz; + u32 rx_copybreak; + u32 rx_pending; + u16 ocp_base; u16 speed; u8 *intr_buff; @@ -1467,18 +1477,72 @@ static inline void *tx_agg_align(void *data) return (void *)ALIGN((uintptr_t)data, TX_ALIGN); } +static void free_rx_agg(struct r8152 *tp, struct rx_agg *agg) +{ + list_del(&agg->info_list); + + usb_free_urb(agg->urb); + put_page(agg->page); + kfree(agg); + + atomic_dec(&tp->rx_count); +} + +static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags) +{ + struct net_device *netdev = tp->netdev; + int node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1; + unsigned int order = get_order(tp->rx_buf_sz); + struct rx_agg *rx_agg; + unsigned long flags; + + rx_agg = kmalloc_node(sizeof(*rx_agg), mflags, node); + if (!rx_agg) + return NULL; + + rx_agg->page = alloc_pages(mflags | __GFP_COMP, order); + if (!rx_agg->page) + goto free_rx; + + rx_agg->buffer = page_address(rx_agg->page); + + rx_agg->urb = usb_alloc_urb(0, mflags); + if (!rx_agg->urb) + goto free_buf; + + rx_agg->context = tp; + + INIT_LIST_HEAD(&rx_agg->list); + INIT_LIST_HEAD(&rx_agg->info_list); + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&rx_agg->info_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); + + atomic_inc(&tp->rx_count); + + return rx_agg; + +free_buf: + __free_pages(rx_agg->page, order); +free_rx: + kfree(rx_agg); + return NULL; +} + static void free_all_mem(struct r8152 *tp) { + struct rx_agg *agg, *agg_next; + unsigned long flags; int i; - for (i = 0; i < RTL8152_MAX_RX; i++) { - usb_free_urb(tp->rx_info[i].urb); - tp->rx_info[i].urb = NULL; + spin_lock_irqsave(&tp->rx_lock, flags); - kfree(tp->rx_info[i].buffer); - tp->rx_info[i].buffer = NULL; - tp->rx_info[i].head = NULL; - } + list_for_each_entry_safe(agg, agg_next, &tp->rx_info, info_list) + free_rx_agg(tp, agg); + + spin_unlock_irqrestore(&tp->rx_lock, flags); + + WARN_ON(atomic_read(&tp->rx_count)); for (i = 0; i < RTL8152_MAX_TX; i++) { usb_free_urb(tp->tx_info[i].urb); @@ -1502,46 +1566,28 @@ static int alloc_all_mem(struct r8152 *tp) struct usb_interface *intf = tp->intf; struct usb_host_interface *alt = intf->cur_altsetting; struct usb_host_endpoint *ep_intr = alt->endpoint + 2; - struct urb *urb; int node, i; - u8 *buf; node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1; spin_lock_init(&tp->rx_lock); spin_lock_init(&tp->tx_lock); + INIT_LIST_HEAD(&tp->rx_info); INIT_LIST_HEAD(&tp->tx_free); INIT_LIST_HEAD(&tp->rx_done); skb_queue_head_init(&tp->tx_queue); skb_queue_head_init(&tp->rx_queue); + atomic_set(&tp->rx_count, 0); for (i = 0; i < RTL8152_MAX_RX; i++) { - buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node); - if (!buf) - goto err1; - - if (buf != rx_agg_align(buf)) { - kfree(buf); - buf = kmalloc_node(agg_buf_sz + RX_ALIGN, GFP_KERNEL, - node); - if (!buf) - goto err1; - } - - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) { - kfree(buf); + if (!alloc_rx_agg(tp, GFP_KERNEL)) goto err1; - } - - INIT_LIST_HEAD(&tp->rx_info[i].list); - tp->rx_info[i].context = tp; - tp->rx_info[i].urb = urb; - tp->rx_info[i].buffer = buf; - tp->rx_info[i].head = rx_agg_align(buf); } for (i = 0; i < RTL8152_MAX_TX; i++) { + struct urb *urb; + u8 *buf; + buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node); if (!buf) goto err1; @@ -1907,6 +1953,46 @@ return_result: return checksum; } +static inline bool rx_count_exceed(struct r8152 *tp) +{ + return atomic_read(&tp->rx_count) > RTL8152_MAX_RX; +} + +static inline int agg_offset(struct rx_agg *agg, void *addr) +{ + return (int)(addr - agg->buffer); +} + +static struct rx_agg *rtl_get_free_rx(struct r8152 *tp, gfp_t mflags) +{ + struct rx_agg *agg, *agg_next, *agg_free = NULL; + unsigned long flags; + + spin_lock_irqsave(&tp->rx_lock, flags); + + list_for_each_entry_safe(agg, agg_next, &tp->rx_used, list) { + if (page_count(agg->page) == 1) { + if (!agg_free) { + list_del_init(&agg->list); + agg_free = agg; + continue; + } + if (rx_count_exceed(tp)) { + list_del_init(&agg->list); + free_rx_agg(tp, agg); + } + break; + } + } + + spin_unlock_irqrestore(&tp->rx_lock, flags); + + if (!agg_free && atomic_read(&tp->rx_count) < tp->rx_pending) + agg_free = alloc_rx_agg(tp, mflags); + + return agg_free; +} + static int rx_bottom(struct r8152 *tp, int budget) { unsigned long flags; @@ -1942,7 +2028,7 @@ static int rx_bottom(struct r8152 *tp, int budget) list_for_each_safe(cursor, next, &rx_queue) { struct rx_desc *rx_desc; - struct rx_agg *agg; + struct rx_agg *agg, *agg_free; int len_used = 0; struct urb *urb; u8 *rx_data; @@ -1954,14 +2040,16 @@ static int rx_bottom(struct r8152 *tp, int budget) if (urb->actual_length < ETH_ZLEN) goto submit; - rx_desc = agg->head; - rx_data = agg->head; + agg_free = rtl_get_free_rx(tp, GFP_ATOMIC); + + rx_desc = agg->buffer; + rx_data = agg->buffer; len_used += sizeof(struct rx_desc); while (urb->actual_length > len_used) { struct net_device *netdev = tp->netdev; struct net_device_stats *stats = &netdev->stats; - unsigned int pkt_len; + unsigned int pkt_len, rx_frag_head_sz; struct sk_buff *skb; /* limite the skb numbers for rx_queue */ @@ -1979,22 +2067,37 @@ static int rx_bottom(struct r8152 *tp, int budget) pkt_len -= ETH_FCS_LEN; rx_data += sizeof(struct rx_desc); - skb = napi_alloc_skb(napi, pkt_len); + if (!agg_free || tp->rx_copybreak > pkt_len) + rx_frag_head_sz = pkt_len; + else + rx_frag_head_sz = tp->rx_copybreak; + + skb = napi_alloc_skb(napi, rx_frag_head_sz); if (!skb) { stats->rx_dropped++; goto find_next_rx; } skb->ip_summed = r8152_rx_csum(tp, rx_desc); - memcpy(skb->data, rx_data, pkt_len); - skb_put(skb, pkt_len); + memcpy(skb->data, rx_data, rx_frag_head_sz); + skb_put(skb, rx_frag_head_sz); + pkt_len -= rx_frag_head_sz; + rx_data += rx_frag_head_sz; + if (pkt_len) { + skb_add_rx_frag(skb, 0, agg->page, + agg_offset(agg, rx_data), + pkt_len, + SKB_DATA_ALIGN(pkt_len)); + get_page(agg->page); + } + skb->protocol = eth_type_trans(skb, netdev); rtl_rx_vlan_tag(rx_desc, skb); if (work_done < budget) { napi_gro_receive(napi, skb); work_done++; stats->rx_packets++; - stats->rx_bytes += pkt_len; + stats->rx_bytes += skb->len; } else { __skb_queue_tail(&tp->rx_queue, skb); } @@ -2002,10 +2105,24 @@ static int rx_bottom(struct r8152 *tp, int budget) find_next_rx: rx_data = rx_agg_align(rx_data + pkt_len + ETH_FCS_LEN); rx_desc = (struct rx_desc *)rx_data; - len_used = (int)(rx_data - (u8 *)agg->head); + len_used = agg_offset(agg, rx_data); len_used += sizeof(struct rx_desc); } + WARN_ON(!agg_free && page_count(agg->page) > 1); + + if (agg_free) { + spin_lock_irqsave(&tp->rx_lock, flags); + if (page_count(agg->page) == 1) { + list_add(&agg_free->list, &tp->rx_used); + } else { + list_add_tail(&agg->list, &tp->rx_used); + agg = agg_free; + urb = agg->urb; + } + spin_unlock_irqrestore(&tp->rx_lock, flags); + } + submit: if (!ret) { ret = r8152_submit_rx(tp, agg, GFP_ATOMIC); @@ -2113,7 +2230,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) return 0; usb_fill_bulk_urb(agg->urb, tp->udev, usb_rcvbulkpipe(tp->udev, 1), - agg->head, agg_buf_sz, + agg->buffer, tp->rx_buf_sz, (usb_complete_t)read_bulk_callback, agg); ret = usb_submit_urb(agg->urb, mem_flags); @@ -2330,44 +2447,80 @@ static void rxdy_gated_en(struct r8152 *tp, bool enable) static int rtl_start_rx(struct r8152 *tp) { - int i, ret = 0; + struct rx_agg *agg, *agg_next; + struct list_head tmp_list; + unsigned long flags; + int ret = 0, i = 0; - INIT_LIST_HEAD(&tp->rx_done); - for (i = 0; i < RTL8152_MAX_RX; i++) { - INIT_LIST_HEAD(&tp->rx_info[i].list); - ret = r8152_submit_rx(tp, &tp->rx_info[i], GFP_KERNEL); - if (ret) - break; - } + INIT_LIST_HEAD(&tmp_list); - if (ret && ++i < RTL8152_MAX_RX) { - struct list_head rx_queue; - unsigned long flags; + spin_lock_irqsave(&tp->rx_lock, flags); - INIT_LIST_HEAD(&rx_queue); + INIT_LIST_HEAD(&tp->rx_done); + INIT_LIST_HEAD(&tp->rx_used); - do { - struct rx_agg *agg = &tp->rx_info[i++]; - struct urb *urb = agg->urb; + list_splice_init(&tp->rx_info, &tmp_list); - urb->actual_length = 0; - list_add_tail(&agg->list, &rx_queue); - } while (i < RTL8152_MAX_RX); + spin_unlock_irqrestore(&tp->rx_lock, flags); - spin_lock_irqsave(&tp->rx_lock, flags); - list_splice_tail(&rx_queue, &tp->rx_done); - spin_unlock_irqrestore(&tp->rx_lock, flags); + list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) { + INIT_LIST_HEAD(&agg->list); + + /* Only RTL8152_MAX_RX rx_agg need to be submitted. */ + if (++i > RTL8152_MAX_RX) { + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_used); + spin_unlock_irqrestore(&tp->rx_lock, flags); + } else if (unlikely(ret < 0)) { + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_done); + spin_unlock_irqrestore(&tp->rx_lock, flags); + } else { + ret = r8152_submit_rx(tp, agg, GFP_KERNEL); + } } + spin_lock_irqsave(&tp->rx_lock, flags); + WARN_ON(!list_empty(&tp->rx_info)); + list_splice(&tmp_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); + return ret; } static int rtl_stop_rx(struct r8152 *tp) { - int i; + struct rx_agg *agg, *agg_next; + struct list_head tmp_list; + unsigned long flags; + + INIT_LIST_HEAD(&tmp_list); + + /* The usb_kill_urb() couldn't be used in atomic. + * Therefore, move the list of rx_info to a tmp one. + * Then, list_for_each_entry_safe could be used without + * spin lock. + */ + + spin_lock_irqsave(&tp->rx_lock, flags); + list_splice_init(&tp->rx_info, &tmp_list); + spin_unlock_irqrestore(&tp->rx_lock, flags); + + list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) { + /* At least RTL8152_MAX_RX rx_agg have the page_count being + * equal to 1, so the other ones could be freed safely. + */ + if (page_count(agg->page) > 1) + free_rx_agg(tp, agg); + else + usb_kill_urb(agg->urb); + } - for (i = 0; i < RTL8152_MAX_RX; i++) - usb_kill_urb(tp->rx_info[i].urb); + /* Move back the list of temp to the rx_info */ + spin_lock_irqsave(&tp->rx_lock, flags); + WARN_ON(!list_empty(&tp->rx_info)); + list_splice(&tmp_list, &tp->rx_info); + spin_unlock_irqrestore(&tp->rx_lock, flags); while (!skb_queue_empty(&tp->rx_queue)) dev_kfree_skb(__skb_dequeue(&tp->rx_queue)); @@ -2447,7 +2600,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp) static void r8153_set_rx_early_size(struct r8152 *tp) { - u32 ocp_data = agg_buf_sz - rx_reserved_size(tp->netdev->mtu); + u32 ocp_data = tp->rx_buf_sz - rx_reserved_size(tp->netdev->mtu); switch (tp->version) { case RTL_VER_03: @@ -3191,9 +3344,9 @@ static void r8152b_enter_oob(struct r8152 *tp) rtl_rx_vlan_en(tp, true); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR); ocp_data |= ALDPS_PROXY_MODE; - ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data); ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; @@ -3577,9 +3730,9 @@ static void r8153_enter_oob(struct r8152 *tp) rtl_rx_vlan_en(tp, true); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR); ocp_data |= ALDPS_PROXY_MODE; - ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data); ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; @@ -4954,6 +5107,77 @@ static int rtl8152_set_coalesce(struct net_device *netdev, return ret; } +static int rtl8152_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *tunable, void *d) +{ + struct r8152 *tp = netdev_priv(netdev); + + switch (tunable->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)d = tp->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int rtl8152_set_tunable(struct net_device *netdev, + const struct ethtool_tunable *tunable, + const void *d) +{ + struct r8152 *tp = netdev_priv(netdev); + u32 val; + + switch (tunable->id) { + case ETHTOOL_RX_COPYBREAK: + val = *(u32 *)d; + if (val < ETH_ZLEN) { + netif_err(tp, rx_err, netdev, + "Invalid rx copy break value\n"); + return -EINVAL; + } + + if (tp->rx_copybreak != val) { + napi_disable(&tp->napi); + tp->rx_copybreak = val; + napi_enable(&tp->napi); + } + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void rtl8152_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct r8152 *tp = netdev_priv(netdev); + + ring->rx_max_pending = RTL8152_RX_MAX_PENDING; + ring->rx_pending = tp->rx_pending; +} + +static int rtl8152_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct r8152 *tp = netdev_priv(netdev); + + if (ring->rx_pending < (RTL8152_MAX_RX * 2)) + return -EINVAL; + + if (tp->rx_pending != ring->rx_pending) { + napi_disable(&tp->napi); + tp->rx_pending = ring->rx_pending; + napi_enable(&tp->napi); + } + + return 0; +} + static const struct ethtool_ops ops = { .get_drvinfo = rtl8152_get_drvinfo, .get_link = ethtool_op_get_link, @@ -4971,6 +5195,10 @@ static const struct ethtool_ops ops = { .set_eee = rtl_ethtool_set_eee, .get_link_ksettings = rtl8152_get_link_ksettings, .set_link_ksettings = rtl8152_set_link_ksettings, + .get_tunable = rtl8152_get_tunable, + .set_tunable = rtl8152_set_tunable, + .get_ringparam = rtl8152_get_ringparam, + .set_ringparam = rtl8152_set_ringparam, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) @@ -5115,6 +5343,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8152_in_nway; ops->hw_phy_cfg = r8152b_hw_phy_cfg; ops->autosuspend_en = rtl_runtime_suspend_enable; + tp->rx_buf_sz = 16 * 1024; break; case RTL_VER_03: @@ -5132,6 +5361,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153_hw_phy_cfg; ops->autosuspend_en = rtl8153_runtime_enable; + tp->rx_buf_sz = 32 * 1024; break; case RTL_VER_08: @@ -5147,6 +5377,7 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153b_hw_phy_cfg; ops->autosuspend_en = rtl8153b_runtime_enable; + tp->rx_buf_sz = 32 * 1024; break; default: @@ -5321,6 +5552,9 @@ static int rtl8152_probe(struct usb_interface *intf, tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100; tp->duplex = DUPLEX_FULL; + tp->rx_copybreak = RTL8152_RXFG_HEADSZ; + tp->rx_pending = 10 * RTL8152_MAX_RX; + intf->needs_remote_wakeup = 1; tp->rtl_ops.init(tp); diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c index a9ac3f37b904..e2e679a01b65 100644 --- a/drivers/net/wan/sdla.c +++ b/drivers/net/wan/sdla.c @@ -413,6 +413,7 @@ static void sdla_errors(struct net_device *dev, int cmd, int dlci, int ret, int case SDLA_RET_NO_BUFS: if (cmd == SDLA_INFORMATION_WRITE) break; + /* Else, fall through */ default: netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n", diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/net/wimax/i2400m/debugfs.c index 6544ac9df047..73f5892ce6c1 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/net/wimax/i2400m/debugfs.c @@ -30,15 +30,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_netdev_queue_stopped, debugfs_netdev_queue_stopped_get, NULL, "%llu\n"); - -static -struct dentry *debugfs_create_netdev_queue_stopped( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0400, parent, i2400m, - &fops_netdev_queue_stopped); -} - /* * We don't allow partial reads of this file, as then the reader would * get weirdly confused data as it is updated. @@ -167,15 +158,6 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_suspend, NULL, debugfs_i2400m_suspend_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_suspend( - const char *name, struct dentry *parent, struct i2400m *i2400m) -{ - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_suspend); -} - - /* * Reset the device * @@ -205,73 +187,25 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_i2400m_reset, NULL, debugfs_i2400m_reset_set, "%llu\n"); -static -struct dentry *debugfs_create_i2400m_reset( - const char *name, struct dentry *parent, struct i2400m *i2400m) +void i2400m_debugfs_add(struct i2400m *i2400m) { - return debugfs_create_file(name, 0200, parent, i2400m, - &fops_i2400m_reset); -} - - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int i2400m_debugfs_add(struct i2400m *i2400m) -{ - int result; - struct device *dev = i2400m_dev(i2400m); struct dentry *dentry = i2400m->wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400m->debugfs_dentry = dentry; - __debugfs_register("dl_", control, dentry); - __debugfs_register("dl_", driver, dentry); - __debugfs_register("dl_", debugfs, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", netdev, dentry); - __debugfs_register("dl_", rfkill, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - - fd = debugfs_create_size_t("tx_in", 0400, dentry, - &i2400m->tx_in); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_in: %d\n", result); - goto error; - } - fd = debugfs_create_size_t("tx_out", 0400, dentry, - &i2400m->tx_out); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_out: %d\n", result); - goto error; - } + d_level_register_debugfs("dl_", control, dentry); + d_level_register_debugfs("dl_", driver, dentry); + d_level_register_debugfs("dl_", debugfs, dentry); + d_level_register_debugfs("dl_", fw, dentry); + d_level_register_debugfs("dl_", netdev, dentry); + d_level_register_debugfs("dl_", rfkill, dentry); + d_level_register_debugfs("dl_", rx, dentry); + d_level_register_debugfs("dl_", tx, dentry); - fd = debugfs_create_u32("state", 0600, dentry, - &i2400m->state); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "state: %d\n", result); - goto error; - } + debugfs_create_size_t("tx_in", 0400, dentry, &i2400m->tx_in); + debugfs_create_size_t("tx_out", 0400, dentry, &i2400m->tx_out); + debugfs_create_u32("state", 0600, dentry, &i2400m->state); /* * Trace received messages from user space @@ -295,60 +229,22 @@ int i2400m_debugfs_add(struct i2400m *i2400m) * It is not really very atomic, but it is also not too * critical. */ - fd = debugfs_create_u8("trace_msg_from_user", 0600, dentry, - &i2400m->trace_msg_from_user); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "trace_msg_from_user: %d\n", result); - goto error; - } + debugfs_create_u8("trace_msg_from_user", 0600, dentry, + &i2400m->trace_msg_from_user); - fd = debugfs_create_netdev_queue_stopped("netdev_queue_stopped", - dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "netdev_queue_stopped: %d\n", result); - goto error; - } + debugfs_create_file("netdev_queue_stopped", 0400, dentry, i2400m, + &fops_netdev_queue_stopped); - fd = debugfs_create_file("rx_stats", 0600, dentry, i2400m, - &i2400m_rx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_stats: %d\n", result); - goto error; - } + debugfs_create_file("rx_stats", 0600, dentry, i2400m, + &i2400m_rx_stats_fops); - fd = debugfs_create_file("tx_stats", 0600, dentry, i2400m, - &i2400m_tx_stats_fops); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "tx_stats: %d\n", result); - goto error; - } + debugfs_create_file("tx_stats", 0600, dentry, i2400m, + &i2400m_tx_stats_fops); - fd = debugfs_create_i2400m_suspend("suspend", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry suspend: %d\n", - result); - goto error; - } + debugfs_create_file("suspend", 0200, dentry, i2400m, + &fops_i2400m_suspend); - fd = debugfs_create_i2400m_reset("reset", dentry, i2400m); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry reset: %d\n", result); - goto error; - } - - result = 0; -error: - return result; + debugfs_create_file("reset", 0200, dentry, i2400m, &fops_i2400m_reset); } void i2400m_debugfs_rm(struct i2400m *i2400m) diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/net/wimax/i2400m/driver.c index 0a29222a1bf9..f66c0f8f6f4a 100644 --- a/drivers/net/wimax/i2400m/driver.c +++ b/drivers/net/wimax/i2400m/driver.c @@ -905,11 +905,7 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) goto error_sysfs_setup; } - result = i2400m_debugfs_add(i2400m); - if (result < 0) { - dev_err(dev, "cannot setup i2400m's debugfs: %d\n", result); - goto error_debugfs_setup; - } + i2400m_debugfs_add(i2400m); result = i2400m_dev_start(i2400m, bm_flags); if (result < 0) @@ -919,7 +915,6 @@ int i2400m_setup(struct i2400m *i2400m, enum i2400m_bri bm_flags) error_dev_start: i2400m_debugfs_rm(i2400m); -error_debugfs_setup: sysfs_remove_group(&i2400m->wimax_dev.net_dev->dev.kobj, &i2400m_dev_attr_group); error_sysfs_setup: diff --git a/drivers/net/wimax/i2400m/i2400m.h b/drivers/net/wimax/i2400m/i2400m.h index 5a34e72bab9a..a3733a6d14f5 100644 --- a/drivers/net/wimax/i2400m/i2400m.h +++ b/drivers/net/wimax/i2400m/i2400m.h @@ -812,13 +812,10 @@ enum i2400m_pt; int i2400m_tx(struct i2400m *, const void *, size_t, enum i2400m_pt); #ifdef CONFIG_DEBUG_FS -int i2400m_debugfs_add(struct i2400m *); +void i2400m_debugfs_add(struct i2400m *); void i2400m_debugfs_rm(struct i2400m *); #else -static inline int i2400m_debugfs_add(struct i2400m *i2400m) -{ - return 0; -} +static inline void i2400m_debugfs_add(struct i2400m *i2400m) {} static inline void i2400m_debugfs_rm(struct i2400m *i2400m) {} #endif diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index 2075e7b1fff6..6953f904232f 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -366,61 +366,25 @@ struct d_level D_LEVEL[] = { }; size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - static -int i2400mu_debugfs_add(struct i2400mu *i2400mu) +void i2400mu_debugfs_add(struct i2400mu *i2400mu) { - int result; - struct device *dev = &i2400mu->usb_iface->dev; struct dentry *dentry = i2400mu->i2400m.wimax_dev.debugfs_dentry; - struct dentry *fd; dentry = debugfs_create_dir("i2400m-usb", dentry); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - goto error; - } i2400mu->debugfs_dentry = dentry; - __debugfs_register("dl_", usb, dentry); - __debugfs_register("dl_", fw, dentry); - __debugfs_register("dl_", notif, dentry); - __debugfs_register("dl_", rx, dentry); - __debugfs_register("dl_", tx, dentry); - /* Don't touch these if you don't know what you are doing */ - fd = debugfs_create_u8("rx_size_auto_shrink", 0600, dentry, - &i2400mu->rx_size_auto_shrink); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size_auto_shrink: %d\n", result); - goto error; - } + d_level_register_debugfs("dl_", usb, dentry); + d_level_register_debugfs("dl_", fw, dentry); + d_level_register_debugfs("dl_", notif, dentry); + d_level_register_debugfs("dl_", rx, dentry); + d_level_register_debugfs("dl_", tx, dentry); - fd = debugfs_create_size_t("rx_size", 0600, dentry, - &i2400mu->rx_size); - result = PTR_ERR(fd); - if (IS_ERR(fd) && result != -ENODEV) { - dev_err(dev, "Can't create debugfs entry " - "rx_size: %d\n", result); - goto error; - } - - return 0; + /* Don't touch these if you don't know what you are doing */ + debugfs_create_u8("rx_size_auto_shrink", 0600, dentry, + &i2400mu->rx_size_auto_shrink); -error: - debugfs_remove_recursive(i2400mu->debugfs_dentry); - return result; + debugfs_create_size_t("rx_size", 0600, dentry, &i2400mu->rx_size); } @@ -534,15 +498,9 @@ int i2400mu_probe(struct usb_interface *iface, dev_err(dev, "cannot setup device: %d\n", result); goto error_setup; } - result = i2400mu_debugfs_add(i2400mu); - if (result < 0) { - dev_err(dev, "Can't register i2400mu's debugfs: %d\n", result); - goto error_debugfs_add; - } + i2400mu_debugfs_add(i2400mu); return 0; -error_debugfs_add: - i2400m_release(i2400m); error_setup: usb_set_intfdata(iface, NULL); usb_put_dev(i2400mu->usb_dev); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index d55312ef58c9..9b0bb89599fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -776,7 +776,6 @@ struct iwl_rss_config_cmd { u8 indirection_table[IWL_RSS_INDIRECTION_TABLE_SIZE]; } __packed; /* RSS_CONFIG_CMD_API_S_VER_1 */ -#define IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE 128 #define IWL_MULTI_QUEUE_SYNC_SENDER_POS 0 #define IWL_MULTI_QUEUE_SYNC_SENDER_MSK 0xf @@ -812,10 +811,12 @@ struct iwl_rxq_sync_notification { * * @IWL_MVM_RXQ_EMPTY: empty sync notification * @IWL_MVM_RXQ_NOTIF_DEL_BA: notify RSS queues of delBA + * @IWL_MVM_RXQ_NSSN_SYNC: notify all the RSS queues with the new NSSN */ enum iwl_mvm_rxq_notif_type { IWL_MVM_RXQ_EMPTY, IWL_MVM_RXQ_NOTIF_DEL_BA, + IWL_MVM_RXQ_NSSN_SYNC, }; /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index e411ac98290d..4d81776f576d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -2438,17 +2438,19 @@ static void iwl_fw_dbg_info_apply(struct iwl_fw_runtime *fwrt, { u32 img_name_len = le32_to_cpu(dbg_info->img_name_len); u32 dbg_cfg_name_len = le32_to_cpu(dbg_info->dbg_cfg_name_len); - const char err_str[] = - "WRT: ext=%d. Invalid %s name length %d, expected %d\n"; if (img_name_len != IWL_FW_INI_MAX_IMG_NAME_LEN) { - IWL_WARN(fwrt, err_str, ext, "image", img_name_len, + IWL_WARN(fwrt, + "WRT: ext=%d. Invalid image name length %d, expected %d\n", + ext, img_name_len, IWL_FW_INI_MAX_IMG_NAME_LEN); return; } if (dbg_cfg_name_len != IWL_FW_INI_MAX_DBG_CFG_NAME_LEN) { - IWL_WARN(fwrt, err_str, ext, "debug cfg", dbg_cfg_name_len, + IWL_WARN(fwrt, + "WRT: ext=%d. Invalid debug cfg name length %d, expected %d\n", + ext, dbg_cfg_name_len, IWL_FW_INI_MAX_DBG_CFG_NAME_LEN); return; } @@ -2775,8 +2777,6 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, struct iwl_ucode_tlv *tlv = iter; void *ini_tlv = (void *)tlv->data; u32 type = le32_to_cpu(tlv->type); - const char invalid_ap_str[] = - "WRT: ext=%d. Invalid apply point %d for %s\n"; switch (type) { case IWL_UCODE_TLV_TYPE_DEBUG_INFO: @@ -2786,8 +2786,9 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, struct iwl_fw_ini_allocation_data *buf_alloc = ini_tlv; if (pnt != IWL_FW_INI_APPLY_EARLY) { - IWL_ERR(fwrt, invalid_ap_str, ext, pnt, - "buffer allocation"); + IWL_ERR(fwrt, + "WRT: ext=%d. Invalid apply point %d for buffer allocation\n", + ext, pnt); goto next; } @@ -2797,8 +2798,9 @@ static void _iwl_fw_dbg_apply_point(struct iwl_fw_runtime *fwrt, } case IWL_UCODE_TLV_TYPE_HCMD: if (pnt < IWL_FW_INI_APPLY_AFTER_ALIVE) { - IWL_ERR(fwrt, invalid_ap_str, ext, pnt, - "host command"); + IWL_ERR(fwrt, + "WRT: ext=%d. Invalid apply point %d for host command\n", + ext, pnt); goto next; } iwl_fw_dbg_send_hcmd(fwrt, tlv, ext); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 57d09049e615..38672dd5aae9 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1640,6 +1640,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) init_completion(&drv->request_firmware_complete); INIT_LIST_HEAD(&drv->list); + iwl_load_fw_dbg_tlv(drv->trans->dev, drv->trans); + #ifdef CONFIG_IWLWIFI_DEBUGFS /* Create the device debugfs entries. */ drv->dbgfs_drv = debugfs_create_dir(dev_name(trans->dev), @@ -1660,8 +1662,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) err_fw: #ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive(drv->dbgfs_drv); - iwl_fw_dbg_free(drv->trans); #endif + iwl_fw_dbg_free(drv->trans); kfree(drv); err: return ERR_PTR(ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 1d608e9e9101..5de54d1559dd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -755,7 +755,7 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm) for (i = 0; i < n_profiles; i++) { /* the tables start at element 3 */ - static int pos = 3; + int pos = 3; /* The EWRD profiles officially go from 2 to 4, but we * save them in sar_profiles[1-3] (because we don't @@ -880,6 +880,22 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b) return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd); } +static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm) +{ + /* + * The GEO_TX_POWER_LIMIT command is not supported on earlier + * firmware versions. Unfortunately, we don't have a TLV API + * flag to rely on, so rely on the major version which is in + * the first byte of ucode_ver. This was implemented + * initially on version 38 and then backported to 36, 29 and + * 17. + */ + return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 36 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 || + IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17; +} + int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) { struct iwl_geo_tx_power_profiles_resp *resp; @@ -909,6 +925,9 @@ int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm) .data = { data }, }; + if (!iwl_mvm_sar_geo_support(mvm)) + return -EOPNOTSUPP; + ret = iwl_mvm_send_cmd(mvm, &cmd); if (ret) { IWL_ERR(mvm, "Failed to get geographic profile info %d\n", ret); @@ -934,13 +953,7 @@ static int iwl_mvm_sar_geo_init(struct iwl_mvm *mvm) int ret, i, j; u16 cmd_wide_id = WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT); - /* - * This command is not supported on earlier firmware versions. - * Unfortunately, we don't have a TLV API flag to rely on, so - * rely on the major version which is in the first byte of - * ucode_ver. - */ - if (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) < 41) + if (!iwl_mvm_sar_geo_support(mvm)) return 0; ret = iwl_mvm_sar_get_wgds_table(mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index e63623251d61..b74bd58f3f45 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -207,11 +207,11 @@ static const struct cfg80211_pmsr_capabilities iwl_mvm_pmsr_capa = { }, }; -static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, - enum set_key_cmd cmd, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct ieee80211_key_conf *key); +static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key); void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type) { @@ -474,7 +474,19 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); ieee80211_hw_set(hw, BUFF_MMPDU_TXQ); ieee80211_hw_set(hw, STA_MMPDU_TXQ); - ieee80211_hw_set(hw, TX_AMSDU); + /* + * On older devices, enabling TX A-MSDU occasionally leads to + * something getting messed up, the command read from the FIFO + * gets out of sync and isn't a TX command, so that we have an + * assert EDC. + * + * It's not clear where the bug is, but since we didn't used to + * support A-MSDU until moving the mac80211 iTXQs, just leave it + * for older devices. We also don't see this issue on any newer + * devices. + */ + if (mvm->cfg->device_family >= IWL_DEVICE_FAMILY_9000) + ieee80211_hw_set(hw, TX_AMSDU); ieee80211_hw_set(hw, TX_FRAG_LIST); if (iwl_mvm_has_tlc_offload(mvm)) { @@ -2726,7 +2738,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw, mvmvif->ap_early_keys[i] = NULL; - ret = iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key); + ret = __iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key); if (ret) goto out_quota_failed; } @@ -3494,11 +3506,11 @@ static int iwl_mvm_mac_sched_scan_stop(struct ieee80211_hw *hw, return ret; } -static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, - enum set_key_cmd cmd, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - struct ieee80211_key_conf *key) +static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); @@ -3553,8 +3565,6 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, return -EOPNOTSUPP; } - mutex_lock(&mvm->mutex); - switch (cmd) { case SET_KEY: if ((vif->type == NL80211_IFTYPE_ADHOC || @@ -3700,7 +3710,22 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, ret = -EINVAL; } + return ret; +} + +static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) +{ + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + int ret; + + mutex_lock(&mvm->mutex); + ret = __iwl_mvm_mac_set_key(hw, cmd, vif, sta, key); mutex_unlock(&mvm->mutex); + return ret; } @@ -5042,7 +5067,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, u32 qmask = BIT(mvm->trans->num_rx_queues) - 1; int ret; - lockdep_assert_held(&mvm->mutex); if (!iwl_mvm_has_new_rx_api(mvm)) return; @@ -5053,13 +5077,15 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, atomic_set(&mvm->queue_sync_counter, mvm->trans->num_rx_queues); - ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size); + ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, + size, !notif->sync); if (ret) { IWL_ERR(mvm, "Failed to trigger RX queues sync (%d)\n", ret); goto out; } if (notif->sync) { + lockdep_assert_held(&mvm->mutex); ret = wait_event_timeout(mvm->rx_sync_waitq, atomic_read(&mvm->queue_sync_counter) == 0 || iwl_mvm_is_radio_killed(mvm), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 48c77af54e99..a263cc629d75 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1664,9 +1664,9 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue); int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, - const u8 *data, u32 count); -void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, - int queue); + const u8 *data, u32 count, bool async); +void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, + struct iwl_rx_cmd_buffer *rxb, int queue); void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); @@ -1813,7 +1813,7 @@ iwl_mvm_vif_dbgfs_clean(struct iwl_mvm *mvm, struct ieee80211_vif *vif) #endif /* CONFIG_IWLWIFI_DEBUGFS */ /* rate scaling */ -int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync); +int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq); void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg); int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate); void rs_update_last_rssi(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 719f793b3487..a9bb43a2f27b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -620,7 +620,7 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm, enum iwl_mcc_source src; char mcc[3]; struct ieee80211_regdomain *regd; - u32 wgds_tbl_idx; + int wgds_tbl_idx; lockdep_assert_held(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index d7d6f3398f86..4888054dc3d8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1088,7 +1088,7 @@ static void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode, iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, 0); else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP, RX_QUEUES_NOTIFICATION))) - iwl_mvm_rx_queue_notif(mvm, rxb, 0); + iwl_mvm_rx_queue_notif(mvm, napi, rxb, 0); else if (cmd == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE)) iwl_mvm_rx_frame_release(mvm, napi, rxb, 0); else if (cmd == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF)) @@ -1812,7 +1812,7 @@ static void iwl_mvm_rx_mq_rss(struct iwl_op_mode *op_mode, iwl_mvm_rx_frame_release(mvm, napi, rxb, queue); else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP, RX_QUEUES_NOTIFICATION))) - iwl_mvm_rx_queue_notif(mvm, rxb, queue); + iwl_mvm_rx_queue_notif(mvm, napi, rxb, queue); else if (likely(cmd == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD))) iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, queue); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 009e72abcd51..e4415e58fa78 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1197,239 +1197,6 @@ static u8 rs_get_tid(struct ieee80211_hdr *hdr) return tid; } -void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - int tid, struct ieee80211_tx_info *info, bool ndp) -{ - int legacy_success; - int retries; - int i; - struct iwl_lq_cmd *table; - u32 lq_hwrate; - struct rs_rate lq_rate, tx_resp_rate; - struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; - u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; - u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; - u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); - u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; - - /* Treat uninitialized rate scaling data same as non-existing. */ - if (!lq_sta) { - IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); - return; - } else if (!lq_sta->pers.drv) { - IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); - return; - } - - /* This packet was aggregated but doesn't carry status info */ - if ((info->flags & IEEE80211_TX_CTL_AMPDU) && - !(info->flags & IEEE80211_TX_STAT_AMPDU)) - return; - - if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, - &tx_resp_rate)) { - WARN_ON_ONCE(1); - return; - } - -#ifdef CONFIG_MAC80211_DEBUGFS - /* Disable last tx check if we are debugging with fixed rate but - * update tx stats */ - if (lq_sta->pers.dbg_fixed_rate) { - int index = tx_resp_rate.index; - enum rs_column column; - int attempts, success; - - column = rs_get_column_from_rate(&tx_resp_rate); - if (WARN_ONCE(column == RS_COLUMN_INVALID, - "Can't map rate 0x%x to column", - tx_resp_hwrate)) - return; - - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - attempts = info->status.ampdu_len; - success = info->status.ampdu_ack_len; - } else { - attempts = info->status.rates[0].count; - success = !!(info->flags & IEEE80211_TX_STAT_ACK); - } - - lq_sta->pers.tx_stats[column][index].total += attempts; - lq_sta->pers.tx_stats[column][index].success += success; - - IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", - tx_resp_hwrate, success, attempts); - return; - } -#endif - - if (time_after(jiffies, - (unsigned long)(lq_sta->last_tx + - (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { - IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); - iwl_mvm_rs_rate_init(mvm, sta, info->band, true); - return; - } - lq_sta->last_tx = jiffies; - - /* Ignore this Tx frame response if its initial rate doesn't match - * that of latest Link Quality command. There may be stragglers - * from a previous Link Quality command, but we're no longer interested - * in those; they're either from the "active" mode while we're trying - * to check "search" mode, or a prior "search" mode after we've moved - * to a new "search" mode (which might become the new "active" mode). - */ - table = &lq_sta->lq; - lq_hwrate = le32_to_cpu(table->rs_table[0]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* Here we actually compare this rate to the latest LQ command */ - if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { - IWL_DEBUG_RATE(mvm, - "tx resp color 0x%x does not match 0x%x\n", - lq_color, LQ_FLAG_COLOR_GET(table->flags)); - - /* - * Since rates mis-match, the last LQ command may have failed. - * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with - * ... driver. - */ - lq_sta->missed_rate_counter++; - if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { - lq_sta->missed_rate_counter = 0; - IWL_DEBUG_RATE(mvm, - "Too many rates mismatch. Send sync LQ. rs_state %d\n", - lq_sta->rs_state); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false); - } - /* Regardless, ignore this status info for outdated rate */ - return; - } else - /* Rate did match, so reset the missed_rate_counter */ - lq_sta->missed_rate_counter = 0; - - if (!lq_sta->search_better_tbl) { - curr_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - } else { - curr_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - other_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - } - - if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { - IWL_DEBUG_RATE(mvm, - "Neither active nor search matches tx rate\n"); - tmp_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); - tmp_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]); - rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); - rs_dump_rate(mvm, &lq_rate, "ACTUAL"); - - /* - * no matching table found, let's by-pass the data collection - * and continue to perform rate scale to find the rate table - */ - rs_stay_in_table(lq_sta, true); - goto done; - } - - /* - * Updating the frame history depends on whether packets were - * aggregated. - * - * For aggregation, all packets were transmitted at the same rate, the - * first index into rate scale table. - */ - if (info->flags & IEEE80211_TX_STAT_AMPDU) { - rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len, - reduced_txp); - - /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat - * it as a single frame loss as we don't want the success ratio - * to dip too quickly because a BA wasn't received. - * For TPC, there's no need for this optimisation since we want - * to recover very quickly from a bad power reduction and, - * therefore we'd like the success ratio to get an immediate hit - * when failing to get a BA, so we'd switch back to a lower or - * zero power reduction. When FW transmits agg with a rate - * different from the initial rate, it will not use reduced txp - * and will send BA notification twice (one empty with reduced - * txp equal to the value from LQ and one with reduced txp 0). - * We need to update counters for each txp level accordingly. - */ - if (info->status.ampdu_ack_len == 0) - info->status.ampdu_len = 1; - - rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, tx_resp_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len); - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += info->status.ampdu_ack_len; - lq_sta->total_failed += (info->status.ampdu_len - - info->status.ampdu_ack_len); - } - } else { - /* For legacy, update frame history with for each Tx retry. */ - retries = info->status.rates[0].count - 1; - /* HW doesn't send more than 15 retries */ - retries = min(retries, 15); - - /* The last transmission may have been successful */ - legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); - /* Collect data for each rate used during failed TX attempts */ - for (i = 0; i <= retries; ++i) { - lq_hwrate = le32_to_cpu(table->rs_table[i]); - if (rs_rate_from_ucode_rate(lq_hwrate, info->band, - &lq_rate)) { - WARN_ON_ONCE(1); - return; - } - - /* - * Only collect stats if retried rate is in the same RS - * table as active/search. - */ - if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) - tmp_tbl = curr_tbl; - else if (rs_rate_column_match(&lq_rate, - &other_tbl->rate)) - tmp_tbl = other_tbl; - else - continue; - - rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success, - reduced_txp); - rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, - tx_resp_rate.index, 1, - i < retries ? 0 : legacy_success); - } - - /* Update success/fail counts if not searching for new mode */ - if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { - lq_sta->total_success += legacy_success; - lq_sta->total_failed += retries + (1 - legacy_success); - } - } - /* The last TX rate is cached in lq_sta; it's set in if/else above */ - lq_sta->last_rate_n_flags = lq_hwrate; - IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); -done: - /* See if there's a better rate or modulation mode to try. */ - if (sta->supp_rates[info->band]) - rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); -} - /* * mac80211 sends us Tx status */ @@ -1442,8 +1209,9 @@ static void rs_drv_mac80211_tx_status(void *mvm_r, struct iwl_op_mode *op_mode = mvm_r; struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - if (!iwl_mvm_sta_from_mac80211(sta)->vif) + if (!mvmsta->vif) return; if (!ieee80211_is_data(hdr->frame_control) || @@ -1584,6 +1352,18 @@ static void rs_set_expected_tpt_table(struct iwl_lq_sta *lq_sta, tbl->expected_tpt = rs_get_expected_tpt_table(lq_sta, column, rate->bw); } +/* rs uses two tables, one is active and the second is for searching better + * configuration. This function, according to the index of the currently + * active table returns the search table, which is located at the + * index complementary to 1 according to the active table (active = 1, + * search = 0 or active = 0, search = 1). + * Since lq_info is an arary of size 2, make sure index cannot be out of bounds. + */ +static inline u8 rs_search_tbl(u8 active_tbl) +{ + return (active_tbl ^ 1) & 1; +} + static s32 rs_get_best_rate(struct iwl_mvm *mvm, struct iwl_lq_sta *lq_sta, struct iwl_scale_tbl_info *tbl, /* "search" */ @@ -1794,7 +1574,7 @@ static void rs_update_rate_tbl(struct iwl_mvm *mvm, struct iwl_scale_tbl_info *tbl) { rs_fill_lq_cmd(mvm, sta, lq_sta, &tbl->rate); - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); } static bool rs_tweak_rate_tbl(struct iwl_mvm *mvm, @@ -1931,9 +1711,9 @@ static int rs_switch_to_column(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum rs_column col_id) { - struct iwl_scale_tbl_info *tbl = &(lq_sta->lq_info[lq_sta->active_tbl]); + struct iwl_scale_tbl_info *tbl = &lq_sta->lq_info[lq_sta->active_tbl]; struct iwl_scale_tbl_info *search_tbl = - &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; struct rs_rate *rate = &search_tbl->rate; const struct rs_tx_column *column = &rs_tx_columns[col_id]; const struct rs_tx_column *curr_column = &rs_tx_columns[tbl->column]; @@ -2341,7 +2121,7 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -2565,7 +2345,7 @@ lq_update: /* If new "search" mode was selected, set up in uCode table */ if (lq_sta->search_better_tbl) { /* Access the "search" table, clear its history. */ - tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]); + tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; rs_rate_scale_clear_tbl_windows(mvm, tbl); /* Use new "search" start rate */ @@ -2896,7 +2676,7 @@ void rs_update_last_rssi(struct iwl_mvm *mvm, static void rs_initialize_lq(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct iwl_lq_sta *lq_sta, - enum nl80211_band band, bool update) + enum nl80211_band band) { struct iwl_scale_tbl_info *tbl; struct rs_rate *rate; @@ -2908,7 +2688,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, if (!lq_sta->search_better_tbl) active_tbl = lq_sta->active_tbl; else - active_tbl = 1 - lq_sta->active_tbl; + active_tbl = rs_search_tbl(lq_sta->active_tbl); tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; @@ -2926,7 +2706,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, rs_set_expected_tpt_table(lq_sta, tbl); rs_fill_lq_cmd(mvm, sta, lq_sta, rate); /* TODO restore station should remember the lq cmd */ - iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, !update); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); } static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, @@ -3175,7 +2955,7 @@ void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg) * Called after adding a new station to initialize rate scaling */ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, - enum nl80211_band band, bool update) + enum nl80211_band band) { int i, j; struct ieee80211_hw *hw = mvm->hw; @@ -3186,6 +2966,8 @@ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct ieee80211_supported_band *sband; unsigned long supp; /* must be unsigned long for for_each_set_bit */ + lockdep_assert_held(&mvmsta->lq_sta.rs_drv.pers.lock); + /* clear all non-persistent lq data */ memset(lq_sta, 0, offsetof(typeof(*lq_sta), pers)); @@ -3255,7 +3037,7 @@ static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, #ifdef CONFIG_IWLWIFI_DEBUGFS iwl_mvm_reset_frame_stats(mvm); #endif - rs_initialize_lq(mvm, sta, lq_sta, band, update); + rs_initialize_lq(mvm, sta, lq_sta, band); } static void rs_drv_rate_update(void *mvm_r, @@ -3278,6 +3060,258 @@ static void rs_drv_rate_update(void *mvm_r, iwl_mvm_rs_rate_init(mvm, sta, sband->band, true); } +static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, + bool ndp) +{ + int legacy_success; + int retries; + int i; + struct iwl_lq_cmd *table; + u32 lq_hwrate; + struct rs_rate lq_rate, tx_resp_rate; + struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl; + u32 tlc_info = (uintptr_t)info->status.status_driver_data[0]; + u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK; + u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info); + u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1]; + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv; + + /* Treat uninitialized rate scaling data same as non-existing. */ + if (!lq_sta) { + IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n"); + return; + } else if (!lq_sta->pers.drv) { + IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n"); + return; + } + + /* This packet was aggregated but doesn't carry status info */ + if ((info->flags & IEEE80211_TX_CTL_AMPDU) && + !(info->flags & IEEE80211_TX_STAT_AMPDU)) + return; + + if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, + &tx_resp_rate)) { + WARN_ON_ONCE(1); + return; + } + +#ifdef CONFIG_MAC80211_DEBUGFS + /* Disable last tx check if we are debugging with fixed rate but + * update tx stats + */ + if (lq_sta->pers.dbg_fixed_rate) { + int index = tx_resp_rate.index; + enum rs_column column; + int attempts, success; + + column = rs_get_column_from_rate(&tx_resp_rate); + if (WARN_ONCE(column == RS_COLUMN_INVALID, + "Can't map rate 0x%x to column", + tx_resp_hwrate)) + return; + + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + attempts = info->status.ampdu_len; + success = info->status.ampdu_ack_len; + } else { + attempts = info->status.rates[0].count; + success = !!(info->flags & IEEE80211_TX_STAT_ACK); + } + + lq_sta->pers.tx_stats[column][index].total += attempts; + lq_sta->pers.tx_stats[column][index].success += success; + + IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n", + tx_resp_hwrate, success, attempts); + return; + } +#endif + + if (time_after(jiffies, + (unsigned long)(lq_sta->last_tx + + (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) { + IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n"); + /* reach here only in case of driver RS, call directly + * the unlocked version + */ + rs_drv_rate_init(mvm, sta, info->band); + return; + } + lq_sta->last_tx = jiffies; + + /* Ignore this Tx frame response if its initial rate doesn't match + * that of latest Link Quality command. There may be stragglers + * from a previous Link Quality command, but we're no longer interested + * in those; they're either from the "active" mode while we're trying + * to check "search" mode, or a prior "search" mode after we've moved + * to a new "search" mode (which might become the new "active" mode). + */ + table = &lq_sta->lq; + lq_hwrate = le32_to_cpu(table->rs_table[0]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Here we actually compare this rate to the latest LQ command */ + if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) { + IWL_DEBUG_RATE(mvm, + "tx resp color 0x%x does not match 0x%x\n", + lq_color, LQ_FLAG_COLOR_GET(table->flags)); + + /* Since rates mis-match, the last LQ command may have failed. + * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with + * ... driver. + */ + lq_sta->missed_rate_counter++; + if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) { + lq_sta->missed_rate_counter = 0; + IWL_DEBUG_RATE(mvm, + "Too many rates mismatch. Send sync LQ. rs_state %d\n", + lq_sta->rs_state); + iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq); + } + /* Regardless, ignore this status info for outdated rate */ + return; + } + + /* Rate did match, so reset the missed_rate_counter */ + lq_sta->missed_rate_counter = 0; + + if (!lq_sta->search_better_tbl) { + curr_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + other_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + } else { + curr_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + other_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + } + + if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) { + IWL_DEBUG_RATE(mvm, + "Neither active nor search matches tx rate\n"); + tmp_tbl = &lq_sta->lq_info[lq_sta->active_tbl]; + rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE"); + tmp_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)]; + rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH"); + rs_dump_rate(mvm, &lq_rate, "ACTUAL"); + + /* no matching table found, let's by-pass the data collection + * and continue to perform rate scale to find the rate table + */ + rs_stay_in_table(lq_sta, true); + goto done; + } + + /* Updating the frame history depends on whether packets were + * aggregated. + * + * For aggregation, all packets were transmitted at the same rate, the + * first index into rate scale table. + */ + if (info->flags & IEEE80211_TX_STAT_AMPDU) { + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len, + reduced_txp); + + /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat + * it as a single frame loss as we don't want the success ratio + * to dip too quickly because a BA wasn't received. + * For TPC, there's no need for this optimisation since we want + * to recover very quickly from a bad power reduction and, + * therefore we'd like the success ratio to get an immediate hit + * when failing to get a BA, so we'd switch back to a lower or + * zero power reduction. When FW transmits agg with a rate + * different from the initial rate, it will not use reduced txp + * and will send BA notification twice (one empty with reduced + * txp equal to the value from LQ and one with reduced txp 0). + * We need to update counters for each txp level accordingly. + */ + if (info->status.ampdu_ack_len == 0) + info->status.ampdu_len = 1; + + rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, + tx_resp_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len); + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += info->status.ampdu_ack_len; + lq_sta->total_failed += (info->status.ampdu_len - + info->status.ampdu_ack_len); + } + } else { + /* For legacy, update frame history with for each Tx retry. */ + retries = info->status.rates[0].count - 1; + /* HW doesn't send more than 15 retries */ + retries = min(retries, 15); + + /* The last transmission may have been successful */ + legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK); + /* Collect data for each rate used during failed TX attempts */ + for (i = 0; i <= retries; ++i) { + lq_hwrate = le32_to_cpu(table->rs_table[i]); + if (rs_rate_from_ucode_rate(lq_hwrate, info->band, + &lq_rate)) { + WARN_ON_ONCE(1); + return; + } + + /* Only collect stats if retried rate is in the same RS + * table as active/search. + */ + if (rs_rate_column_match(&lq_rate, &curr_tbl->rate)) + tmp_tbl = curr_tbl; + else if (rs_rate_column_match(&lq_rate, + &other_tbl->rate)) + tmp_tbl = other_tbl; + else + continue; + + rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success, + reduced_txp); + rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl, + tx_resp_rate.index, 1, + i < retries ? 0 : legacy_success); + } + + /* Update success/fail counts if not searching for new mode */ + if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { + lq_sta->total_success += legacy_success; + lq_sta->total_failed += retries + (1 - legacy_success); + } + } + /* The last TX rate is cached in lq_sta; it's set in if/else above */ + lq_sta->last_rate_n_flags = lq_hwrate; + IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp); +done: + /* See if there's a better rate or modulation mode to try. */ + if (sta->supp_rates[info->band]) + rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp); +} + +void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int tid, struct ieee80211_tx_info *info, bool ndp) +{ + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + /* If it's locked we are in middle of init flow + * just wait for next tx status to update the lq_sta data + */ + if (!spin_trylock(&mvmsta->lq_sta.rs_drv.pers.lock)) + return; + + __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); +} + #ifdef CONFIG_MAC80211_DEBUGFS static void rs_build_rates_table_from_fixed(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq_cmd, @@ -3569,7 +3603,7 @@ static void rs_set_lq_ss_params(struct iwl_mvm *mvm, bfersta_ss_params &= ~LQ_SS_BFER_ALLOWED; bfersta_lq_cmd->ss_params = cpu_to_le32(bfersta_ss_params); - iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd, false); + iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd); ss_params |= LQ_SS_BFER_ALLOWED; IWL_DEBUG_RATE(mvm, @@ -3735,7 +3769,7 @@ static void rs_program_fix_rate(struct iwl_mvm *mvm, if (lq_sta->pers.dbg_fixed_rate) { rs_fill_lq_cmd(mvm, NULL, lq_sta, NULL); - iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq, false); + iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq); } } @@ -4127,10 +4161,15 @@ static const struct rate_control_ops rs_mvm_ops_drv = { void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum nl80211_band band, bool update) { - if (iwl_mvm_has_tlc_offload(mvm)) + if (iwl_mvm_has_tlc_offload(mvm)) { rs_fw_rate_init(mvm, sta, band, update); - else - rs_drv_rate_init(mvm, sta, band, update); + } else { + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + + spin_lock(&mvmsta->lq_sta.rs_drv.pers.lock); + rs_drv_rate_init(mvm, sta, band); + spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock); + } } int iwl_mvm_rate_control_register(void) @@ -4160,7 +4199,7 @@ static int rs_drv_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, lq->flags &= ~LQ_FLAG_USE_RTS_MSK; } - return iwl_mvm_send_lq_cmd(mvm, lq, false); + return iwl_mvm_send_lq_cmd(mvm, lq); } /** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index f7eb60dbaf20..428642e66658 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -4,7 +4,7 @@ * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2015 Intel Mobile Communications GmbH * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * Contact Information: * Intel Linux Wireless <[email protected]> @@ -390,6 +390,7 @@ struct iwl_lq_sta { s8 last_rssi; struct rs_rate_stats tx_stats[RS_COLUMN_COUNT][IWL_RATE_COUNT]; struct iwl_mvm *drv; + spinlock_t lock; /* for races in reinit/update table */ } pers; }; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 64f950501287..854edd7d7103 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -463,20 +463,22 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, } int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, - const u8 *data, u32 count) + const u8 *data, u32 count, bool async) { - struct iwl_rxq_sync_cmd *cmd; + u8 buf[sizeof(struct iwl_rxq_sync_cmd) + + sizeof(struct iwl_mvm_rss_sync_notif)]; + struct iwl_rxq_sync_cmd *cmd = (void *)buf; u32 data_size = sizeof(*cmd) + count; int ret; - /* should be DWORD aligned */ - if (WARN_ON(count & 3 || count > IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE)) + /* + * size must be a multiple of DWORD + * Ensure we don't overflow buf + */ + if (WARN_ON(count & 3 || + count > sizeof(struct iwl_mvm_rss_sync_notif))) return -EINVAL; - cmd = kzalloc(data_size, GFP_KERNEL); - if (!cmd) - return -ENOMEM; - cmd->rxq_mask = cpu_to_le32(rxq_mask); cmd->count = cpu_to_le32(count); cmd->flags = 0; @@ -485,9 +487,8 @@ int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask, ret = iwl_mvm_send_cmd_pdu(mvm, WIDE_ID(DATA_PATH_GROUP, TRIGGER_RX_QUEUES_NOTIF_CMD), - 0, data_size, cmd); + async ? CMD_ASYNC : 0, data_size, cmd); - kfree(cmd); return ret; } @@ -503,14 +504,31 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 buffer_size) !ieee80211_sn_less(sn1, sn2 - buffer_size); } +static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn) +{ + struct iwl_mvm_rss_sync_notif notif = { + .metadata.type = IWL_MVM_RXQ_NSSN_SYNC, + .metadata.sync = 0, + .nssn_sync.baid = baid, + .nssn_sync.nssn = nssn, + }; + + iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, sizeof(notif)); +} + #define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10) +enum iwl_mvm_release_flags { + IWL_MVM_RELEASE_SEND_RSS_SYNC = BIT(0), + IWL_MVM_RELEASE_FROM_RSS_SYNC = BIT(1), +}; + static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct napi_struct *napi, struct iwl_mvm_baid_data *baid_data, struct iwl_mvm_reorder_buffer *reorder_buf, - u16 nssn) + u16 nssn, u32 flags) { struct iwl_mvm_reorder_buf_entry *entries = &baid_data->entries[reorder_buf->queue * @@ -519,6 +537,18 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, lockdep_assert_held(&reorder_buf->lock); + /* + * We keep the NSSN not too far behind, if we are sync'ing it and it + * is more than 2048 ahead of us, it must be behind us. Discard it. + * This can happen if the queue that hit the 0 / 2048 seqno was lagging + * behind and this queue already processed packets. The next if + * would have caught cases where this queue would have processed less + * than 64 packets, but it may have processed more than 64 packets. + */ + if ((flags & IWL_MVM_RELEASE_FROM_RSS_SYNC) && + ieee80211_sn_less(nssn, ssn)) + goto set_timer; + /* ignore nssn smaller than head sn - this can happen due to timeout */ if (iwl_mvm_is_sn_less(nssn, ssn, reorder_buf->buf_size)) goto set_timer; @@ -529,6 +559,9 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, struct sk_buff *skb; ssn = ieee80211_sn_inc(ssn); + if ((flags & IWL_MVM_RELEASE_SEND_RSS_SYNC) && + (ssn == 2048 || ssn == 0)) + iwl_mvm_sync_nssn(mvm, baid_data->baid, ssn); /* * Empty the list. Will have more than one frame for A-MSDU. @@ -615,7 +648,8 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) sta_id, sn); iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif, sta, baid_data->tid); - iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, buf, sn); + iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, + buf, sn, IWL_MVM_RELEASE_SEND_RSS_SYNC); rcu_read_unlock(); } else { /* @@ -657,7 +691,8 @@ static void iwl_mvm_del_ba(struct iwl_mvm *mvm, int queue, spin_lock_bh(&reorder_buf->lock); iwl_mvm_release_frames(mvm, sta, NULL, ba_data, reorder_buf, ieee80211_sn_add(reorder_buf->head_sn, - reorder_buf->buf_size)); + reorder_buf->buf_size), + 0); spin_unlock_bh(&reorder_buf->lock); del_timer_sync(&reorder_buf->reorder_timer); @@ -665,8 +700,54 @@ out: rcu_read_unlock(); } -void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, - int queue) +static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm, + struct napi_struct *napi, + u8 baid, u16 nssn, int queue, + u32 flags) +{ + struct ieee80211_sta *sta; + struct iwl_mvm_reorder_buffer *reorder_buf; + struct iwl_mvm_baid_data *ba_data; + + IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n", + baid, nssn); + + if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID || + baid >= ARRAY_SIZE(mvm->baid_map))) + return; + + rcu_read_lock(); + + ba_data = rcu_dereference(mvm->baid_map[baid]); + if (WARN_ON_ONCE(!ba_data)) + goto out; + + sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) + goto out; + + reorder_buf = &ba_data->reorder_buf[queue]; + + spin_lock_bh(&reorder_buf->lock); + iwl_mvm_release_frames(mvm, sta, napi, ba_data, + reorder_buf, nssn, flags); + spin_unlock_bh(&reorder_buf->lock); + +out: + rcu_read_unlock(); +} + +static void iwl_mvm_nssn_sync(struct iwl_mvm *mvm, + struct napi_struct *napi, int queue, + const struct iwl_mvm_nssn_sync_data *data) +{ + iwl_mvm_release_frames_from_notif(mvm, napi, data->baid, + data->nssn, queue, + IWL_MVM_RELEASE_FROM_RSS_SYNC); +} + +void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, + struct iwl_rx_cmd_buffer *rxb, int queue) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_rxq_sync_notification *notif; @@ -687,6 +768,10 @@ void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, case IWL_MVM_RXQ_NOTIF_DEL_BA: iwl_mvm_del_ba(mvm, queue, (void *)internal_notif->data); break; + case IWL_MVM_RXQ_NSSN_SYNC: + iwl_mvm_nssn_sync(mvm, napi, queue, + (void *)internal_notif->data); + break; default: WARN_ONCE(1, "Invalid identifier %d", internal_notif->type); } @@ -785,7 +870,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, } if (ieee80211_is_back_req(hdr->frame_control)) { - iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn); + iwl_mvm_release_frames(mvm, sta, napi, baid_data, + buffer, nssn, 0); goto drop; } @@ -794,7 +880,10 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * If the SN is smaller than the NSSN it might need to first go into * the reorder buffer, in which case we just release up to it and the * rest of the function will take care of storing it and releasing up to - * the nssn + * the nssn. + * This should not happen. This queue has been lagging and it should + * have been updated by a IWL_MVM_RXQ_NSSN_SYNC notification. Be nice + * and update the other queues. */ if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size, buffer->buf_size) || @@ -802,7 +891,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn; iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, - min_sn); + min_sn, IWL_MVM_RELEASE_SEND_RSS_SYNC); } /* drop any oudated packets */ @@ -813,8 +902,23 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, if (!buffer->num_stored && ieee80211_sn_less(sn, nssn)) { if (iwl_mvm_is_sn_less(buffer->head_sn, nssn, buffer->buf_size) && - (!amsdu || last_subframe)) + (!amsdu || last_subframe)) { + /* + * If we crossed the 2048 or 0 SN, notify all the + * queues. This is done in order to avoid having a + * head_sn that lags behind for too long. When that + * happens, we can get to a situation where the head_sn + * is within the interval [nssn - buf_size : nssn] + * which will make us think that the nssn is a packet + * that we already freed because of the reordering + * buffer and we will ignore it. So maintain the + * head_sn somewhat updated across all the queues: + * when it crosses 0 and 2048. + */ + if (sn == 2048 || sn == 0) + iwl_mvm_sync_nssn(mvm, baid, sn); buffer->head_sn = nssn; + } /* No need to update AMSDU last SN - we are moving the head */ spin_unlock_bh(&buffer->lock); return false; @@ -829,8 +933,11 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * while technically there is no hole and we can move forward. */ if (!buffer->num_stored && sn == buffer->head_sn) { - if (!amsdu || last_subframe) + if (!amsdu || last_subframe) { + if (sn == 2048 || sn == 0) + iwl_mvm_sync_nssn(mvm, baid, sn); buffer->head_sn = ieee80211_sn_inc(buffer->head_sn); + } /* No need to update AMSDU last SN - we are moving the head */ spin_unlock_bh(&buffer->lock); return false; @@ -875,7 +982,9 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * release notification with up to date NSSN. */ if (!amsdu || last_subframe) - iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn); + iwl_mvm_release_frames(mvm, sta, napi, baid_data, + buffer, nssn, + IWL_MVM_RELEASE_SEND_RSS_SYNC); spin_unlock_bh(&buffer->lock); return true; @@ -1840,40 +1949,14 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, out: rcu_read_unlock(); } + void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi, struct iwl_rx_cmd_buffer *rxb, int queue) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_frame_release *release = (void *)pkt->data; - struct ieee80211_sta *sta; - struct iwl_mvm_reorder_buffer *reorder_buf; - struct iwl_mvm_baid_data *ba_data; - - int baid = release->baid; - - IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n", - release->baid, le16_to_cpu(release->nssn)); - if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID)) - return; - - rcu_read_lock(); - - ba_data = rcu_dereference(mvm->baid_map[baid]); - if (WARN_ON_ONCE(!ba_data)) - goto out; - - sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]); - if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) - goto out; - - reorder_buf = &ba_data->reorder_buf[queue]; - - spin_lock_bh(&reorder_buf->lock); - iwl_mvm_release_frames(mvm, sta, napi, ba_data, reorder_buf, - le16_to_cpu(release->nssn)); - spin_unlock_bh(&reorder_buf->lock); - -out: - rcu_read_unlock(); + iwl_mvm_release_frames_from_notif(mvm, napi, release->baid, + le16_to_cpu(release->nssn), + queue, 0); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index f545a737a92d..10f18536dd0d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1684,6 +1684,8 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, */ if (iwl_mvm_has_tlc_offload(mvm)) iwl_mvm_rs_add_sta(mvm, mvm_sta); + else + spin_lock_init(&mvm_sta->lq_sta.rs_drv.pers.lock); iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant); @@ -2421,7 +2423,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) static void iwl_mvm_sync_rxq_del_ba(struct iwl_mvm *mvm, u8 baid) { - struct iwl_mvm_delba_notif notif = { + struct iwl_mvm_rss_sync_notif notif = { .metadata.type = IWL_MVM_RXQ_NOTIF_DEL_BA, .metadata.sync = 1, .delba.baid = baid, @@ -2972,7 +2974,7 @@ out: IWL_DEBUG_HT(mvm, "Tx aggregation enabled on ra = %pM tid = %d\n", sta->addr, tid); - return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq, false); + return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq); } static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 4487cc3e07c1..8d70093847cb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -343,9 +343,17 @@ struct iwl_mvm_delba_data { u32 baid; } __packed; -struct iwl_mvm_delba_notif { +struct iwl_mvm_nssn_sync_data { + u32 baid; + u32 nssn; +} __packed; + +struct iwl_mvm_rss_sync_notif { struct iwl_mvm_internal_rxq_notif metadata; - struct iwl_mvm_delba_data delba; + union { + struct iwl_mvm_delba_data delba; + struct iwl_mvm_nssn_sync_data nssn_sync; + }; } __packed; /** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index a3e5d88f1c07..6ac114a393cc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -831,6 +831,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, unsigned int tcp_payload_len; unsigned int mss = skb_shinfo(skb)->gso_size; bool ipv4 = (skb->protocol == htons(ETH_P_IP)); + bool qos = ieee80211_is_data_qos(hdr->frame_control); u16 ip_base_id = ipv4 ? ntohs(ip_hdr(skb)->id) : 0; skb_shinfo(skb)->gso_size = num_subframes * mss; @@ -864,7 +865,7 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, if (tcp_payload_len > mss) { skb_shinfo(tmp)->gso_size = mss; } else { - if (ieee80211_is_data_qos(hdr->frame_control)) { + if (qos) { u8 *qc; if (ipv4) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 9ecd5f09615a..b8e20a01c192 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -653,12 +653,12 @@ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id, * this case to clear the state indicating that station creation is in * progress. */ -int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync) +int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq) { struct iwl_host_cmd cmd = { .id = LQ_CMD, .len = { sizeof(struct iwl_lq_cmd), }, - .flags = sync ? 0 : CMD_ASYNC, + .flags = CMD_ASYNC, .data = { lq, }, }; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index ea2a03d4bf55..de711c1160d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -604,10 +604,13 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x6010, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x6014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8010, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xE010, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xE014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index fa4245d0d4a8..2f0ba7ef53b8 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -435,6 +435,8 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans, DMA_TO_DEVICE); } + meta->tbs = 0; + if (trans->cfg->use_tfh) { struct iwl_tfh_tfd *tfd_fh = (void *)tfd; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 3aeff7a3c3d8..f86c2891310a 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3619,10 +3619,12 @@ static int hwsim_dump_radio_nl(struct sk_buff *skb, hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &hwsim_genl_family, NLM_F_MULTI, HWSIM_CMD_GET_RADIO); - if (!hdr) + if (hdr) { + genl_dump_check_consistent(cb, hdr); + genlmsg_end(skb, hdr); + } else { res = -EMSGSIZE; - genl_dump_check_consistent(cb, hdr); - genlmsg_end(skb, hdr); + } } done: diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 3e442c7f7882..095837fba300 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -124,6 +124,7 @@ enum { #define MWIFIEX_MAX_TOTAL_SCAN_TIME (MWIFIEX_TIMER_10S - MWIFIEX_TIMER_1S) +#define WPA_GTK_OUI_OFFSET 2 #define RSN_GTK_OUI_OFFSET 2 #define MWIFIEX_OUI_NOT_PRESENT 0 diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c index 0d6d41727037..21dda385f6c6 100644 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@ -181,7 +181,8 @@ mwifiex_is_wpa_oui_present(struct mwifiex_bssdescriptor *bss_desc, u32 cipher) u8 ret = MWIFIEX_OUI_NOT_PRESENT; if (has_vendor_hdr(bss_desc->bcn_wpa_ie, WLAN_EID_VENDOR_SPECIFIC)) { - iebody = (struct ie_body *) bss_desc->bcn_wpa_ie->data; + iebody = (struct ie_body *)((u8 *)bss_desc->bcn_wpa_ie->data + + WPA_GTK_OUI_OFFSET); oui = &mwifiex_wpa_oui[cipher][0]; ret = mwifiex_search_oui_in_ie(iebody, oui); if (ret) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3ef07b63613e..4679fcf1a1c4 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1653,9 +1653,6 @@ static int __init netback_init(void) #ifdef CONFIG_DEBUG_FS xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL); - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - pr_warn("Init of debugfs returned %ld!\n", - PTR_ERR(xen_netback_dbg_root)); #endif /* CONFIG_DEBUG_FS */ return 0; diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 41034264bd34..f533b7372d59 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -170,50 +170,26 @@ DEFINE_SHOW_ATTRIBUTE(xenvif_ctrl); static void xenvif_debugfs_addif(struct xenvif *vif) { - struct dentry *pfile; int i; - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - return; - vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name, xen_netback_dbg_root); - if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) { - for (i = 0; i < vif->num_queues; ++i) { - char filename[sizeof("io_ring_q") + 4]; - - snprintf(filename, sizeof(filename), "io_ring_q%d", i); - pfile = debugfs_create_file(filename, - 0600, - vif->xenvif_dbg_root, - &vif->queues[i], - &xenvif_dbg_io_ring_ops_fops); - if (IS_ERR_OR_NULL(pfile)) - pr_warn("Creation of io_ring file returned %ld!\n", - PTR_ERR(pfile)); - } + for (i = 0; i < vif->num_queues; ++i) { + char filename[sizeof("io_ring_q") + 4]; - if (vif->ctrl_irq) { - pfile = debugfs_create_file("ctrl", - 0400, - vif->xenvif_dbg_root, - vif, - &xenvif_ctrl_fops); - if (IS_ERR_OR_NULL(pfile)) - pr_warn("Creation of ctrl file returned %ld!\n", - PTR_ERR(pfile)); - } - } else - netdev_warn(vif->dev, - "Creation of vif debugfs dir returned %ld!\n", - PTR_ERR(vif->xenvif_dbg_root)); + snprintf(filename, sizeof(filename), "io_ring_q%d", i); + debugfs_create_file(filename, 0600, vif->xenvif_dbg_root, + &vif->queues[i], + &xenvif_dbg_io_ring_ops_fops); + } + + if (vif->ctrl_irq) + debugfs_create_file("ctrl", 0400, vif->xenvif_dbg_root, vif, + &xenvif_ctrl_fops); } static void xenvif_debugfs_delif(struct xenvif *vif) { - if (IS_ERR_OR_NULL(xen_netback_dbg_root)) - return; - debugfs_remove_recursive(vif->xenvif_dbg_root); vif->xenvif_dbg_root = NULL; } diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index e65d027b91fa..529be35ac178 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -244,7 +244,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv) /* Reset possible fault of previous session */ clear_bit(NFCMRVL_PHY_ERROR, &priv->flags); - if (priv->config.reset_n_io) { + if (gpio_is_valid(priv->config.reset_n_io)) { nfc_info(priv->dev, "reset the chip\n"); gpio_set_value(priv->config.reset_n_io, 0); usleep_range(5000, 10000); @@ -255,7 +255,7 @@ void nfcmrvl_chip_reset(struct nfcmrvl_private *priv) void nfcmrvl_chip_halt(struct nfcmrvl_private *priv) { - if (priv->config.reset_n_io) + if (gpio_is_valid(priv->config.reset_n_io)) gpio_set_value(priv->config.reset_n_io, 0); } diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 9a22056e8d9e..e5a622ce4b95 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -26,7 +26,7 @@ static unsigned int hci_muxed; static unsigned int flow_control; static unsigned int break_control; -static unsigned int reset_n_io; +static int reset_n_io = -EINVAL; /* ** NFCMRVL NCI OPS @@ -231,5 +231,5 @@ MODULE_PARM_DESC(break_control, "Tell if UART driver must drive break signal."); module_param(hci_muxed, uint, 0); MODULE_PARM_DESC(hci_muxed, "Tell if transport is muxed in HCI one."); -module_param(reset_n_io, uint, 0); +module_param(reset_n_io, int, 0); MODULE_PARM_DESC(reset_n_io, "GPIO that is wired to RESET_N signal."); diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index 945cc903d8f1..888e298f610b 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -305,6 +305,7 @@ static int nfcmrvl_probe(struct usb_interface *intf, /* No configuration for USB */ memset(&config, 0, sizeof(config)); + config.reset_n_io = -EINVAL; nfc_info(&udev->dev, "intf %p id %p\n", intf, id); diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index c3e10b6ab3a4..f25f1ec5f9e9 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -333,6 +333,8 @@ static int st_nci_hci_connectivity_event_received(struct nci_dev *ndev, transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM; transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], transaction->aid_len); diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index 06fc542fd198..6586378cacb0 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -317,6 +317,8 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); + if (!transaction) + return -ENOMEM; transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 62d00fffa4af..3508a79110c7 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -62,14 +62,14 @@ static ssize_t sector_size_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_btt->lbasize, btt_lbasize_supported); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -91,11 +91,11 @@ static ssize_t uuid_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = nd_uuid_store(dev, &nd_btt->uuid, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -120,13 +120,13 @@ static ssize_t namespace_store(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -138,14 +138,14 @@ static ssize_t size_show(struct device *dev, struct nd_btt *nd_btt = to_nd_btt(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) rc = sprintf(buf, "%llu\n", nd_btt->size); else { /* no size to convey if the btt instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2dca3034fee0..798c5c4aea9c 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -26,7 +26,7 @@ int nvdimm_major; static int nvdimm_bus_major; -static struct class *nd_class; +struct class *nd_class; static DEFINE_IDA(nd_ida); static int to_nd_device_type(struct device *dev) @@ -73,7 +73,7 @@ static void nvdimm_bus_probe_end(struct nvdimm_bus *nvdimm_bus) { nvdimm_bus_lock(&nvdimm_bus->dev); if (--nvdimm_bus->probe_active == 0) - wake_up(&nvdimm_bus->probe_wait); + wake_up(&nvdimm_bus->wait); nvdimm_bus_unlock(&nvdimm_bus->dev); } @@ -91,7 +91,10 @@ static int nvdimm_bus_probe(struct device *dev) dev->driver->name, dev_name(dev)); nvdimm_bus_probe_start(nvdimm_bus); + debug_nvdimm_lock(dev); rc = nd_drv->probe(dev); + debug_nvdimm_unlock(dev); + if (rc == 0) nd_region_probe_success(nvdimm_bus, dev); else @@ -113,8 +116,11 @@ static int nvdimm_bus_remove(struct device *dev) struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); int rc = 0; - if (nd_drv->remove) + if (nd_drv->remove) { + debug_nvdimm_lock(dev); rc = nd_drv->remove(dev); + debug_nvdimm_unlock(dev); + } nd_region_disable(nvdimm_bus, dev); dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, @@ -140,7 +146,7 @@ static void nvdimm_bus_shutdown(struct device *dev) void nd_device_notify(struct device *dev, enum nvdimm_event event) { - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_device_driver *nd_drv; @@ -148,7 +154,7 @@ void nd_device_notify(struct device *dev, enum nvdimm_event event) if (nd_drv->notify) nd_drv->notify(dev, event); } - device_unlock(dev); + nd_device_unlock(dev); } EXPORT_SYMBOL(nd_device_notify); @@ -296,7 +302,7 @@ static void nvdimm_bus_release(struct device *dev) kfree(nvdimm_bus); } -static bool is_nvdimm_bus(struct device *dev) +bool is_nvdimm_bus(struct device *dev) { return dev->release == nvdimm_bus_release; } @@ -341,7 +347,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); INIT_LIST_HEAD(&nvdimm_bus->mapping_list); - init_waitqueue_head(&nvdimm_bus->probe_wait); + init_waitqueue_head(&nvdimm_bus->wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); if (nvdimm_bus->id < 0) { kfree(nvdimm_bus); @@ -426,6 +432,9 @@ static int nd_bus_remove(struct device *dev) list_del_init(&nvdimm_bus->list); mutex_unlock(&nvdimm_bus_list_mutex); + wait_event(nvdimm_bus->wait, + atomic_read(&nvdimm_bus->ioctl_active) == 0); + nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); @@ -547,13 +556,38 @@ EXPORT_SYMBOL(nd_device_register); void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + nd_device_lock(dev); + killed = kill_device(dev); + nd_device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break; @@ -859,10 +893,12 @@ void wait_nvdimm_bus_probe_idle(struct device *dev) do { if (nvdimm_bus->probe_active == 0) break; - nvdimm_bus_unlock(&nvdimm_bus->dev); - wait_event(nvdimm_bus->probe_wait, + nvdimm_bus_unlock(dev); + nd_device_unlock(dev); + wait_event(nvdimm_bus->wait, nvdimm_bus->probe_active == 0); - nvdimm_bus_lock(&nvdimm_bus->dev); + nd_device_lock(dev); + nvdimm_bus_lock(dev); } while (true); } @@ -945,20 +981,19 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, int read_only, unsigned int ioctl_cmd, unsigned long arg) { struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; - static char out_env[ND_CMD_MAX_ENVELOPE]; - static char in_env[ND_CMD_MAX_ENVELOPE]; const struct nd_cmd_desc *desc = NULL; unsigned int cmd = _IOC_NR(ioctl_cmd); struct device *dev = &nvdimm_bus->dev; void __user *p = (void __user *) arg; + char *out_env = NULL, *in_env = NULL; const char *cmd_name, *dimm_name; u32 in_len = 0, out_len = 0; unsigned int func = cmd; unsigned long cmd_mask; struct nd_cmd_pkg pkg; int rc, i, cmd_rc; + void *buf = NULL; u64 buf_len = 0; - void *buf; if (nvdimm) { desc = nd_cmd_dimm_desc(cmd); @@ -989,7 +1024,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, case ND_CMD_ARS_START: case ND_CMD_CLEAR_ERROR: case ND_CMD_CALL: - dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n", + dev_dbg(dev, "'%s' command while read-only.\n", nvdimm ? nvdimm_cmd_name(cmd) : nvdimm_bus_cmd_name(cmd)); return -EPERM; @@ -998,6 +1033,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, } /* process an input envelope */ + in_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!in_env) + return -ENOMEM; for (i = 0; i < desc->in_num; i++) { u32 in_size, copy; @@ -1005,14 +1043,17 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (in_size == UINT_MAX) { dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n", __func__, dimm_name, cmd_name, i); - return -ENXIO; + rc = -ENXIO; + goto out; } - if (in_len < sizeof(in_env)) - copy = min_t(u32, sizeof(in_env) - in_len, in_size); + if (in_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - in_len, in_size); else copy = 0; - if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) - return -EFAULT; + if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) { + rc = -EFAULT; + goto out; + } in_len += in_size; } @@ -1024,6 +1065,12 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, } /* process an output envelope */ + out_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!out_env) { + rc = -ENOMEM; + goto out; + } + for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, (u32 *) in_env, (u32 *) out_env, 0); @@ -1032,15 +1079,18 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (out_size == UINT_MAX) { dev_dbg(dev, "%s unknown output size cmd: %s field: %d\n", dimm_name, cmd_name, i); - return -EFAULT; + rc = -EFAULT; + goto out; } - if (out_len < sizeof(out_env)) - copy = min_t(u32, sizeof(out_env) - out_len, out_size); + if (out_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - out_len, out_size); else copy = 0; if (copy && copy_from_user(&out_env[out_len], - p + in_len + out_len, copy)) - return -EFAULT; + p + in_len + out_len, copy)) { + rc = -EFAULT; + goto out; + } out_len += out_size; } @@ -1048,19 +1098,23 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (buf_len > ND_IOCTL_MAX_BUFLEN) { dev_dbg(dev, "%s cmd: %s buf_len: %llu > %d\n", dimm_name, cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN); - return -EINVAL; + rc = -EINVAL; + goto out; } buf = vmalloc(buf_len); - if (!buf) - return -ENOMEM; + if (!buf) { + rc = -ENOMEM; + goto out; + } if (copy_from_user(buf, p, buf_len)) { rc = -EFAULT; goto out; } - nvdimm_bus_lock(&nvdimm_bus->dev); + nd_device_lock(dev); + nvdimm_bus_lock(dev); rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, func, buf); if (rc) goto out_unlock; @@ -1075,39 +1129,24 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, nvdimm_account_cleared_poison(nvdimm_bus, clear_err->address, clear_err->cleared); } - nvdimm_bus_unlock(&nvdimm_bus->dev); if (copy_to_user(p, buf, buf_len)) rc = -EFAULT; - vfree(buf); - return rc; - - out_unlock: - nvdimm_bus_unlock(&nvdimm_bus->dev); - out: +out_unlock: + nvdimm_bus_unlock(dev); + nd_device_unlock(dev); +out: + kfree(in_env); + kfree(out_env); vfree(buf); return rc; } -static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - long id = (long) file->private_data; - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; - - ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); - mutex_lock(&nvdimm_bus_list_mutex); - list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - if (nvdimm_bus->id == id) { - rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg); - break; - } - } - mutex_unlock(&nvdimm_bus_list_mutex); - - return rc; -} +enum nd_ioctl_mode { + BUS_IOCTL, + DIMM_IOCTL, +}; static int match_dimm(struct device *dev, void *data) { @@ -1122,31 +1161,62 @@ static int match_dimm(struct device *dev, void *data) return 0; } -static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg, + enum nd_ioctl_mode mode) + { - int rc = -ENXIO, ro; - struct nvdimm_bus *nvdimm_bus; + struct nvdimm_bus *nvdimm_bus, *found = NULL; + long id = (long) file->private_data; + struct nvdimm *nvdimm = NULL; + int rc, ro; ro = ((file->f_flags & O_ACCMODE) == O_RDONLY); mutex_lock(&nvdimm_bus_list_mutex); list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) { - struct device *dev = device_find_child(&nvdimm_bus->dev, - file->private_data, match_dimm); - struct nvdimm *nvdimm; - - if (!dev) - continue; + if (mode == DIMM_IOCTL) { + struct device *dev; + + dev = device_find_child(&nvdimm_bus->dev, + file->private_data, match_dimm); + if (!dev) + continue; + nvdimm = to_nvdimm(dev); + found = nvdimm_bus; + } else if (nvdimm_bus->id == id) { + found = nvdimm_bus; + } - nvdimm = to_nvdimm(dev); - rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); - put_device(dev); - break; + if (found) { + atomic_inc(&nvdimm_bus->ioctl_active); + break; + } } mutex_unlock(&nvdimm_bus_list_mutex); + if (!found) + return -ENXIO; + + nvdimm_bus = found; + rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg); + + if (nvdimm) + put_device(&nvdimm->dev); + if (atomic_dec_and_test(&nvdimm_bus->ioctl_active)) + wake_up(&nvdimm_bus->wait); + return rc; } +static long bus_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, BUS_IOCTL); +} + +static long dimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return nd_ioctl(file, cmd, arg, DIMM_IOCTL); +} + static int nd_open(struct inode *inode, struct file *file) { long minor = iminor(inode); @@ -1158,16 +1228,16 @@ static int nd_open(struct inode *inode, struct file *file) static const struct file_operations nvdimm_bus_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nd_ioctl, - .compat_ioctl = nd_ioctl, + .unlocked_ioctl = bus_ioctl, + .compat_ioctl = bus_ioctl, .llseek = noop_llseek, }; static const struct file_operations nvdimm_fops = { .owner = THIS_MODULE, .open = nd_open, - .unlocked_ioctl = nvdimm_ioctl, - .compat_ioctl = nvdimm_ioctl, + .unlocked_ioctl = dimm_ioctl, + .compat_ioctl = dimm_ioctl, .llseek = noop_llseek, }; diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 5e1f060547bf..9204f1e9fd14 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -246,7 +246,7 @@ static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, * * Enforce that uuids can only be changed while the device is disabled * (driver detached) - * LOCKING: expects device_lock() is held on entry + * LOCKING: expects nd_device_lock() is held on entry */ int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, size_t len) @@ -347,15 +347,15 @@ static DEVICE_ATTR_RO(provider); static int flush_namespaces(struct device *dev, void *data) { - device_lock(dev); - device_unlock(dev); + nd_device_lock(dev); + nd_device_unlock(dev); return 0; } static int flush_regions_dimms(struct device *dev, void *data) { - device_lock(dev); - device_unlock(dev); + nd_device_lock(dev); + nd_device_unlock(dev); device_for_each_child(dev, NULL, flush_namespaces); return 0; } diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index dfecd6e17043..29a065e769ea 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -484,12 +484,12 @@ static ssize_t security_store(struct device *dev, * done while probing is idle and the DIMM is not in active use * in any region. */ - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __security_store(dev, buf, len); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 2d8d7e554877..a16e52251a30 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -410,7 +410,7 @@ static ssize_t alt_name_store(struct device *dev, struct nd_region *nd_region = to_nd_region(dev->parent); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __alt_name_store(dev, buf, len); @@ -418,7 +418,7 @@ static ssize_t alt_name_store(struct device *dev, rc = nd_namespace_label_update(nd_region, dev); dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1077,7 +1077,7 @@ static ssize_t size_store(struct device *dev, if (rc) return rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __size_store(dev, val); @@ -1103,7 +1103,7 @@ static ssize_t size_store(struct device *dev, dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1286,7 +1286,7 @@ static ssize_t uuid_store(struct device *dev, } else return -ENXIO; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); if (to_ndns(dev)->claim) @@ -1302,7 +1302,7 @@ static ssize_t uuid_store(struct device *dev, dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1376,7 +1376,7 @@ static ssize_t sector_size_store(struct device *dev, } else return -ENXIO; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); if (to_ndns(dev)->claim) rc = -EBUSY; @@ -1387,7 +1387,7 @@ static ssize_t sector_size_store(struct device *dev, dev_dbg(dev, "result: %zd %s: %s%s", rc, rc < 0 ? "tried" : "wrote", buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -1502,9 +1502,9 @@ static ssize_t holder_show(struct device *dev, struct nd_namespace_common *ndns = to_ndns(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = sprintf(buf, "%s\n", ndns->claim ? dev_name(ndns->claim) : ""); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1541,7 +1541,7 @@ static ssize_t holder_class_store(struct device *dev, struct nd_region *nd_region = to_nd_region(dev->parent); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); rc = __holder_class_store(dev, buf); @@ -1549,7 +1549,7 @@ static ssize_t holder_class_store(struct device *dev, rc = nd_namespace_label_update(nd_region, dev); dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc < 0 ? rc : len; } @@ -1560,7 +1560,7 @@ static ssize_t holder_class_show(struct device *dev, struct nd_namespace_common *ndns = to_ndns(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (ndns->claim_class == NVDIMM_CCLASS_NONE) rc = sprintf(buf, "\n"); else if ((ndns->claim_class == NVDIMM_CCLASS_BTT) || @@ -1572,7 +1572,7 @@ static ssize_t holder_class_show(struct device *dev, rc = sprintf(buf, "dax\n"); else rc = sprintf(buf, "<unknown>\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1586,7 +1586,7 @@ static ssize_t mode_show(struct device *dev, char *mode; ssize_t rc; - device_lock(dev); + nd_device_lock(dev); claim = ndns->claim; if (claim && is_nd_btt(claim)) mode = "safe"; @@ -1599,7 +1599,7 @@ static ssize_t mode_show(struct device *dev, else mode = "raw"; rc = sprintf(buf, "%s\n", mode); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -1703,8 +1703,8 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) * Flush any in-progess probes / removals in the driver * for the raw personality of this namespace. */ - device_lock(&ndns->dev); - device_unlock(&ndns->dev); + nd_device_lock(&ndns->dev); + nd_device_unlock(&ndns->dev); if (ndns->dev.driver) { dev_dbg(&ndns->dev, "is active, can't bind %s\n", dev_name(dev)); diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 391e88de3a29..0ac52b6eb00e 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -9,6 +9,7 @@ #include <linux/sizes.h> #include <linux/mutex.h> #include <linux/nd.h> +#include "nd.h" extern struct list_head nvdimm_bus_list; extern struct mutex nvdimm_bus_list_mutex; @@ -17,10 +18,11 @@ extern struct workqueue_struct *nvdimm_wq; struct nvdimm_bus { struct nvdimm_bus_descriptor *nd_desc; - wait_queue_head_t probe_wait; + wait_queue_head_t wait; struct list_head list; struct device dev; int id, probe_active; + atomic_t ioctl_active; struct list_head mapping_list; struct mutex reconfig_mutex; struct badrange badrange; @@ -181,4 +183,71 @@ ssize_t nd_namespace_store(struct device *dev, struct nd_namespace_common **_ndns, const char *buf, size_t len); struct nd_pfn *to_nd_pfn_safe(struct device *dev); +bool is_nvdimm_bus(struct device *dev); + +#ifdef CONFIG_PROVE_LOCKING +extern struct class *nd_class; + +enum { + LOCK_BUS, + LOCK_NDCTL, + LOCK_REGION, + LOCK_DIMM = LOCK_REGION, + LOCK_NAMESPACE, + LOCK_CLAIM, +}; + +static inline void debug_nvdimm_lock(struct device *dev) +{ + if (is_nd_region(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_REGION); + else if (is_nvdimm(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_DIMM); + else if (is_nd_btt(dev) || is_nd_pfn(dev) || is_nd_dax(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_CLAIM); + else if (dev->parent && (is_nd_region(dev->parent))) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_NAMESPACE); + else if (is_nvdimm_bus(dev)) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_BUS); + else if (dev->class && dev->class == nd_class) + mutex_lock_nested(&dev->lockdep_mutex, LOCK_NDCTL); + else + dev_WARN(dev, "unknown lock level\n"); +} + +static inline void debug_nvdimm_unlock(struct device *dev) +{ + mutex_unlock(&dev->lockdep_mutex); +} + +static inline void nd_device_lock(struct device *dev) +{ + device_lock(dev); + debug_nvdimm_lock(dev); +} + +static inline void nd_device_unlock(struct device *dev) +{ + debug_nvdimm_unlock(dev); + device_unlock(dev); +} +#else +static inline void nd_device_lock(struct device *dev) +{ + device_lock(dev); +} + +static inline void nd_device_unlock(struct device *dev) +{ + device_unlock(dev); +} + +static inline void debug_nvdimm_lock(struct device *dev) +{ +} + +static inline void debug_nvdimm_unlock(struct device *dev) +{ +} +#endif #endif /* __ND_CORE_H__ */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index df2bdbd22450..3e7b11cf1aae 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -67,7 +67,7 @@ static ssize_t mode_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc = 0; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); if (dev->driver) rc = -EBUSY; @@ -89,7 +89,7 @@ static ssize_t mode_store(struct device *dev, dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -132,14 +132,14 @@ static ssize_t align_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_pfn->align, nd_pfn_supported_alignments()); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -161,11 +161,11 @@ static ssize_t uuid_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); - device_unlock(dev); + nd_device_unlock(dev); return rc ? rc : len; } @@ -190,13 +190,13 @@ static ssize_t namespace_store(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len); dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -208,7 +208,7 @@ static ssize_t resource_show(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; u64 offset = __le64_to_cpu(pfn_sb->dataoff); @@ -222,7 +222,7 @@ static ssize_t resource_show(struct device *dev, /* no address to convey if the pfn instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } @@ -234,7 +234,7 @@ static ssize_t size_show(struct device *dev, struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) { struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; u64 offset = __le64_to_cpu(pfn_sb->dataoff); @@ -250,7 +250,7 @@ static ssize_t size_show(struct device *dev, /* no size to convey if the pfn instance is disabled */ rc = -ENXIO; } - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 2bf3acd69613..4c121dd03dd9 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -522,8 +522,8 @@ static int nd_pmem_remove(struct device *dev) nvdimm_namespace_detach_btt(to_nd_btt(dev)); else { /* - * Note, this assumes device_lock() context to not race - * nd_pmem_notify() + * Note, this assumes nd_device_lock() context to not + * race nd_pmem_notify() */ sysfs_put(pmem->bb_state); pmem->bb_state = NULL; diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index ef46cc3a71ae..37bf8719a2a4 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -34,17 +34,6 @@ static int nd_region_probe(struct device *dev) if (rc) return rc; - rc = nd_region_register_namespaces(nd_region, &err); - if (rc < 0) - return rc; - - ndrd = dev_get_drvdata(dev); - ndrd->ns_active = rc; - ndrd->ns_count = rc + err; - - if (rc && err && rc == err) - return -ENODEV; - if (is_nd_pmem(&nd_region->dev)) { struct resource ndr_res; @@ -60,6 +49,17 @@ static int nd_region_probe(struct device *dev) nvdimm_badblocks_populate(nd_region, &nd_region->bb, &ndr_res); } + rc = nd_region_register_namespaces(nd_region, &err); + if (rc < 0) + return rc; + + ndrd = dev_get_drvdata(dev); + ndrd->ns_active = rc; + ndrd->ns_count = rc + err; + + if (rc && err && rc == err) + return -ENODEV; + nd_region->btt_seed = nd_btt_create(nd_region); nd_region->pfn_seed = nd_pfn_create(nd_region); nd_region->dax_seed = nd_dax_create(nd_region); @@ -102,7 +102,7 @@ static int nd_region_remove(struct device *dev) nvdimm_bus_unlock(dev); /* - * Note, this assumes device_lock() context to not race + * Note, this assumes nd_device_lock() context to not race * nd_region_notify() */ sysfs_put(nd_region->bb_state); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 56f2227f192a..af30cbe7a8ea 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -331,7 +331,7 @@ static ssize_t set_cookie_show(struct device *dev, * the v1.1 namespace label cookie definition. To read all this * data we need to wait for probing to settle. */ - device_lock(dev); + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); if (nd_region->ndr_mappings) { @@ -348,7 +348,7 @@ static ssize_t set_cookie_show(struct device *dev, } } nvdimm_bus_unlock(dev); - device_unlock(dev); + nd_device_unlock(dev); if (rc) return rc; @@ -424,10 +424,12 @@ static ssize_t available_size_show(struct device *dev, * memory nvdimm_bus_lock() is dropped, but that's userspace's * problem to not race itself. */ + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_available_dpa(nd_region); nvdimm_bus_unlock(dev); + nd_device_unlock(dev); return sprintf(buf, "%llu\n", available); } @@ -439,10 +441,12 @@ static ssize_t max_available_extent_show(struct device *dev, struct nd_region *nd_region = to_nd_region(dev); unsigned long long available = 0; + nd_device_lock(dev); nvdimm_bus_lock(dev); wait_nvdimm_bus_probe_idle(dev); available = nd_region_allocatable_dpa(nd_region); nvdimm_bus_unlock(dev); + nd_device_unlock(dev); return sprintf(buf, "%llu\n", available); } @@ -561,12 +565,12 @@ static ssize_t region_badblocks_show(struct device *dev, struct nd_region *nd_region = to_nd_region(dev); ssize_t rc; - device_lock(dev); + nd_device_lock(dev); if (dev->driver) rc = badblocks_show(&nd_region->bb, buf, 0); else rc = -ENXIO; - device_unlock(dev); + nd_device_unlock(dev); return rc; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cc09b81fc7f4..8f3fbe5ca937 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2311,17 +2311,15 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off); } -static void __nvme_release_subsystem(struct nvme_subsystem *subsys) +static void nvme_release_subsystem(struct device *dev) { + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + ida_simple_remove(&nvme_subsystems_ida, subsys->instance); kfree(subsys); } -static void nvme_release_subsystem(struct device *dev) -{ - __nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev)); -} - static void nvme_destroy_subsystem(struct kref *ref) { struct nvme_subsystem *subsys = @@ -2477,7 +2475,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) mutex_lock(&nvme_subsystems_lock); found = __nvme_find_get_subsystem(subsys->subnqn); if (found) { - __nvme_release_subsystem(subsys); + put_device(&subsys->dev); subsys = found; if (!nvme_validate_cntlid(subsys, ctrl, id)) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index a9a927677970..4f0d0d12744e 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -12,11 +12,6 @@ module_param(multipath, bool, 0444); MODULE_PARM_DESC(multipath, "turn on native support for multiple controllers per subsystem"); -inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) -{ - return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3)); -} - /* * If multipathing is enabled we need to always use the subsystem instance * number for numbering our devices to avoid conflicts between subsystems that @@ -622,7 +617,8 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { int error; - if (!nvme_ctrl_use_ana(ctrl)) + /* check if multipath is enabled and we have the capability */ + if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3))) return 0; ctrl->anacap = id->anacap; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 716a876119c8..26b563f9985b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -485,7 +485,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct block_device_operations nvme_ns_head_ops; #ifdef CONFIG_NVME_MULTIPATH -bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl); +static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) +{ + return ctrl->ana_log_buf != NULL; +} + void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); void nvme_failover_req(struct request *req); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index bb970ca82517..db160cee42ad 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2254,9 +2254,7 @@ static int nvme_dev_add(struct nvme_dev *dev) if (!dev->ctrl.tagset) { dev->tagset.ops = &nvme_mq_ops; dev->tagset.nr_hw_queues = dev->online_queues - 1; - dev->tagset.nr_maps = 1; /* default */ - if (dev->io_queues[HCTX_TYPE_READ]) - dev->tagset.nr_maps++; + dev->tagset.nr_maps = 2; /* default + read */ if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; dev->tagset.timeout = NVME_IO_TIMEOUT; @@ -3029,6 +3027,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_LIGHTNVM, }, { PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */ .driver_data = NVME_QUIRK_LIGHTNVM, }, + { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 2d06b8095a19..df352b334ea7 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -723,8 +723,8 @@ static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd, cpu_pm_pmu_setup(armpmu, cmd); break; case CPU_PM_EXIT: - cpu_pm_pmu_setup(armpmu, cmd); case CPU_PM_ENTER_FAILED: + cpu_pm_pmu_setup(armpmu, cmd); armpmu->start(armpmu); break; default: diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c index 48d6f0d87583..83ed1fbf73cf 100644 --- a/drivers/platform/olpc/olpc-xo175-ec.c +++ b/drivers/platform/olpc/olpc-xo175-ec.c @@ -736,6 +736,12 @@ static const struct of_device_id olpc_xo175_ec_of_match[] = { }; MODULE_DEVICE_TABLE(of, olpc_xo175_ec_of_match); +static const struct spi_device_id olpc_xo175_ec_id_table[] = { + { "xo1.75-ec", 0 }, + {} +}; +MODULE_DEVICE_TABLE(spi, olpc_xo175_ec_id_table); + static struct spi_driver olpc_xo175_ec_spi_driver = { .driver = { .name = "olpc-xo175-ec", diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index 235c0b89f824..c510d0d72475 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -812,6 +812,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { INTEL_CPU_FAM6(KABYLAKE_DESKTOP, spt_reg_map), INTEL_CPU_FAM6(CANNONLAKE_MOBILE, cnp_reg_map), INTEL_CPU_FAM6(ICELAKE_MOBILE, icl_reg_map), + INTEL_CPU_FAM6(ICELAKE_NNPI, icl_reg_map), {} }; diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index b0d3110ae378..e4c68efac0c2 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -93,7 +93,7 @@ static struct gpiod_lookup_table gpios_led_table = { static struct gpio_keys_button apu2_keys_buttons[] = { { - .code = KEY_SETUP, + .code = KEY_RESTART, .active_low = 1, .desc = "front button", .type = EV_KEY, @@ -255,6 +255,4 @@ MODULE_DESCRIPTION("PC Engines APUv2/APUv3 board GPIO/LED/keys driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(dmi, apu_gpio_dmi_table); MODULE_ALIAS("platform:pcengines-apuv2"); -MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME); -MODULE_SOFTDEP("pre: platform:leds-gpio"); -MODULE_SOFTDEP("pre: platform:gpio_keys_polled"); +MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME " platform:leds-gpio platform:gpio_keys_polled"); diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 9fd6dd342169..6df481896b5f 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -1454,7 +1454,7 @@ static void __exit rapl_exit(void) unregister_pm_notifier(&rapl_pm_notifier); } -module_init(rapl_init); +fs_initcall(rapl_init); module_exit(rapl_exit); MODULE_DESCRIPTION("Intel Runtime Average Power Limit (RAPL) common code"); diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 540e8aafc990..f808c5fa9838 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -671,7 +671,7 @@ static int __init powercap_init(void) return class_register(&powercap_class); } -device_initcall(powercap_init); +fs_initcall(powercap_init); MODULE_DESCRIPTION("PowerCap sysfs Driver"); MODULE_AUTHOR("Srinivas Pandruvada <[email protected]>"); diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 152053361862..989506bd90b1 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -174,14 +174,14 @@ #define AXP803_DCDC5_1140mV_STEPS 35 #define AXP803_DCDC5_1140mV_END \ (AXP803_DCDC5_1140mV_START + AXP803_DCDC5_1140mV_STEPS) -#define AXP803_DCDC5_NUM_VOLTAGES 68 +#define AXP803_DCDC5_NUM_VOLTAGES 69 #define AXP803_DCDC6_600mV_START 0x00 #define AXP803_DCDC6_600mV_STEPS 50 #define AXP803_DCDC6_600mV_END \ (AXP803_DCDC6_600mV_START + AXP803_DCDC6_600mV_STEPS) #define AXP803_DCDC6_1120mV_START 0x33 -#define AXP803_DCDC6_1120mV_STEPS 14 +#define AXP803_DCDC6_1120mV_STEPS 20 #define AXP803_DCDC6_1120mV_END \ (AXP803_DCDC6_1120mV_START + AXP803_DCDC6_1120mV_STEPS) #define AXP803_DCDC6_NUM_VOLTAGES 72 @@ -240,7 +240,7 @@ #define AXP806_DCDCA_600mV_END \ (AXP806_DCDCA_600mV_START + AXP806_DCDCA_600mV_STEPS) #define AXP806_DCDCA_1120mV_START 0x33 -#define AXP806_DCDCA_1120mV_STEPS 14 +#define AXP806_DCDCA_1120mV_STEPS 20 #define AXP806_DCDCA_1120mV_END \ (AXP806_DCDCA_1120mV_START + AXP806_DCDCA_1120mV_STEPS) #define AXP806_DCDCA_NUM_VOLTAGES 72 @@ -774,8 +774,8 @@ static const struct regulator_linear_range axp806_dcdcd_ranges[] = { AXP806_DCDCD_600mV_END, 20000), REGULATOR_LINEAR_RANGE(1600000, - AXP806_DCDCD_600mV_START, - AXP806_DCDCD_600mV_END, + AXP806_DCDCD_1600mV_START, + AXP806_DCDCD_1600mV_END, 100000), }; diff --git a/drivers/regulator/lp87565-regulator.c b/drivers/regulator/lp87565-regulator.c index 5d067f7c2116..0c440c5e2832 100644 --- a/drivers/regulator/lp87565-regulator.c +++ b/drivers/regulator/lp87565-regulator.c @@ -163,7 +163,7 @@ static int lp87565_regulator_probe(struct platform_device *pdev) struct lp87565 *lp87565 = dev_get_drvdata(pdev->dev.parent); struct regulator_config config = { }; struct regulator_dev *rdev; - int i, min_idx = LP87565_BUCK_0, max_idx = LP87565_BUCK_3; + int i, min_idx, max_idx; platform_set_drvdata(pdev, lp87565); @@ -182,9 +182,9 @@ static int lp87565_regulator_probe(struct platform_device *pdev) max_idx = LP87565_BUCK_3210; break; default: - dev_err(lp87565->dev, "Invalid lp config %d\n", - lp87565->dev_type); - return -EINVAL; + min_idx = LP87565_BUCK_0; + max_idx = LP87565_BUCK_3; + break; } for (i = min_idx; i <= max_idx; i++) { diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 397918ebba55..9112faa6a9a0 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -416,8 +416,10 @@ device_node *regulator_of_get_init_node(struct device *dev, if (!name) name = child->name; - if (!strcmp(desc->of_match, name)) + if (!strcmp(desc->of_match, name)) { + of_node_put(search); return of_node_get(child); + } } of_node_put(search); diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index b9ce93e9df89..99f86612f775 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -383,6 +383,20 @@ suborder_not_supported(struct dasd_ccw_req *cqr) char msg_format; char msg_no; + /* + * intrc values ENODEV, ENOLINK and EPERM + * will be optained from sleep_on to indicate that no + * IO operation can be started + */ + if (cqr->intrc == -ENODEV) + return 1; + + if (cqr->intrc == -ENOLINK) + return 1; + + if (cqr->intrc == -EPERM) + return 1; + sense = dasd_get_sense(&cqr->irb); if (!sense) return 0; @@ -447,12 +461,8 @@ static int read_unit_address_configuration(struct dasd_device *device, lcu->flags &= ~NEED_UAC_UPDATE; spin_unlock_irqrestore(&lcu->lock, flags); - do { - rc = dasd_sleep_on(cqr); - if (rc && suborder_not_supported(cqr)) - return -EOPNOTSUPP; - } while (rc && (cqr->retries > 0)); - if (rc) { + rc = dasd_sleep_on(cqr); + if (rc && !suborder_not_supported(cqr)) { spin_lock_irqsave(&lcu->lock, flags); lcu->flags |= NEED_UAC_UPDATE; spin_unlock_irqrestore(&lcu->lock, flags); diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 8c9d412b6d33..e7cf0a1d4f71 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -398,6 +398,7 @@ static void raw3215_irq(struct ccw_device *cdev, unsigned long intparm, } if (dstat == 0x08) break; + /* else, fall through */ case 0x04: /* Device end interrupt. */ if ((raw = req->info) == NULL) diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c index 8d3370da2dfc..3e0b2f63a9d2 100644 --- a/drivers/s390/char/tape_core.c +++ b/drivers/s390/char/tape_core.c @@ -677,6 +677,7 @@ tape_generic_remove(struct ccw_device *cdev) switch (device->tape_state) { case TS_INIT: tape_state_set(device, TS_NOT_OPER); + /* fallthrough */ case TS_NOT_OPER: /* * Nothing to do. @@ -949,6 +950,7 @@ __tape_start_request(struct tape_device *device, struct tape_request *request) break; if (device->tape_state == TS_UNUSED) break; + /* fallthrough */ default: if (device->tape_state == TS_BLKUSE) break; @@ -1116,6 +1118,7 @@ __tape_do_irq (struct ccw_device *cdev, unsigned long intparm, struct irb *irb) case -ETIMEDOUT: DBF_LH(1, "(%08x): Request timed out\n", device->cdev_id); + /* fallthrough */ case -EIO: __tape_end_request(device, request, -EIO); break; diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 730c4e68094b..4142c85e77d8 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -319,9 +319,7 @@ static int qdio_siga_output(struct qdio_q *q, unsigned int *busy_bit, int retries = 0, cc; unsigned long laob = 0; - WARN_ON_ONCE(aob && ((queue_type(q) != QDIO_IQDIO_QFMT) || - !q->u.out.use_cq)); - if (q->u.out.use_cq && aob != 0) { + if (aob) { fc = QDIO_SIGA_WRITEQ; laob = aob; } @@ -621,9 +619,6 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q, { unsigned long phys_aob = 0; - if (!q->use_cq) - return 0; - if (!q->aobs[bufnr]) { struct qaob *aob = qdio_allocate_aob(); q->aobs[bufnr] = aob; @@ -1308,6 +1303,8 @@ static void qdio_detect_hsicq(struct qdio_irq *irq_ptr) for_each_output_queue(irq_ptr, q, i) { if (use_cq) { + if (multicast_outbound(q)) + continue; if (qdio_enable_async_operation(&q->u.out) < 0) { use_cq = 0; continue; @@ -1553,18 +1550,19 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags, /* One SIGA-W per buffer required for unicast HSI */ WARN_ON_ONCE(count > 1 && !multicast_outbound(q)); - phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr); + if (q->u.out.use_cq) + phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr); rc = qdio_kick_outbound_q(q, phys_aob); } else if (need_siga_sync(q)) { rc = qdio_siga_sync_q(q); + } else if (count < QDIO_MAX_BUFFERS_PER_Q && + get_buf_state(q, prev_buf(bufnr), &state, 0) > 0 && + state == SLSB_CU_OUTPUT_PRIMED) { + /* The previous buffer is not processed yet, tack on. */ + qperf_inc(q, fast_requeue); } else { - /* try to fast requeue buffers */ - get_buf_state(q, prev_buf(bufnr), &state, 0); - if (state != SLSB_CU_OUTPUT_PRIMED) - rc = qdio_kick_outbound_q(q, 0); - else - qperf_inc(q, fast_requeue); + rc = qdio_kick_outbound_q(q, 0); } /* in case of SIGA errors we must process the error immediately */ diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c index 8c1d2357ef5b..7a838e3d7c0f 100644 --- a/drivers/s390/cio/vfio_ccw_async.c +++ b/drivers/s390/cio/vfio_ccw_async.c @@ -70,7 +70,7 @@ static void vfio_ccw_async_region_release(struct vfio_ccw_private *private, } -const struct vfio_ccw_regops vfio_ccw_async_region_ops = { +static const struct vfio_ccw_regops vfio_ccw_async_region_ops = { .read = vfio_ccw_async_region_read, .write = vfio_ccw_async_region_write, .release = vfio_ccw_async_region_release, diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 1d4c893ead23..3645d1720c4b 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -72,8 +72,10 @@ static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len) sizeof(*pa->pa_iova_pfn) + sizeof(*pa->pa_pfn), GFP_KERNEL); - if (unlikely(!pa->pa_iova_pfn)) + if (unlikely(!pa->pa_iova_pfn)) { + pa->pa_nr = 0; return -ENOMEM; + } pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr; pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT; @@ -421,7 +423,7 @@ static int ccwchain_loop_tic(struct ccwchain *chain, static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp) { struct ccwchain *chain; - int len; + int len, ret; /* Copy 2K (the most we support today) of possible CCWs */ len = copy_from_iova(cp->mdev, cp->guest_cp, cda, @@ -448,7 +450,12 @@ static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp) memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1)); /* Loop for tics on this new chain. */ - return ccwchain_loop_tic(chain, cp); + ret = ccwchain_loop_tic(chain, cp); + + if (ret) + ccwchain_free(chain); + + return ret; } /* Loop for TICs. */ @@ -642,17 +649,16 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb) /* Build a ccwchain for the first CCW segment */ ret = ccwchain_handle_ccw(orb->cmd.cpa, cp); - if (ret) - cp_free(cp); - - /* It is safe to force: if not set but idals used - * ccwchain_calc_length returns an error. - */ - cp->orb.cmd.c64 = 1; - if (!ret) + if (!ret) { cp->initialized = true; + /* It is safe to force: if it was not set but idals used + * ccwchain_calc_length would have returned an error. + */ + cp->orb.cmd.c64 = 1; + } + return ret; } diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index 2b90a5ecaeb9..9208c0e56c33 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -88,7 +88,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - if (is_final) + if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) cp_free(&private->cp); } mutex_lock(&private->io_mutex); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 5ea83dc4f1d7..dad2be333d82 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -152,6 +152,7 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) ap_msg->receive(aq, ap_msg, aq->reply); break; } + /* fall through */ case AP_RESPONSE_NO_PENDING_REPLY: if (!status.queue_empty || aq->queue_count <= 0) break; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 12fe9deb265e..a36251d138fb 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -801,10 +801,7 @@ static int convert_response_ica(struct zcrypt_queue *zq, if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_ica(zq, reply, outputdata, outputdatalength); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", @@ -837,10 +834,7 @@ static int convert_response_xcrb(struct zcrypt_queue *zq, } if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_xcrb(zq, reply, xcRB); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ zq->online = 0; @@ -870,7 +864,7 @@ static int convert_response_ep11_xcrb(struct zcrypt_queue *zq, return convert_error(zq, reply); if (msg->cprbx.cprb_ver_id == 0x04) return convert_type86_ep11_xcrb(zq, reply, xcRB); - /* Fall through, no break, incorrect cprb version is an unknown resp.*/ + /* fall through - wrong cprb version is an unknown resp */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", @@ -900,10 +894,7 @@ static int convert_response_rng(struct zcrypt_queue *zq, return -EINVAL; if (msg->cprbx.cprb_ver_id == 0x02) return convert_type86_rng(zq, reply, data); - /* - * Fall through, no break, incorrect cprb version is an unknown - * response - */ + /* fall through - wrong cprb version is an unknown response */ default: /* Unknown response type, this should NEVER EVER happen */ zq->online = 0; pr_err("Cryptographic device %02x.%04x failed and was set offline\n", diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 1a55e5942d36..957889a42d2e 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -145,6 +145,8 @@ struct airq_info { struct airq_iv *aiv; }; static struct airq_info *airq_areas[MAX_AIRQ_AREAS]; +static DEFINE_MUTEX(airq_areas_lock); + static u8 *summary_indicators; static inline u8 *get_summary_indicator(struct airq_info *info) @@ -265,9 +267,11 @@ static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs, unsigned long bit, flags; for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) { + mutex_lock(&airq_areas_lock); if (!airq_areas[i]) airq_areas[i] = new_airq_info(i); info = airq_areas[i]; + mutex_unlock(&airq_areas_lock); if (!info) return 0; write_lock_irqsave(&info->lock, flags); diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 75f66f8ad3ea..1b92f3c19ff3 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1523,10 +1523,10 @@ config SCSI_VIRTIO source "drivers/scsi/csiostor/Kconfig" -endif # SCSI_LOWLEVEL - source "drivers/scsi/pcmcia/Kconfig" +endif # SCSI_LOWLEVEL + source "drivers/scsi/device_handler/Kconfig" endmenu diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index f0066f8a1786..4971104b1817 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -40,6 +40,7 @@ #define ALUA_FAILOVER_TIMEOUT 60 #define ALUA_FAILOVER_RETRIES 5 #define ALUA_RTPG_DELAY_MSECS 5 +#define ALUA_RTPG_RETRY_DELAY 2 /* device handler flags */ #define ALUA_OPTIMIZE_STPG 0x01 @@ -682,7 +683,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) case SCSI_ACCESS_STATE_TRANSITIONING: if (time_before(jiffies, pg->expiry)) { /* State transition, retry */ - pg->interval = 2; + pg->interval = ALUA_RTPG_RETRY_DELAY; err = SCSI_DH_RETRY; } else { struct alua_dh_data *h; @@ -807,6 +808,8 @@ static void alua_rtpg_work(struct work_struct *work) spin_lock_irqsave(&pg->lock, flags); pg->flags &= ~ALUA_PG_RUNNING; pg->flags |= ALUA_PG_RUN_RTPG; + if (!pg->interval) + pg->interval = ALUA_RTPG_RETRY_DELAY; spin_unlock_irqrestore(&pg->lock, flags); queue_delayed_work(kaluad_wq, &pg->rtpg_work, pg->interval * HZ); @@ -818,6 +821,8 @@ static void alua_rtpg_work(struct work_struct *work) spin_lock_irqsave(&pg->lock, flags); if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) { pg->flags &= ~ALUA_PG_RUNNING; + if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG)) + pg->interval = ALUA_RTPG_RETRY_DELAY; pg->flags |= ALUA_PG_RUN_RTPG; spin_unlock_irqrestore(&pg->lock, flags); queue_delayed_work(kaluad_wq, &pg->rtpg_work, diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 590ec8009f52..1791a393795d 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -1019,7 +1019,7 @@ static void fcoe_ctlr_recv_adv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fcoe_fcf *fcf; struct fcoe_fcf new; - unsigned long sol_tov = msecs_to_jiffies(FCOE_CTRL_SOL_TOV); + unsigned long sol_tov = msecs_to_jiffies(FCOE_CTLR_SOL_TOV); int first = 0; int mtu_valid; int found = 0; @@ -2005,7 +2005,7 @@ EXPORT_SYMBOL_GPL(fcoe_wwn_from_mac); */ static inline struct fcoe_rport *fcoe_ctlr_rport(struct fc_rport_priv *rdata) { - return (struct fcoe_rport *)(rdata + 1); + return container_of(rdata, struct fcoe_rport, rdata); } /** @@ -2269,7 +2269,7 @@ static void fcoe_ctlr_vn_start(struct fcoe_ctlr *fip) */ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; @@ -2277,16 +2277,12 @@ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, struct fip_wwn_desc *wwn = NULL; struct fip_vn_desc *vn = NULL; struct fip_size_desc *size = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub; - memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags); @@ -2349,15 +2345,17 @@ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; case FIP_DT_VN_ID: if (dlen != sizeof(struct fip_vn_desc)) goto len_err; vn = (struct fip_vn_desc *)desc; memcpy(frport->vn_mac, vn->fd_mac, ETH_ALEN); - rdata->ids.port_id = ntoh24(vn->fd_fc_id); - rdata->ids.port_name = get_unaligned_be64(&vn->fd_wwpn); + frport->rdata.ids.port_id = ntoh24(vn->fd_fc_id); + frport->rdata.ids.port_name = + get_unaligned_be64(&vn->fd_wwpn); break; case FIP_DT_FC4F: if (dlen != sizeof(struct fip_fc4_feat)) @@ -2403,16 +2401,14 @@ static void fcoe_ctlr_vn_send_claim(struct fcoe_ctlr *fip) /** * fcoe_ctlr_vn_probe_req() - handle incoming VN2VN probe request. * @fip: The FCoE controller - * @rdata: parsed remote port with frport from the probe request + * @frport: parsed FCoE rport from the probe request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - struct fcoe_rport *frport = fcoe_ctlr_rport(rdata); - - if (rdata->ids.port_id != fip->port_id) + if (frport->rdata.ids.port_id != fip->port_id) return; switch (fip->state) { @@ -2432,7 +2428,7 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, * Probe's REC bit is not set. * If we don't reply, we will change our address. */ - if (fip->lp->wwpn > rdata->ids.port_name && + if (fip->lp->wwpn > frport->rdata.ids.port_name && !(frport->flags & FIP_FL_REC_OR_P2P)) { LIBFCOE_FIP_DBG(fip, "vn_probe_req: " "port_id collision\n"); @@ -2456,14 +2452,14 @@ static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_probe_reply() - handle incoming VN2VN probe reply. * @fip: The FCoE controller - * @rdata: parsed remote port with frport from the probe request + * @frport: parsed FCoE rport from the probe request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - if (rdata->ids.port_id != fip->port_id) + if (frport->rdata.ids.port_id != fip->port_id) return; switch (fip->state) { case FIP_ST_VNMP_START: @@ -2486,11 +2482,11 @@ static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_add() - Add a VN2VN entry to the list, based on a claim reply. * @fip: The FCoE controller - * @new: newly-parsed remote port with frport as a template for new rdata + * @new: newly-parsed FCoE rport as a template for new rdata * * Called with ctlr_mutex held. */ -static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) +static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fcoe_rport *new) { struct fc_lport *lport = fip->lp; struct fc_rport_priv *rdata; @@ -2498,7 +2494,7 @@ static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) struct fcoe_rport *frport; u32 port_id; - port_id = new->ids.port_id; + port_id = new->rdata.ids.port_id; if (port_id == fip->port_id) return; @@ -2515,22 +2511,28 @@ static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new) rdata->disc_id = lport->disc.disc_id; ids = &rdata->ids; - if ((ids->port_name != -1 && ids->port_name != new->ids.port_name) || - (ids->node_name != -1 && ids->node_name != new->ids.node_name)) { + if ((ids->port_name != -1 && + ids->port_name != new->rdata.ids.port_name) || + (ids->node_name != -1 && + ids->node_name != new->rdata.ids.node_name)) { mutex_unlock(&rdata->rp_mutex); LIBFCOE_FIP_DBG(fip, "vn_add rport logoff %6.6x\n", port_id); fc_rport_logoff(rdata); mutex_lock(&rdata->rp_mutex); } - ids->port_name = new->ids.port_name; - ids->node_name = new->ids.node_name; + ids->port_name = new->rdata.ids.port_name; + ids->node_name = new->rdata.ids.node_name; mutex_unlock(&rdata->rp_mutex); frport = fcoe_ctlr_rport(rdata); LIBFCOE_FIP_DBG(fip, "vn_add rport %6.6x %s state %d\n", port_id, frport->fcoe_len ? "old" : "new", rdata->rp_state); - *frport = *fcoe_ctlr_rport(new); + frport->fcoe_len = new->fcoe_len; + frport->flags = new->flags; + frport->login_count = new->login_count; + memcpy(frport->enode_mac, new->enode_mac, ETH_ALEN); + memcpy(frport->vn_mac, new->vn_mac, ETH_ALEN); frport->time = 0; } @@ -2562,16 +2564,14 @@ static int fcoe_ctlr_vn_lookup(struct fcoe_ctlr *fip, u32 port_id, u8 *mac) /** * fcoe_ctlr_vn_claim_notify() - handle received FIP VN2VN Claim Notification * @fip: The FCoE controller - * @new: newly-parsed remote port with frport as a template for new rdata + * @new: newly-parsed FCoE rport as a template for new rdata * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { - struct fcoe_rport *frport = fcoe_ctlr_rport(new); - - if (frport->flags & FIP_FL_REC_OR_P2P) { + if (new->flags & FIP_FL_REC_OR_P2P) { LIBFCOE_FIP_DBG(fip, "send probe req for P2P/REC\n"); fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0); return; @@ -2580,7 +2580,7 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, case FIP_ST_VNMP_START: case FIP_ST_VNMP_PROBE1: case FIP_ST_VNMP_PROBE2: - if (new->ids.port_id == fip->port_id) { + if (new->rdata.ids.port_id == fip->port_id) { LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " "restart, state %d\n", fip->state); @@ -2589,8 +2589,8 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, break; case FIP_ST_VNMP_CLAIM: case FIP_ST_VNMP_UP: - if (new->ids.port_id == fip->port_id) { - if (new->ids.port_name > fip->lp->wwpn) { + if (new->rdata.ids.port_id == fip->port_id) { + if (new->rdata.ids.port_name > fip->lp->wwpn) { LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " "restart, port_id collision\n"); fcoe_ctlr_vn_restart(fip); @@ -2602,15 +2602,16 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, break; } LIBFCOE_FIP_DBG(fip, "vn_claim_notify: send reply to %x\n", - new->ids.port_id); - fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, frport->enode_mac, - min((u32)frport->fcoe_len, + new->rdata.ids.port_id); + fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, new->enode_mac, + min((u32)new->fcoe_len, fcoe_ctlr_fcoe_size(fip))); fcoe_ctlr_vn_add(fip, new); break; default: LIBFCOE_FIP_DBG(fip, "vn_claim_notify: " - "ignoring claim from %x\n", new->ids.port_id); + "ignoring claim from %x\n", + new->rdata.ids.port_id); break; } } @@ -2618,15 +2619,15 @@ static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_claim_resp() - handle received Claim Response * @fip: The FCoE controller that received the frame - * @new: newly-parsed remote port with frport from the Claim Response + * @new: newly-parsed FCoE rport from the Claim Response * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_claim_resp(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { LIBFCOE_FIP_DBG(fip, "claim resp from from rport %x - state %s\n", - new->ids.port_id, fcoe_ctlr_state(fip->state)); + new->rdata.ids.port_id, fcoe_ctlr_state(fip->state)); if (fip->state == FIP_ST_VNMP_UP || fip->state == FIP_ST_VNMP_CLAIM) fcoe_ctlr_vn_add(fip, new); } @@ -2634,28 +2635,28 @@ static void fcoe_ctlr_vn_claim_resp(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vn_beacon() - handle received beacon. * @fip: The FCoE controller that received the frame - * @new: newly-parsed remote port with frport from the Beacon + * @new: newly-parsed FCoE rport from the Beacon * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip, - struct fc_rport_priv *new) + struct fcoe_rport *new) { struct fc_lport *lport = fip->lp; struct fc_rport_priv *rdata; struct fcoe_rport *frport; - frport = fcoe_ctlr_rport(new); - if (frport->flags & FIP_FL_REC_OR_P2P) { + if (new->flags & FIP_FL_REC_OR_P2P) { LIBFCOE_FIP_DBG(fip, "p2p beacon while in vn2vn mode\n"); fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0); return; } - rdata = fc_rport_lookup(lport, new->ids.port_id); + rdata = fc_rport_lookup(lport, new->rdata.ids.port_id); if (rdata) { - if (rdata->ids.node_name == new->ids.node_name && - rdata->ids.port_name == new->ids.port_name) { + if (rdata->ids.node_name == new->rdata.ids.node_name && + rdata->ids.port_name == new->rdata.ids.port_name) { frport = fcoe_ctlr_rport(rdata); + LIBFCOE_FIP_DBG(fip, "beacon from rport %x\n", rdata->ids.port_id); if (!frport->time && fip->state == FIP_ST_VNMP_UP) { @@ -2678,7 +2679,7 @@ static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip, * Don't add the neighbor yet. */ LIBFCOE_FIP_DBG(fip, "beacon from new rport %x. sending claim notify\n", - new->ids.port_id); + new->rdata.ids.port_id); if (time_after(jiffies, fip->sol_time + msecs_to_jiffies(FIP_VN_ANN_WAIT))) fcoe_ctlr_vn_send_claim(fip); @@ -2738,10 +2739,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fip_header *fiph; enum fip_vn2vn_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc, vlan_id = 0; fiph = (struct fip_header *)skb->data; @@ -2757,7 +2755,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) goto drop; } - rc = fcoe_ctlr_vn_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vn_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vn_recv vn_parse error %d\n", rc); goto drop; @@ -2766,19 +2764,19 @@ static int fcoe_ctlr_vn_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) mutex_lock(&fip->ctlr_mutex); switch (sub) { case FIP_SC_VN_PROBE_REQ: - fcoe_ctlr_vn_probe_req(fip, &buf.rdata); + fcoe_ctlr_vn_probe_req(fip, &frport); break; case FIP_SC_VN_PROBE_REP: - fcoe_ctlr_vn_probe_reply(fip, &buf.rdata); + fcoe_ctlr_vn_probe_reply(fip, &frport); break; case FIP_SC_VN_CLAIM_NOTIFY: - fcoe_ctlr_vn_claim_notify(fip, &buf.rdata); + fcoe_ctlr_vn_claim_notify(fip, &frport); break; case FIP_SC_VN_CLAIM_REP: - fcoe_ctlr_vn_claim_resp(fip, &buf.rdata); + fcoe_ctlr_vn_claim_resp(fip, &frport); break; case FIP_SC_VN_BEACON: - fcoe_ctlr_vn_beacon(fip, &buf.rdata); + fcoe_ctlr_vn_beacon(fip, &frport); break; default: LIBFCOE_FIP_DBG(fip, "vn_recv unknown subcode %d\n", sub); @@ -2802,22 +2800,18 @@ drop: */ static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; struct fip_mac_desc *macd = NULL; struct fip_wwn_desc *wwn = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub; - memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags); @@ -2871,7 +2865,8 @@ static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip, if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; default: LIBFCOE_FIP_DBG(fip, "unexpected descriptor type %x " @@ -2957,13 +2952,13 @@ static void fcoe_ctlr_vlan_send(struct fcoe_ctlr *fip, /** * fcoe_ctlr_vlan_disk_reply() - send FIP VLAN Discovery Notification. * @fip: The FCoE controller + * @frport: The newly-parsed FCoE rport from the Discovery Request * * Called with ctlr_mutex held. */ static void fcoe_ctlr_vlan_disc_reply(struct fcoe_ctlr *fip, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { - struct fcoe_rport *frport = fcoe_ctlr_rport(rdata); enum fip_vlan_subcode sub = FIP_SC_VL_NOTE; if (fip->mode == FIP_MODE_VN2VN) @@ -2982,22 +2977,19 @@ static int fcoe_ctlr_vlan_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) { struct fip_header *fiph; enum fip_vlan_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc; fiph = (struct fip_header *)skb->data; sub = fiph->fip_subcode; - rc = fcoe_ctlr_vlan_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vlan_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vlan_recv vlan_parse error %d\n", rc); goto drop; } mutex_lock(&fip->ctlr_mutex); if (sub == FIP_SC_VL_REQ) - fcoe_ctlr_vlan_disc_reply(fip, &buf.rdata); + fcoe_ctlr_vlan_disc_reply(fip, &frport); mutex_unlock(&fip->ctlr_mutex); drop: diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 43a6b5350775..1bb6aada93fa 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2334,6 +2334,8 @@ static int handle_ioaccel_mode2_error(struct ctlr_info *h, case IOACCEL2_SERV_RESPONSE_COMPLETE: switch (c2->error_data.status) { case IOACCEL2_STATUS_SR_TASK_COMP_GOOD: + if (cmd) + cmd->result = 0; break; case IOACCEL2_STATUS_SR_TASK_COMP_CHK_COND: cmd->result |= SAM_STAT_CHECK_CONDITION; @@ -2483,8 +2485,10 @@ static void process_ioaccel2_completion(struct ctlr_info *h, /* check for good status */ if (likely(c2->error_data.serv_response == 0 && - c2->error_data.status == 0)) + c2->error_data.status == 0)) { + cmd->result = 0; return hpsa_cmd_free_and_done(h, c, cmd); + } /* * Any RAID offload error results in retry which will use @@ -5654,6 +5658,12 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *sh, struct scsi_cmnd *cmd) return SCSI_MLQUEUE_DEVICE_BUSY; /* + * This is necessary because the SML doesn't zero out this field during + * error recovery. + */ + cmd->result = 0; + + /* * Call alternate submit routine for I/O accelerated commands. * Retries always go down the normal I/O path. */ @@ -6081,8 +6091,6 @@ static struct CommandList *cmd_tagged_alloc(struct ctlr_info *h, if (idx != h->last_collision_tag) { /* Print once per tag */ dev_warn(&h->pdev->dev, "%s: tag collision (tag=%d)\n", __func__, idx); - if (c->scsi_cmd != NULL) - scsi_print_command(c->scsi_cmd); if (scmd) scsi_print_command(scmd); h->last_collision_tag = idx; @@ -7798,7 +7806,7 @@ static void hpsa_free_pci_init(struct ctlr_info *h) hpsa_disable_interrupt_mode(h); /* pci_init 2 */ /* * call pci_disable_device before pci_release_regions per - * Documentation/PCI/pci.rst + * Documentation/driver-api/pci/pci.rst */ pci_disable_device(h->pdev); /* pci_init 1 */ pci_release_regions(h->pdev); /* pci_init 2 */ @@ -7881,7 +7889,7 @@ clean2: /* intmode+region, pci */ clean1: /* * call pci_disable_device before pci_release_regions per - * Documentation/PCI/pci.rst + * Documentation/driver-api/pci/pci.rst */ pci_disable_device(h->pdev); pci_release_regions(h->pdev); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index acd16e0d52cf..8cdbac076a1b 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4864,8 +4864,8 @@ static int ibmvfc_remove(struct vio_dev *vdev) spin_lock_irqsave(vhost->host->host_lock, flags); ibmvfc_purge_requests(vhost, DID_ERROR); - ibmvfc_free_event_pool(vhost); spin_unlock_irqrestore(vhost->host->host_lock, flags); + ibmvfc_free_event_pool(vhost); ibmvfc_free_mem(vhost); spin_lock(&ibmvfc_driver_lock); diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index e0f3852fdad1..da6e97d8dc3b 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -128,6 +128,7 @@ EXPORT_SYMBOL(fc_rport_lookup); struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) { struct fc_rport_priv *rdata; + size_t rport_priv_size = sizeof(*rdata); lockdep_assert_held(&lport->disc.disc_mutex); @@ -135,7 +136,9 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) if (rdata) return rdata; - rdata = kzalloc(sizeof(*rdata) + lport->rport_priv_size, GFP_KERNEL); + if (lport->rport_priv_size > 0) + rport_priv_size = lport->rport_priv_size; + rdata = kzalloc(rport_priv_size, GFP_KERNEL); if (!rdata) return NULL; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index b2339d04a700..f9f07935556e 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3163,6 +3163,7 @@ fw_crash_buffer_show(struct device *cdev, (struct megasas_instance *) shost->hostdata; u32 size; unsigned long dmachunk = CRASH_DMA_BUF_SIZE; + unsigned long chunk_left_bytes; unsigned long src_addr; unsigned long flags; u32 buff_offset; @@ -3186,6 +3187,8 @@ fw_crash_buffer_show(struct device *cdev, } size = (instance->fw_crash_buffer_size * dmachunk) - buff_offset; + chunk_left_bytes = dmachunk - (buff_offset % dmachunk); + size = (size > chunk_left_bytes) ? chunk_left_bytes : size; size = (size >= PAGE_SIZE) ? (PAGE_SIZE - 1) : size; src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] + @@ -8763,7 +8766,7 @@ static int __init megasas_init(void) if ((event_log_level < MFI_EVT_CLASS_DEBUG) || (event_log_level > MFI_EVT_CLASS_DEAD)) { - printk(KERN_WARNING "megarid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n"); + pr_warn("megaraid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n"); event_log_level = MFI_EVT_CLASS_CRITICAL; } diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index a32b3f0fcd15..120e3c4de8c2 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -537,7 +537,7 @@ static int megasas_create_sg_sense_fusion(struct megasas_instance *instance) return 0; } -int +static int megasas_alloc_cmdlist_fusion(struct megasas_instance *instance) { u32 max_mpt_cmd, i, j; @@ -576,7 +576,8 @@ megasas_alloc_cmdlist_fusion(struct megasas_instance *instance) return 0; } -int + +static int megasas_alloc_request_fusion(struct megasas_instance *instance) { struct fusion_context *fusion; @@ -657,7 +658,7 @@ retry_alloc: return 0; } -int +static int megasas_alloc_reply_fusion(struct megasas_instance *instance) { int i, count; @@ -734,7 +735,7 @@ megasas_alloc_reply_fusion(struct megasas_instance *instance) return 0; } -int +static int megasas_alloc_rdpq_fusion(struct megasas_instance *instance) { int i, j, k, msix_count; @@ -916,7 +917,7 @@ megasas_free_reply_fusion(struct megasas_instance *instance) { * and is used as SMID of the cmd. * SMID value range is from 1 to max_fw_cmds. */ -int +static int megasas_alloc_cmds_fusion(struct megasas_instance *instance) { int i; @@ -1736,7 +1737,7 @@ static inline void megasas_free_ioc_init_cmd(struct megasas_instance *instance) * * This is the main function for initializing firmware. */ -u32 +static u32 megasas_init_adapter_fusion(struct megasas_instance *instance) { struct fusion_context *fusion; @@ -1962,7 +1963,7 @@ megasas_fusion_stop_watchdog(struct megasas_instance *instance) * @ext_status : ext status of cmd returned by FW */ -void +static void map_cmd_status(struct fusion_context *fusion, struct scsi_cmnd *scmd, u8 status, u8 ext_status, u32 data_length, u8 *sense) @@ -2375,7 +2376,7 @@ int megasas_make_sgl(struct megasas_instance *instance, struct scsi_cmnd *scp, * * Used to set the PD LBA in CDB for FP IOs */ -void +static void megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len, struct IO_REQUEST_INFO *io_info, struct scsi_cmnd *scp, struct MR_DRV_RAID_MAP_ALL *local_map_ptr, u32 ref_tag) @@ -2714,7 +2715,7 @@ megasas_set_raidflag_cpu_affinity(struct fusion_context *fusion, * Prepares the io_request and chain elements (sg_frame) for IO * The IO can be for PD (Fast Path) or LD */ -void +static void megasas_build_ldio_fusion(struct megasas_instance *instance, struct scsi_cmnd *scp, struct megasas_cmd_fusion *cmd) @@ -3211,7 +3212,7 @@ megasas_build_syspd_fusion(struct megasas_instance *instance, * Invokes helper functions to prepare request frames * and sets flags appropriate for IO/Non-IO cmd */ -int +static int megasas_build_io_fusion(struct megasas_instance *instance, struct scsi_cmnd *scp, struct megasas_cmd_fusion *cmd) @@ -3325,9 +3326,9 @@ megasas_get_request_descriptor(struct megasas_instance *instance, u16 index) /* megasas_prepate_secondRaid1_IO * It prepares the raid 1 second IO */ -void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance, - struct megasas_cmd_fusion *cmd, - struct megasas_cmd_fusion *r1_cmd) +static void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance, + struct megasas_cmd_fusion *cmd, + struct megasas_cmd_fusion *r1_cmd) { union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, *req_desc2 = NULL; struct fusion_context *fusion; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 684662888792..050c0f029ef9 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2703,6 +2703,8 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) { u64 required_mask, coherent_mask; struct sysinfo s; + /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ + int dma_mask = (ioc->hba_mpi_version_belonged > MPI2_VERSION) ? 63 : 64; if (ioc->is_mcpu_endpoint) goto try_32bit; @@ -2712,17 +2714,17 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) goto try_32bit; if (ioc->dma_mask) - coherent_mask = DMA_BIT_MASK(64); + coherent_mask = DMA_BIT_MASK(dma_mask); else coherent_mask = DMA_BIT_MASK(32); - if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) || + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(dma_mask)) || dma_set_coherent_mask(&pdev->dev, coherent_mask)) goto try_32bit; ioc->base_add_sg_single = &_base_add_sg_single_64; ioc->sge_size = sizeof(Mpi2SGESimple64_t); - ioc->dma_mask = 64; + ioc->dma_mask = dma_mask; goto out; try_32bit: @@ -2744,7 +2746,7 @@ static int _base_change_consistent_dma_mask(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) { - if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(ioc->dma_mask))) { if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32))) return -ENODEV; } @@ -4989,7 +4991,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc) total_sz += sz; } while (ioc->rdpq_array_enable && (++i < ioc->reply_queue_count)); - if (ioc->dma_mask == 64) { + if (ioc->dma_mask > 32) { if (_base_change_consistent_dma_mask(ioc, ioc->pdev) != 0) { ioc_warn(ioc, "no suitable consistent DMA mask for %s\n", pci_name(ioc->pdev)); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 4059655639d9..da83034d4759 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4877,7 +4877,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) ql_log(ql_log_warn, vha, 0xd049, "Failed to allocate ct_sns request.\n"); kfree(fcport); - fcport = NULL; + return NULL; } INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9381171c2fc0..11e64b50497f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1784,8 +1784,10 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize); } - shost->max_sectors = min_t(unsigned int, shost->max_sectors, - dma_max_mapping_size(dev) << SECTOR_SHIFT); + if (dev->dma_mask) { + shost->max_sectors = min_t(unsigned int, shost->max_sectors, + dma_max_mapping_size(dev) >> SECTOR_SHIFT); + } blk_queue_max_hw_sectors(q, shost->max_sectors); if (shost->unchecked_isa_dma) blk_queue_bounce_limit(q, BLK_BOUNCE_ISA); diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index 62c6ba17991a..c9519e62308c 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -419,7 +419,7 @@ static void qe_upload_microcode(const void *base, /* * Upload a microcode to the I-RAM at a specific address. * - * See Documentation/powerpc/qe_firmware.txt for information on QE microcode + * See Documentation/powerpc/qe_firmware.rst for information on QE microcode * uploading. * * Currently, only version 1 is supported, so the 'version' field must be diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index 6f243a90c844..840b1b8ff3dc 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -834,7 +834,8 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr, bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv); /* handle all the 3-wire mode */ - if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf)) + if (spi->mode & SPI_3WIRE && tfr->rx_buf && + tfr->rx_buf != ctlr->dummy_rx) cs |= BCM2835_SPI_CS_REN; else cs &= ~BCM2835_SPI_CS_REN; diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c index 41a49b93ca60..448c00e4065b 100644 --- a/drivers/spi/spi-fsl-qspi.c +++ b/drivers/spi/spi-fsl-qspi.c @@ -206,7 +206,7 @@ static const struct fsl_qspi_devtype_data imx6sx_data = { }; static const struct fsl_qspi_devtype_data imx7d_data = { - .rxfifo = SZ_512, + .rxfifo = SZ_128, .txfifo = SZ_512, .ahb_buf_size = SZ_1K, .quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK, diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c index eca9d52ecf65..9eb82150666e 100644 --- a/drivers/spi/spi-gpio.c +++ b/drivers/spi/spi-gpio.c @@ -410,6 +410,12 @@ static int spi_gpio_probe(struct platform_device *pdev) bb = &spi_gpio->bitbang; bb->master = master; + /* + * There is some additional business, apart from driving the CS GPIO + * line, that we need to do on selection. This makes the local + * callback for chipselect always get called. + */ + master->flags |= SPI_MASTER_GPIO_SS; bb->chipselect = spi_gpio_chipselect; bb->set_line_direction = spi_gpio_set_direction; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index fc7ab4b26880..bb6a14d1ab0f 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1457,6 +1457,14 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = { { PCI_VDEVICE(INTEL, 0x02aa), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x02ab), LPSS_CNL_SSP }, { PCI_VDEVICE(INTEL, 0x02fb), LPSS_CNL_SSP }, + /* TGL-LP */ + { PCI_VDEVICE(INTEL, 0xa0aa), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0ab), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0de), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0df), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fb), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fd), LPSS_CNL_SSP }, + { PCI_VDEVICE(INTEL, 0xa0fe), LPSS_CNL_SSP }, { }, }; @@ -1831,14 +1839,16 @@ static int pxa2xx_spi_probe(struct platform_device *pdev) status = devm_spi_register_controller(&pdev->dev, controller); if (status != 0) { dev_err(&pdev->dev, "problem registering spi controller\n"); - goto out_error_clock_enabled; + goto out_error_pm_runtime_enabled; } return status; -out_error_clock_enabled: +out_error_pm_runtime_enabled: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + +out_error_clock_enabled: clk_disable_unprepare(ssp->clk); out_error_dma_irq_alloc: diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 22dd4c457d6a..c70caf4ea490 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -875,10 +875,12 @@ static u8 cxgbit_get_iscsi_dcb_priority(struct net_device *ndev, u16 local_port) return 0; if (caps & DCB_CAP_DCBX_VER_IEEE) { - iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY; - + iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_STREAM; ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app); - + if (!ret) { + iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY; + ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app); + } } else if (caps & DCB_CAP_DCBX_VER_CEE) { iscsi_dcb_app.selector = DCB_APP_IDTYPE_PORTNUM; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index 343b129c2cfa..e877b917c15f 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -589,7 +589,8 @@ static void cxgbit_dcb_workfn(struct work_struct *work) iscsi_app = &dcb_work->dcb_app; if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) { - if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY) + if ((iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_STREAM) && + (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY)) goto out; priority = iscsi_app->app.priority; diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index 213ab3cc6b80..d3446acf9bbd 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -487,6 +487,7 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, rapl_mmio_cpu_online, rapl_mmio_cpu_down_prep); if (ret < 0) { powercap_unregister_control_type(rapl_mmio_priv.control_type); + rapl_mmio_priv.control_type = NULL; return ret; } rapl_mmio_priv.pcap_rapl_online = ret; @@ -496,6 +497,9 @@ static int proc_thermal_rapl_add(struct pci_dev *pdev, static void proc_thermal_rapl_remove(void) { + if (IS_ERR_OR_NULL(rapl_mmio_priv.control_type)) + return; + cpuhp_remove_state(rapl_mmio_priv.pcap_rapl_online); powercap_unregister_control_type(rapl_mmio_priv.control_type); } diff --git a/drivers/tty/hvc/hvcs.c b/drivers/tty/hvc/hvcs.c index cb4db1b3ca3c..5fb214e67d73 100644 --- a/drivers/tty/hvc/hvcs.c +++ b/drivers/tty/hvc/hvcs.c @@ -47,7 +47,7 @@ * using the 2.6 Linux kernel kref construct. * * For direction on installation and usage of this driver please reference - * Documentation/powerpc/hvcs.txt. + * Documentation/powerpc/hvcs.rst. */ #include <linux/device.h> diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index fd385c8c53a5..3083dbae35f7 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1035,25 +1035,6 @@ config SERIAL_VT8500_CONSOLE depends on SERIAL_VT8500=y select SERIAL_CORE_CONSOLE -config SERIAL_NETX - tristate "NetX serial port support" - depends on ARCH_NETX - select SERIAL_CORE - help - If you have a machine based on a Hilscher NetX SoC you - can enable its onboard serial port by enabling this option. - - To compile this driver as a module, choose M here: the - module will be called netx-serial. - -config SERIAL_NETX_CONSOLE - bool "Console on NetX serial port" - depends on SERIAL_NETX=y - select SERIAL_CORE_CONSOLE - help - If you have enabled the serial port on the Hilscher NetX SoC - you can make it the console by answering Y to this option. - config SERIAL_OMAP tristate "OMAP serial port support" depends on ARCH_OMAP2PLUS diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 7cd7cabfa6c4..15a0fccadf7e 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -59,7 +59,6 @@ obj-$(CONFIG_SERIAL_ATMEL) += atmel_serial.o obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o obj-$(CONFIG_SERIAL_MSM) += msm_serial.o obj-$(CONFIG_SERIAL_QCOM_GENI) += qcom_geni_serial.o -obj-$(CONFIG_SERIAL_NETX) += netx-serial.o obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o obj-$(CONFIG_SERIAL_OMAP) += omap-serial.o obj-$(CONFIG_SERIAL_ALTERA_UART) += altera_uart.o diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c deleted file mode 100644 index b3556863491f..000000000000 --- a/drivers/tty/serial/netx-serial.c +++ /dev/null @@ -1,733 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2005 Sascha Hauer <[email protected]>, Pengutronix - */ - -#if defined(CONFIG_SERIAL_NETX_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) -#define SUPPORT_SYSRQ -#endif - -#include <linux/device.h> -#include <linux/module.h> -#include <linux/ioport.h> -#include <linux/init.h> -#include <linux/console.h> -#include <linux/sysrq.h> -#include <linux/platform_device.h> -#include <linux/tty.h> -#include <linux/tty_flip.h> -#include <linux/serial_core.h> -#include <linux/serial.h> - -#include <asm/io.h> -#include <asm/irq.h> -#include <mach/hardware.h> -#include <mach/netx-regs.h> - -/* We've been assigned a range on the "Low-density serial ports" major */ -#define SERIAL_NX_MAJOR 204 -#define MINOR_START 170 - -enum uart_regs { - UART_DR = 0x00, - UART_SR = 0x04, - UART_LINE_CR = 0x08, - UART_BAUDDIV_MSB = 0x0c, - UART_BAUDDIV_LSB = 0x10, - UART_CR = 0x14, - UART_FR = 0x18, - UART_IIR = 0x1c, - UART_ILPR = 0x20, - UART_RTS_CR = 0x24, - UART_RTS_LEAD = 0x28, - UART_RTS_TRAIL = 0x2c, - UART_DRV_ENABLE = 0x30, - UART_BRM_CR = 0x34, - UART_RXFIFO_IRQLEVEL = 0x38, - UART_TXFIFO_IRQLEVEL = 0x3c, -}; - -#define SR_FE (1<<0) -#define SR_PE (1<<1) -#define SR_BE (1<<2) -#define SR_OE (1<<3) - -#define LINE_CR_BRK (1<<0) -#define LINE_CR_PEN (1<<1) -#define LINE_CR_EPS (1<<2) -#define LINE_CR_STP2 (1<<3) -#define LINE_CR_FEN (1<<4) -#define LINE_CR_5BIT (0<<5) -#define LINE_CR_6BIT (1<<5) -#define LINE_CR_7BIT (2<<5) -#define LINE_CR_8BIT (3<<5) -#define LINE_CR_BITS_MASK (3<<5) - -#define CR_UART_EN (1<<0) -#define CR_SIREN (1<<1) -#define CR_SIRLP (1<<2) -#define CR_MSIE (1<<3) -#define CR_RIE (1<<4) -#define CR_TIE (1<<5) -#define CR_RTIE (1<<6) -#define CR_LBE (1<<7) - -#define FR_CTS (1<<0) -#define FR_DSR (1<<1) -#define FR_DCD (1<<2) -#define FR_BUSY (1<<3) -#define FR_RXFE (1<<4) -#define FR_TXFF (1<<5) -#define FR_RXFF (1<<6) -#define FR_TXFE (1<<7) - -#define IIR_MIS (1<<0) -#define IIR_RIS (1<<1) -#define IIR_TIS (1<<2) -#define IIR_RTIS (1<<3) -#define IIR_MASK 0xf - -#define RTS_CR_AUTO (1<<0) -#define RTS_CR_RTS (1<<1) -#define RTS_CR_COUNT (1<<2) -#define RTS_CR_MOD2 (1<<3) -#define RTS_CR_RTS_POL (1<<4) -#define RTS_CR_CTS_CTR (1<<5) -#define RTS_CR_CTS_POL (1<<6) -#define RTS_CR_STICK (1<<7) - -#define UART_PORT_SIZE 0x40 -#define DRIVER_NAME "netx-uart" - -struct netx_port { - struct uart_port port; -}; - -static void netx_stop_tx(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val & ~CR_TIE, port->membase + UART_CR); -} - -static void netx_stop_rx(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val & ~CR_RIE, port->membase + UART_CR); -} - -static void netx_enable_ms(struct uart_port *port) -{ - unsigned int val; - val = readl(port->membase + UART_CR); - writel(val | CR_MSIE, port->membase + UART_CR); -} - -static inline void netx_transmit_buffer(struct uart_port *port) -{ - struct circ_buf *xmit = &port->state->xmit; - - if (port->x_char) { - writel(port->x_char, port->membase + UART_DR); - port->icount.tx++; - port->x_char = 0; - return; - } - - if (uart_tx_stopped(port) || uart_circ_empty(xmit)) { - netx_stop_tx(port); - return; - } - - do { - /* send xmit->buf[xmit->tail] - * out the port here */ - writel(xmit->buf[xmit->tail], port->membase + UART_DR); - xmit->tail = (xmit->tail + 1) & - (UART_XMIT_SIZE - 1); - port->icount.tx++; - if (uart_circ_empty(xmit)) - break; - } while (!(readl(port->membase + UART_FR) & FR_TXFF)); - - if (uart_circ_empty(xmit)) - netx_stop_tx(port); -} - -static void netx_start_tx(struct uart_port *port) -{ - writel( - readl(port->membase + UART_CR) | CR_TIE, port->membase + UART_CR); - - if (!(readl(port->membase + UART_FR) & FR_TXFF)) - netx_transmit_buffer(port); -} - -static unsigned int netx_tx_empty(struct uart_port *port) -{ - return readl(port->membase + UART_FR) & FR_BUSY ? 0 : TIOCSER_TEMT; -} - -static void netx_txint(struct uart_port *port) -{ - struct circ_buf *xmit = &port->state->xmit; - - if (uart_circ_empty(xmit) || uart_tx_stopped(port)) { - netx_stop_tx(port); - return; - } - - netx_transmit_buffer(port); - - if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) - uart_write_wakeup(port); -} - -static void netx_rxint(struct uart_port *port, unsigned long *flags) -{ - unsigned char rx, flg, status; - - while (!(readl(port->membase + UART_FR) & FR_RXFE)) { - rx = readl(port->membase + UART_DR); - flg = TTY_NORMAL; - port->icount.rx++; - status = readl(port->membase + UART_SR); - if (status & SR_BE) { - writel(0, port->membase + UART_SR); - if (uart_handle_break(port)) - continue; - } - - if (unlikely(status & (SR_FE | SR_PE | SR_OE))) { - - if (status & SR_PE) - port->icount.parity++; - else if (status & SR_FE) - port->icount.frame++; - if (status & SR_OE) - port->icount.overrun++; - - status &= port->read_status_mask; - - if (status & SR_BE) - flg = TTY_BREAK; - else if (status & SR_PE) - flg = TTY_PARITY; - else if (status & SR_FE) - flg = TTY_FRAME; - } - - if (uart_handle_sysrq_char(port, rx)) - continue; - - uart_insert_char(port, status, SR_OE, rx, flg); - } - - spin_unlock_irqrestore(&port->lock, *flags); - tty_flip_buffer_push(&port->state->port); - spin_lock_irqsave(&port->lock, *flags); -} - -static irqreturn_t netx_int(int irq, void *dev_id) -{ - struct uart_port *port = dev_id; - unsigned long flags; - unsigned char status; - - spin_lock_irqsave(&port->lock,flags); - - status = readl(port->membase + UART_IIR) & IIR_MASK; - while (status) { - if (status & IIR_RIS) - netx_rxint(port, &flags); - if (status & IIR_TIS) - netx_txint(port); - if (status & IIR_MIS) { - if (readl(port->membase + UART_FR) & FR_CTS) - uart_handle_cts_change(port, 1); - else - uart_handle_cts_change(port, 0); - } - writel(0, port->membase + UART_IIR); - status = readl(port->membase + UART_IIR) & IIR_MASK; - } - - spin_unlock_irqrestore(&port->lock,flags); - return IRQ_HANDLED; -} - -static unsigned int netx_get_mctrl(struct uart_port *port) -{ - unsigned int ret = TIOCM_DSR | TIOCM_CAR; - - if (readl(port->membase + UART_FR) & FR_CTS) - ret |= TIOCM_CTS; - - return ret; -} - -static void netx_set_mctrl(struct uart_port *port, unsigned int mctrl) -{ - unsigned int val; - - /* FIXME: Locking needed ? */ - if (mctrl & TIOCM_RTS) { - val = readl(port->membase + UART_RTS_CR); - writel(val | RTS_CR_RTS, port->membase + UART_RTS_CR); - } -} - -static void netx_break_ctl(struct uart_port *port, int break_state) -{ - unsigned int line_cr; - spin_lock_irq(&port->lock); - - line_cr = readl(port->membase + UART_LINE_CR); - if (break_state != 0) - line_cr |= LINE_CR_BRK; - else - line_cr &= ~LINE_CR_BRK; - writel(line_cr, port->membase + UART_LINE_CR); - - spin_unlock_irq(&port->lock); -} - -static int netx_startup(struct uart_port *port) -{ - int ret; - - ret = request_irq(port->irq, netx_int, 0, - DRIVER_NAME, port); - if (ret) { - dev_err(port->dev, "unable to grab irq%d\n",port->irq); - goto exit; - } - - writel(readl(port->membase + UART_LINE_CR) | LINE_CR_FEN, - port->membase + UART_LINE_CR); - - writel(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE | CR_UART_EN, - port->membase + UART_CR); - -exit: - return ret; -} - -static void netx_shutdown(struct uart_port *port) -{ - writel(0, port->membase + UART_CR) ; - - free_irq(port->irq, port); -} - -static void -netx_set_termios(struct uart_port *port, struct ktermios *termios, - struct ktermios *old) -{ - unsigned int baud, quot; - unsigned char old_cr; - unsigned char line_cr = LINE_CR_FEN; - unsigned char rts_cr = 0; - - switch (termios->c_cflag & CSIZE) { - case CS5: - line_cr |= LINE_CR_5BIT; - break; - case CS6: - line_cr |= LINE_CR_6BIT; - break; - case CS7: - line_cr |= LINE_CR_7BIT; - break; - case CS8: - line_cr |= LINE_CR_8BIT; - break; - } - - if (termios->c_cflag & CSTOPB) - line_cr |= LINE_CR_STP2; - - if (termios->c_cflag & PARENB) { - line_cr |= LINE_CR_PEN; - if (!(termios->c_cflag & PARODD)) - line_cr |= LINE_CR_EPS; - } - - if (termios->c_cflag & CRTSCTS) - rts_cr = RTS_CR_AUTO | RTS_CR_CTS_CTR | RTS_CR_RTS_POL; - - baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16); - quot = baud * 4096; - quot /= 1000; - quot *= 256; - quot /= 100000; - - spin_lock_irq(&port->lock); - - uart_update_timeout(port, termios->c_cflag, baud); - - old_cr = readl(port->membase + UART_CR); - - /* disable interrupts */ - writel(old_cr & ~(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE), - port->membase + UART_CR); - - /* drain transmitter */ - while (readl(port->membase + UART_FR) & FR_BUSY); - - /* disable UART */ - writel(old_cr & ~CR_UART_EN, port->membase + UART_CR); - - /* modem status interrupts */ - old_cr &= ~CR_MSIE; - if (UART_ENABLE_MS(port, termios->c_cflag)) - old_cr |= CR_MSIE; - - writel((quot>>8) & 0xff, port->membase + UART_BAUDDIV_MSB); - writel(quot & 0xff, port->membase + UART_BAUDDIV_LSB); - writel(line_cr, port->membase + UART_LINE_CR); - - writel(rts_cr, port->membase + UART_RTS_CR); - - /* - * Characters to ignore - */ - port->ignore_status_mask = 0; - if (termios->c_iflag & IGNPAR) - port->ignore_status_mask |= SR_PE; - if (termios->c_iflag & IGNBRK) { - port->ignore_status_mask |= SR_BE; - /* - * If we're ignoring parity and break indicators, - * ignore overruns too (for real raw support). - */ - if (termios->c_iflag & IGNPAR) - port->ignore_status_mask |= SR_PE; - } - - port->read_status_mask = 0; - if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) - port->read_status_mask |= SR_BE; - if (termios->c_iflag & INPCK) - port->read_status_mask |= SR_PE | SR_FE; - - writel(old_cr, port->membase + UART_CR); - - spin_unlock_irq(&port->lock); -} - -static const char *netx_type(struct uart_port *port) -{ - return port->type == PORT_NETX ? "NETX" : NULL; -} - -static void netx_release_port(struct uart_port *port) -{ - release_mem_region(port->mapbase, UART_PORT_SIZE); -} - -static int netx_request_port(struct uart_port *port) -{ - return request_mem_region(port->mapbase, UART_PORT_SIZE, - DRIVER_NAME) != NULL ? 0 : -EBUSY; -} - -static void netx_config_port(struct uart_port *port, int flags) -{ - if (flags & UART_CONFIG_TYPE && netx_request_port(port) == 0) - port->type = PORT_NETX; -} - -static int -netx_verify_port(struct uart_port *port, struct serial_struct *ser) -{ - int ret = 0; - - if (ser->type != PORT_UNKNOWN && ser->type != PORT_NETX) - ret = -EINVAL; - - return ret; -} - -static struct uart_ops netx_pops = { - .tx_empty = netx_tx_empty, - .set_mctrl = netx_set_mctrl, - .get_mctrl = netx_get_mctrl, - .stop_tx = netx_stop_tx, - .start_tx = netx_start_tx, - .stop_rx = netx_stop_rx, - .enable_ms = netx_enable_ms, - .break_ctl = netx_break_ctl, - .startup = netx_startup, - .shutdown = netx_shutdown, - .set_termios = netx_set_termios, - .type = netx_type, - .release_port = netx_release_port, - .request_port = netx_request_port, - .config_port = netx_config_port, - .verify_port = netx_verify_port, -}; - -static struct netx_port netx_ports[] = { - { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART0), - .mapbase = NETX_PA_UART0, - .irq = NETX_IRQ_UART0, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 0, - }, - }, { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART1), - .mapbase = NETX_PA_UART1, - .irq = NETX_IRQ_UART1, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 1, - }, - }, { - .port = { - .type = PORT_NETX, - .iotype = UPIO_MEM, - .membase = (char __iomem *)io_p2v(NETX_PA_UART2), - .mapbase = NETX_PA_UART2, - .irq = NETX_IRQ_UART2, - .uartclk = 100000000, - .fifosize = 16, - .flags = UPF_BOOT_AUTOCONF, - .ops = &netx_pops, - .line = 2, - }, - } -}; - -#ifdef CONFIG_SERIAL_NETX_CONSOLE - -static void netx_console_putchar(struct uart_port *port, int ch) -{ - while (readl(port->membase + UART_FR) & FR_BUSY); - writel(ch, port->membase + UART_DR); -} - -static void -netx_console_write(struct console *co, const char *s, unsigned int count) -{ - struct uart_port *port = &netx_ports[co->index].port; - unsigned char cr_save; - - cr_save = readl(port->membase + UART_CR); - writel(cr_save | CR_UART_EN, port->membase + UART_CR); - - uart_console_write(port, s, count, netx_console_putchar); - - while (readl(port->membase + UART_FR) & FR_BUSY); - writel(cr_save, port->membase + UART_CR); -} - -static void __init -netx_console_get_options(struct uart_port *port, int *baud, - int *parity, int *bits, int *flow) -{ - unsigned char line_cr; - - *baud = (readl(port->membase + UART_BAUDDIV_MSB) << 8) | - readl(port->membase + UART_BAUDDIV_LSB); - *baud *= 1000; - *baud /= 4096; - *baud *= 1000; - *baud /= 256; - *baud *= 100; - - line_cr = readl(port->membase + UART_LINE_CR); - *parity = 'n'; - if (line_cr & LINE_CR_PEN) { - if (line_cr & LINE_CR_EPS) - *parity = 'e'; - else - *parity = 'o'; - } - - switch (line_cr & LINE_CR_BITS_MASK) { - case LINE_CR_8BIT: - *bits = 8; - break; - case LINE_CR_7BIT: - *bits = 7; - break; - case LINE_CR_6BIT: - *bits = 6; - break; - case LINE_CR_5BIT: - *bits = 5; - break; - } - - if (readl(port->membase + UART_RTS_CR) & RTS_CR_AUTO) - *flow = 'r'; -} - -static int __init -netx_console_setup(struct console *co, char *options) -{ - struct netx_port *sport; - int baud = 9600; - int bits = 8; - int parity = 'n'; - int flow = 'n'; - - /* - * Check whether an invalid uart number has been specified, and - * if so, search for the first available port that does have - * console support. - */ - if (co->index == -1 || co->index >= ARRAY_SIZE(netx_ports)) - co->index = 0; - sport = &netx_ports[co->index]; - - if (options) { - uart_parse_options(options, &baud, &parity, &bits, &flow); - } else { - /* if the UART is enabled, assume it has been correctly setup - * by the bootloader and get the options - */ - if (readl(sport->port.membase + UART_CR) & CR_UART_EN) { - netx_console_get_options(&sport->port, &baud, - &parity, &bits, &flow); - } - - } - - return uart_set_options(&sport->port, co, baud, parity, bits, flow); -} - -static struct uart_driver netx_reg; -static struct console netx_console = { - .name = "ttyNX", - .write = netx_console_write, - .device = uart_console_device, - .setup = netx_console_setup, - .flags = CON_PRINTBUFFER, - .index = -1, - .data = &netx_reg, -}; - -static int __init netx_console_init(void) -{ - register_console(&netx_console); - return 0; -} -console_initcall(netx_console_init); - -#define NETX_CONSOLE &netx_console -#else -#define NETX_CONSOLE NULL -#endif - -static struct uart_driver netx_reg = { - .owner = THIS_MODULE, - .driver_name = DRIVER_NAME, - .dev_name = "ttyNX", - .major = SERIAL_NX_MAJOR, - .minor = MINOR_START, - .nr = ARRAY_SIZE(netx_ports), - .cons = NETX_CONSOLE, -}; - -static int serial_netx_suspend(struct platform_device *pdev, pm_message_t state) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_suspend_port(&netx_reg, &sport->port); - - return 0; -} - -static int serial_netx_resume(struct platform_device *pdev) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_resume_port(&netx_reg, &sport->port); - - return 0; -} - -static int serial_netx_probe(struct platform_device *pdev) -{ - struct uart_port *port = &netx_ports[pdev->id].port; - - dev_info(&pdev->dev, "initialising\n"); - - port->dev = &pdev->dev; - - writel(1, port->membase + UART_RXFIFO_IRQLEVEL); - uart_add_one_port(&netx_reg, &netx_ports[pdev->id].port); - platform_set_drvdata(pdev, &netx_ports[pdev->id]); - - return 0; -} - -static int serial_netx_remove(struct platform_device *pdev) -{ - struct netx_port *sport = platform_get_drvdata(pdev); - - if (sport) - uart_remove_one_port(&netx_reg, &sport->port); - - return 0; -} - -static struct platform_driver serial_netx_driver = { - .probe = serial_netx_probe, - .remove = serial_netx_remove, - - .suspend = serial_netx_suspend, - .resume = serial_netx_resume, - - .driver = { - .name = DRIVER_NAME, - }, -}; - -static int __init netx_serial_init(void) -{ - int ret; - - printk(KERN_INFO "Serial: NetX driver\n"); - - ret = uart_register_driver(&netx_reg); - if (ret) - return ret; - - ret = platform_driver_register(&serial_netx_driver); - if (ret != 0) - uart_unregister_driver(&netx_reg); - - return 0; -} - -static void __exit netx_serial_exit(void) -{ - platform_driver_unregister(&serial_netx_driver); - uart_unregister_driver(&netx_reg); -} - -module_init(netx_serial_init); -module_exit(netx_serial_exit); - -MODULE_AUTHOR("Sascha Hauer"); -MODULE_DESCRIPTION("NetX serial port driver"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 717292c1c0df..60ff236a3d63 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -93,8 +93,7 @@ static void __ldsem_wake_readers(struct ld_semaphore *sem) list_for_each_entry_safe(waiter, next, &sem->read_wait, list) { tsk = waiter->task; - smp_mb(); - waiter->task = NULL; + smp_store_release(&waiter->task, NULL); wake_up_process(tsk); put_task_struct(tsk); } @@ -194,7 +193,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout) for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!waiter.task) + if (!smp_load_acquire(&waiter.task)) break; if (!timeout) break; diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index ec92f36ab5c4..34aa39d1aed9 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3771,7 +3771,11 @@ static ssize_t show_bind(struct device *dev, struct device_attribute *attr, char *buf) { struct con_driver *con = dev_get_drvdata(dev); - int bind = con_is_bound(con->con); + int bind; + + console_lock(); + bind = con_is_bound(con->con); + console_unlock(); return snprintf(buf, PAGE_SIZE, "%i\n", bind); } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 88533938ce19..9320787ac2e6 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -3052,8 +3052,8 @@ int usb_hcd_setup_local_mem(struct usb_hcd *hcd, phys_addr_t phys_addr, local_mem = devm_memremap(hcd->self.sysdev, phys_addr, size, MEMREMAP_WC); - if (!local_mem) - return -ENOMEM; + if (IS_ERR(local_mem)) + return PTR_ERR(local_mem); /* * Here we pass a dma_addr_t but the arg type is a phys_addr_t. diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index fe9422d3bcdc..b0882c13a1d1 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -149,7 +149,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd) break; case PCI_VENDOR_ID_AMD: /* AMD PLL quirk */ - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ehci->amd_pll_fix = 1; /* AMD8111 EHCI doesn't work, according to AMD errata */ if (pdev->device == 0x7463) { @@ -186,7 +186,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd) break; case PCI_VENDOR_ID_ATI: /* AMD PLL quirk */ - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ehci->amd_pll_fix = 1; /* diff --git a/drivers/usb/host/hwa-hc.c b/drivers/usb/host/hwa-hc.c index 09a8ebd95588..6968b9f2b76b 100644 --- a/drivers/usb/host/hwa-hc.c +++ b/drivers/usb/host/hwa-hc.c @@ -159,7 +159,7 @@ out: return result; error_set_cluster_id: - wusb_cluster_id_put(wusbhc->cluster_id); + wusb_cluster_id_put(addr); error_cluster_id_get: goto out; diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c index a033f7d855e0..f4e13a3fddee 100644 --- a/drivers/usb/host/ohci-pci.c +++ b/drivers/usb/host/ohci-pci.c @@ -152,7 +152,7 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd) { struct ohci_hcd *ohci = hcd_to_ohci(hcd); - if (usb_amd_find_chipset_info()) + if (usb_amd_quirk_pll_check()) ohci->flags |= OHCI_QUIRK_AMD_PLL; /* SB800 needs pre-fetch fix */ diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 3ce71cbfbb58..f6d04491df60 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -132,7 +132,7 @@ static struct amd_chipset_info { struct amd_chipset_type sb_type; int isoc_reqs; int probe_count; - int probe_result; + bool need_pll_quirk; } amd_chipset; static DEFINE_SPINLOCK(amd_lock); @@ -201,11 +201,11 @@ void sb800_prefetch(struct device *dev, int on) } EXPORT_SYMBOL_GPL(sb800_prefetch); -int usb_amd_find_chipset_info(void) +static void usb_amd_find_chipset_info(void) { unsigned long flags; struct amd_chipset_info info; - int ret; + info.need_pll_quirk = 0; spin_lock_irqsave(&amd_lock, flags); @@ -213,27 +213,34 @@ int usb_amd_find_chipset_info(void) if (amd_chipset.probe_count > 0) { amd_chipset.probe_count++; spin_unlock_irqrestore(&amd_lock, flags); - return amd_chipset.probe_result; + return; } memset(&info, 0, sizeof(info)); spin_unlock_irqrestore(&amd_lock, flags); if (!amd_chipset_sb_type_init(&info)) { - ret = 0; goto commit; } - /* Below chipset generations needn't enable AMD PLL quirk */ - if (info.sb_type.gen == AMD_CHIPSET_UNKNOWN || - info.sb_type.gen == AMD_CHIPSET_SB600 || - info.sb_type.gen == AMD_CHIPSET_YANGTZE || - (info.sb_type.gen == AMD_CHIPSET_SB700 && - info.sb_type.rev > 0x3b)) { + switch (info.sb_type.gen) { + case AMD_CHIPSET_SB700: + info.need_pll_quirk = info.sb_type.rev <= 0x3B; + break; + case AMD_CHIPSET_SB800: + case AMD_CHIPSET_HUDSON2: + case AMD_CHIPSET_BOLTON: + info.need_pll_quirk = 1; + break; + default: + info.need_pll_quirk = 0; + break; + } + + if (!info.need_pll_quirk) { if (info.smbus_dev) { pci_dev_put(info.smbus_dev); info.smbus_dev = NULL; } - ret = 0; goto commit; } @@ -252,7 +259,6 @@ int usb_amd_find_chipset_info(void) } } - ret = info.probe_result = 1; printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n"); commit: @@ -263,7 +269,6 @@ commit: /* Mark that we where here */ amd_chipset.probe_count++; - ret = amd_chipset.probe_result; spin_unlock_irqrestore(&amd_lock, flags); @@ -276,10 +281,7 @@ commit: amd_chipset = info; spin_unlock_irqrestore(&amd_lock, flags); } - - return ret; } -EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info); int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev) { @@ -315,6 +317,13 @@ bool usb_amd_prefetch_quirk(void) } EXPORT_SYMBOL_GPL(usb_amd_prefetch_quirk); +bool usb_amd_quirk_pll_check(void) +{ + usb_amd_find_chipset_info(); + return amd_chipset.need_pll_quirk; +} +EXPORT_SYMBOL_GPL(usb_amd_quirk_pll_check); + /* * The hardware normally enables the A-link power management feature, which * lets the system lower the power consumption in idle states. @@ -520,7 +529,7 @@ void usb_amd_dev_put(void) amd_chipset.nb_type = 0; memset(&amd_chipset.sb_type, 0, sizeof(amd_chipset.sb_type)); amd_chipset.isoc_reqs = 0; - amd_chipset.probe_result = 0; + amd_chipset.need_pll_quirk = 0; spin_unlock_irqrestore(&amd_lock, flags); diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index 63c633077d9e..e729de21fad7 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -5,11 +5,11 @@ #ifdef CONFIG_USB_PCI void uhci_reset_hc(struct pci_dev *pdev, unsigned long base); int uhci_check_and_reset_hc(struct pci_dev *pdev, unsigned long base); -int usb_amd_find_chipset_info(void); int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev); bool usb_amd_hang_symptom_quirk(void); bool usb_amd_prefetch_quirk(void); void usb_amd_dev_put(void); +bool usb_amd_quirk_pll_check(void); void usb_amd_quirk_pll_disable(void); void usb_amd_quirk_pll_enable(void); void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c2fe218e051f..1e0236e90687 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -130,7 +130,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_AMD_0x96_HOST; /* AMD PLL quirk */ - if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) + if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_quirk_pll_check()) xhci->quirks |= XHCI_AMD_PLL_FIX; if (pdev->vendor == PCI_VENDOR_ID_AMD && diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 7a264962a1a9..f5c41448d067 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2175,7 +2175,8 @@ static inline bool xhci_urb_suitable_for_idt(struct urb *urb) if (!usb_endpoint_xfer_isoc(&urb->ep->desc) && usb_urb_dir_out(urb) && usb_endpoint_maxp(&urb->ep->desc) >= TRB_IDT_MAX_SIZE && urb->transfer_buffer_length <= TRB_IDT_MAX_SIZE && - !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) + !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP) && + !urb->num_sgs) return true; return false; diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 4d6ae3795a88..6ca9111d150a 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -375,7 +375,8 @@ out_err: #ifdef CONFIG_OF static void usb251xb_get_ports_field(struct usb251xb *hub, - const char *prop_name, u8 port_cnt, u8 *fld) + const char *prop_name, u8 port_cnt, + bool ds_only, u8 *fld) { struct device *dev = hub->dev; struct property *prop; @@ -383,7 +384,7 @@ static void usb251xb_get_ports_field(struct usb251xb *hub, u32 port; of_property_for_each_u32(dev->of_node, prop_name, prop, p, port) { - if ((port >= 1) && (port <= port_cnt)) + if ((port >= ds_only ? 1 : 0) && (port <= port_cnt)) *fld |= BIT(port); else dev_warn(dev, "port %u doesn't exist\n", port); @@ -501,15 +502,15 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, hub->non_rem_dev = USB251XB_DEF_NON_REMOVABLE_DEVICES; usb251xb_get_ports_field(hub, "non-removable-ports", data->port_cnt, - &hub->non_rem_dev); + true, &hub->non_rem_dev); hub->port_disable_sp = USB251XB_DEF_PORT_DISABLE_SELF; usb251xb_get_ports_field(hub, "sp-disabled-ports", data->port_cnt, - &hub->port_disable_sp); + true, &hub->port_disable_sp); hub->port_disable_bp = USB251XB_DEF_PORT_DISABLE_BUS; usb251xb_get_ports_field(hub, "bp-disabled-ports", data->port_cnt, - &hub->port_disable_bp); + true, &hub->port_disable_bp); hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF; if (!of_property_read_u32(np, "sp-max-total-current-microamp", @@ -573,9 +574,7 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, */ hub->port_swap = USB251XB_DEF_PORT_SWAP; usb251xb_get_ports_field(hub, "swap-dx-lanes", data->port_cnt, - &hub->port_swap); - if (of_get_property(np, "swap-us-lanes", NULL)) - hub->port_swap |= BIT(0); + false, &hub->port_swap); /* The following parameters are currently not exposed to devicetree, but * may be as soon as needed. diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 30790240aec6..05b80211290d 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -28,6 +28,8 @@ * status of a command. */ +#include <linux/blkdev.h> +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/mutex.h> @@ -99,6 +101,7 @@ static int slave_alloc (struct scsi_device *sdev) static int slave_configure(struct scsi_device *sdev) { struct us_data *us = host_to_us(sdev->host); + struct device *dev = us->pusb_dev->bus->sysdev; /* * Many devices have trouble transferring more than 32KB at a time, @@ -129,6 +132,14 @@ static int slave_configure(struct scsi_device *sdev) } /* + * The max_hw_sectors should be up to maximum size of a mapping for + * the device. Otherwise, a DMA API might fail on swiotlb environment. + */ + blk_queue_max_hw_sectors(sdev->request_queue, + min_t(size_t, queue_max_hw_sectors(sdev->request_queue), + dma_max_mapping_size(dev) >> SECTOR_SHIFT)); + + /* * Some USB host controllers can't do DMA; they have to use PIO. * They indicate this by setting their dma_mask to NULL. For * such controllers we need to make sure the block layer sets diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 819296332913..42a8c2a13ab1 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -96,7 +96,7 @@ struct vhost_uaddr { }; #if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0 -#define VHOST_ARCH_CAN_ACCEL_UACCESS 1 +#define VHOST_ARCH_CAN_ACCEL_UACCESS 0 #else #define VHOST_ARCH_CAN_ACCEL_UACCESS 0 #endif diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 4c339c7e66e5..a446a7221e13 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1143,7 +1143,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) goto out_put_map; if (!use_ptemod) { - err = vm_map_pages(vma, map->pages, map->count); + err = vm_map_pages_zero(vma, map->pages, map->count); if (err) goto out_put_map; } else { diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 2f5ce7230a43..c6070e70dd73 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -724,25 +724,6 @@ static long privcmd_ioctl_restrict(struct file *file, void __user *udata) return 0; } -struct remap_pfn { - struct mm_struct *mm; - struct page **pages; - pgprot_t prot; - unsigned long i; -}; - -static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data) -{ - struct remap_pfn *r = data; - struct page *page = r->pages[r->i]; - pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot)); - - set_pte_at(r->mm, addr, ptep, pte); - r->i++; - - return 0; -} - static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) { struct privcmd_data *data = file->private_data; @@ -774,7 +755,8 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) goto out; } - if (xen_feature(XENFEAT_auto_translated_physmap)) { + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { unsigned int nr = DIV_ROUND_UP(kdata.num, XEN_PFN_PER_PAGE); struct page **pages; unsigned int i; @@ -808,16 +790,9 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata) if (rc) goto out; - if (xen_feature(XENFEAT_auto_translated_physmap)) { - struct remap_pfn r = { - .mm = vma->vm_mm, - .pages = vma->vm_private_data, - .prot = vma->vm_page_prot, - }; - - rc = apply_to_page_range(r.mm, kdata.addr, - kdata.num << PAGE_SHIFT, - remap_pfn_fn, &r); + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && + xen_feature(XENFEAT_auto_translated_physmap)) { + rc = xen_remap_vma_range(vma, kdata.addr, kdata.num << PAGE_SHIFT); } else { unsigned int domid = (xdata.flags & XENMEM_rsrc_acq_caller_owned) ? diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index cfbe46785a3b..ae1df496bf38 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -83,34 +83,18 @@ static inline dma_addr_t xen_virt_to_bus(void *address) return xen_phys_to_bus(virt_to_phys(address)); } -static int check_pages_physically_contiguous(unsigned long xen_pfn, - unsigned int offset, - size_t length) +static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { - unsigned long next_bfn; - int i; - int nr_pages; + unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); + unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); next_bfn = pfn_to_bfn(xen_pfn); - nr_pages = (offset + length + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT; - for (i = 1; i < nr_pages; i++) { + for (i = 1; i < nr_pages; i++) if (pfn_to_bfn(++xen_pfn) != ++next_bfn) - return 0; - } - return 1; -} + return 1; -static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) -{ - unsigned long xen_pfn = XEN_PFN_DOWN(p); - unsigned int offset = p & ~XEN_PAGE_MASK; - - if (offset + size <= XEN_PAGE_SIZE) - return 0; - if (check_pages_physically_contiguous(xen_pfn, offset, size)) - return 0; - return 1; + return 0; } static int is_xen_swiotlb_buffer(dma_addr_t dma_addr) @@ -338,6 +322,7 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs); return NULL; } + SetPageXenRemapped(virt_to_page(ret)); } memset(ret, 0, size); return ret; @@ -361,8 +346,9 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, /* Convert the size to actually allocated. */ size = 1UL << (order + XEN_PAGE_SHIFT); - if (((dev_addr + size - 1 <= dma_mask)) || - range_straddles_page_boundary(phys, size)) + if (!WARN_ON((dev_addr + size - 1 > dma_mask) || + range_straddles_page_boundary(phys, size)) && + TestClearPageXenRemapped(virt_to_page(vaddr))) xen_destroy_contiguous_region(phys, order); xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs); diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 73427d8e0116..e5694133ebe5 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -116,13 +116,12 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value, { int err; u16 old_value; - pci_power_t new_state, old_state; + pci_power_t new_state; err = pci_read_config_word(dev, offset, &old_value); if (err) goto out; - old_state = (pci_power_t)(old_value & PCI_PM_CTRL_STATE_MASK); new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); new_value &= PM_OK_BITS; diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c index ba883a80b3c0..7b1077f0abcb 100644 --- a/drivers/xen/xlate_mmu.c +++ b/drivers/xen/xlate_mmu.c @@ -262,3 +262,35 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt, return 0; } EXPORT_SYMBOL_GPL(xen_xlate_map_ballooned_pages); + +struct remap_pfn { + struct mm_struct *mm; + struct page **pages; + pgprot_t prot; + unsigned long i; +}; + +static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data) +{ + struct remap_pfn *r = data; + struct page *page = r->pages[r->i]; + pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot)); + + set_pte_at(r->mm, addr, ptep, pte); + r->i++; + + return 0; +} + +/* Used by the privcmd module, but has to be built-in on ARM */ +int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, unsigned long len) +{ + struct remap_pfn r = { + .mm = vma->vm_mm, + .pages = vma->vm_private_data, + .prot = vma->vm_page_prot, + }; + + return apply_to_page_range(vma->vm_mm, addr, len, remap_pfn_fn, &r); +} +EXPORT_SYMBOL_GPL(xen_remap_vma_range); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 1ce73e014139..114f281f3687 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -339,8 +339,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->tmp_u = htonl(0); afs_extract_to_tmp(call); } + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -366,8 +367,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -394,8 +396,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -407,8 +409,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) no_more_data: call->unmarshall = 4; afs_extract_to_buf(call, (21 + 3 + 6) * 4); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -1471,8 +1474,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, 12 * 4); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1483,8 +1487,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1498,8 +1503,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1511,8 +1517,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1526,8 +1533,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1540,8 +1548,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1555,8 +1564,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1850,8 +1860,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the capabilities word count */ + /* Extract the capabilities word count */ case 1: ret = afs_extract_data(call, true); if (ret < 0) @@ -1863,8 +1874,9 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) call->count2 = count; iov_iter_discard(&call->iter, READ, count * sizeof(__be32)); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract capabilities words */ + /* Extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) @@ -2020,9 +2032,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -2039,8 +2051,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, 21 * sizeof(__be32)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -2060,9 +2072,9 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -2078,8 +2090,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, 3 * sizeof(__be32)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -2096,8 +2108,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -2193,6 +2205,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* extract the returned data length */ case 1: @@ -2210,6 +2223,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; + /* Fall through */ /* extract the returned data */ case 2: @@ -2219,6 +2233,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) afs_extract_to_buf(call, (21 + 6) * 4); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 3: diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 18722aaeda33..2575503170fc 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -450,8 +450,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->offset = req->pos & (PAGE_SIZE - 1); afs_extract_to_tmp64(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the returned data length */ + /* extract the returned data length */ case 1: _debug("extract data length"); ret = afs_extract_data(call, true); @@ -477,8 +478,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) call->bvec[0].bv_page = req->pages[req->index]; iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); ASSERTCMP(size, <=, PAGE_SIZE); + /* Fall through */ - /* Fall through - and extract the returned data */ + /* extract the returned data */ case 2: _debug("extract data %zu/%llu", iov_iter_count(&call->iter), req->remain); @@ -505,8 +507,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) /* Discard any excess data the server gave us */ iov_iter_discard(&call->iter, READ, req->actual_len - req->len); call->unmarshall = 3; - /* Fall through */ + case 3: _debug("extract discard %zu/%llu", iov_iter_count(&call->iter), req->actual_len - req->len); @@ -521,8 +523,9 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSCallBack) + sizeof(struct yfs_xdr_YFSVolSync)); + /* Fall through */ - /* Fall through - and extract the metadata */ + /* extract the metadata */ case 4: ret = afs_extract_data(call, false); if (ret < 0) @@ -539,8 +542,8 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) req->file_size = call->out_scb->status.size; call->unmarshall++; - /* Fall through */ + case 5: break; } @@ -1429,8 +1432,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) case 0: call->unmarshall++; afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); + /* Fall through */ - /* Fall through - and extract the returned status record */ + /* extract the returned status record */ case 1: _debug("extract status"); ret = afs_extract_data(call, true); @@ -1441,8 +1445,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ - /* Fall through - and extract the volume name length */ + /* extract the volume name length */ case 2: ret = afs_extract_data(call, true); if (ret < 0) @@ -1456,8 +1461,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the volume name */ + /* extract the volume name */ case 3: _debug("extract volname"); ret = afs_extract_data(call, true); @@ -1469,8 +1475,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("volname '%s'", p); afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message length */ + /* extract the offline message length */ case 4: ret = afs_extract_data(call, true); if (ret < 0) @@ -1484,8 +1491,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the offline message */ + /* extract the offline message */ case 5: _debug("extract offline"); ret = afs_extract_data(call, true); @@ -1498,8 +1506,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day length */ + /* extract the message of the day length */ case 6: ret = afs_extract_data(call, true); if (ret < 0) @@ -1513,8 +1522,9 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) size = (call->count + 3) & ~3; /* It's padded */ afs_extract_to_buf(call, size); call->unmarshall++; + /* Fall through */ - /* Fall through - and extract the message of the day */ + /* extract the message of the day */ case 7: _debug("extract motd"); ret = afs_extract_data(call, false); @@ -1526,8 +1536,8 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) _debug("motd '%s'", p); call->unmarshall++; - /* Fall through */ + case 8: break; } @@ -1805,9 +1815,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file status count and array in two steps */ - /* Fall through */ case 1: _debug("extract status count"); ret = afs_extract_data(call, true); @@ -1824,8 +1834,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_counts: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); - /* Fall through */ + case 2: _debug("extract status array %u", call->count); ret = afs_extract_data(call, true); @@ -1845,9 +1855,9 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; afs_extract_to_tmp(call); + /* Fall through */ /* Extract the callback count and array in two steps */ - /* Fall through */ case 3: _debug("extract CB count"); ret = afs_extract_data(call, true); @@ -1863,8 +1873,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) call->unmarshall++; more_cbs: afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); - /* Fall through */ + case 4: _debug("extract CB array"); ret = afs_extract_data(call, true); @@ -1881,8 +1891,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; - /* Fall through */ + case 5: ret = afs_extract_data(call, false); if (ret < 0) @@ -1892,8 +1902,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; - /* Fall through */ + case 6: break; } @@ -1978,6 +1988,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) case 0: afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the file ACL length */ case 1: @@ -1999,6 +2010,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the file ACL */ case 2: @@ -2008,6 +2020,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) afs_extract_to_tmp(call); call->unmarshall++; + /* Fall through */ /* Extract the volume ACL length */ case 3: @@ -2029,6 +2042,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) iov_iter_discard(&call->iter, READ, size); } call->unmarshall++; + /* Fall through */ /* Extract the volume ACL */ case 4: @@ -2041,6 +2055,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); call->unmarshall++; + /* Fall through */ /* extract the metadata */ case 5: @@ -2057,6 +2072,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; + /* Fall through */ case 6: break; diff --git a/fs/block_dev.c b/fs/block_dev.c index 4707dfff991b..a6f7c892cb4a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -345,15 +345,24 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; + bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret = 0; + gfp_t gfp; + ssize_t ret; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); + if (nowait) + gfp = GFP_NOWAIT; + else + gfp = GFP_KERNEL; + + bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool); + if (!bio) + return -EAGAIN; dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); @@ -375,7 +384,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) if (!is_poll) blk_start_plug(&plug); + ret = 0; for (;;) { + int err; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; bio->bi_write_hint = iocb->ki_hint; @@ -383,8 +395,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { + err = bio_iov_iter_get_pages(bio, iter); + if (unlikely(err)) { + if (!ret) + ret = err; bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; @@ -399,6 +413,14 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) task_io_account_write(bio->bi_iter.bi_size); } + /* + * Tell underlying layer to not block for resource shortage. + * And if we would have blocked, return error inline instead + * of through the bio->bi_end_io() callback. + */ + if (nowait) + bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE); + dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; @@ -412,6 +434,12 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } + ret = dio->size; if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -432,8 +460,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) atomic_inc(&dio->ref); } - submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, nr_pages); + qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } + ret = dio->size; + + bio = bio_alloc(gfp, nr_pages); + if (!bio) { + if (!ret) + ret = -EAGAIN; + goto error; + } } if (!is_poll) @@ -453,13 +493,16 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); +out: if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); - if (likely(!ret)) - ret = dio->size; bio_put(&dio->bio); return ret; +error: + if (!is_poll) + blk_finish_plug(&plug); + goto out; } static ssize_t @@ -1139,8 +1182,7 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) * Pointer to the block device containing @bdev on success, ERR_PTR() * value on failure. */ -static struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder) +struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) { struct gendisk *disk; struct block_device *whole; @@ -1187,6 +1229,62 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, return ERR_PTR(err); } } +EXPORT_SYMBOL(bd_start_claiming); + +static void bd_clear_claiming(struct block_device *whole, void *holder) +{ + lockdep_assert_held(&bdev_lock); + /* tell others that we're done */ + BUG_ON(whole->bd_claiming != holder); + whole->bd_claiming = NULL; + wake_up_bit(&whole->bd_claiming, 0); +} + +/** + * bd_finish_claiming - finish claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Finish exclusive open of a block device. Mark the device as exlusively + * open by the holder and wake up all waiters for exclusive open to finish. + */ +void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, whole, holder)); + /* + * Note that for a whole device bd_holders will be incremented twice, + * and bd_holder will be set to bd_may_claim before being set to holder + */ + whole->bd_holders++; + whole->bd_holder = bd_may_claim; + bdev->bd_holders++; + bdev->bd_holder = holder; + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_finish_claiming); + +/** + * bd_abort_claiming - abort claiming of a block device + * @bdev: block device of interest + * @whole: whole block device (returned from bd_start_claiming()) + * @holder: holder that has claimed @bdev + * + * Abort claiming of a block device when the exclusive open failed. This can be + * also used when exclusive open is not actually desired and we just needed + * to block other exclusive openers for a while. + */ +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder) +{ + spin_lock(&bdev_lock); + bd_clear_claiming(whole, holder); + spin_unlock(&bdev_lock); +} +EXPORT_SYMBOL(bd_abort_claiming); #ifdef CONFIG_SYSFS struct bd_holder_disk { @@ -1656,29 +1754,7 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) /* finish claiming */ mutex_lock(&bdev->bd_mutex); - spin_lock(&bdev_lock); - - if (!res) { - BUG_ON(!bd_may_claim(bdev, whole, holder)); - /* - * Note that for a whole device bd_holders - * will be incremented twice, and bd_holder - * will be set to bd_may_claim before being - * set to holder - */ - whole->bd_holders++; - whole->bd_holder = bd_may_claim; - bdev->bd_holders++; - bdev->bd_holder = holder; - } - - /* tell others that we're done */ - BUG_ON(whole->bd_claiming != holder); - whole->bd_claiming = NULL; - wake_up_bit(&whole->bd_claiming, 0); - - spin_unlock(&bdev_lock); - + bd_finish_claiming(bdev, whole, holder); /* * Block event polling for write claims if requested. Any * write holder makes the write_holder state stick until diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 89116afda7a2..e5d85311d5d5 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1483,7 +1483,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr, ulist_init(roots); ulist_init(tmp); - trans = btrfs_attach_transaction(root); + trans = btrfs_join_transaction_nostart(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 98fccce4208c..393eceda57c8 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -346,9 +346,12 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); eb->blocking_writers--; - /* Use the lighter barrier after atomic */ - smp_mb__after_atomic(); - cond_wake_up_nomb(&eb->write_lock_wq); + /* + * We need to order modifying blocking_writers above with + * actually waking up the sleepers to ensure they see the + * updated value of blocking_writers + */ + cond_wake_up(&eb->write_lock_wq); } else { btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 1744ba8b2754..ae7f64a8facb 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -985,13 +985,14 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct extent_state **cached_state) { struct btrfs_ordered_extent *ordered; - struct extent_state *cachedp = NULL; + struct extent_state *cache = NULL; + struct extent_state **cachedp = &cache; if (cached_state) - cachedp = *cached_state; + cachedp = cached_state; while (1) { - lock_extent_bits(tree, start, end, &cachedp); + lock_extent_bits(tree, start, end, cachedp); ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1); if (!ordered) { @@ -1001,10 +1002,10 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, * aren't exposing it outside of this function */ if (!cached_state) - refcount_dec(&cachedp->refs); + refcount_dec(&cache->refs); break; } - unlock_extent_cached(tree, start, end, &cachedp); + unlock_extent_cached(tree, start, end, cachedp); btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 69b59bf75882..c3c0c064c25d 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6322,68 +6322,21 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - if (sctx->cur_ino != sctx->cmp_key->objectid) { - - if (result == BTRFS_COMPARE_TREE_CHANGED) { - struct extent_buffer *leaf_l; - struct extent_buffer *leaf_r; - struct btrfs_file_extent_item *ei_l; - struct btrfs_file_extent_item *ei_r; - - leaf_l = sctx->left_path->nodes[0]; - leaf_r = sctx->right_path->nodes[0]; - ei_l = btrfs_item_ptr(leaf_l, - sctx->left_path->slots[0], - struct btrfs_file_extent_item); - ei_r = btrfs_item_ptr(leaf_r, - sctx->right_path->slots[0], - struct btrfs_file_extent_item); - - /* - * We may have found an extent item that has changed - * only its disk_bytenr field and the corresponding - * inode item was not updated. This case happens due to - * very specific timings during relocation when a leaf - * that contains file extent items is COWed while - * relocation is ongoing and its in the stage where it - * updates data pointers. So when this happens we can - * safely ignore it since we know it's the same extent, - * but just at different logical and physical locations - * (when an extent is fully replaced with a new one, we - * know the generation number must have changed too, - * since snapshot creation implies committing the current - * transaction, and the inode item must have been updated - * as well). - * This replacement of the disk_bytenr happens at - * relocation.c:replace_file_extents() through - * relocation.c:btrfs_reloc_cow_block(). - */ - if (btrfs_file_extent_generation(leaf_l, ei_l) == - btrfs_file_extent_generation(leaf_r, ei_r) && - btrfs_file_extent_ram_bytes(leaf_l, ei_l) == - btrfs_file_extent_ram_bytes(leaf_r, ei_r) && - btrfs_file_extent_compression(leaf_l, ei_l) == - btrfs_file_extent_compression(leaf_r, ei_r) && - btrfs_file_extent_encryption(leaf_l, ei_l) == - btrfs_file_extent_encryption(leaf_r, ei_r) && - btrfs_file_extent_other_encoding(leaf_l, ei_l) == - btrfs_file_extent_other_encoding(leaf_r, ei_r) && - btrfs_file_extent_type(leaf_l, ei_l) == - btrfs_file_extent_type(leaf_r, ei_r) && - btrfs_file_extent_disk_bytenr(leaf_l, ei_l) != - btrfs_file_extent_disk_bytenr(leaf_r, ei_r) && - btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) && - btrfs_file_extent_offset(leaf_l, ei_l) == - btrfs_file_extent_offset(leaf_r, ei_r) && - btrfs_file_extent_num_bytes(leaf_l, ei_l) == - btrfs_file_extent_num_bytes(leaf_r, ei_r)) - return 0; - } - - inconsistent_snapshot_error(sctx, result, "extent"); - return -EIO; - } + /* + * We have found an extent item that changed without the inode item + * having changed. This can happen either after relocation (where the + * disk_bytenr of an extent item is replaced at + * relocation.c:replace_file_extents()) or after deduplication into a + * file in both the parent and send snapshots (where an extent item can + * get modified or replaced with a new one). Note that deduplication + * updates the inode item, but it only changes the iversion (sequence + * field in the inode item) of the inode, so if a file is deduplicated + * the same amount of times in both the parent and send snapshots, its + * iversion becames the same in both snapshots, whence the inode item is + * the same on both snapshots. + */ + if (sctx->cur_ino != sctx->cmp_key->objectid) + return 0; if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3b8ae1a8f02d..e3adb714c04b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -28,15 +28,18 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { [TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH), [TRANS_STATE_COMMIT_DOING] = (__TRANS_START | __TRANS_ATTACH | - __TRANS_JOIN), + __TRANS_JOIN | + __TRANS_JOIN_NOSTART), [TRANS_STATE_UNBLOCKED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | - __TRANS_JOIN_NOLOCK), + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), }; void btrfs_put_transaction(struct btrfs_transaction *transaction) @@ -543,7 +546,8 @@ again: ret = join_transaction(fs_info, type); if (ret == -EBUSY) { wait_current_trans(fs_info); - if (unlikely(type == TRANS_ATTACH)) + if (unlikely(type == TRANS_ATTACH || + type == TRANS_JOIN_NOSTART)) ret = -ENOENT; } } while (ret == -EBUSY); @@ -660,6 +664,16 @@ struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root } /* + * Similar to regular join but it never starts a transaction when none is + * running or after waiting for the current one to finish. + */ +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root) +{ + return start_transaction(root, 0, TRANS_JOIN_NOSTART, + BTRFS_RESERVE_NO_FLUSH, true); +} + +/* * btrfs_attach_transaction() - catch the running transaction * * It is used when we want to commit the current the transaction, but @@ -2037,6 +2051,16 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) } } else { spin_unlock(&fs_info->trans_lock); + /* + * The previous transaction was aborted and was already removed + * from the list of transactions at fs_info->trans_list. So we + * abort to prevent writing a new superblock that reflects a + * corrupt state (pointing to trees with unwritten nodes/leafs). + */ + if (test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) { + ret = -EROFS; + goto cleanup_transaction; + } } extwriter_counter_dec(cur_trans, trans->type); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 527ea94b57d9..2c5a6f6e5bb0 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -94,11 +94,13 @@ struct btrfs_transaction { #define __TRANS_JOIN (1U << 11) #define __TRANS_JOIN_NOLOCK (1U << 12) #define __TRANS_DUMMY (1U << 13) +#define __TRANS_JOIN_NOSTART (1U << 14) #define TRANS_START (__TRANS_START | __TRANS_FREEZABLE) #define TRANS_ATTACH (__TRANS_ATTACH) #define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE) #define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK) +#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART) #define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH) @@ -183,6 +185,7 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv( int min_factor); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root); +struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root); struct btrfs_trans_handle *btrfs_attach_transaction_barrier( struct btrfs_root *root); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6e30949d9f77..a7ec2d3dff92 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -638,9 +638,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ diff --git a/fs/coredump.c b/fs/coredump.c index e42e17e55bfd..b1ea7dfbd149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -7,6 +7,7 @@ #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> +#include <linux/ctype.h> #include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> @@ -187,11 +188,13 @@ put_exe_file: * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, struct coredump_params *cprm) +static int format_corename(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); + bool was_space = false; int pid_in_pattern = 0; int err = 0; @@ -201,12 +204,35 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) + if (ispipe) { + int argvs = sizeof(core_pattern) / 2; + (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); + if (!(*argv)) + return -ENOMEM; + (*argv)[(*argc)++] = 0; ++pat_ptr; + } /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { + /* + * Split on spaces before doing template expansion so that + * %e and %E don't get split if they have spaces in them + */ + if (ispipe) { + if (isspace(*pat_ptr)) { + was_space = true; + pat_ptr++; + continue; + } else if (was_space) { + was_space = false; + err = cn_printf(cn, "%c", '\0'); + if (err) + return err; + (*argv)[(*argc)++] = cn->used; + } + } if (*pat_ptr != '%') { err = cn_printf(cn, "%c", *pat_ptr++); } else { @@ -546,6 +572,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct cred *cred; int retval = 0; int ispipe; + size_t *argv = NULL; + int argc = 0; struct files_struct *displaced; /* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; @@ -592,9 +620,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm); + ispipe = format_corename(&cn, &cprm, &argv, &argc); if (ispipe) { + int argi; int dump_count; char **helper_argv; struct subprocess_info *sub_info; @@ -637,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], @@ -652,7 +685,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); - argv_free(helper_argv); + kfree(helper_argv); if (retval) { printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); @@ -766,6 +799,7 @@ fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(argv); kfree(cn.corename); coredump_finish(mm, core_dumped); revert_creds(old_cred); @@ -266,7 +266,7 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry) static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ - if (entry && dax_is_conflict(entry)) + if (entry && !dax_is_conflict(entry)) dax_wake_entry(xas, entry, false); } diff --git a/fs/exec.c b/fs/exec.c index c71cbfe6826a..f7f6a140856a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1828,7 +1828,7 @@ static int __do_execve_file(int fd, struct filename *filename, membarrier_execve(current); rseq_execve(current); acct_update_integrals(current); - task_numa_free(current); + task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); if (filename) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f8d46df8fa9e..3e58a6f697dd 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1653,19 +1653,12 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) { struct f2fs_inode_info *fi = F2FS_I(inode); - u32 oldflags; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) return -EPERM; - oldflags = fi->i_flags; - - if ((iflags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) - if (!capable(CAP_LINUX_IMMUTABLE)) - return -EPERM; - - fi->i_flags = iflags | (oldflags & ~mask); + fi->i_flags = iflags | (fi->i_flags & ~mask); if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); @@ -1770,7 +1763,8 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - u32 fsflags; + struct f2fs_inode_info *fi = F2FS_I(inode); + u32 fsflags, old_fsflags; u32 iflags; int ret; @@ -1794,8 +1788,14 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) inode_lock(inode); + old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); + if (ret) + goto out; + ret = f2fs_setflags_common(inode, iflags, f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL)); +out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -2855,52 +2855,32 @@ static inline u32 f2fs_xflags_to_iflags(u32 xflags) return iflags; } -static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) +static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa) { - struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - struct fsxattr fa; - memset(&fa, 0, sizeof(struct fsxattr)); - fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags); + simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags)); if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) - fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, - fi->i_projid); - - if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) - return -EFAULT; - return 0; + fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid); } -static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) { - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() == &init_user_ns) - return 0; + struct inode *inode = file_inode(filp); + struct fsxattr fa; - if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid) - return -EINVAL; - - if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) { - if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) - return -EINVAL; - } else { - if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) - return -EINVAL; - } + f2fs_fill_fsxattr(inode, &fa); + if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) + return -EFAULT; return 0; } static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct fsxattr fa; + struct fsxattr fa, old_fa; u32 iflags; int err; @@ -2923,9 +2903,12 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return err; inode_lock(inode); - err = f2fs_ioctl_check_project(inode, &fa); + + f2fs_fill_fsxattr(inode, &old_fa); + err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); if (err) goto out; + err = f2fs_setflags_common(inode, iflags, f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS)); if (err) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 6691f526fa40..8974672db78f 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -796,6 +796,29 @@ static int move_data_block(struct inode *inode, block_t bidx, if (lfs_mode) down_write(&fio.sbi->io_order_lock); + mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), + fio.old_blkaddr, false); + if (!mpage) + goto up_out; + + fio.encrypted_page = mpage; + + /* read source block in mpage */ + if (!PageUptodate(mpage)) { + err = f2fs_submit_page_bio(&fio); + if (err) { + f2fs_put_page(mpage, 1); + goto up_out; + } + lock_page(mpage); + if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) || + !PageUptodate(mpage))) { + err = -EIO; + f2fs_put_page(mpage, 1); + goto up_out; + } + } + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); @@ -803,44 +826,18 @@ static int move_data_block(struct inode *inode, block_t bidx, newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; - goto recover_block; - } - - mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), - fio.old_blkaddr, FGP_LOCK, GFP_NOFS); - if (mpage) { - bool updated = false; - - if (PageUptodate(mpage)) { - memcpy(page_address(fio.encrypted_page), - page_address(mpage), PAGE_SIZE); - updated = true; - } f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); - if (updated) - goto write_page; - } - - err = f2fs_submit_page_bio(&fio); - if (err) - goto put_page_out; - - /* write page */ - lock_page(fio.encrypted_page); - - if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) { - err = -EIO; - goto put_page_out; - } - if (unlikely(!PageUptodate(fio.encrypted_page))) { - err = -EIO; - goto put_page_out; + goto recover_block; } -write_page: + /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); + memcpy(page_address(fio.encrypted_page), + page_address(mpage), PAGE_SIZE); + f2fs_put_page(mpage, 1); + invalidate_mapping_pages(META_MAPPING(fio.sbi), + fio.old_blkaddr, fio.old_blkaddr); + set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); @@ -871,11 +868,12 @@ write_page: put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: - if (lfs_mode) - up_write(&fio.sbi->io_order_lock); if (err) f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); +up_out: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); put_out: f2fs_put_dnode(&dn); out: diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6de6cda44031..78a1b873e48a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2422,6 +2422,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, size_t crc_offset = 0; __u32 crc = 0; + if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { + f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", + F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); + return -EINVAL; + } + /* Check checksum_offset and crc in superblock */ if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { crc_offset = le32_to_cpu(raw_super->checksum_offset); @@ -2429,26 +2435,20 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, offsetof(struct f2fs_super_block, crc)) { f2fs_info(sbi, "Invalid SB checksum offset: %zu", crc_offset); - return 1; + return -EFSCORRUPTED; } crc = le32_to_cpu(raw_super->crc); if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { f2fs_info(sbi, "Invalid SB checksum value: %u", crc); - return 1; + return -EFSCORRUPTED; } } - if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { - f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)", - F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic)); - return 1; - } - /* Currently, support only 4KB page cache size */ if (F2FS_BLKSIZE != PAGE_SIZE) { f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB", PAGE_SIZE); - return 1; + return -EFSCORRUPTED; } /* Currently, support only 4KB block size */ @@ -2456,14 +2456,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (blocksize != F2FS_BLKSIZE) { f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB", blocksize); - return 1; + return -EFSCORRUPTED; } /* check log blocks per segment */ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { f2fs_info(sbi, "Invalid log blocks per segment (%u)", le32_to_cpu(raw_super->log_blocks_per_seg)); - return 1; + return -EFSCORRUPTED; } /* Currently, support 512/1024/2048/4096 bytes sector size */ @@ -2473,7 +2473,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, F2FS_MIN_LOG_SECTOR_SIZE) { f2fs_info(sbi, "Invalid log sectorsize (%u)", le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->log_sectors_per_block) + le32_to_cpu(raw_super->log_sectorsize) != @@ -2481,7 +2481,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)", le32_to_cpu(raw_super->log_sectors_per_block), le32_to_cpu(raw_super->log_sectorsize)); - return 1; + return -EFSCORRUPTED; } segment_count = le32_to_cpu(raw_super->segment_count); @@ -2495,7 +2495,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { f2fs_info(sbi, "Invalid segment count (%u)", segment_count); - return 1; + return -EFSCORRUPTED; } if (total_sections > segment_count || @@ -2503,25 +2503,25 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, segs_per_sec > segment_count || !segs_per_sec) { f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)", segment_count, total_sections, segs_per_sec); - return 1; + return -EFSCORRUPTED; } if ((segment_count / segs_per_sec) < total_sections) { f2fs_info(sbi, "Small segment_count (%u < %u * %u)", segment_count, segs_per_sec, total_sections); - return 1; + return -EFSCORRUPTED; } if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)", segment_count, le64_to_cpu(raw_super->block_count)); - return 1; + return -EFSCORRUPTED; } if (secs_per_zone > total_sections || !secs_per_zone) { f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)", secs_per_zone, total_sections); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || raw_super->hot_ext_count > F2FS_MAX_EXTENSION || @@ -2531,7 +2531,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->extension_count), raw_super->hot_ext_count, F2FS_MAX_EXTENSION); - return 1; + return -EFSCORRUPTED; } if (le32_to_cpu(raw_super->cp_payload) > @@ -2539,7 +2539,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, f2fs_info(sbi, "Insane cp_payload (%u > %u)", le32_to_cpu(raw_super->cp_payload), blocks_per_seg - F2FS_CP_PACKS); - return 1; + return -EFSCORRUPTED; } /* check reserved ino info */ @@ -2550,12 +2550,12 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, le32_to_cpu(raw_super->node_ino), le32_to_cpu(raw_super->meta_ino), le32_to_cpu(raw_super->root_ino)); - return 1; + return -EFSCORRUPTED; } /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, bh)) - return 1; + return -EFSCORRUPTED; return 0; } @@ -2870,10 +2870,10 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, } /* sanity checking of raw super */ - if (sanity_check_raw_super(sbi, bh)) { + err = sanity_check_raw_super(sbi, bh); + if (err) { f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock", block + 1); - err = -EFSCORRUPTED; brelse(bh); continue; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 79581b9bdebb..4df26ef2b2b1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1002,11 +1002,16 @@ static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, unsigned copied, struct page *page, struct iomap *iomap) { + struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); if (page && !gfs2_is_stuffed(ip)) gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied); + + if (tr->tr_num_buf_new) + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + gfs2_trans_end(sdp); } @@ -1099,8 +1104,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, tr = current->journal_info; if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - else - gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]); gfs2_trans_end(sdp); } @@ -1181,10 +1184,16 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); + + if (unlikely(!written)) + goto out_unlock; + if (iomap->flags & IOMAP_F_SIZE_CHANGED) mark_inode_dirty(inode); - gfs2_write_unlock(inode); + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); +out_unlock: + gfs2_write_unlock(inode); out: return 0; } diff --git a/fs/io_uring.c b/fs/io_uring.c index e2a66e12fbc6..d542f1cf4428 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -202,7 +202,7 @@ struct async_list { struct file *file; off_t io_end; - size_t io_pages; + size_t io_len; }; struct io_ring_ctx { @@ -333,7 +333,8 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_FAIL_LINK 128 /* fail rest of links */ +#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_FAIL_LINK 256 /* fail rest of links */ u64 user_data; u32 result; u32 sequence; @@ -429,7 +430,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx, if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; + return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req) nxt->flags |= REQ_F_LINK; } + nxt->flags |= REQ_F_LINK_DONE; INIT_WORK(&nxt->work, io_sq_wq_submit_work); queue_work(req->ctx->sqo_wq, &nxt->work); } @@ -1064,8 +1066,44 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) - iov_iter_advance(iter, offset); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= (seg_skip << PAGE_SHIFT); + iter->iov_offset = offset & ~PAGE_MASK; + if (iter->iov_offset) + iter->count -= iter->iov_offset; + } + } + return 0; } @@ -1120,28 +1158,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) off_t io_end = kiocb->ki_pos + len; if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) { - unsigned long max_pages; + unsigned long max_bytes; /* Use 8x RA size as a decent limiter for both reads/writes */ - max_pages = filp->f_ra.ra_pages; - if (!max_pages) - max_pages = VM_READAHEAD_PAGES; - max_pages *= 8; - - /* If max pages are exceeded, reset the state */ - len >>= PAGE_SHIFT; - if (async_list->io_pages + len <= max_pages) { + max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); + if (!max_bytes) + max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); + + /* If max len are exceeded, reset the state */ + if (async_list->io_len + len <= max_bytes) { req->flags |= REQ_F_SEQ_PREV; - async_list->io_pages += len; + async_list->io_len += len; } else { io_end = 0; - async_list->io_pages = 0; + async_list->io_len = 0; } } /* New file? Reset state. */ if (async_list->file != filp) { - async_list->io_pages = 0; + async_list->io_len = 0; async_list->file = filp; } async_list->io_end = io_end; @@ -1630,6 +1666,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); + INIT_LIST_HEAD(&req->list); + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; spin_lock_irq(&ctx->completion_lock); @@ -1800,6 +1838,7 @@ restart: do { struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; + unsigned int flags = req->flags; /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; @@ -1844,6 +1883,10 @@ restart: /* async context always use a copy of the sqe */ kfree(sqe); + /* req from defer and link list needn't decrease async cnt */ + if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + goto out; + if (!async_list) break; if (!list_empty(&req_list)) { @@ -1891,6 +1934,7 @@ restart: } } +out: if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); @@ -1917,6 +1961,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) ret = true; spin_lock(&list->lock); list_add_tail(&req->list, &list->list); + /* + * Ensure we see a simultaneous modification from io_sq_wq_submit_work() + */ + smp_mb(); if (!atomic_read(&list->cnt)) { list_del_init(&req->list); ret = false; diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile index 2d165388d952..93cd11938bf5 100644 --- a/fs/iomap/Makefile +++ b/fs/iomap/Makefile @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0-or-newer +# SPDX-License-Identifier: GPL-2.0-or-later # # Copyright (c) 2019 Oracle. # All Rights Reserved. diff --git a/fs/namespace.c b/fs/namespace.c index 6464ea4acba9..d28d30b13043 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1463,7 +1463,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); - if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { @@ -1471,10 +1470,11 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); - hlist_add_head(&p->mnt_umount, &unmounted); } } change_mnt_propagation(p, MS_PRIVATE); + if (disconnect) + hlist_add_head(&p->mnt_umount, &unmounted); } } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 385f3aaa2448..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3825,7 +3825,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb); int low_bucket = 0, bucket, high_bucket; struct ocfs2_xattr_bucket *search; - u32 last_hash; u64 blkno, lower_blkno = 0; search = ocfs2_xattr_bucket_new(inode); @@ -3869,8 +3868,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, if (xh->xh_count) xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1]; - last_hash = le32_to_cpu(xe->xe_name_hash); - /* record lower_blkno which may be the insert place. */ lower_blkno = blkno; diff --git a/fs/open.c b/fs/open.c index b5b80469b93d..a59abe3c669a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -374,6 +374,25 @@ long do_faccessat(int dfd, const char __user *filename, int mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); diff --git a/fs/super.c b/fs/super.c index 113c58f19425..5960578a4076 100644 --- a/fs/super.c +++ b/fs/super.c @@ -478,13 +478,10 @@ EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { - struct user_namespace *user_ns = fc->global ? &init_user_ns - : fc->user_ns; - if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else - return ns_capable(user_ns, CAP_SYS_ADMIN); + return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 94c4f1de1922..77ff9f97bcda 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -278,7 +278,11 @@ xchk_da_btree_block_check_sibling( /* Compare upper level pointer to sibling pointer. */ if (ds->state->altpath.blk[level].blkno != sibling) xchk_da_set_corrupt(ds, level); - xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp); + if (ds->state->altpath.blk[level].bp) { + xfs_trans_brelse(ds->dargs.trans, + ds->state->altpath.blk[level].bp); + ds->state->altpath.blk[level].bp = NULL; + } out: return error; } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index a8a06bb78ea8..f5c955d35be4 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -272,6 +272,7 @@ xfs_bulkstat_to_bstat( struct xfs_bstat *bs1, const struct xfs_bulkstat *bstat) { + /* memset is needed here because of padding holes in the structure. */ memset(bs1, 0, sizeof(struct xfs_bstat)); bs1->bs_ino = bstat->bs_ino; bs1->bs_mode = bstat->bs_mode; @@ -388,6 +389,8 @@ xfs_inumbers_to_inogrp( struct xfs_inogrp *ig1, const struct xfs_inumbers *ig) { + /* memset is needed here because of padding holes in the structure. */ + memset(ig1, 0, sizeof(struct xfs_inogrp)); ig1->xi_startino = ig->xi_startino; ig1->xi_alloccount = ig->xi_alloccount; ig1->xi_allocmask = ig->xi_allocmask; diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index 8666fe7f35d7..02970b11f71f 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -118,26 +118,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) { - int oldval = 0, ret; - - pagefault_disable(); - - switch (op) { - case FUTEX_OP_SET: - case FUTEX_OP_ADD: - case FUTEX_OP_OR: - case FUTEX_OP_ANDN: - case FUTEX_OP_XOR: - default: - ret = -ENOSYS; - } - - pagefault_enable(); - - if (!ret) - *oval = oldval; - - return ret; + return -ENOSYS; } static inline int diff --git a/include/asm-generic/getorder.h b/include/asm-generic/getorder.h index c64bea7a52be..e9f20b813a69 100644 --- a/include/asm-generic/getorder.h +++ b/include/asm-generic/getorder.h @@ -7,24 +7,6 @@ #include <linux/compiler.h> #include <linux/log2.h> -/* - * Runtime evaluation of get_order() - */ -static inline __attribute_const__ -int __get_order(unsigned long size) -{ - int order; - - size--; - size >>= PAGE_SHIFT; -#if BITS_PER_LONG == 32 - order = fls(size); -#else - order = fls64(size); -#endif - return order; -} - /** * get_order - Determine the allocation order of a memory size * @size: The size for which to get the order @@ -43,19 +25,27 @@ int __get_order(unsigned long size) * to hold an object of the specified size. * * The result is undefined if the size is 0. - * - * This function may be used to initialise variables with compile time - * evaluations of constants. */ -#define get_order(n) \ -( \ - __builtin_constant_p(n) ? ( \ - ((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT : \ - (((n) < (1UL << PAGE_SHIFT)) ? 0 : \ - ilog2((n) - 1) - PAGE_SHIFT + 1) \ - ) : \ - __get_order(n) \ -) +static inline __attribute_const__ int get_order(unsigned long size) +{ + if (__builtin_constant_p(size)) { + if (!size) + return BITS_PER_LONG - PAGE_SHIFT; + + if (size < (1UL << PAGE_SHIFT)) + return 0; + + return ilog2((size) - 1) - PAGE_SHIFT + 1; + } + + size--; + size >>= PAGE_SHIFT; +#if BITS_PER_LONG == 32 + return fls(size); +#else + return fls64(size); +#endif +} #endif /* __ASSEMBLY__ */ diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index 72d51d1e9dd9..5cf2c5dd8b1e 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -149,6 +149,8 @@ struct drm_client_buffer { struct drm_client_buffer * drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); +void *drm_client_buffer_vmap(struct drm_client_buffer *buffer); +void drm_client_buffer_vunmap(struct drm_client_buffer *buffer); int drm_client_modeset_create(struct drm_client_dev *client); void drm_client_modeset_free(struct drm_client_dev *client); diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 759d462d028b..f57eea0481e0 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -853,6 +853,13 @@ struct drm_mode_config { uint32_t preferred_depth, prefer_shadow; /** + * @prefer_shadow_fbdev: + * + * Hint to framebuffer emulation to prefer shadow-fb rendering. + */ + bool prefer_shadow_fbdev; + + /** * @quirk_addfb_prefer_xbgr_30bpp: * * Special hack for legacy ADDFB to keep nouveau userspace happy. Should diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 689a58231288..12811091fd50 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -181,6 +181,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; +extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index feff3fe4467e..1b1fa1557e68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,6 +311,7 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ + __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -345,6 +346,7 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) +#define REQ_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) @@ -418,12 +420,13 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U +#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE; + return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 18f4cc2c6acd..f9a506147c8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -713,7 +713,7 @@ struct xdp_buff; struct sk_buff; struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_flush(struct bpf_map *map); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -721,7 +721,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); -void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); void __cpu_map_flush(struct bpf_map *map); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx); @@ -801,8 +800,10 @@ static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, return NULL; } -static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map, + u32 key) { + return NULL; } static inline void __dev_map_flush(struct bpf_map *map) @@ -834,10 +835,6 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) return NULL; } -static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) -{ -} - static inline void __cpu_map_flush(struct bpf_map *map) { } diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index eec5aeeeaf92..36a9c2325176 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -62,6 +62,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops) #if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) diff --git a/include/linux/clk.h b/include/linux/clk.h index 3c096c7a51dc..853a8f181394 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -359,6 +359,7 @@ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, /** * devm_clk_bulk_get_optional - managed get multiple optional consumer clocks * @dev: device for clock "consumer" + * @num_clks: the number of clk_bulk_data * @clks: pointer to the clk_bulk_data table of consumer * * Behaves the same as devm_clk_bulk_get() except where there is no clock diff --git a/include/linux/cred.h b/include/linux/cred.h index 7eb43a038330..f7a30e0099be 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -145,7 +145,11 @@ struct cred { struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ - struct rcu_head rcu; /* RCU deletion hook */ + /* RCU deletion */ + union { + int non_rcu; /* Can we skip RCU deletion? */ + struct rcu_head rcu; /* RCU deletion hook */ + }; } __randomize_layout; extern void __put_cred(struct cred *); @@ -246,6 +250,7 @@ static inline const struct cred *get_cred(const struct cred *cred) if (!cred) return cred; validate_creds(cred); + nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } @@ -257,6 +262,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) if (!atomic_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); + nonconst_cred->non_rcu = 0; return cred; } diff --git a/include/linux/device.h b/include/linux/device.h index c330b75c6c57..6717adee33f0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -915,6 +915,8 @@ struct dev_links_info { * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. + * @lockdep_mutex: An optional debug lock that a subsystem can use as a + * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. @@ -998,6 +1000,9 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ +#ifdef CONFIG_PROVE_LOCKING + struct mutex lockdep_mutex; +#endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ @@ -1383,6 +1388,7 @@ extern int (*platform_notify_remove)(struct device *dev); */ extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); +extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); diff --git a/include/linux/dim.h b/include/linux/dim.h index d3a0fbfff2bb..9fa4b3f88c39 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -272,62 +272,6 @@ dim_update_sample_with_comps(u16 event_ctr, u64 packets, u64 bytes, u64 comps, /* Net DIM */ -/* - * Net DIM profiles: - * There are different set of profiles for each CQ period mode. - * There are different set of profiles for RX/TX CQs. - * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES - */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - -#define NET_DIM_RX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ -} - -#define NET_DIM_RX_CQE_PROFILES { \ - {2, 256}, \ - {8, 128}, \ - {16, 64}, \ - {32, 64}, \ - {64, 64} \ -} - -#define NET_DIM_TX_EQE_PROFILES { \ - {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ - {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ -} - -#define NET_DIM_TX_CQE_PROFILES { \ - {5, 128}, \ - {8, 64}, \ - {16, 32}, \ - {32, 32}, \ - {64, 32} \ -} - -static const struct dim_cq_moder -rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_RX_EQE_PROFILES, - NET_DIM_RX_CQE_PROFILES, -}; - -static const struct dim_cq_moder -tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_TX_EQE_PROFILES, - NET_DIM_TX_CQE_PROFILES, -}; - /** * net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile * @cq_period_mode: CQ period mode diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index e11b115dd0e4..f7d1eea32c78 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -689,8 +689,8 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) */ static inline bool dma_addressing_limited(struct device *dev) { - return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) < - dma_get_required_mask(dev); + return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) < + dma_get_required_mask(dev); } #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 17cd0078377c..1dd014c9c87b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -45,7 +45,6 @@ struct elevator_mq_ops { struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); bool (*has_work)(struct blk_mq_hw_ctx *); void (*completed_request)(struct request *, u64); - void (*started_request)(struct request *); void (*requeue_request)(struct request *); struct request *(*former_request)(struct request_queue *, struct request *); struct request *(*next_request)(struct request_queue *, struct request *); diff --git a/include/linux/filter.h b/include/linux/filter.h index ff65d22cf336..92c6e31fb008 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -24,6 +24,7 @@ #include <net/sch_generic.h> +#include <asm/byteorder.h> #include <uapi/linux/filter.h> #include <uapi/linux/bpf.h> @@ -747,6 +748,18 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } +static inline u8 +bpf_ctx_narrow_load_shift(u32 off, u32 size, u32 size_default) +{ + u8 load_off = off & (size_default - 1); + +#ifdef __LITTLE_ENDIAN + return load_off * 8; +#else + return (size_default - (load_off + size)) * 8; +#endif +} + #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 56b8e358af5c..997a530ff4e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2598,6 +2598,12 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); +extern struct block_device *bd_start_claiming(struct block_device *bdev, + void *holder); +extern void bd_finish_claiming(struct block_device *bdev, + struct block_device *whole, void *holder); +extern void bd_abort_claiming(struct block_device *bdev, + struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); extern int __blkdev_reread_part(struct block_device *bdev); extern int blkdev_reread_part(struct block_device *bdev); diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 9ddcf50a3c59..a7f08fb0f865 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -247,7 +247,7 @@ static inline void gpiod_put(struct gpio_desc *desc) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void devm_gpiod_unhinge(struct device *dev, @@ -256,7 +256,7 @@ static inline void devm_gpiod_unhinge(struct device *dev, might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void gpiod_put_array(struct gpio_descs *descs) @@ -264,7 +264,7 @@ static inline void gpiod_put_array(struct gpio_descs *descs) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(descs); } static inline struct gpio_desc *__must_check @@ -317,7 +317,7 @@ static inline void devm_gpiod_put(struct device *dev, struct gpio_desc *desc) might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline void devm_gpiod_put_array(struct device *dev, @@ -326,32 +326,32 @@ static inline void devm_gpiod_put_array(struct device *dev, might_sleep(); /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(descs); } static inline int gpiod_get_direction(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_input(struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_output(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } @@ -359,7 +359,7 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_array_value(unsigned int array_size, @@ -368,13 +368,13 @@ static inline int gpiod_get_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -382,13 +382,13 @@ static inline int gpiod_set_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_raw_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_raw_array_value(unsigned int array_size, @@ -397,13 +397,13 @@ static inline int gpiod_get_raw_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, @@ -411,14 +411,14 @@ static inline int gpiod_set_raw_array_value(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_array_value_cansleep(unsigned int array_size, @@ -427,13 +427,13 @@ static inline int gpiod_get_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -441,13 +441,13 @@ static inline int gpiod_set_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, @@ -456,14 +456,14 @@ static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); } static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, @@ -471,41 +471,41 @@ static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size, unsigned long *value_bitmap) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc_array); return 0; } static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -ENOSYS; } static inline int gpiod_is_active_low(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_cansleep(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return 0; } static inline int gpiod_to_irq(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } @@ -513,7 +513,7 @@ static inline int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } @@ -525,7 +525,7 @@ static inline struct gpio_desc *gpio_to_desc(unsigned gpio) static inline int desc_to_gpio(const struct gpio_desc *desc) { /* GPIO can never have been requested */ - WARN_ON(1); + WARN_ON(desc); return -EINVAL; } diff --git a/include/linux/hmm.h b/include/linux/hmm.h index b8a08b2a10ca..7ef56dc18050 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -484,60 +484,6 @@ long hmm_range_dma_unmap(struct hmm_range *range, */ #define HMM_RANGE_DEFAULT_TIMEOUT 1000 -/* This is a temporary helper to avoid merge conflict between trees. */ -static inline bool hmm_vma_range_done(struct hmm_range *range) -{ - bool ret = hmm_range_valid(range); - - hmm_range_unregister(range); - return ret; -} - -/* This is a temporary helper to avoid merge conflict between trees. */ -static inline int hmm_vma_fault(struct hmm_mirror *mirror, - struct hmm_range *range, bool block) -{ - long ret; - - /* - * With the old API the driver must set each individual entries with - * the requested flags (valid, write, ...). So here we set the mask to - * keep intact the entries provided by the driver and zero out the - * default_flags. - */ - range->default_flags = 0; - range->pfn_flags_mask = -1UL; - - ret = hmm_range_register(range, mirror, - range->start, range->end, - PAGE_SHIFT); - if (ret) - return (int)ret; - - if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) { - /* - * The mmap_sem was taken by driver we release it here and - * returns -EAGAIN which correspond to mmap_sem have been - * drop in the old API. - */ - up_read(&range->vma->vm_mm->mmap_sem); - return -EAGAIN; - } - - ret = hmm_range_fault(range, block); - if (ret <= 0) { - if (ret == -EBUSY || !ret) { - /* Same as above, drop mmap_sem to match old API. */ - up_read(&range->vma->vm_mm->mmap_sem); - ret = -EBUSY; - } else if (ret == -EAGAIN) - ret = -EBUSY; - hmm_range_unregister(range); - return ret; - } - return 0; -} - /* Below are for HMM internal use only! Not to be used by device driver! */ static inline void hmm_mm_init(struct mm_struct *mm) { diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index 8b728750a625..69e813bcb947 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -80,6 +80,9 @@ extern int register_pppox_proto(int proto_num, const struct pppox_proto *pp); extern void unregister_pppox_proto(int proto_num); extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */ extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); + +#define PPPOEIOCSFWD32 _IOW(0xB1 ,0, compat_size_t) /* PPPoX socket states */ enum { diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index b4f5403383fc..9661416a9bb4 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -41,11 +41,11 @@ struct rmnet_map_ul_csum_header { __be16 csum_start_offset; #if defined(__LITTLE_ENDIAN_BITFIELD) u16 csum_insert_offset:14; - u16 udp_ip4_ind:1; + u16 udp_ind:1; u16 csum_enabled:1; #elif defined (__BIG_ENDIAN_BITFIELD) u16 csum_enabled:1; - u16 udp_ip4_ind:1; + u16 udp_ind:1; u16 csum_insert_offset:14; #else #error "Please fix <asm/byteorder.h>" diff --git a/include/linux/iova.h b/include/linux/iova.h index 781b96ac706f..a0637abffee8 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -155,6 +155,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); +bool has_iova_flush_queue(struct iova_domain *iovad); int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); @@ -235,6 +236,11 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } +static inline bool has_iova_flush_queue(struct iova_domain *iovad) +{ + return false; +} + static inline int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0e6da1840c7d..df23f17eed64 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -189,7 +189,6 @@ enum mlx5_coredev_type { }; struct mlx5_field_desc { - struct dentry *dent; int i; }; @@ -242,11 +241,6 @@ struct mlx5_cmd_msg { struct mlx5_cmd_debug { struct dentry *dbg_root; - struct dentry *dbg_in; - struct dentry *dbg_out; - struct dentry *dbg_outlen; - struct dentry *dbg_status; - struct dentry *dbg_run; void *in_msg; void *out_msg; u8 status; @@ -271,8 +265,6 @@ struct mlx5_cmd_stats { u64 sum; u64 n; struct dentry *root; - struct dentry *avg; - struct dentry *count; /* protect command average calculations */ spinlock_t lock; }; @@ -477,6 +469,17 @@ struct mlx5_core_sriov { u16 max_vfs; }; +struct mlx5_fc_pool { + struct mlx5_core_dev *dev; + struct mutex pool_lock; /* protects pool lists */ + struct list_head fully_used; + struct list_head partially_used; + struct list_head unused; + int available_fcs; + int used_fcs; + int threshold; +}; + struct mlx5_fc_stats { spinlock_t counters_idr_lock; /* protects counters_idr */ struct idr counters_idr; @@ -488,6 +491,8 @@ struct mlx5_fc_stats { struct delayed_work work; unsigned long next_query; unsigned long sampling_interval; /* jiffies */ + u32 *bulk_query_out; + struct mlx5_fc_pool fc_pool; }; struct mlx5_events; @@ -959,7 +964,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, @@ -971,7 +976,7 @@ int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 46b5ba029802..38a70d16d8d5 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -44,7 +44,6 @@ struct mlx5_eswitch_rep_data { struct mlx5_eswitch_rep { struct mlx5_eswitch_rep_data rep_data[NUM_REP_TYPES]; u16 vport; - u8 hw_id[ETH_ALEN]; u16 vlan; /* Only IB rep is using vport_index */ u16 vport_index; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 04a569568eac..1cb1045ce313 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -126,6 +126,11 @@ struct mlx5_flow_destination { }; }; +struct mod_hdr_tbl { + struct mutex lock; /* protects hlist */ + DECLARE_HASHTABLE(hlist, 8); +}; + struct mlx5_flow_namespace * mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * @@ -220,6 +225,7 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); +u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b3d5752657d9..da5e7eaed438 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1040,6 +1040,21 @@ enum { MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; +#define MLX5_FC_BULK_SIZE_FACTOR 128 + +enum mlx5_fc_bulk_alloc_bitmask { + MLX5_FC_BULK_128 = (1 << 0), + MLX5_FC_BULK_256 = (1 << 1), + MLX5_FC_BULK_512 = (1 << 2), + MLX5_FC_BULK_1024 = (1 << 3), + MLX5_FC_BULK_2048 = (1 << 4), + MLX5_FC_BULK_4096 = (1 << 5), + MLX5_FC_BULK_8192 = (1 << 6), + MLX5_FC_BULK_16384 = (1 << 7), +}; + +#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1244,7 +1259,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2e0[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_at_300[0x18]; + u8 reserved_at_300[0x10]; + u8 flow_counter_bulk_alloc[0x8]; u8 log_max_mcg[0x8]; u8 reserved_at_320[0x3]; @@ -2766,7 +2782,7 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; u8 tls_en[0x1]; - u8 reserved_at_1[0x2]; + u8 reserved_at_2[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; @@ -2941,6 +2957,13 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, }; +enum { + ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, + ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, +}; + struct mlx5_ifc_scheduling_context_bits { u8 element_type[0x8]; u8 reserved_at_8[0x18]; @@ -5975,10 +5998,12 @@ struct mlx5_ifc_modify_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; u8 cq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; @@ -7815,7 +7840,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x38]; + u8 flow_counter_bulk[0x8]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index b2c1648f7e5d..5714fd35a83c 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -814,6 +814,7 @@ struct tee_client_device_id { /** * struct wmi_device_id - WMI device identifier * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba + * @context: pointer to driver specific data */ struct wmi_device_id { const char guid_string[UUID_STRING_LEN+1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88292953aa6f..55ac223553f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -332,6 +332,8 @@ struct napi_struct { struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; + struct list_head rx_list; /* Pending GRO_NORMAL skbs */ + int rx_count; /* length of rx_list */ struct hrtimer timer; struct list_head dev_list; struct hlist_node napi_hash_node; @@ -4239,6 +4241,7 @@ extern int dev_weight_rx_bias; extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; +extern int gro_normal_batch; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, diff --git a/include/linux/of.h b/include/linux/of.h index 0cf857012f11..844f89e1b039 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1164,7 +1164,7 @@ static inline int of_property_read_string_index(const struct device_node *np, } /** - * of_property_read_bool - Findfrom a property + * of_property_read_bool - Find a property * @np: device node from which the property value is to be read. * @propname: name of the property to be searched. * diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 1dda31825ec4..71283739ffd2 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -32,6 +32,7 @@ #endif /* CONFIG_SPARSEMEM */ +#ifndef BUILD_VDSO32_64 /* * page->flags layout: * @@ -76,20 +77,22 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#ifdef CONFIG_KASAN_SW_TAGS +#define KASAN_TAG_WIDTH 8 +#else +#define KASAN_TAG_WIDTH 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 #endif -#ifdef CONFIG_KASAN_SW_TAGS -#define KASAN_TAG_WIDTH 8 #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \ > BITS_PER_LONG - NR_PAGEFLAGS -#error "KASAN: not enough bits in page flags for tag" -#endif -#else -#define KASAN_TAG_WIDTH 0 +#error "Not enough bits in page flags" #endif /* @@ -104,4 +107,5 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif +#endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b848517da64c..f91cb8898ff0 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -152,6 +152,8 @@ enum pageflags { PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, + /* Remapped by swiotlb-xen. */ + PG_xen_remapped = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, @@ -329,6 +331,8 @@ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); +PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) + TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) diff --git a/include/linux/phy.h b/include/linux/phy.h index 462b90b73f93..5ac7d21375ac 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -403,6 +403,8 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + /* used with phy_speed_down */ + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; @@ -665,6 +667,7 @@ size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); +int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started @@ -984,6 +987,8 @@ int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); +int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, + u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); @@ -1069,7 +1074,7 @@ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); -int genphy_config_aneg(struct phy_device *phydev); +int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); @@ -1077,6 +1082,12 @@ int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); + +static inline int genphy_config_aneg(struct phy_device *phydev) +{ + return __genphy_config_aneg(phydev, false); +} + static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index eef02e64b422..23021366a4e5 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -689,7 +689,7 @@ enum qed_link_mode_bits { QED_LM_40000baseLR4_Full_BIT = BIT(9), QED_LM_50000baseKR2_Full_BIT = BIT(10), QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_2500baseX_Full_BIT = BIT(12), + QED_LM_TP_BIT = BIT(12), QED_LM_Backplane_BIT = BIT(13), QED_LM_1000baseKX_Full_BIT = BIT(14), QED_LM_10000baseKX4_Full_BIT = BIT(15), diff --git a/include/linux/sched.h b/include/linux/sched.h index 8dc1811487f5..9f51932bd543 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1092,7 +1092,15 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct numa_group *numa_group; + /* + * This pointer is only modified for current in syscall and + * pagefault context (and for tasks being destroyed), so it can be read + * from any of the following contexts: + * - RCU read-side critical section + * - current->numa_group from everywhere + * - task's runqueue locked, task not running + */ + struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h index e7dd04a84ba8..3988762efe15 100644 --- a/include/linux/sched/numa_balancing.h +++ b/include/linux/sched/numa_balancing.h @@ -19,7 +19,7 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); -extern void task_numa_free(struct task_struct *p); +extern void task_numa_free(struct task_struct *p, bool final); extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, int src_nid, int dst_cpu); #else @@ -34,7 +34,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p) static inline void set_numabalancing_state(bool enabled) { } -static inline void task_numa_free(struct task_struct *p) +static inline void task_numa_free(struct task_struct *p, bool final) { } static inline bool should_numa_migrate_memory(struct task_struct *p, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3aef8d82ea59..7eb28b72d9ba 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1271,7 +1271,7 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) struct bpf_flow_dissector; bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen); + __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 50ced8aba9db..e4b3fb4bb77c 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -354,7 +354,13 @@ static inline void sk_psock_restore_proto(struct sock *sk, sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { - sk->sk_prot = psock->sk_proto; + struct inet_connection_sock *icsk = inet_csk(sk); + bool has_ulp = !!icsk->icsk_ulp_data; + + if (has_ulp) + tcp_update_ulp(sk, psock->sk_proto); + else + sk->sk_prot = psock->sk_proto; psock->sk_proto = NULL; } } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7b3e354bcd3c..5cc6b6faf359 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -173,6 +173,7 @@ struct plat_stmmacenet_data { int has_gmac4; bool has_sun8i; bool tso_en; + int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; int has_xgmac; diff --git a/include/linux/wait.h b/include/linux/wait.h index b6f77cf60dd7..30c515520fb2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -127,6 +127,19 @@ static inline int waitqueue_active(struct wait_queue_head *wq_head) } /** + * wq_has_single_sleeper - check if there is only one sleeper + * @wq_head: wait queue head + * + * Returns true of wq_head has only one sleeper on the list. + * + * Please refer to the comment for waitqueue_active. + */ +static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) +{ + return list_is_singular(&wq_head->head); +} + +/** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index 7cb63e4ec0ae..4dd2c1cea6a9 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -98,9 +98,7 @@ * To manipulate from user space the levels, create a debugfs dentry * and then register each submodule with: * - * result = d_level_register_debugfs("PREFIX_", submodule_X, parent); - * if (result < 0) - * goto error; + * d_level_register_debugfs("PREFIX_", submodule_X, parent); * * Where PREFIX_ is a name of your chosing. This will create debugfs * file with a single numeric value that can be use to tweak it. To @@ -408,25 +406,13 @@ do { \ * @submodule: name of submodule (not a string, just the name) * @dentry: debugfs parent dentry * - * Returns: 0 if ok, < 0 errno on error. - * * For removing, just use debugfs_remove_recursive() on the parent. */ #define d_level_register_debugfs(prefix, name, parent) \ ({ \ - int rc; \ - struct dentry *fd; \ - struct dentry *verify_parent_type = parent; \ - fd = debugfs_create_u8( \ - prefix #name, 0600, verify_parent_type, \ + debugfs_create_u8( \ + prefix #name, 0600, parent, \ &(D_LEVEL[__D_SUBMODULE_ ## name].level)); \ - rc = PTR_ERR(fd); \ - if (IS_ERR(fd) && rc != -ENODEV) \ - printk(KERN_ERR "%s: Can't create debugfs entry %s: " \ - "%d\n", __func__, prefix #name, rc); \ - else \ - rc = 0; \ - rc; \ }) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 35ec1f0a2bf9..8140c4837122 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7335,6 +7335,21 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, gfp_t gfp); +/** + * cfg80211_iftype_allowed - check whether the interface can be allowed + * @wiphy: the wiphy + * @iftype: interface type + * @is_4addr: use_4addr flag, must be '0' when check_swif is '1' + * @check_swif: check iftype against software interfaces + * + * Check whether the interface is allowed to operate; additionally, this API + * can be used to check iftype against the software interfaces when + * check_swif is '1'. + */ +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif); + + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/net/devlink.h b/include/net/devlink.h index bc36f942a7d5..451268f64880 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -702,7 +702,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u64 region_size); void devlink_region_destroy(struct devlink_region *region); u32 devlink_region_shapshot_id_get(struct devlink *devlink); -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); int devlink_info_serial_number_put(struct devlink_info_req *req, diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 00b9aab5fdc1..e8069b6c474c 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -4,6 +4,7 @@ #include <linux/kernel.h> #include <linux/list.h> #include <net/flow_dissector.h> +#include <linux/rhashtable.h> struct flow_match { struct flow_dissector *dissector; @@ -117,6 +118,8 @@ enum flow_action_id { FLOW_ACTION_GOTO, FLOW_ACTION_REDIRECT, FLOW_ACTION_MIRRED, + FLOW_ACTION_REDIRECT_INGRESS, + FLOW_ACTION_MIRRED_INGRESS, FLOW_ACTION_VLAN_PUSH, FLOW_ACTION_VLAN_POP, FLOW_ACTION_VLAN_MANGLE, @@ -126,6 +129,7 @@ enum flow_action_id { FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, + FLOW_ACTION_PTYPE, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, @@ -168,6 +172,7 @@ struct flow_action_entry { const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ + u16 ptype; /* FLOW_ACTION_PTYPE */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; u32 index; @@ -366,4 +371,40 @@ static inline void flow_block_init(struct flow_block *flow_block) INIT_LIST_HEAD(&flow_block->cb_list); } +typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, + enum tc_setup_type type, void *type_data); + +typedef void flow_indr_block_ing_cmd_t(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command); + +struct flow_indr_block_ing_entry { + flow_indr_block_ing_cmd_t *cb; + struct list_head list; +}; + +void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry); + +void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry); + +int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +void __flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, void *cb_ident); + +void flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident); + +void flow_indr_block_call(struct net_device *dev, + struct flow_block_offload *bo, + enum flow_block_command command); + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index 4977fbe7ed08..8a5969d9b80b 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -64,6 +64,10 @@ struct nft_rule; struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule); void nft_flow_rule_destroy(struct nft_flow_rule *flow); int nft_flow_rule_offload_commit(struct net *net); +void nft_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command); #define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ (__reg)->base_offset = \ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index bc24a8ec1ce5..c0c0791b1912 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -116,6 +116,7 @@ struct netns_ipv4 { int sysctl_tcp_l3mdev_accept; #endif int sysctl_tcp_mtu_probing; + int sysctl_tcp_mtu_probe_floor; int sysctl_tcp_base_mss; int sysctl_tcp_min_snd_mss; int sysctl_tcp_probe_threshold; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e429809ca90d..0790a4ed909c 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -70,15 +70,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) return block->q; } -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident); - int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -137,32 +128,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, { } -static inline -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - return 0; -} - -static inline -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - return 0; -} - -static inline -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ -} - -static inline -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ -} - static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6b6b01234dd9..d9f359af0b93 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -23,9 +23,6 @@ struct tcf_walker; struct module; struct bpf_flow_keys; -typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, - enum tc_setup_type type, void *type_data); - struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index c757585a05b0..1cace4c69e44 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -32,6 +32,24 @@ static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) return false; } +static inline bool is_tcf_mirred_ingress_redirect(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_REDIR; +#endif + return false; +} + +static inline bool is_tcf_mirred_ingress_mirror(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_MIRROR; +#endif + return false; +} + static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { return rtnl_dereference(to_mirred(a)->tcfm_dev); diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h index 8b9ef3664262..cfdc7cb82cad 100644 --- a/include/net/tc_act/tc_police.h +++ b/include/net/tc_act/tc_police.h @@ -54,7 +54,7 @@ static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh(police->params); + params = rcu_dereference_bh_rtnl(police->params); return params->rate.rate_bytes_ps; } @@ -63,7 +63,7 @@ static inline s64 tcf_police_tcfp_burst(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh(police->params); + params = rcu_dereference_bh_rtnl(police->params); return params->tcfp_burst; } diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h index 0a559d4b6f0f..b4fce0fae645 100644 --- a/include/net/tc_act/tc_sample.h +++ b/include/net/tc_act/tc_sample.h @@ -44,7 +44,7 @@ static inline int tcf_sample_trunc_size(const struct tc_action *a) static inline struct psample_group * tcf_sample_psample_group(const struct tc_action *a) { - return rcu_dereference(to_sample(a)->psample_group); + return rcu_dereference_rtnl(to_sample(a)->psample_group); } #endif /* __NET_TC_SAMPLE_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 4c04e2985508..b22a1f641f02 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -54,4 +54,31 @@ static inline u32 tcf_skbedit_mark(const struct tc_action *a) return mark; } +/* Return true iff action is ptype */ +static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + u32 flags; + + if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { + rcu_read_lock(); + flags = rcu_dereference(to_skbedit(a)->params)->flags; + rcu_read_unlock(); + return flags == SKBEDIT_F_PTYPE; + } +#endif + return false; +} + +static inline u32 tcf_skbedit_ptype(const struct tc_action *a) +{ + u16 ptype; + + rcu_read_lock(); + ptype = rcu_dereference(to_skbedit(a)->params)->ptype; + rcu_read_unlock(); + + return ptype; +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index e5cf514ba118..77fe87f7a992 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -64,7 +64,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U -/* The least MTU to use for probing */ +/* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ @@ -415,6 +415,16 @@ void tcp_parse_options(const struct net *net, const struct sk_buff *skb, const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* + * BPF SKB-less helpers + */ +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie); +u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, + struct tcphdr *th, u32 *cookie); +u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct tcphdr *th); +/* * TCP v4 functions exported for the inet6 API */ @@ -2108,6 +2118,8 @@ struct tcp_ulp_ops { /* initialize ulp */ int (*init)(struct sock *sk); + /* update ulp */ + void (*update)(struct sock *sk, struct proto *p); /* cleanup ulp */ void (*release)(struct sock *sk); @@ -2119,6 +2131,7 @@ void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); +void tcp_update_ulp(struct sock *sk, struct proto *p); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ diff --git a/include/net/tls.h b/include/net/tls.h index 584609174fe0..41b2d41bb1b8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -107,9 +107,7 @@ struct tls_device { enum { TLS_BASE, TLS_SW, -#ifdef CONFIG_TLS_DEVICE TLS_HW, -#endif TLS_HW_RECORD, TLS_NUM_CONFIG, }; @@ -162,6 +160,7 @@ struct tls_sw_context_tx { int async_capable; #define BIT_TX_SCHEDULED 0 +#define BIT_TX_CLOSING 1 unsigned long tx_bitmask; }; @@ -272,6 +271,8 @@ struct tls_context { unsigned long flags; /* cache cold stuff */ + struct proto *sk_proto; + void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout); @@ -355,13 +356,17 @@ int tls_sk_attach(struct sock *sk, int optname, char __user *optval, unsigned int optlen); int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); +void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -void tls_sw_close(struct sock *sk, long timeout); -void tls_sw_free_resources_tx(struct sock *sk); +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); +void tls_sw_release_resources_tx(struct sock *sk); +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); bool tls_sw_stream_read(const struct sock *sk); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c5f8a9f17063..4f225175cb91 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2647,7 +2647,9 @@ struct ib_client { const union ib_gid *gid, const struct sockaddr *addr, void *client_data); - struct list_head list; + + refcount_t uses; + struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 0eeea520a853..e06c77d76463 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -608,7 +608,7 @@ static inline void rvt_qp_wqe_reserve( /** * rvt_qp_wqe_unreserve - clean reserved operation * @qp - the rvt qp - * @wqe - the send wqe + * @flags - send wqe flags * * This decrements the reserve use count. * @@ -620,11 +620,9 @@ static inline void rvt_qp_wqe_reserve( * the compiler does not juggle the order of the s_last * ring index and the decrementing of s_reserved_used. */ -static inline void rvt_qp_wqe_unreserve( - struct rvt_qp *qp, - struct rvt_swqe *wqe) +static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags) { - if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) { + if (unlikely(flags & RVT_SEND_RESERVE_USED)) { atomic_dec(&qp->s_reserved_used); /* insure no compiler re-order up to s_last change */ smp_mb__after_atomic(); @@ -853,6 +851,7 @@ rvt_qp_complete_swqe(struct rvt_qp *qp, u32 byte_len, last; int flags = wqe->wr.send_flags; + rvt_qp_wqe_unreserve(qp, flags); rvt_put_qp_swqe(qp, wqe); need_completion = diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 2d64b53f947c..9b87e1a1c646 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -115,7 +115,7 @@ struct fc_disc_port { struct fc_lport *lp; struct list_head peers; struct work_struct rport_work; - u32 port_id; + u32 port_id; }; /** @@ -155,14 +155,14 @@ struct fc_rport_operations { */ struct fc_rport_libfc_priv { struct fc_lport *local_port; - enum fc_rport_state rp_state; + enum fc_rport_state rp_state; u16 flags; #define FC_RP_FLAGS_REC_SUPPORTED (1 << 0) #define FC_RP_FLAGS_RETRY (1 << 1) #define FC_RP_STARTED (1 << 2) #define FC_RP_FLAGS_CONF_REQ (1 << 3) - unsigned int e_d_tov; - unsigned int r_a_tov; + unsigned int e_d_tov; + unsigned int r_a_tov; }; /** @@ -191,24 +191,24 @@ struct fc_rport_priv { struct fc_lport *local_port; struct fc_rport *rport; struct kref kref; - enum fc_rport_state rp_state; + enum fc_rport_state rp_state; struct fc_rport_identifiers ids; u16 flags; - u16 max_seq; + u16 max_seq; u16 disc_id; u16 maxframe_size; - unsigned int retries; - unsigned int major_retries; - unsigned int e_d_tov; - unsigned int r_a_tov; - struct mutex rp_mutex; + unsigned int retries; + unsigned int major_retries; + unsigned int e_d_tov; + unsigned int r_a_tov; + struct mutex rp_mutex; struct delayed_work retry_work; - enum fc_rport_event event; + enum fc_rport_event event; struct fc_rport_operations *ops; - struct list_head peers; - struct work_struct event_work; + struct list_head peers; + struct work_struct event_work; u32 supported_classes; - u16 prli_count; + u16 prli_count; struct rcu_head rcu; u16 sp_features; u8 spp_type; @@ -618,12 +618,12 @@ struct libfc_function_template { * @disc_callback: Callback routine called when discovery completes */ struct fc_disc { - unsigned char retry_count; - unsigned char pending; - unsigned char requested; - unsigned short seq_count; - unsigned char buf_len; - u16 disc_id; + unsigned char retry_count; + unsigned char pending; + unsigned char requested; + unsigned short seq_count; + unsigned char buf_len; + u16 disc_id; struct list_head rports; void *priv; @@ -697,7 +697,7 @@ struct fc_lport { struct fc_rport_priv *ms_rdata; struct fc_rport_priv *ptp_rdata; void *scsi_priv; - struct fc_disc disc; + struct fc_disc disc; /* Virtual port information */ struct list_head vports; @@ -715,7 +715,7 @@ struct fc_lport { u8 retry_count; /* Fabric information */ - u32 port_id; + u32 port_id; u64 wwpn; u64 wwnn; unsigned int service_params; @@ -743,11 +743,11 @@ struct fc_lport { struct fc_ns_fts fcts; /* Miscellaneous */ - struct mutex lp_mutex; - struct list_head list; + struct mutex lp_mutex; + struct list_head list; struct delayed_work retry_work; void *prov[FC_FC4_PROV_SIZE]; - struct list_head lport_list; + struct list_head lport_list; }; /** diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index c50fb297e265..2568cb0627ec 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -31,7 +31,7 @@ * FIP tunable parameters. */ #define FCOE_CTLR_START_DELAY 2000 /* mS after first adv. to choose FCF */ -#define FCOE_CTRL_SOL_TOV 2000 /* min. solicitation interval (mS) */ +#define FCOE_CTLR_SOL_TOV 2000 /* min. solicitation interval (mS) */ #define FCOE_CTLR_FCF_LIMIT 20 /* max. number of FCF entries */ #define FCOE_CTLR_VN2VN_LOGIN_LIMIT 3 /* max. VN2VN rport login retries */ @@ -229,6 +229,7 @@ struct fcoe_fcf { * @vn_mac: VN_Node assigned MAC address for data */ struct fcoe_rport { + struct fc_rport_priv rdata; unsigned long time; u16 fcoe_len; u16 flags; diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 3f9d6b6a5691..c1036d16ed03 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -259,7 +259,7 @@ static inline int qe_alive_during_sleep(void) /* Structure that defines QE firmware binary files. * - * See Documentation/powerpc/qe_firmware.txt for a description of these + * See Documentation/powerpc/qe_firmware.rst for a description of these * fields. */ struct qe_firmware { diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index c5188ff724d1..bc88d6f964da 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,10 +173,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; wake_up(&stream->runtime->sleep); } diff --git a/include/sound/sof/control.h b/include/sound/sof/control.h index bded69e696d4..6080ea0facd7 100644 --- a/include/sound/sof/control.h +++ b/include/sound/sof/control.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/dai-intel.h b/include/sound/sof/dai-intel.h index 4bb8ee138ba7..65e4c20e567c 100644 --- a/include/sound/sof/dai-intel.h +++ b/include/sound/sof/dai-intel.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 3d174e20aa53..5b8de1b1983c 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/header.h b/include/sound/sof/header.h index 12867bbd4372..10f00c08dbb7 100644 --- a/include/sound/sof/header.h +++ b/include/sound/sof/header.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 16528d2b4a50..a9156b4a062c 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/pm.h b/include/sound/sof/pm.h index 8ae3ad45bdf7..003879401d63 100644 --- a/include/sound/sof/pm.h +++ b/include/sound/sof/pm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/stream.h b/include/sound/sof/stream.h index 643f175cb479..0b71b381b952 100644 --- a/include/sound/sof/stream.h +++ b/include/sound/sof/stream.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index 41dcabf89899..c47b36240920 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/trace.h b/include/sound/sof/trace.h index 9257d5473d97..fda6e8f6ead4 100644 --- a/include/sound/sof/trace.h +++ b/include/sound/sof/trace.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/sound/sof/xtensa.h b/include/sound/sof/xtensa.h index d25c764b10e8..dd53d36b34e1 100644 --- a/include/sound/sof/xtensa.h +++ b/include/sound/sof/xtensa.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. diff --git a/include/trace/events/dma_fence.h b/include/trace/events/dma_fence.h index 2212adda8f77..64e92d56c6a8 100644 --- a/include/trace/events/dma_fence.h +++ b/include/trace/events/dma_fence.h @@ -2,7 +2,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM dma_fence -#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) +#if !defined(_TRACE_DMA_FENCE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_DMA_FENCE_H #include <linux/tracepoint.h> diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index f3a12566bed0..6678cf8b235b 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -3,7 +3,7 @@ #define TRACE_SYSTEM napi #if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_NAPI_H_ +#define _TRACE_NAPI_H #include <linux/netdevice.h> #include <linux/tracepoint.h> @@ -38,7 +38,7 @@ TRACE_EVENT(napi_poll, #undef NO_DEV -#endif /* _TRACE_NAPI_H_ */ +#endif /* _TRACE_NAPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 60d0d8bd336d..0d1a9ebf55ba 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -2,7 +2,7 @@ #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_QDISC_H_ +#define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -44,7 +44,7 @@ TRACE_EVENT(qdisc_dequeue, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); -#endif /* _TRACE_QDISC_H_ */ +#endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/include/trace/events/tegra_apb_dma.h b/include/trace/events/tegra_apb_dma.h index 0818f6286110..971cd02d2daf 100644 --- a/include/trace/events/tegra_apb_dma.h +++ b/include/trace/events/tegra_apb_dma.h @@ -1,5 +1,5 @@ #if !defined(_TRACE_TEGRA_APB_DMA_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_TEGRA_APM_DMA_H +#define _TRACE_TEGRA_APB_DMA_H #include <linux/tracepoint.h> #include <linux/dmaengine.h> @@ -55,7 +55,7 @@ TRACE_EVENT(tegra_dma_isr, TP_printk("%s: irq %d\n", __get_str(chan), __entry->irq) ); -#endif /* _TRACE_TEGRADMA_H */ +#endif /* _TRACE_TEGRA_APB_DMA_H */ /* This part must be outside protection */ #include <trace/define_trace.h> diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 68899fdc985b..8c8420230a10 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -175,7 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP || \ + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \ ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fa1c753dcdbc..4393bd4b2419 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as @@ -2713,6 +2714,33 @@ union bpf_attr { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2824,7 +2852,8 @@ union bpf_attr { FN(strtoul), \ FN(sk_storage_get), \ FN(sk_storage_delete), \ - FN(send_signal), + FN(send_signal), \ + FN(tcp_gen_syncookie), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3507,6 +3536,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3528,6 +3561,8 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; + __be32 flow_label; }; struct bpf_func_info { diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h index 2ec3cc99ea4c..cbc1f5813f50 100644 --- a/include/uapi/linux/bpfilter.h +++ b/include/uapi/linux/bpfilter.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BPFILTER_H #define _UAPI_LINUX_BPFILTER_H diff --git a/include/uapi/linux/ipmi_bmc.h b/include/uapi/linux/ipmi_bmc.h index 1670f0944227..782a03eb1086 100644 --- a/include/uapi/linux/ipmi_bmc.h +++ b/include/uapi/linux/ipmi_bmc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2015-2018, Intel Corporation. */ diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index d10b832c58c5..0a52b7b093d3 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Intel Speed Select Interface: OS to hardware Interface * Copyright (c) 2019, Intel Corporation. diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a7c19540ce21..5e3f12d5359e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -1086,7 +1086,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 5edbd0a675fd..405b31cbf723 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -53,6 +53,11 @@ enum { NET_DM_CMD_CONFIG, NET_DM_CMD_START, NET_DM_CMD_STOP, + NET_DM_CMD_PACKET_ALERT, + NET_DM_CMD_CONFIG_GET, + NET_DM_CMD_CONFIG_NEW, + NET_DM_CMD_STATS_GET, + NET_DM_CMD_STATS_NEW, _NET_DM_CMD_MAX, }; @@ -62,4 +67,50 @@ enum { * Our group identifiers */ #define NET_DM_GRP_ALERT 1 + +enum net_dm_attr { + NET_DM_ATTR_UNSPEC, + + NET_DM_ATTR_ALERT_MODE, /* u8 */ + NET_DM_ATTR_PC, /* u64 */ + NET_DM_ATTR_SYMBOL, /* string */ + NET_DM_ATTR_IN_PORT, /* nested */ + NET_DM_ATTR_TIMESTAMP, /* struct timespec */ + NET_DM_ATTR_PROTO, /* u16 */ + NET_DM_ATTR_PAYLOAD, /* binary */ + NET_DM_ATTR_PAD, + NET_DM_ATTR_TRUNC_LEN, /* u32 */ + NET_DM_ATTR_ORIG_LEN, /* u32 */ + NET_DM_ATTR_QUEUE_LEN, /* u32 */ + NET_DM_ATTR_STATS, /* nested */ + + __NET_DM_ATTR_MAX, + NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 +}; + +/** + * enum net_dm_alert_mode - Alert mode. + * @NET_DM_ALERT_MODE_SUMMARY: A summary of recent drops is sent to user space. + * @NET_DM_ALERT_MODE_PACKET: Each dropped packet is sent to user space along + * with metadata. + */ +enum net_dm_alert_mode { + NET_DM_ALERT_MODE_SUMMARY, + NET_DM_ALERT_MODE_PACKET, +}; + +enum { + NET_DM_ATTR_PORT_NETDEV_IFINDEX, /* u32 */ + + __NET_DM_ATTR_PORT_MAX, + NET_DM_ATTR_PORT_MAX = __NET_DM_ATTR_PORT_MAX - 1 +}; + +enum { + NET_DM_ATTR_STATS_DROPPED, /* u64 */ + + __NET_DM_ATTR_STATS_MAX, + NET_DM_ATTR_STATS_MAX = __NET_DM_ATTR_STATS_MAX - 1 +}; + #endif diff --git a/include/uapi/linux/netfilter/nf_synproxy.h b/include/uapi/linux/netfilter/nf_synproxy.h index 6f3791c8946f..00d787f0260e 100644 --- a/include/uapi/linux/netfilter/nf_synproxy.h +++ b/include/uapi/linux/netfilter/nf_synproxy.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NF_SYNPROXY_H #define _NF_SYNPROXY_H diff --git a/include/uapi/linux/netfilter/xt_connlabel.h b/include/uapi/linux/netfilter/xt_connlabel.h index 2312f0ec07b2..323f0dfc2a4e 100644 --- a/include/uapi/linux/netfilter/xt_connlabel.h +++ b/include/uapi/linux/netfilter/xt_connlabel.h @@ -1,4 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_XT_CONNLABEL_H +#define _UAPI_XT_CONNLABEL_H + #include <linux/types.h> #define XT_CONNLABEL_MAXBIT 127 @@ -11,3 +15,5 @@ struct xt_connlabel_mtinfo { __u16 bit; __u16 options; }; + +#endif /* _UAPI_XT_CONNLABEL_H */ diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 8654b2442f6a..592a0c1b77c9 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * Userspace interface for AMD Secure Encrypted Virtualization (SEV) * platform management commands. diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 782069dcf607..4accfa7e266d 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ /* Types and definitions for AF_RXRPC. * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 5642c05e0da0..3cc3af1c2ee1 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -150,9 +150,6 @@ #define PORT_PNX8XXX 70 -/* Hilscher netx */ -#define PORT_NETX 71 - /* SUN4V Hypervisor Console */ #define PORT_SUNHV 72 diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 8eb96021709c..c3409c8ec0dd 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -6,17 +6,24 @@ * Desired design of maximum size and alignment (see RFC2553) */ #define _K_SS_MAXSIZE 128 /* Implementation specific max size */ -#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *)) - /* Implementation specific desired alignment */ typedef unsigned short __kernel_sa_family_t; +/* + * The definition uses anonymous union and struct in order to control the + * default alignment. + */ struct __kernel_sockaddr_storage { - __kernel_sa_family_t ss_family; /* address family */ - /* Following field(s) are implementation specific */ - char __data[_K_SS_MAXSIZE - sizeof(unsigned short)]; + union { + struct { + __kernel_sa_family_t ss_family; /* address family */ + /* Following field(s) are implementation specific */ + char __data[_K_SS_MAXSIZE - sizeof(unsigned short)]; /* space to achieve desired size, */ /* _SS_MAXSIZE value minus size of ss_family */ -} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */ + }; + void *__align; /* implementation specific desired alignment */ + }; +}; #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/include/uapi/linux/usb/g_uvc.h b/include/uapi/linux/usb/g_uvc.h index 3c9ee3020cbb..652f169a019e 100644 --- a/include/uapi/linux/usb/g_uvc.h +++ b/include/uapi/linux/usb/g_uvc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * g_uvc.h -- USB Video Class Gadget driver API * diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h index 26f39816af14..c27289fd619a 100644 --- a/include/uapi/linux/vbox_vmmdev_types.h +++ b/include/uapi/linux/vbox_vmmdev_types.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */ /* * Virtual Device for Guest <-> VMM/Host communication, type definitions * which are also used for the vboxguest ioctl interface / by vboxsf diff --git a/include/uapi/linux/vboxguest.h b/include/uapi/linux/vboxguest.h index 612f0c7d3558..9cec58a6a5ea 100644 --- a/include/uapi/linux/vboxguest.h +++ b/include/uapi/linux/vboxguest.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */ /* * VBoxGuest - VirtualBox Guest Additions Driver Interface. * diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index ba1b460c9944..237e36a280cb 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: BSD-3-Clause */ /* - * Virtio-iommu definition v0.9 + * Virtio-iommu definition v0.12 * - * Copyright (C) 2018 Arm Ltd. + * Copyright (C) 2019 Arm Ltd. */ #ifndef _UAPI_LINUX_VIRTIO_IOMMU_H #define _UAPI_LINUX_VIRTIO_IOMMU_H @@ -11,26 +11,31 @@ /* Feature bits */ #define VIRTIO_IOMMU_F_INPUT_RANGE 0 -#define VIRTIO_IOMMU_F_DOMAIN_BITS 1 +#define VIRTIO_IOMMU_F_DOMAIN_RANGE 1 #define VIRTIO_IOMMU_F_MAP_UNMAP 2 #define VIRTIO_IOMMU_F_BYPASS 3 #define VIRTIO_IOMMU_F_PROBE 4 +#define VIRTIO_IOMMU_F_MMIO 5 -struct virtio_iommu_range { - __u64 start; - __u64 end; +struct virtio_iommu_range_64 { + __le64 start; + __le64 end; +}; + +struct virtio_iommu_range_32 { + __le32 start; + __le32 end; }; struct virtio_iommu_config { /* Supported page sizes */ - __u64 page_size_mask; + __le64 page_size_mask; /* Supported IOVA range */ - struct virtio_iommu_range input_range; + struct virtio_iommu_range_64 input_range; /* Max domain ID size */ - __u8 domain_bits; - __u8 padding[3]; + struct virtio_iommu_range_32 domain_range; /* Probe buffer size */ - __u32 probe_size; + __le32 probe_size; }; /* Request types */ @@ -49,6 +54,7 @@ struct virtio_iommu_config { #define VIRTIO_IOMMU_S_RANGE 0x05 #define VIRTIO_IOMMU_S_NOENT 0x06 #define VIRTIO_IOMMU_S_FAULT 0x07 +#define VIRTIO_IOMMU_S_NOMEM 0x08 struct virtio_iommu_req_head { __u8 type; @@ -78,12 +84,10 @@ struct virtio_iommu_req_detach { #define VIRTIO_IOMMU_MAP_F_READ (1 << 0) #define VIRTIO_IOMMU_MAP_F_WRITE (1 << 1) -#define VIRTIO_IOMMU_MAP_F_EXEC (1 << 2) -#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 3) +#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 2) #define VIRTIO_IOMMU_MAP_F_MASK (VIRTIO_IOMMU_MAP_F_READ | \ VIRTIO_IOMMU_MAP_F_WRITE | \ - VIRTIO_IOMMU_MAP_F_EXEC | \ VIRTIO_IOMMU_MAP_F_MMIO) struct virtio_iommu_req_map { diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index 9a63ed6d062f..b022787ffb94 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ /* * Definitions for virtio-pmem devices. * diff --git a/include/uapi/linux/vmcore.h b/include/uapi/linux/vmcore.h index 022619668e0e..3e9da91866ff 100644 --- a/include/uapi/linux/vmcore.h +++ b/include/uapi/linux/vmcore.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_VMCORE_H #define _UAPI_VMCORE_H diff --git a/include/uapi/linux/wmi.h b/include/uapi/linux/wmi.h index c36f2d7675a4..7085c5dca9fa 100644 --- a/include/uapi/linux/wmi.h +++ b/include/uapi/linux/wmi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ /* * User API methods for ACPI-WMI mapping driver * diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 6d701af9fc42..fb792e882cef 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __QCOM_FASTRPC_H__ #define __QCOM_FASTRPC_H__ diff --git a/include/uapi/rdma/rvt-abi.h b/include/uapi/rdma/rvt-abi.h index 7328293c715c..7c05a02d2be5 100644 --- a/include/uapi/rdma/rvt-abi.h +++ b/include/uapi/rdma/rvt-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * This file contains defines, structures, etc. that are used diff --git a/include/uapi/rdma/siw-abi.h b/include/uapi/rdma/siw-abi.h index 3dd8071ace7b..7de68f1dc707 100644 --- a/include/uapi/rdma/siw-abi.h +++ b/include/uapi/rdma/siw-abi.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) or BSD-3-Clause */ /* Authors: Bernard Metzler <[email protected]> */ /* Copyright (c) 2008-2019, IBM Corporation */ diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h index 17c7abd0803a..9988db6ad244 100644 --- a/include/uapi/scsi/scsi_bsg_ufs.h +++ b/include/uapi/scsi/scsi_bsg_ufs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * UFS Transport SGIO v4 BSG Message Support * diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f39352cef382..9eee32f5e407 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * skl-tplg-interface.h - Intel DSP FW private data interface * diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 4969817124a8..98b30c1613b2 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -109,6 +109,9 @@ static inline int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, } #endif +int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long len); + /* * xen_remap_domain_gfn_array() - map an array of foreign frames by gfn * @vma: VMA to map the pages into diff --git a/kernel/Makefile b/kernel/Makefile index a8d923b5481b..ef0d95a190b4 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -111,7 +111,6 @@ obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o -obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 29d781061cd5..e1d9adb212f9 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o endif +ifeq ($(CONFIG_SYSFS),y) +obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o +endif diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 0a00eaca6fae..6a6a154cfa7b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -964,7 +964,6 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; - ctx->optlen = max_optlen; return 0; } @@ -984,7 +983,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, .level = *level, .optname = *optname, }; - int ret; + int ret, max_optlen; /* Opportunistic check to see whether we have any BPF program * attached to the hook so we don't waste time allocating @@ -994,10 +993,18 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) return 0; - ret = sockopt_alloc_buf(&ctx, *optlen); + /* Allocate a bit more than the initial user buffer for + * BPF program. The canonical use case is overriding + * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). + */ + max_optlen = max_t(int, 16, *optlen); + + ret = sockopt_alloc_buf(&ctx, max_optlen); if (ret) return ret; + ctx.optlen = *optlen; + if (copy_from_user(ctx.optval, optval, *optlen) != 0) { ret = -EFAULT; goto out; @@ -1016,7 +1023,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; - } else if (ctx.optlen > *optlen || ctx.optlen < -1) { + } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ ret = -EFAULT; } else { @@ -1063,6 +1070,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, if (ret) return ret; + ctx.optlen = max_optlen; + if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d83cf8ccc872..9af048a932b5 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -37,6 +37,12 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> @@ -59,10 +65,11 @@ struct xdp_bulk_queue { struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ + struct hlist_node index_hlist; struct bpf_dtab *dtab; - unsigned int bit; struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; + unsigned int idx; /* keep track of map index for tracepoint */ }; struct bpf_dtab { @@ -70,33 +77,45 @@ struct bpf_dtab { struct bpf_dtab_netdev **netdev_map; struct list_head __percpu *flush_list; struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +static struct hlist_head *dev_map_create_hash(unsigned int entries) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc_array(entries, sizeof(*hash), GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { - struct bpf_dtab *dtab; int err, cpu; u64 cost; - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); + return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; - dtab = kzalloc(sizeof(*dtab), GFP_USER); - if (!dtab) - return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&dtab->map, attr); @@ -104,12 +123,18 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += sizeof(struct list_head) * num_possible_cpus(); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + + if (!dtab->n_buckets) /* Overflow check */ + return -EINVAL; + cost += sizeof(struct hlist_head) * dtab->n_buckets; + } + /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) - goto free_dtab; - - err = -ENOMEM; + return -EINVAL; dtab->flush_list = alloc_percpu(struct list_head); if (!dtab->flush_list) @@ -124,19 +149,48 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!dtab->netdev_map) goto free_percpu; - spin_lock(&dev_map_lock); - list_add_tail_rcu(&dtab->list, &dev_map_list); - spin_unlock(&dev_map_lock); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); + if (!dtab->dev_index_head) + goto free_map_area; - return &dtab->map; + spin_lock_init(&dtab->index_lock); + } + return 0; + +free_map_area: + bpf_map_area_free(dtab->netdev_map); free_percpu: free_percpu(dtab->flush_list); free_charge: bpf_map_charge_finish(&dtab->map.memory); -free_dtab: - kfree(dtab); - return ERR_PTR(err); + return -ENOMEM; +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + int err; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + err = dev_map_init_map(dtab, attr); + if (err) { + kfree(dtab); + return ERR_PTR(err); + } + + spin_lock(&dev_map_lock); + list_add_tail_rcu(&dtab->list, &dev_map_list); + spin_unlock(&dev_map_lock); + + return &dtab->map; } static void dev_map_free(struct bpf_map *map) @@ -188,6 +242,7 @@ static void dev_map_free(struct bpf_map *map) free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); + kfree(dtab->dev_index_head); kfree(dtab); } @@ -208,6 +263,70 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) +{ + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} + +struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->idx == key) + return dev; + + return NULL; +} + +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; + return 0; + } + + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { @@ -235,7 +354,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, + trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx, sent, drops, bq->dev_rx, dev, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); @@ -363,6 +482,15 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + struct net_device *dev = obj ? obj->dev : NULL; + + return dev ? &dev->ifindex : NULL; +} + static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { @@ -412,17 +540,74 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + +static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, + struct bpf_dtab *dtab, + u32 ifindex, + unsigned int idx) +{ gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; + struct bpf_dtab_netdev *dev; + struct xdp_bulk_queue *bq; + int cpu; + + dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), + sizeof(void *), gfp); + if (!dev->bulkq) { + kfree(dev); + return ERR_PTR(-ENOMEM); + } + + for_each_possible_cpu(cpu) { + bq = per_cpu_ptr(dev->bulkq, cpu); + bq->obj = dev; + } + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + free_percpu(dev->bulkq); + kfree(dev); + return ERR_PTR(-EINVAL); + } + + dev->idx = idx; + dev->dtab = dtab; + + return dev; +} + +static int __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; u32 ifindex = *(u32 *)value; - struct xdp_bulk_queue *bq; u32 i = *(u32 *)key; - int cpu; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -434,31 +619,9 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); - if (!dev) - return -ENOMEM; - - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return -ENOMEM; - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - - dev->dev = dev_get_by_index(net, ifindex); - if (!dev->dev) { - free_percpu(dev->bulkq); - kfree(dev); - return -EINVAL; - } - - dev->bit = i; - dev->dtab = dtab; + dev = __dev_map_alloc_node(net, dtab, ifindex, i); + if (IS_ERR(dev)) + return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed @@ -472,6 +635,63 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, return 0; } +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + u32 ifindex = *(u32 *)value; + u32 idx = *(u32 *)key; + unsigned long flags; + + if (unlikely(map_flags > BPF_EXIST || !ifindex)) + return -EINVAL; + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + return -EEXIST; + + dev = __dev_map_alloc_node(net, dtab, ifindex, idx); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock_irqsave(&dtab->index_lock, flags); + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + const struct bpf_map_ops dev_map_ops = { .map_alloc = dev_map_alloc, .map_free = dev_map_free, @@ -482,6 +702,16 @@ const struct bpf_map_ops dev_map_ops = { .map_check_btf = map_check_no_btf, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, +}; + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c new file mode 100644 index 000000000000..4659349fc795 --- /dev/null +++ b/kernel/bpf/sysfs_btf.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide kernel BTF information for introspection and use by eBPF tools. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kobject.h> +#include <linux/init.h> +#include <linux/sysfs.h> + +/* See scripts/link-vmlinux.sh, gen_btf() func for details */ +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; + +static ssize_t +btf_vmlinux_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + return len; +} + +static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = { + .attr = { .name = "vmlinux", .mode = 0444, }, + .read = btf_vmlinux_read, +}; + +static struct kobject *btf_kobj; + +static int __init btf_vmlinux_init(void) +{ + int err; + + if (!_binary__btf_vmlinux_bin_start) + return 0; + + btf_kobj = kobject_create_and_add("btf", kernel_kobj); + if (IS_ERR(btf_kobj)) { + err = PTR_ERR(btf_kobj); + btf_kobj = NULL; + return err; + } + + bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); +} + +subsys_initcall(btf_vmlinux_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5900cbb966b1..10c0ff93f52b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3457,6 +3457,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; @@ -3539,6 +3540,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; @@ -8616,8 +8618,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = (off & (size_default - 1)) * 8; - + u8 shift = bpf_ctx_narrow_load_shift(off, size, + size_default); if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, diff --git a/kernel/cred.c b/kernel/cred.c index f9a0ce66c9c3..c0a4c12d38b2 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -144,7 +144,10 @@ void __put_cred(struct cred *cred) BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); - call_rcu(&cred->rcu, put_cred_rcu); + if (cred->non_rcu) + put_cred_rcu(&cred->rcu); + else + call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); @@ -261,6 +264,7 @@ struct cred *prepare_creds(void) old = task->cred; memcpy(new, old, sizeof(struct cred)); + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_group_info(new->group_info); @@ -544,7 +548,19 @@ const struct cred *override_creds(const struct cred *new) validate_creds(old); validate_creds(new); - get_cred(new); + + /* + * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. + * + * That means that we do not clear the 'non_rcu' flag, since + * we are only installing the cred into the thread-synchronous + * '->cred' pointer, not the '->real_cred' pointer that is + * visible to other threads under RCU. + * + * Also note that we did validate_creds() manually, not depending + * on the validation in 'get_cred()'. + */ + get_new_cred((struct cred *)new); alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); alter_cred_subscribers(old, -1); @@ -681,6 +697,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + new->non_rcu = 0; atomic_set(&new->usage, 1); set_cred_subscribers(new, 0); get_uid(new->user); diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index bfc0c17f2a3d..2bd410f934b3 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -243,8 +243,9 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) /* CMA can be used only in the context which permits sleeping */ if (cma && gfpflags_allow_blocking(gfp)) { - align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT); - page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN); + size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT); + + page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN); } /* Fallback allocation of normal pages */ @@ -266,7 +267,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp) */ void dma_free_contiguous(struct device *dev, struct page *page, size_t size) { - if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT)) + if (!cma_release(dev_get_cma_area(dev), page, + PAGE_ALIGN(size) >> PAGE_SHIFT)) __free_pages(page, get_order(size)); } diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 1f628e7ac709..b945239621d8 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -116,11 +116,16 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, int ret; if (!dev_is_dma_coherent(dev)) { + unsigned long pfn; + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) return -ENXIO; - page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr, - dma_addr)); + /* If the PFN is not valid, we do not have a struct page */ + pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + if (!pfn_valid(pfn)) + return -ENXIO; + page = pfn_to_page(pfn); } else { page = virt_to_page(cpu_addr); } @@ -170,7 +175,11 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, if (!dev_is_dma_coherent(dev)) { if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) return -ENXIO; + + /* If the PFN is not valid, we do not have a struct page */ pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + if (!pfn_valid(pfn)) + return -ENXIO; } else { pfn = page_to_pfn(virt_to_page(cpu_addr)); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 026a14541a38..0463c1151bae 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11274,7 +11274,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, goto err_unlock; } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); diff --git a/kernel/exit.c b/kernel/exit.c index 4436158a6d30..5b4a5dcce8f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -734,9 +734,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead) autoreap = true; } - tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; - if (tsk->exit_state == EXIT_DEAD) + if (autoreap) { + tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); + } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) diff --git a/kernel/fork.c b/kernel/fork.c index d8ae0f1b4148..2852d0e76ea3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -726,7 +726,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(tsk == current); cgroup_free(tsk); - task_numa_free(tsk); + task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 341f52117f88..4861cf8e274b 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -448,7 +448,7 @@ static void print_lockdep_off(const char *bug_msg) unsigned long nr_stack_trace_entries; -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the graph_lock. @@ -491,7 +491,7 @@ unsigned int max_lockdep_depth; DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats); #endif -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING /* * Locking printouts: */ @@ -2969,7 +2969,7 @@ static void check_chain_key(struct task_struct *curr) #endif } -#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) +#ifdef CONFIG_PROVE_LOCKING static int mark_lock(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit); @@ -3608,7 +3608,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this, return ret; } -#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ +#else /* CONFIG_PROVE_LOCKING */ static inline int mark_usage(struct task_struct *curr, struct held_lock *hlock, int check) @@ -3627,7 +3627,7 @@ static inline int separate_irq_context(struct task_struct *curr, return 0; } -#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */ +#endif /* CONFIG_PROVE_LOCKING */ /* * Initialize a lock instance's lock-class mapping info: @@ -4321,8 +4321,7 @@ static void __lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie */ static void check_flags(unsigned long flags) { -#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \ - defined(CONFIG_TRACE_IRQFLAGS) +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) if (!debug_locks) return; diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 65b6a1600c8f..bda006f8a88b 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -200,7 +200,6 @@ static void lockdep_stats_debug_show(struct seq_file *m) static int lockdep_stats_show(struct seq_file *m, void *v) { - struct lock_class *class; unsigned long nr_unused = 0, nr_uncategorized = 0, nr_irq_safe = 0, nr_irq_unsafe = 0, nr_softirq_safe = 0, nr_softirq_unsafe = 0, @@ -211,6 +210,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v) sum_forward_deps = 0; #ifdef CONFIG_PROVE_LOCKING + struct lock_class *class; + list_for_each_entry(class, &all_lock_classes, lock_entry) { if (class->usage_mask == 0) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index edd1c082dbf5..5e069734363c 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -908,6 +908,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, might_sleep(); +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(lock->magic != lock); +#endif + ww = container_of(lock, struct ww_mutex, base); if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) @@ -1379,8 +1383,13 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, */ int __sched mutex_trylock(struct mutex *lock) { - bool locked = __mutex_trylock(lock); + bool locked; + +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(lock->magic != lock); +#endif + locked = __mutex_trylock(lock); if (locked) mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 37524a47f002..bd0f0d05724c 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -666,7 +666,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem, preempt_disable(); rcu_read_lock(); owner = rwsem_owner_flags(sem, &flags); - if ((flags & nonspinnable) || (owner && !owner_on_cpu(owner))) + /* + * Don't check the read-owner as the entry may be stale. + */ + if ((flags & nonspinnable) || + (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner))) ret = false; rcu_read_unlock(); preempt_enable(); @@ -1000,6 +1004,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, int state) atomic_long_add(-RWSEM_READER_BIAS, &sem->count); adjustment = 0; if (rwsem_optimistic_spin(sem, false)) { + /* rwsem_optimistic_spin() implies ACQUIRE on success */ /* * Wake up other readers in the wait list if the front * waiter is a reader. @@ -1014,6 +1019,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, int state) } return sem; } else if (rwsem_reader_phase_trylock(sem, waiter.last_rowner)) { + /* rwsem_reader_phase_trylock() implies ACQUIRE on success */ return sem; } @@ -1032,6 +1038,8 @@ queue: */ if (adjustment && !(atomic_long_read(&sem->count) & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) { + /* Provide lock ACQUIRE */ + smp_acquire__after_ctrl_dep(); raw_spin_unlock_irq(&sem->wait_lock); rwsem_set_reader_owned(sem); lockevent_inc(rwsem_rlock_fast); @@ -1065,15 +1073,18 @@ queue: wake_up_q(&wake_q); /* wait to be given the lock */ - while (true) { + for (;;) { set_current_state(state); - if (!waiter.task) + if (!smp_load_acquire(&waiter.task)) { + /* Matches rwsem_mark_wake()'s smp_store_release(). */ break; + } if (signal_pending_state(state, current)) { raw_spin_lock_irq(&sem->wait_lock); if (waiter.task) goto out_nolock; raw_spin_unlock_irq(&sem->wait_lock); + /* Ordered by sem->wait_lock against rwsem_mark_wake(). */ break; } schedule(); @@ -1083,6 +1094,7 @@ queue: __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock); return sem; + out_nolock: list_del(&waiter.list); if (list_empty(&sem->wait_list)) { @@ -1123,8 +1135,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) /* do optimistic spinning and steal lock if possible */ if (rwsem_can_spin_on_owner(sem, RWSEM_WR_NONSPINNABLE) && - rwsem_optimistic_spin(sem, true)) + rwsem_optimistic_spin(sem, true)) { + /* rwsem_optimistic_spin() implies ACQUIRE on success */ return sem; + } /* * Disable reader optimistic spinning for this rwsem after @@ -1184,9 +1198,11 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) wait: /* wait until we successfully acquire the lock */ set_current_state(state); - while (true) { - if (rwsem_try_write_lock(sem, wstate)) + for (;;) { + if (rwsem_try_write_lock(sem, wstate)) { + /* rwsem_try_write_lock() implies ACQUIRE on success */ break; + } raw_spin_unlock_irq(&sem->wait_lock); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 036be95a87e9..bc9cfeaac8bd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1086,6 +1086,21 @@ struct numa_group { unsigned long faults[0]; }; +/* + * For functions that can be called in multiple contexts that permit reading + * ->numa_group (see struct task_struct for locking rules). + */ +static struct numa_group *deref_task_numa_group(struct task_struct *p) +{ + return rcu_dereference_check(p->numa_group, p == current || + (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu))); +} + +static struct numa_group *deref_curr_numa_group(struct task_struct *p) +{ + return rcu_dereference_protected(p->numa_group, p == current); +} + static inline unsigned long group_faults_priv(struct numa_group *ng); static inline unsigned long group_faults_shared(struct numa_group *ng); @@ -1129,10 +1144,12 @@ static unsigned int task_scan_start(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long period = smin; + struct numa_group *ng; /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); @@ -1140,6 +1157,7 @@ static unsigned int task_scan_start(struct task_struct *p) period *= shared + 1; period /= private + shared + 1; } + rcu_read_unlock(); return max(smin, period); } @@ -1148,13 +1166,14 @@ static unsigned int task_scan_max(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long smax; + struct numa_group *ng; /* Watch for min being lower than max due to floor calculations */ smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + ng = deref_curr_numa_group(p); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); unsigned long period = smax; @@ -1186,7 +1205,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; p->numa_faults = NULL; - p->numa_group = NULL; + RCU_INIT_POINTER(p->numa_group, NULL); p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; @@ -1233,7 +1252,16 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p) pid_t task_numa_group_id(struct task_struct *p) { - return p->numa_group ? p->numa_group->gid : 0; + struct numa_group *ng; + pid_t gid = 0; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) + gid = ng->gid; + rcu_read_unlock(); + + return gid; } /* @@ -1258,11 +1286,13 @@ static inline unsigned long task_faults(struct task_struct *p, int nid) static inline unsigned long group_faults(struct task_struct *p, int nid) { - if (!p->numa_group) + struct numa_group *ng = deref_task_numa_group(p); + + if (!ng) return 0; - return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + - p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; + return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + ng->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) @@ -1400,12 +1430,13 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, static inline unsigned long group_weight(struct task_struct *p, int nid, int dist) { + struct numa_group *ng = deref_task_numa_group(p); unsigned long faults, total_faults; - if (!p->numa_group) + if (!ng) return 0; - total_faults = p->numa_group->total_faults; + total_faults = ng->total_faults; if (!total_faults) return 0; @@ -1419,7 +1450,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { - struct numa_group *ng = p->numa_group; + struct numa_group *ng = deref_curr_numa_group(p); int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; @@ -1600,13 +1631,14 @@ static bool load_too_imbalanced(long src_load, long dst_load, static void task_numa_compare(struct task_numa_env *env, long taskimp, long groupimp, bool maymove) { + struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p); struct rq *dst_rq = cpu_rq(env->dst_cpu); + long imp = p_ng ? groupimp : taskimp; struct task_struct *cur; long src_load, dst_load; - long load; - long imp = env->p->numa_group ? groupimp : taskimp; - long moveimp = imp; int dist = env->dist; + long moveimp = imp; + long load; if (READ_ONCE(dst_rq->numa_migrate_on)) return; @@ -1645,21 +1677,22 @@ static void task_numa_compare(struct task_numa_env *env, * If dst and source tasks are in the same NUMA group, or not * in any group then look only at task weights. */ - if (cur->numa_group == env->p->numa_group) { + cur_ng = rcu_dereference(cur->numa_group); + if (cur_ng == p_ng) { imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* * Add some hysteresis to prevent swapping the * tasks within a group over tiny differences. */ - if (cur->numa_group) + if (cur_ng) imp -= imp / 16; } else { /* * Compare the group weights. If a task is all by itself * (not part of a group), use the task weight instead. */ - if (cur->numa_group && env->p->numa_group) + if (cur_ng && p_ng) imp += group_weight(cur, env->src_nid, dist) - group_weight(cur, env->dst_nid, dist); else @@ -1757,11 +1790,12 @@ static int task_numa_migrate(struct task_struct *p) .best_imp = 0, .best_cpu = -1, }; + unsigned long taskweight, groupweight; struct sched_domain *sd; + long taskimp, groupimp; + struct numa_group *ng; struct rq *best_rq; - unsigned long taskweight, groupweight; int nid, ret, dist; - long taskimp, groupimp; /* * Pick the lowest SD_NUMA domain, as that would have the smallest @@ -1807,7 +1841,8 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { + ng = deref_curr_numa_group(p); + if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1840,7 +1875,7 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group) { + if (ng) { if (env.best_cpu == -1) nid = env.src_nid; else @@ -2135,6 +2170,7 @@ static void task_numa_placement(struct task_struct *p) unsigned long total_faults; u64 runtime, period; spinlock_t *group_lock = NULL; + struct numa_group *ng; /* * The p->mm->numa_scan_seq field gets updated without @@ -2152,8 +2188,9 @@ static void task_numa_placement(struct task_struct *p) runtime = numa_get_avg_runtime(p, &period); /* If the task is part of a group prevent parallel updates to group stats */ - if (p->numa_group) { - group_lock = &p->numa_group->lock; + ng = deref_curr_numa_group(p); + if (ng) { + group_lock = &ng->lock; spin_lock_irq(group_lock); } @@ -2194,7 +2231,7 @@ static void task_numa_placement(struct task_struct *p) p->numa_faults[cpu_idx] += f_diff; faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; - if (p->numa_group) { + if (ng) { /* * safe because we can only change our own group * @@ -2202,14 +2239,14 @@ static void task_numa_placement(struct task_struct *p) * nid and priv in a specific region because it * is at the beginning of the numa_faults array. */ - p->numa_group->faults[mem_idx] += diff; - p->numa_group->faults_cpu[mem_idx] += f_diff; - p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[mem_idx]; + ng->faults[mem_idx] += diff; + ng->faults_cpu[mem_idx] += f_diff; + ng->total_faults += diff; + group_faults += ng->faults[mem_idx]; } } - if (!p->numa_group) { + if (!ng) { if (faults > max_faults) { max_faults = faults; max_nid = nid; @@ -2220,8 +2257,8 @@ static void task_numa_placement(struct task_struct *p) } } - if (p->numa_group) { - numa_group_count_active_nodes(p->numa_group); + if (ng) { + numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_nid); } @@ -2255,7 +2292,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, int cpu = cpupid_to_cpu(cpupid); int i; - if (unlikely(!p->numa_group)) { + if (unlikely(!deref_curr_numa_group(p))) { unsigned int size = sizeof(struct numa_group) + 4*nr_node_ids*sizeof(unsigned long); @@ -2291,7 +2328,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!grp) goto no_join; - my_grp = p->numa_group; + my_grp = deref_curr_numa_group(p); if (grp == my_grp) goto no_join; @@ -2353,13 +2390,24 @@ no_join: return; } -void task_numa_free(struct task_struct *p) +/* + * Get rid of NUMA staticstics associated with a task (either current or dead). + * If @final is set, the task is dead and has reached refcount zero, so we can + * safely free all relevant data structures. Otherwise, there might be + * concurrent reads from places like load balancing and procfs, and we should + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) { - struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults; + /* safe: p either is current or is being freed by current */ + struct numa_group *grp = rcu_dereference_raw(p->numa_group); + unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; + if (!numa_faults) + return; + if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) @@ -2372,8 +2420,14 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - kfree(numa_faults); + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } } /* @@ -2426,7 +2480,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - ng = p->numa_group; + ng = deref_curr_numa_group(p); if (!priv && !local && ng && ng->active_nodes > 1 && numa_is_active_node(cpu_node, ng) && numa_is_active_node(mem_node, ng)) @@ -10444,18 +10498,22 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m) { int node; unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + struct numa_group *ng; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); for_each_online_node(node) { if (p->numa_faults) { tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; } - if (p->numa_group) { - gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], - gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + if (ng) { + gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; } print_numa_stats(m, node, tsf, tpf, gsf, gpf); } + rcu_read_unlock(); } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/signal.c b/kernel/signal.c index 91b789dd6e72..e667be6907d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -349,7 +349,7 @@ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. * Group stop states are cleared and the group stop count is consumed if * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group - * stop, the appropriate %SIGNAL_* flags are set. + * stop, the appropriate `SIGNAL_*` flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. @@ -1885,6 +1885,7 @@ static void do_notify_pidfd(struct task_struct *task) { struct pid *pid; + WARN_ON(task->exit_state == 0); pid = task_pid(task); wake_up_all(&pid->wait_pidfd); } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 69ebf3c2f1b5..78af97163147 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -137,6 +137,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) return 0; + /* + * Do not trace a function if it's filtered by set_graph_notrace. + * Make the index of ret stack negative to indicate that it should + * ignore further functions. But it needs its own ret stack entry + * to recover the original index in order to continue tracing after + * returning from the function. + */ if (ftrace_graph_notrace_addr(trace->func)) { trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT); /* @@ -156,16 +163,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return 0; /* - * Do not trace a function if it's filtered by set_graph_notrace. - * Make the index of ret stack negative to indicate that it should - * ignore further functions. But it needs its own ret stack entry - * to recover the original index in order to continue tracing after - * returning from the function. - */ - if (ftrace_graph_notrace_addr(trace->func)) - return 1; - - /* * Stop here if tracing_threshold is set. We only write function return * events to the ring buffer. */ diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 4fafba1a923b..7fa97a8b5717 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -106,7 +106,6 @@ endchoice config KASAN_STACK_ENABLE bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST - default !(CLANG_VERSION < 90000) depends on KASAN help The LLVM stack address sanitizer has a know problem that @@ -115,11 +114,11 @@ config KASAN_STACK_ENABLE Disabling asan-stack makes it safe to run kernels build with clang-8 with KASAN enabled, though it loses some of the functionality. - This feature is always disabled when compile-testing with clang-8 - or earlier to avoid cluttering the output in stack overflow - warnings, but clang-8 users can still enable it for builds without - CONFIG_COMPILE_TEST. On gcc and later clang versions it is - assumed to always be safe to use and enabled by default. + This feature is always disabled when compile-testing with clang + to avoid cluttering the output in stack overflow warnings, + but clang users can still enable it for builds without + CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe + to use and enabled by default. config KASAN_STACK int diff --git a/lib/Makefile b/lib/Makefile index 095601ce371d..29c02a924973 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -279,7 +279,8 @@ obj-$(CONFIG_UCS2_STRING) += ucs2_string.o obj-$(CONFIG_UBSAN) += ubsan.o UBSAN_SANITIZE_ubsan.o := n -CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +KASAN_SANITIZE_ubsan.o := n +CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN) obj-$(CONFIG_SBITMAP) += sbitmap.o diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 439d641ec796..38045d6d0538 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -74,8 +74,8 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, delta_us); curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us); if (curr_stats->epms != 0) - curr_stats->cpe_ratio = - (curr_stats->cpms * 100) / curr_stats->epms; + curr_stats->cpe_ratio = DIV_ROUND_DOWN_ULL( + curr_stats->cpms * 100, curr_stats->epms); else curr_stats->cpe_ratio = 0; diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 5bcc902c5388..a4db51c21266 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -5,6 +5,62 @@ #include <linux/dim.h> +/* + * Net DIM profiles: + * There are different set of profiles for each CQ period mode. + * There are different set of profiles for RX/TX CQs. + * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES + */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + +#define NET_DIM_RX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ +} + +#define NET_DIM_RX_CQE_PROFILES { \ + {2, 256}, \ + {8, 128}, \ + {16, 64}, \ + {32, 64}, \ + {64, 64} \ +} + +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + +static const struct dim_cq_moder +rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, +}; + +static const struct dim_cq_moder +tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, +}; + struct dim_cq_moder net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 42695bc8d451..0083b5cc646c 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -66,7 +66,7 @@ CFLAGS_vpermxor1.o += $(altivec_flags) CFLAGS_vpermxor2.o += $(altivec_flags) CFLAGS_vpermxor4.o += $(altivec_flags) CFLAGS_vpermxor8.o += $(altivec_flags) -targets += vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o +targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 83ea6c4e623c..6ca97a63b3d6 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -886,8 +886,11 @@ static int __init test_firmware_init(void) return -ENOMEM; rc = __test_firmware_config_init(); - if (rc) + if (rc) { + kfree(test_fw_config); + pr_err("could not init firmware test config: %d\n", rc); return rc; + } rc = misc_register(&test_fw_misc_device); if (rc) { diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 62d19f270cad..9729f271d150 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -222,7 +222,7 @@ static int __init do_kmem_cache_size(size_t size, bool want_ctor, * Copy the buffer to check that it's not wiped on * free(). */ - buf_copy = kmalloc(size, GFP_KERNEL); + buf_copy = kmalloc(size, GFP_ATOMIC); if (buf_copy) memcpy(buf_copy, buf, size); diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 2d1c1f241fd9..e630e7ff57f1 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -51,7 +51,7 @@ static int do_hres(const struct vdso_data *vd, clockid_t clk, ns = vdso_ts->nsec; last = vd->cycle_last; if (unlikely((s64)cycles < 0)) - return clock_gettime_fallback(clk, ts); + return -1; ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult); ns >>= vd->shift; @@ -82,14 +82,14 @@ static void do_coarse(const struct vdso_data *vd, clockid_t clk, } static __maybe_unused int -__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +__cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts) { const struct vdso_data *vd = __arch_get_vdso_data(); u32 msk; /* Check for negative values or invalid clocks */ if (unlikely((u32) clock >= MAX_CLOCKS)) - goto fallback; + return -1; /* * Convert the clockid to a bitmask and use it to check which @@ -104,9 +104,17 @@ __cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) } else if (msk & VDSO_RAW) { return do_hres(&vd[CS_RAW], clock, ts); } + return -1; +} + +static __maybe_unused int +__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + int ret = __cvdso_clock_gettime_common(clock, ts); -fallback: - return clock_gettime_fallback(clock, ts); + if (unlikely(ret)) + return clock_gettime_fallback(clock, ts); + return 0; } static __maybe_unused int @@ -115,20 +123,21 @@ __cvdso_clock_gettime32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - if (res == NULL) - goto fallback; + ret = __cvdso_clock_gettime_common(clock, &ts); - ret = __cvdso_clock_gettime(clock, &ts); +#ifdef VDSO_HAS_32BIT_FALLBACK + if (unlikely(ret)) + return clock_gettime32_fallback(clock, res); +#else + if (unlikely(ret)) + ret = clock_gettime_fallback(clock, &ts); +#endif - if (ret == 0) { + if (likely(!ret)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } - return ret; - -fallback: - return clock_gettime_fallback(clock, (struct __kernel_timespec *)res); } static __maybe_unused int @@ -169,17 +178,18 @@ static __maybe_unused time_t __cvdso_time(time_t *time) #ifdef VDSO_HAS_CLOCK_GETRES static __maybe_unused -int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) +int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res) { const struct vdso_data *vd = __arch_get_vdso_data(); - u64 ns; + u64 hrtimer_res; u32 msk; - u64 hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); + u64 ns; /* Check for negative values or invalid clocks */ if (unlikely((u32) clock >= MAX_CLOCKS)) - goto fallback; + return -1; + hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res); /* * Convert the clockid to a bitmask and use it to check which * clocks are handled in the VDSO directly. @@ -201,18 +211,22 @@ int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) */ ns = hrtimer_res; } else { - goto fallback; + return -1; } - if (res) { - res->tv_sec = 0; - res->tv_nsec = ns; - } + res->tv_sec = 0; + res->tv_nsec = ns; return 0; +} + +int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res) +{ + int ret = __cvdso_clock_getres_common(clock, res); -fallback: - return clock_getres_fallback(clock, res); + if (unlikely(ret)) + return clock_getres_fallback(clock, res); + return 0; } static __maybe_unused int @@ -221,19 +235,20 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res) struct __kernel_timespec ts; int ret; - if (res == NULL) - goto fallback; + ret = __cvdso_clock_getres_common(clock, &ts); - ret = __cvdso_clock_getres(clock, &ts); +#ifdef VDSO_HAS_32BIT_FALLBACK + if (unlikely(ret)) + return clock_getres32_fallback(clock, res); +#else + if (unlikely(ret)) + ret = clock_getres_fallback(clock, &ts); +#endif - if (ret == 0) { + if (likely(!ret)) { res->tv_sec = ts.tv_sec; res->tv_nsec = ts.tv_nsec; } - return ret; - -fallback: - return clock_getres_fallback(clock, (struct __kernel_timespec *)res); } #endif /* VDSO_HAS_CLOCK_GETRES */ diff --git a/mm/Makefile b/mm/Makefile index 338e528ad436..d0b295c3b764 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,6 @@ obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 83a7b614061f..798275a51887 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -21,7 +21,6 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * memory corruption is possible and we should stop execution. */ BUG_ON(!trylock_page(page)); - list_del(&page->lru); balloon_page_insert(b_dev_info, page); unlock_page(page); __count_vm_event(BALLOON_INFLATE); @@ -33,8 +32,8 @@ static void balloon_page_enqueue_one(struct balloon_dev_info *b_dev_info, * @b_dev_info: balloon device descriptor where we will insert a new page to * @pages: pages to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a balloon pages before definitively - * removing it from the guest system. + * Driver must call this function to properly enqueue balloon pages before + * definitively removing them from the guest system. * * Return: number of pages that were enqueued. */ @@ -47,6 +46,7 @@ size_t balloon_page_list_enqueue(struct balloon_dev_info *b_dev_info, spin_lock_irqsave(&b_dev_info->pages_lock, flags); list_for_each_entry_safe(page, tmp, pages, lru) { + list_del(&page->lru); balloon_page_enqueue_one(b_dev_info, page); n_pages++; } @@ -63,12 +63,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_enqueue); * @n_req_pages: number of requested pages. * * Driver must call this function to properly de-allocate a previous enlisted - * balloon pages before definetively releasing it back to the guest system. + * balloon pages before definitively releasing it back to the guest system. * This function tries to remove @n_req_pages from the ballooned pages and * return them to the caller in the @pages list. * - * Note that this function may fail to dequeue some pages temporarily empty due - * to compaction isolated pages. + * Note that this function may fail to dequeue some pages even if the balloon + * isn't empty - since the page list can be temporarily empty due to compaction + * of isolated pages. * * Return: number of pages that were added to the @pages list. */ @@ -112,12 +113,13 @@ EXPORT_SYMBOL_GPL(balloon_page_list_dequeue); /* * balloon_page_alloc - allocates a new page for insertion into the balloon - * page list. + * page list. + * + * Driver must call this function to properly allocate a new balloon page. + * Driver must call balloon_page_enqueue before definitively removing the page + * from the guest system. * - * Driver must call it to properly allocate a new enlisted balloon page. - * Driver must call balloon_page_enqueue before definitively removing it from - * the guest system. This function returns the page address for the recently - * allocated page or NULL in the case we fail to allocate a new page this turn. + * Return: struct page for the allocated page or NULL on allocation failure. */ struct page *balloon_page_alloc(void) { @@ -128,15 +130,17 @@ struct page *balloon_page_alloc(void) EXPORT_SYMBOL_GPL(balloon_page_alloc); /* - * balloon_page_enqueue - allocates a new page and inserts it into the balloon - * page list. - * @b_dev_info: balloon device descriptor where we will insert a new page to + * balloon_page_enqueue - inserts a new page into the balloon page list. + * + * @b_dev_info: balloon device descriptor where we will insert a new page * @page: new page to enqueue - allocated using balloon_page_alloc. * - * Driver must call it to properly enqueue a new allocated balloon page - * before definitively removing it from the guest system. - * This function returns the page address for the recently enqueued page or - * NULL in the case we fail to allocate a new page this turn. + * Drivers must call this function to properly enqueue a new allocated balloon + * page before definitively removing the page from the guest system. + * + * Drivers must not call balloon_page_enqueue on pages that have been pushed to + * a list with balloon_page_push before removing them with balloon_page_pop. To + * enqueue a list of pages, use balloon_page_list_enqueue instead. */ void balloon_page_enqueue(struct balloon_dev_info *b_dev_info, struct page *page) @@ -151,14 +155,23 @@ EXPORT_SYMBOL_GPL(balloon_page_enqueue); /* * balloon_page_dequeue - removes a page from balloon's page list and returns - * the its address to allow the driver release the page. + * its address to allow the driver to release the page. * @b_dev_info: balloon device decriptor where we will grab a page from. * - * Driver must call it to properly de-allocate a previous enlisted balloon page - * before definetively releasing it back to the guest system. - * This function returns the page address for the recently dequeued page or - * NULL in the case we find balloon's page list temporarily empty due to - * compaction isolated pages. + * Driver must call this function to properly dequeue a previously enqueued page + * before definitively releasing it back to the guest system. + * + * Caller must perform its own accounting to ensure that this + * function is called only if some pages are actually enqueued. + * + * Note that this function may fail to dequeue some pages even if there are + * some enqueued pages - since the page list can be temporarily empty due to + * the compaction of isolated pages. + * + * TODO: remove the caller accounting requirements, and allow caller to wait + * until all pages can be dequeued. + * + * Return: struct page for the dequeued page, or NULL if no page was dequeued. */ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) { @@ -171,9 +184,9 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) if (n_pages != 1) { /* * If we are unable to dequeue a balloon page because the page - * list is empty and there is no isolated pages, then something + * list is empty and there are no isolated pages, then something * went out of track and some balloon pages are lost. - * BUG() here, otherwise the balloon driver may get stuck into + * BUG() here, otherwise the balloon driver may get stuck in * an infinite loop while attempting to release all its pages. */ spin_lock_irqsave(&b_dev_info->pages_lock, flags); @@ -224,8 +237,8 @@ int balloon_page_migrate(struct address_space *mapping, /* * We can not easily support the no copy case here so ignore it as it - * is unlikely to be use with ballon pages. See include/linux/hmm.h for - * user of the MIGRATE_SYNC_NO_COPY mode. + * is unlikely to be used with balloon pages. See include/linux/hmm.h + * for a user of the MIGRATE_SYNC_NO_COPY mode. */ if (mode == MIGRATE_SYNC_NO_COPY) return -EINVAL; diff --git a/mm/compaction.c b/mm/compaction.c index 9e1b9acb116b..952dc2fb24e5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -842,13 +842,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Periodically drop the lock (if held) regardless of its - * contention, to give chance to IRQs. Abort async compaction - * if contended. + * contention, to give chance to IRQs. Abort completely if + * a fatal signal is pending. */ if (!(low_pfn % SWAP_CLUSTER_MAX) && compact_unlock_should_abort(&pgdat->lru_lock, - flags, &locked, cc)) - break; + flags, &locked, cc)) { + low_pfn = 0; + goto fatal_pending; + } if (!pfn_valid_within(low_pfn)) goto isolate_fail; @@ -1060,6 +1062,7 @@ isolate_abort: trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); +fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); @@ -946,7 +946,7 @@ EXPORT_SYMBOL(hmm_range_unregister); * @range: range * Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid * permission (for instance asking for write and range is read only), - * -EAGAIN if you need to retry, -EFAULT invalid (ie either no valid + * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid * vma or it is illegal to access that range), number of valid pages * in range->pfns[] (from range start address). * @@ -967,7 +967,7 @@ long hmm_range_snapshot(struct hmm_range *range) do { /* If range is no longer valid force retry. */ if (!range->valid) - return -EAGAIN; + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) @@ -1062,10 +1062,8 @@ long hmm_range_fault(struct hmm_range *range, bool block) do { /* If range is no longer valid force retry. */ - if (!range->valid) { - up_read(&hmm->mm->mmap_sem); - return -EAGAIN; - } + if (!range->valid) + return -EBUSY; vma = find_vma(hmm->mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dbbd518fb6b3..6e9e8cca663e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -114,7 +114,7 @@ /* GFP bitmask for kmemleak internal allocations */ #define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN | __GFP_NOFAIL) + __GFP_NOWARN) /* scanning area inside a memory block */ struct kmemleak_scan_area { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a9bbddb0e55..c73f09913165 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -132,7 +132,6 @@ static void release_memory_resource(struct resource *res) return; release_resource(res); kfree(res); - return; } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE @@ -979,7 +978,6 @@ static void rollback_node_hotadd(int nid) arch_refresh_nodedata(nid, NULL); free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); - return; } diff --git a/kernel/memremap.c b/mm/memremap.c index 6ee03a816d67..6ee03a816d67 100644 --- a/kernel/memremap.c +++ b/mm/memremap.c diff --git a/mm/migrate.c b/mm/migrate.c index 8992741f10aa..a42858d8e00b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -767,12 +767,12 @@ recheck_buffers: } bh = bh->b_this_page; } while (bh != head); - spin_unlock(&mapping->private_lock); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } + spin_unlock(&mapping->private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -805,6 +805,8 @@ recheck_buffers: rc = MIGRATEPAGE_SUCCESS; unlock_buffers: + if (check_refs) + spin_unlock(&mapping->private_lock); bh = head; do { unlock_buffer(bh); @@ -2338,16 +2340,13 @@ next: static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk; - - mm_walk.pmd_entry = migrate_vma_collect_pmd; - mm_walk.pte_entry = NULL; - mm_walk.pte_hole = migrate_vma_collect_hole; - mm_walk.hugetlb_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.vma = migrate->vma; - mm_walk.mm = migrate->vma->vm_mm; - mm_walk.private = migrate; + struct mm_walk mm_walk = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, + .vma = migrate->vma, + .mm = migrate->vma->vm_mm, + .private = migrate, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, migrate->start, diff --git a/mm/slub.c b/mm/slub.c index e6c030e47364..8834563cdb4b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1432,7 +1432,9 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) + if (slab_want_init_on_free(s)) { + void *p = NULL; + do { object = next; next = get_freepointer(s, object); @@ -1445,8 +1447,10 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, next); + set_freepointer(s, object, p); + p = object; } while (object != old_tail); + } /* * Compiler cannot detect this function can be removed if slab_free_hook() diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4fa8d84599b0..e0fc963acc41 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1259,6 +1259,12 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) return false; /* + * First make sure the mappings are removed from all page-tables + * before they are freed. + */ + vmalloc_sync_all(); + + /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. */ @@ -3038,6 +3044,9 @@ EXPORT_SYMBOL(remap_vmalloc_range); /* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. + * + * The purpose of this function is to make sure the vmalloc area + * mappings are identical in all page-tables in the system. */ void __weak vmalloc_sync_all(void) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 44df66a98f2a..dbdc46a84f63 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -699,7 +699,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, unsigned long ret, freed = 0; struct shrinker *shrinker; - if (!mem_cgroup_is_root(memcg)) + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 22672cb3e25d..64054edc2e3c 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -79,6 +79,7 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface) static void batadv_v_iface_disable(struct batadv_hard_iface *hard_iface) { + batadv_v_ogm_iface_disable(hard_iface); batadv_v_elp_iface_disable(hard_iface); } @@ -1081,6 +1082,12 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface) */ atomic_set(&hard_iface->bat_v.throughput_override, 0); atomic_set(&hard_iface->bat_v.elp_interval, 500); + + hard_iface->bat_v.aggr_len = 0; + skb_queue_head_init(&hard_iface->bat_v.aggr_list); + spin_lock_init(&hard_iface->bat_v.aggr_list_lock); + INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq, + batadv_v_ogm_aggr_work); } /** diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index fad95ef64e01..319249f0f85f 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -17,12 +17,14 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -77,6 +79,20 @@ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, } /** + * batadv_v_ogm_start_queue_timer() - restart the OGM aggregation timer + * @hard_iface: the interface to use to send the OGM + */ +static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface) +{ + unsigned int msecs = BATADV_MAX_AGGREGATION_MS * 1000; + + /* msecs * [0.9, 1.1] */ + msecs += prandom_u32() % (msecs / 5) - (msecs / 10); + queue_delayed_work(batadv_event_workqueue, &hard_iface->bat_v.aggr_wq, + msecs_to_jiffies(msecs / 1000)); +} + +/** * batadv_v_ogm_start_timer() - restart the OGM sending timer * @bat_priv: the bat priv with all the soft interface information */ @@ -116,6 +132,130 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, } /** + * batadv_v_ogm_len() - OGMv2 packet length + * @skb: the OGM to check + * + * Return: Length of the given OGMv2 packet, including tvlv length, excluding + * ethernet header length. + */ +static unsigned int batadv_v_ogm_len(struct sk_buff *skb) +{ + struct batadv_ogm2_packet *ogm_packet; + + ogm_packet = (struct batadv_ogm2_packet *)skb->data; + return BATADV_OGM2_HLEN + ntohs(ogm_packet->tvlv_len); +} + +/** + * batadv_v_ogm_queue_left() - check if given OGM still fits aggregation queue + * @skb: the OGM to check + * @hard_iface: the interface to use to send the OGM + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + * + * Return: True, if the given OGMv2 packet still fits, false otherwise. + */ +static bool batadv_v_ogm_queue_left(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + unsigned int max = min_t(unsigned int, hard_iface->net_dev->mtu, + BATADV_MAX_AGGREGATION_BYTES); + unsigned int ogm_len = batadv_v_ogm_len(skb); + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + return hard_iface->bat_v.aggr_len + ogm_len <= max; +} + +/** + * batadv_v_ogm_aggr_list_free - free all elements in an aggregation queue + * @hard_iface: the interface holding the aggregation queue + * + * Empties the OGMv2 aggregation queue and frees all the skbs it contained. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) +{ + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) + kfree_skb(skb); + + hard_iface->bat_v.aggr_len = 0; +} + +/** + * batadv_v_ogm_aggr_send() - flush & send aggregation queue + * @hard_iface: the interface with the aggregation queue to flush + * + * Aggregates all OGMv2 packets currently in the aggregation queue into a + * single OGMv2 packet and transmits this aggregate. + * + * The aggregation queue is empty after this call. + * + * Caller needs to hold the hard_iface->bat_v.aggr_list_lock. + */ +static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) +{ + unsigned int aggr_len = hard_iface->bat_v.aggr_len; + struct sk_buff *skb_aggr; + unsigned int ogm_len; + struct sk_buff *skb; + + lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock); + + if (!aggr_len) + return; + + skb_aggr = dev_alloc_skb(aggr_len + ETH_HLEN + NET_IP_ALIGN); + if (!skb_aggr) { + batadv_v_ogm_aggr_list_free(hard_iface); + return; + } + + skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN); + skb_reset_network_header(skb_aggr); + + while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) { + hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb); + + ogm_len = batadv_v_ogm_len(skb); + skb_put_data(skb_aggr, skb->data, ogm_len); + + consume_skb(skb); + } + + batadv_v_ogm_send_to_if(skb_aggr, hard_iface); +} + +/** + * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface + * @skb: the OGM to queue + * @hard_iface: the interface to queue the OGM on + */ +static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, + struct batadv_hard_iface *hard_iface) +{ + struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + + if (!atomic_read(&bat_priv->aggregated_ogms)) { + batadv_v_ogm_send_to_if(skb, hard_iface); + return; + } + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + if (!batadv_v_ogm_queue_left(skb, hard_iface)) + batadv_v_ogm_aggr_send(hard_iface); + + hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); + skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_send() - periodic worker broadcasting the own OGM * @work: work queue item */ @@ -210,7 +350,7 @@ static void batadv_v_ogm_send(struct work_struct *work) break; } - batadv_v_ogm_send_to_if(skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -224,6 +364,27 @@ out: } /** + * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface + * @work: work queue item + * + * Emits aggregated OGM message in regular intervals. + */ +void batadv_v_ogm_aggr_work(struct work_struct *work) +{ + struct batadv_hard_iface_bat_v *batv; + struct batadv_hard_iface *hard_iface; + + batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); + hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_send(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); + + batadv_v_ogm_start_queue_timer(hard_iface); +} + +/** * batadv_v_ogm_iface_enable() - prepare an interface for B.A.T.M.A.N. V * @hard_iface: the interface to prepare * @@ -235,12 +396,26 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); + batadv_v_ogm_start_queue_timer(hard_iface); batadv_v_ogm_start_timer(bat_priv); return 0; } /** + * batadv_v_ogm_iface_disable() - release OGM interface private resources + * @hard_iface: interface for which the resources have to be released + */ +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface) +{ + cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq); + + spin_lock_bh(&hard_iface->bat_v.aggr_list_lock); + batadv_v_ogm_aggr_list_free(hard_iface); + spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock); +} + +/** * batadv_v_ogm_primary_iface_set() - set a new primary interface * @primary_iface: the new primary interface */ @@ -382,7 +557,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_send_to_if(skb, if_outgoing); + batadv_v_ogm_queue_on_if(skb, if_outgoing); out: if (orig_ifinfo) diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index 2a50df7fc2bf..bf16d040461d 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -11,10 +11,13 @@ #include <linux/skbuff.h> #include <linux/types.h> +#include <linux/workqueue.h> int batadv_v_ogm_init(struct batadv_priv *bat_priv); void batadv_v_ogm_free(struct batadv_priv *bat_priv); +void batadv_v_ogm_aggr_work(struct work_struct *work); int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface); +void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface); struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr); void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 3d4c04d87ff3..6967f2e4c3f4 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.3" +#define BATADV_SOURCE_VERSION "2019.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c7a2e77ca1da..a1146cb10919 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -943,10 +943,10 @@ static const struct net_device_ops batadv_netdev_ops = { static void batadv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); - strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); - strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); - strlcpy(info->bus_info, "batman", sizeof(info->bus_info)); + strscpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); + strscpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); + strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strscpy(info->bus_info, "batman", sizeof(info->bus_info)); } /* Inspired by drivers/net/ethernet/dlink/sundance.c:1702 diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 1efcb97039cd..e5bbc28ed12c 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1070,7 +1070,7 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj, dev_hold(net_dev); INIT_WORK(&store_work->work, batadv_store_mesh_iface_work); store_work->net_dev = net_dev; - strlcpy(store_work->soft_iface_name, buff, + strscpy(store_work->soft_iface_name, buff, sizeof(store_work->soft_iface_name)); queue_work(batadv_event_workqueue, &store_work->work); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 6ae139d74e0f..be7c02aa91e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -117,6 +117,18 @@ struct batadv_hard_iface_bat_v { /** @elp_wq: workqueue used to schedule ELP transmissions */ struct delayed_work elp_wq; + /** @aggr_wq: workqueue used to transmit queued OGM packets */ + struct delayed_work aggr_wq; + + /** @aggr_list: queue for to be aggregated OGM packets */ + struct sk_buff_head aggr_list; + + /** @aggr_len: size of the OGM aggregate (excluding ethernet header) */ + unsigned int aggr_len; + + /** @aggr_list_lock: protects aggr_list */ + spinlock_t aggr_list_lock; + /** * @throughput_override: throughput override to disable link * auto-detection diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 80e6f3a6864d..1153bbcdff72 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -377,6 +377,22 @@ out: return ret; } +static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) +{ + /* make sure the fields we don't use are zeroed */ + if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags))) + return -EINVAL; + + /* flags is allowed */ + + if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + + FIELD_SIZEOF(struct bpf_flow_keys, flags), + sizeof(struct bpf_flow_keys))) + return -EINVAL; + + return 0; +} + int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) @@ -384,9 +400,11 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; + struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; u64 time_start, time_spent = 0; const struct ethhdr *eth; + unsigned int flags = 0; u32 retval, duration; void *data; int ret; @@ -395,9 +413,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; - if (kattr->test.ctx_in || kattr->test.ctx_out) - return -EINVAL; - if (size < ETH_HLEN) return -EINVAL; @@ -410,6 +425,18 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (!repeat) repeat = 1; + user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys)); + if (IS_ERR(user_ctx)) { + kfree(data); + return PTR_ERR(user_ctx); + } + if (user_ctx) { + ret = verify_user_bpf_flow_keys(user_ctx); + if (ret) + goto out; + flags = user_ctx->flags; + } + ctx.flow_keys = &flow_keys; ctx.data = data; ctx.data_end = (__u8 *)data + size; @@ -419,7 +446,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, - size); + size, flags); if (signal_pending(current)) { preempt_enable(); @@ -450,8 +477,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), retval, duration); + if (!ret) + ret = bpf_ctx_finish(kattr, uattr, user_ctx, + sizeof(struct bpf_flow_keys)); out: + kfree(user_ctx); kfree(data); return ret; } diff --git a/net/bridge/br.c b/net/bridge/br.c index d164f63a4345..8a8f9e5f264f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v int err; if (dev->priv_flags & IFF_EBRIDGE) { + err = br_vlan_bridge_event(dev, event, ptr); + if (err) + return notifier_from_errno(err); + if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ br_sysfs_addbr(dev); return NOTIFY_DONE; } - br_vlan_bridge_event(dev, event, ptr); } /* not a port of a bridge */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3d4b2817687f..9b379e110129 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1388,6 +1388,9 @@ br_multicast_leave_group(struct net_bridge *br, if (!br_port_group_equal(p, port, src)) continue; + if (p->flags & MDB_PG_FLAGS_PERMANENT) + break; + rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index c4fd307fbfdc..b7a4942ff1b3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -895,8 +895,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); void br_vlan_get_stats(const struct net_bridge_vlan *v, struct br_vlan_stats *stats); void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr); +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, + void *ptr); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -1086,9 +1086,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p, { } -static inline void br_vlan_bridge_event(struct net_device *dev, - unsigned long event, void *ptr) +static inline int br_vlan_bridge_event(struct net_device *dev, + unsigned long event, void *ptr) { + return 0; } #endif diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 021cc9f66804..f5b2aeebbfe9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1053,7 +1053,6 @@ int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; - bool changed; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) @@ -1068,17 +1067,10 @@ int br_vlan_init(struct net_bridge *br) br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); - ret = br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); - if (ret) - goto err_vlan_add; out: return ret; -err_vlan_add: - vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: @@ -1464,13 +1456,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) } /* Must be protected by RTNL. */ -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr) +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; - struct net_bridge *br; + struct net_bridge *br = netdev_priv(dev); + bool changed; + int ret = 0; switch (event) { + case NETDEV_REGISTER: + ret = br_vlan_add(br, br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + break; + case NETDEV_UNREGISTER: + br_vlan_delete(br, br->default_pvid); + break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); @@ -1478,12 +1480,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event, case NETDEV_CHANGE: case NETDEV_UP: - br = netdev_priv(dev); if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) - return; + break; br_vlan_link_state_change(dev, br); break; } + + return ret; } /* Must be protected by RTNL. */ diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 963dfdc14827..c8177a89f52c 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1770,20 +1770,28 @@ static int compat_calc_entry(const struct ebt_entry *e, return 0; } +static int ebt_compat_init_offsets(unsigned int number) +{ + if (number > INT_MAX) + return -EINVAL; + + /* also count the base chain policies */ + number += NF_BR_NUMHOOKS; + + return xt_compat_init_offsets(NFPROTO_BRIDGE, number); +} static int compat_table_info(const struct ebt_table_info *info, struct compat_ebt_replace *newinfo) { unsigned int size = info->entries_size; const void *entries = info->entries; + int ret; newinfo->entries_size = size; - if (info->nentries) { - int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, - info->nentries); - if (ret) - return ret; - } + ret = ebt_compat_init_offsets(info->nentries); + if (ret) + return ret; return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); @@ -2234,11 +2242,9 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - if (tmp.nentries) { - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; - } + ret = ebt_compat_init_offsets(tmp.nentries); + if (ret < 0) + goto out_unlock; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) @@ -2261,8 +2267,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + } vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bed66f536b34..1804e867f715 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -30,13 +30,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); - if (!br_dev) - goto err; break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); - if (!br_dev) - goto err; break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; @@ -61,13 +57,11 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, return; } default: - goto out; + return nft_meta_get_eval(expr, regs, pkt); } - strncpy((char *)dest, br_dev->name, IFNAMSIZ); + strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; -out: - return nft_meta_get_eval(expr, regs, pkt); err: regs->verdict.code = NFT_BREAK; } diff --git a/net/can/gw.c b/net/can/gw.c index 8abae841d504..ce17f836262b 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1047,32 +1047,50 @@ static __init int cgw_module_init(void) pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", max_hops); - register_pernet_subsys(&cangw_pernet_ops); + ret = register_pernet_subsys(&cangw_pernet_ops); + if (ret) + return ret; + + ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); - if (!cgw_cache) - return -ENOMEM; + goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; - register_netdevice_notifier(¬ifier); + ret = register_netdevice_notifier(¬ifier); + if (ret) + goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); - if (ret) { - unregister_netdevice_notifier(¬ifier); - kmem_cache_destroy(cgw_cache); - return -ENOBUFS; - } - - /* Only the first call to rtnl_register_module can fail */ - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, - cgw_create_job, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, - cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register1; + + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, + cgw_create_job, NULL, 0); + if (ret) + goto out_rtnl_register2; + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, + cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register3; return 0; + +out_rtnl_register3: + rtnl_unregister(PF_CAN, RTM_NEWROUTE); +out_rtnl_register2: + rtnl_unregister(PF_CAN, RTM_GETROUTE); +out_rtnl_register1: + unregister_netdevice_notifier(¬ifier); +out_register_notifier: + kmem_cache_destroy(cgw_cache); +out_cache_create: + unregister_pernet_subsys(&cangw_pernet_ops); + + return ret; } static __exit void cgw_module_exit(void) diff --git a/net/core/dev.c b/net/core/dev.c index e2a11c62197b..49589ed2018d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3963,6 +3963,8 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4374,12 +4376,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, act = bpf_prog_run_xdp(xdp_prog, xdp); + /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; - if (off > 0) - __skb_pull(skb, off); - else if (off < 0) - __skb_push(skb, -off); - skb->mac_header += off; + if (off) { + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + skb->mac_header += off; + skb_reset_network_header(skb); + } /* check if bpf_xdp_adjust_tail was used. it can only "shrink" * pckt. @@ -5742,6 +5749,26 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -5751,8 +5778,8 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, case GRO_HELD: __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) - ret = GRO_DROP; + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -6029,6 +6056,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + gro_normal_list(n); + if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6114,10 +6143,19 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + /* We can't gro_normal_list() here, because napi->poll() might have + * rearmed the napi (napi_complete_done()) in which case it could + * already be running on another CPU. + */ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) + if (rc == BUSY_POLL_BUDGET) { + /* As the whole budget was spent, we still own the napi so can + * safely handle the rx_list. + */ + gro_normal_list(napi); __napi_schedule(napi); + } local_bh_enable(); } @@ -6162,6 +6200,7 @@ restart: } work = napi_poll(napi, BUSY_POLL_BUDGET); trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6267,6 +6306,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -6363,6 +6404,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + gro_normal_list(n); + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -9701,6 +9744,8 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/devlink.c b/net/core/devlink.c index 4f40aeace902..d3dbb904bf3b 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -342,7 +342,6 @@ struct devlink_snapshot { struct list_head list; struct devlink_region *region; devlink_snapshot_data_dest_t *data_destructor; - u64 data_len; u8 *data; u32 id; }; @@ -371,14 +370,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot) -{ - snapshot->region->cur_snapshots--; - list_del(&snapshot->list); - (*snapshot->data_destructor)(snapshot->data); - kfree(snapshot); -} - #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) @@ -3596,6 +3587,16 @@ out_free_msg: nlmsg_free(msg); } +static void devlink_region_snapshot_del(struct devlink_region *region, + struct devlink_snapshot *snapshot) +{ + devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); + region->cur_snapshots--; + list_del(&snapshot->list); + (*snapshot->data_destructor)(snapshot->data); + kfree(snapshot); +} + static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3691,8 +3692,7 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, if (!snapshot) return -EINVAL; - devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); return 0; } @@ -3748,8 +3748,8 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, if (!snapshot) return -EINVAL; - if (end_offset > snapshot->data_len || dump) - end_offset = snapshot->data_len; + if (end_offset > region->size || dump) + end_offset = region->size; while (curr_offset < end_offset) { u32 data_size; @@ -6744,7 +6744,7 @@ void devlink_region_destroy(struct devlink_region *region) /* Free all snapshots of region */ list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) - devlink_region_snapshot_del(snapshot); + devlink_region_snapshot_del(region, snapshot); list_del(®ion->list); @@ -6784,12 +6784,11 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot - * @data_len: size of snapshot data * @data: snapshot data * @snapshot_id: snapshot id to be created * @data_destructor: pointer to destructor function to free data */ -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor) { @@ -6819,7 +6818,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; - snapshot->data_len = data_len; snapshot->data_destructor = data_destructor; list_add_tail(&snapshot->list, ®ion->snapshot_list); @@ -6941,11 +6939,10 @@ int devlink_compat_switch_id_get(struct net_device *dev, { struct devlink_port *devlink_port; - /* RTNL mutex is held here which ensures that devlink_port - * instance cannot disappear in the middle. No need to take + /* Caller must hold RTNL mutex or reference to dev, which ensures that + * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ - ASSERT_RTNL(); devlink_port = netdev_to_devlink_port(dev); if (!devlink_port || !devlink_port->attrs.switch_port) return -EOPNOTSUPP; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 4ea4347f5062..39e094907391 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -43,13 +43,26 @@ * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_MUTEX(trace_state_mutex); + +/* net_dm_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards the global 'hw_stats_list' list. + */ +static DEFINE_MUTEX(net_dm_mutex); + +struct net_dm_stats { + u64 dropped; + struct u64_stats_sync syncp; +}; struct per_cpu_dm_data { - spinlock_t lock; + spinlock_t lock; /* Protects 'skb' and 'send_timer' */ struct sk_buff *skb; + struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; + struct net_dm_stats stats; }; struct dm_hw_stat_delta { @@ -69,6 +82,24 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); +static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; +static u32 net_dm_trunc_len; +static u32 net_dm_queue_len = 1000; + +struct net_dm_alert_ops { + void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, + void *location); + void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, + int work, int budget); + void (*work_item_func)(struct work_struct *work); +}; + +struct net_dm_skb_cb { + void *pc; +}; + +#define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) + static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; @@ -235,48 +266,330 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, rcu_read_unlock(); } -static int set_all_monitor_traces(int state) +static const struct net_dm_alert_ops net_dm_alert_summary_ops = { + .kfree_skb_probe = trace_kfree_skb_hit, + .napi_poll_probe = trace_napi_poll_hit, + .work_item_func = send_dm_alert, +}; + +static void net_dm_packet_trace_kfree_skb_hit(void *ignore, + struct sk_buff *skb, + void *location) { - int rc = 0; - struct dm_hw_stat_delta *new_stat = NULL; - struct dm_hw_stat_delta *temp; + ktime_t tstamp = ktime_get_real(); + struct per_cpu_dm_data *data; + struct sk_buff *nskb; + unsigned long flags; - mutex_lock(&trace_state_mutex); + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return; - if (state == trace_state) { - rc = -EAGAIN; - goto out_unlock; + NET_DM_SKB_CB(nskb)->pc = location; + /* Override the timestamp because we care about the time when the + * packet was dropped. + */ + nskb->tstamp = tstamp; + + data = this_cpu_ptr(&dm_cpu_data); + + spin_lock_irqsave(&data->drop_queue.lock, flags); + if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) + __skb_queue_tail(&data->drop_queue, nskb); + else + goto unlock_free; + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + schedule_work(&data->dm_alert_work); + + return; + +unlock_free: + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + u64_stats_update_begin(&data->stats.syncp); + data->stats.dropped++; + u64_stats_update_end(&data->stats.syncp); + consume_skb(nskb); +} + +static void net_dm_packet_trace_napi_poll_hit(void *ignore, + struct napi_struct *napi, + int work, int budget) +{ +} + +static size_t net_dm_in_port_size(void) +{ + /* NET_DM_ATTR_IN_PORT nest */ + return nla_total_size(0) + + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ + nla_total_size(sizeof(u32)); +} + +#define NET_DM_MAX_SYMBOL_LEN 40 + +static size_t net_dm_packet_report_size(size_t payload_len) +{ + size_t size; + + size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); + + return NLMSG_ALIGN(size) + + /* NET_DM_ATTR_PC */ + nla_total_size(sizeof(u64)) + + /* NET_DM_ATTR_SYMBOL */ + nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + + /* NET_DM_ATTR_IN_PORT */ + net_dm_in_port_size() + + /* NET_DM_ATTR_TIMESTAMP */ + nla_total_size(sizeof(struct timespec)) + + /* NET_DM_ATTR_ORIG_LEN */ + nla_total_size(sizeof(u32)) + + /* NET_DM_ATTR_PROTO */ + nla_total_size(sizeof(u16)) + + /* NET_DM_ATTR_PAYLOAD */ + nla_total_size(payload_len); +} + +static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); + if (!attr) + return -EMSGSIZE; + + if (ifindex && + nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, + size_t payload_len) +{ + u64 pc = (u64)(uintptr_t) NET_DM_SKB_CB(skb)->pc; + char buf[NET_DM_MAX_SYMBOL_LEN]; + struct nlattr *attr; + struct timespec ts; + void *hdr; + int rc; + + hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, + NET_DM_CMD_PACKET_ALERT); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, pc, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + snprintf(buf, sizeof(buf), "%pS", NET_DM_SKB_CB(skb)->pc); + if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) + goto nla_put_failure; + + rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif); + if (rc) + goto nla_put_failure; + + if (ktime_to_timespec_cond(skb->tstamp, &ts) && + nla_put(msg, NET_DM_ATTR_TIMESTAMP, sizeof(ts), &ts)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) + goto nla_put_failure; + + if (!payload_len) + goto out; + + if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) + goto nla_put_failure; + + attr = skb_put(msg, nla_total_size(payload_len)); + attr->nla_type = NET_DM_ATTR_PAYLOAD; + attr->nla_len = nla_attr_size(payload_len); + if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +#define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) + +static void net_dm_packet_report(struct sk_buff *skb) +{ + struct sk_buff *msg; + size_t payload_len; + int rc; + + /* Make sure we start copying the packet from the MAC header */ + if (skb->data > skb_mac_header(skb)) + skb_push(skb, skb->data - skb_mac_header(skb)); + else + skb_pull(skb, skb_mac_header(skb) - skb->data); + + /* Ensure packet fits inside a single netlink attribute */ + payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); + if (net_dm_trunc_len) + payload_len = min_t(size_t, net_dm_trunc_len, payload_len); + + msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); + if (!msg) + goto out; + + rc = net_dm_packet_report_fill(msg, skb, payload_len); + if (rc) { + nlmsg_free(msg); + goto out; } - switch (state) { - case TRACE_ON: - if (!try_module_get(THIS_MODULE)) { - rc = -ENODEV; - break; - } + genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); - rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); - break; +out: + consume_skb(skb); +} - case TRACE_OFF: - rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); - rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); +static void net_dm_packet_work(struct work_struct *work) +{ + struct per_cpu_dm_data *data; + struct sk_buff_head list; + struct sk_buff *skb; + unsigned long flags; + + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - tracepoint_synchronize_unregister(); + __skb_queue_head_init(&list); - /* - * Clean the device list + spin_lock_irqsave(&data->drop_queue.lock, flags); + skb_queue_splice_tail_init(&data->drop_queue, &list); + spin_unlock_irqrestore(&data->drop_queue.lock, flags); + + while ((skb = __skb_dequeue(&list))) + net_dm_packet_report(skb); +} + +static const struct net_dm_alert_ops net_dm_alert_packet_ops = { + .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, + .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, + .work_item_func = net_dm_packet_work, +}; + +static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { + [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, + [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, +}; + +static int net_dm_trace_on_set(struct netlink_ext_ack *extack) +{ + const struct net_dm_alert_ops *ops; + int cpu, rc; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + if (!try_module_get(THIS_MODULE)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + INIT_WORK(&data->dm_alert_work, ops->work_item_func); + timer_setup(&data->send_timer, sched_send_work, 0); + /* Allocate a new per-CPU skb for the summary alert message and + * free the old one which might contain stale data from + * previous tracing. */ - list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { - if (new_stat->dev == NULL) { - list_del_rcu(&new_stat->list); - kfree_rcu(new_stat, rcu); - } + skb = reset_per_cpu_data(data); + consume_skb(skb); + } + + rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); + goto err_module_put; + } + + rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); + goto err_unregister_trace; + } + + return 0; + +err_unregister_trace: + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); +err_module_put: + module_put(THIS_MODULE); + return rc; +} + +static void net_dm_trace_off_set(void) +{ + struct dm_hw_stat_delta *new_stat, *temp; + const struct net_dm_alert_ops *ops; + int cpu; + + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + + unregister_trace_napi_poll(ops->napi_poll_probe, NULL); + unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); + + tracepoint_synchronize_unregister(); + + /* Make sure we do not send notifications to user space after request + * to stop tracing returns. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + while ((skb = __skb_dequeue(&data->drop_queue))) + consume_skb(skb); + } + + list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { + if (new_stat->dev == NULL) { + list_del_rcu(&new_stat->list); + kfree_rcu(new_stat, rcu); } + } + + module_put(THIS_MODULE); +} + +static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) +{ + int rc = 0; - module_put(THIS_MODULE); + if (state == trace_state) { + NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); + return -EAGAIN; + } + switch (state) { + case TRACE_ON: + rc = net_dm_trace_on_set(extack); + break; + case TRACE_OFF: + net_dm_trace_off_set(); break; default: rc = 1; @@ -288,17 +601,84 @@ static int set_all_monitor_traces(int state) else rc = -EINPROGRESS; -out_unlock: - mutex_unlock(&trace_state_mutex); - return rc; } +static int net_dm_alert_mode_get_from_info(struct genl_info *info, + enum net_dm_alert_mode *p_alert_mode) +{ + u8 val; + + val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); + + switch (val) { + case NET_DM_ALERT_MODE_SUMMARY: /* fall-through */ + case NET_DM_ALERT_MODE_PACKET: + *p_alert_mode = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int net_dm_alert_mode_set(struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + enum net_dm_alert_mode alert_mode; + int rc; + + if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) + return 0; + + rc = net_dm_alert_mode_get_from_info(info, &alert_mode); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); + return -EINVAL; + } + + net_dm_alert_mode = alert_mode; + + return 0; +} + +static void net_dm_trunc_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) + return; + + net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); +} + +static void net_dm_queue_len_set(struct genl_info *info) +{ + if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) + return; + + net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); +} static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { - return -ENOTSUPP; + struct netlink_ext_ack *extack = info->extack; + int rc; + + if (trace_state == TRACE_ON) { + NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor while tracing is on"); + return -EBUSY; + } + + rc = net_dm_alert_mode_set(info); + if (rc) + return rc; + + net_dm_trunc_len_set(info); + + net_dm_queue_len_set(info); + + return 0; } static int net_dm_cmd_trace(struct sk_buff *skb, @@ -306,12 +686,146 @@ static int net_dm_cmd_trace(struct sk_buff *skb, { switch (info->genlhdr->cmd) { case NET_DM_CMD_START: - return set_all_monitor_traces(TRACE_ON); + return set_all_monitor_traces(TRACE_ON, info->extack); case NET_DM_CMD_STOP: - return set_all_monitor_traces(TRACE_OFF); + return set_all_monitor_traces(TRACE_OFF, info->extack); + } + + return -EOPNOTSUPP; +} + +static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) + goto nla_put_failure; + + if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_config_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; +} + +static void net_dm_stats_read(struct net_dm_stats *stats) +{ + int cpu; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct net_dm_stats *cpu_stats = &data->stats; + unsigned int start; + u64 dropped; + + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + dropped = cpu_stats->dropped; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->dropped += dropped; } +} + +static int net_dm_stats_put(struct sk_buff *msg) +{ + struct net_dm_stats stats; + struct nlattr *attr; + + net_dm_stats_read(&stats); + + attr = nla_nest_start(msg, NET_DM_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, + stats.dropped, NET_DM_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} - return -ENOTSUPP; +static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) +{ + void *hdr; + int rc; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); + if (!hdr) + return -EMSGSIZE; + + rc = net_dm_stats_put(msg); + if (rc) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + int rc; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rc = net_dm_stats_fill(msg, info); + if (rc) + goto free_msg; + + return genlmsg_reply(msg, info); + +free_msg: + nlmsg_free(msg); + return rc; } static int dropmon_net_event(struct notifier_block *ev_block, @@ -330,12 +844,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; case NETDEV_UNREGISTER: - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -346,18 +860,26 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; } out: return NOTIFY_DONE; } +static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { + [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, + [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, + [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, + [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, +}; + static const struct genl_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, @@ -369,12 +891,38 @@ static const struct genl_ops dropmon_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, }, + { + .cmd = NET_DM_CMD_CONFIG_GET, + .doit = net_dm_cmd_config_get, + }, + { + .cmd = NET_DM_CMD_STATS_GET, + .doit = net_dm_cmd_stats_get, + }, }; +static int net_dm_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_lock(&net_dm_mutex); + + return 0; +} + +static void net_dm_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_unlock(&net_dm_mutex); +} + static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, + .maxattr = NET_DM_ATTR_MAX, + .policy = net_dm_nl_policy, + .pre_doit = net_dm_nl_pre_doit, + .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .ops = dropmon_ops, .n_ops = ARRAY_SIZE(dropmon_ops), @@ -415,13 +963,11 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - INIT_WORK(&data->dm_alert_work, send_dm_alert); - timer_setup(&data->send_timer, sched_send_work, 0); spin_lock_init(&data->lock); - reset_per_cpu_data(data); + skb_queue_head_init(&data->drop_queue); + u64_stats_init(&data->stats.syncp); } - goto out; out_unreg: @@ -440,19 +986,16 @@ static void exit_net_drop_monitor(void) /* * Because of the module_get/put we do in the trace state change path * we are guarnateed not to have any current users when we get here - * all we need to do is make sure that we don't have any running timers - * or pending schedule calls */ for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - del_timer_sync(&data->send_timer); - cancel_work_sync(&data->dm_alert_work); /* * At this point, we should have exclusive access * to this struct and can free the skb inside it */ kfree_skb(data->skb); + WARN_ON(!skb_queue_empty(&data->drop_queue)); } BUG_ON(genl_unregister_family(&net_drop_monitor_family)); diff --git a/net/core/filter.c b/net/core/filter.c index 4e2a79b2fd77..0c1059cdad3d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, int err; switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: { + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: { struct bpf_dtab_netdev *dst = fwd; err = dev_map_enqueue(dst, xdp, dev_rx); @@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void) if (map) { switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: __dev_map_flush(map); break; case BPF_MAP_TYPE_CPUMAP: @@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) switch (map->map_type) { case BPF_MAP_TYPE_DEVMAP: return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_DEVMAP_HASH: + return __dev_map_hash_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); case BPF_MAP_TYPE_XSKMAP: @@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { struct bpf_dtab_netdev *dst = fwd; err = dev_map_generic_redirect(dst, skb, xdp_prog); @@ -5850,6 +5855,75 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, + struct tcphdr *, th, u32, th_len) +{ +#ifdef CONFIG_SYN_COOKIES + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) + return -EINVAL; + + if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + return -ENOENT; + + if (!th->syn || th->ack || th->fin || th->rst) + return -EINVAL; + + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && sk->sk_ipv6only) + return -EINVAL; + + mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); + break; + +#if IS_BUILTIN(CONFIG_IPV6) + case 6: + if (unlikely(iph_len < sizeof(struct ipv6hdr))) + return -EINVAL; + + if (sk->sk_family != AF_INET6) + return -EINVAL; + + mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); + break; +#endif /* CONFIG_IPV6 */ + + default: + return -EPROTONOSUPPORT; + } + if (mss <= 0) + return -ENOENT; + + return cookie | ((u64)mss << 32); +#else + return -EOPNOTSUPP; +#endif /* CONFIG_SYN_COOKIES */ +} + +static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { + .func = bpf_tcp_gen_syncookie, + .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5999,6 +6073,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; default: return bpf_base_func_proto(func_id); } @@ -6019,6 +6095,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; @@ -6135,6 +6213,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; + case BPF_FUNC_tcp_gen_syncookie: + return &bpf_tcp_gen_syncookie_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6174,6 +6254,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; + case BPF_FUNC_tcp_gen_syncookie: + return &bpf_tcp_gen_syncookie_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6267,6 +6349,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; @@ -7455,12 +7539,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, gso_segs): /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, head)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, end)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3e6fedb57bc1..9741b593ea53 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -737,6 +737,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, @@ -781,10 +782,18 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL)) { + key_tags = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL, + target_container); + key_tags->flow_label = ntohl(flow_keys->flow_label); + } } bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, - __be16 proto, int nhoff, int hlen) + __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; @@ -795,6 +804,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != + (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != + (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != + (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); + flow_keys->flags = flags; + preempt_disable(); result = BPF_PROG_RUN(prog, ctx); preempt_enable(); @@ -914,7 +931,7 @@ bool __skb_flow_dissect(const struct net *net, } ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, - hlen); + hlen, flags); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d63b970784dc..64c3d4d72b9c 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -2,6 +2,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <net/flow_offload.h> +#include <linux/rtnetlink.h> +#include <linux/mutex.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { @@ -280,3 +282,241 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, } } EXPORT_SYMBOL(flow_block_cb_setup_simple); + +static LIST_HEAD(block_ing_cb_list); + +static struct rhashtable indr_setup_block_ht; + +struct flow_indr_block_cb { + struct list_head list; + void *cb_priv; + flow_indr_block_bind_cb_t *cb; + void *cb_ident; +}; + +struct flow_indr_block_dev { + struct rhash_head ht_node; + struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params flow_indr_setup_block_ht_params = { + .key_offset = offsetof(struct flow_indr_block_dev, dev), + .head_offset = offsetof(struct flow_indr_block_dev, ht_node), + .key_len = sizeof(struct net_device *), +}; + +static struct flow_indr_block_dev * +flow_indr_block_dev_lookup(struct net_device *dev) +{ + return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, + flow_indr_setup_block_ht_params); +} + +static struct flow_indr_block_dev * +flow_indr_block_dev_get(struct net_device *dev) +{ + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (indr_dev) + goto inc_ref; + + indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); + if (!indr_dev) + return NULL; + + INIT_LIST_HEAD(&indr_dev->cb_list); + indr_dev->dev = dev; + if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params)) { + kfree(indr_dev); + return NULL; + } + +inc_ref: + indr_dev->refcnt++; + return indr_dev; +} + +static void flow_indr_block_dev_put(struct flow_indr_block_dev *indr_dev) +{ + if (--indr_dev->refcnt) + return; + + rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, + flow_indr_setup_block_ht_params); + kfree(indr_dev); +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_lookup(struct flow_indr_block_dev *indr_dev, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + if (indr_block_cb->cb == cb && + indr_block_cb->cb_ident == cb_ident) + return indr_block_cb; + return NULL; +} + +static struct flow_indr_block_cb * +flow_indr_block_cb_add(struct flow_indr_block_dev *indr_dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (indr_block_cb) + return ERR_PTR(-EEXIST); + + indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); + if (!indr_block_cb) + return ERR_PTR(-ENOMEM); + + indr_block_cb->cb_priv = cb_priv; + indr_block_cb->cb = cb; + indr_block_cb->cb_ident = cb_ident; + list_add(&indr_block_cb->list, &indr_dev->cb_list); + + return indr_block_cb; +} + +static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb) +{ + list_del(&indr_block_cb->list); + kfree(indr_block_cb); +} + +static void flow_block_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct flow_indr_block_ing_entry *entry; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &block_ing_cb_list, list) { + entry->cb(dev, cb, cb_priv, command); + } + rcu_read_unlock(); +} + +int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + int err; + + indr_dev = flow_indr_block_dev_get(dev); + if (!indr_dev) + return -ENOMEM; + + indr_block_cb = flow_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); + err = PTR_ERR_OR_ZERO(indr_block_cb); + if (err) + goto err_dev_put; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_BIND); + + return 0; + +err_dev_put: + flow_indr_block_dev_put(indr_dev); + return err; +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_register); + +int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + int err; + + rtnl_lock(); + err = __flow_indr_block_cb_register(dev, cb_priv, cb, cb_ident); + rtnl_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_register); + +void __flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident); + if (!indr_block_cb) + return; + + flow_block_ing_cmd(dev, indr_block_cb->cb, indr_block_cb->cb_priv, + FLOW_BLOCK_UNBIND); + + flow_indr_block_cb_del(indr_block_cb); + flow_indr_block_dev_put(indr_dev); +} +EXPORT_SYMBOL_GPL(__flow_indr_block_cb_unregister); + +void flow_indr_block_cb_unregister(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_ident) +{ + rtnl_lock(); + __flow_indr_block_cb_unregister(dev, cb, cb_ident); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(flow_indr_block_cb_unregister); + +void flow_indr_block_call(struct net_device *dev, + struct flow_block_offload *bo, + enum flow_block_command command) +{ + struct flow_indr_block_cb *indr_block_cb; + struct flow_indr_block_dev *indr_dev; + + indr_dev = flow_indr_block_dev_lookup(dev); + if (!indr_dev) + return; + + list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) + indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, + bo); +} +EXPORT_SYMBOL_GPL(flow_indr_block_call); + +static DEFINE_MUTEX(flow_indr_block_ing_cb_lock); +void flow_indr_add_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_add_tail_rcu(&entry->list, &block_ing_cb_list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_add_block_ing_cb); + +void flow_indr_del_block_ing_cb(struct flow_indr_block_ing_entry *entry) +{ + mutex_lock(&flow_indr_block_ing_cb_lock); + list_del_rcu(&entry->list); + mutex_unlock(&flow_indr_block_ing_cb_lock); +} +EXPORT_SYMBOL_GPL(flow_indr_del_block_ing_cb); + +static int __init init_flow_indr_rhashtable(void) +{ + return rhashtable_init(&indr_setup_block_ht, + &flow_indr_setup_block_ht_params); +} +subsys_initcall(init_flow_indr_rhashtable); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93bffaad2135..6832eeb4b785 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - rcu_assign_sk_user_data(sk, NULL); sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); - sk_psock_restore_proto(sk, psock); write_lock_bh(&sk->sk_callback_lock); + sk_psock_restore_proto(sk, psock); + rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 52d4faeee18b..1330a7442e5b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map) raw_spin_unlock_bh(&stab->lock); rcu_read_unlock(); + synchronize_rcu(); + bpf_map_area_free(stab->sks); kfree(stab); } @@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk; + int err = 0; raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) - *psk = NULL; + sk = xchg(psk, NULL); + + if (likely(sk)) + sock_map_unref(sk, psk); + else + err = -EINVAL; + raw_spin_unlock_bh(&stab->lock); - if (unlikely(!sk)) - return -EINVAL; - sock_map_unref(sk, psk); - return 0; + return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, @@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct inet_connection_sock *icsk = inet_csk(sk); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; @@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; + if (unlikely(icsk->icsk_ulp_data)) + return -EINVAL; link = sk_psock_init_link(); if (!link) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8da5b3a54dac..eb29e5adc84d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -567,6 +567,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_do_static_key, }, + { + .procname = "gro_normal_batch", + .data = &gro_normal_batch, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, { } }; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 6e942dda1bcd..2f69d4b53d46 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -84,13 +84,6 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 9893 family of switches. -config NET_DSA_TAG_KSZ9477 - tristate "Tag driver for Microchip 9477 family of switches" - select NET_DSA_TAG_KSZ_COMMON - help - Say Y if you want to enable support for tagging frames for the - Microchip 9477 family of switches. - config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" help diff --git a/net/dsa/master.c b/net/dsa/master.c index 4b52f8bac5e1..a8e52c9967f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -8,6 +8,70 @@ #include "dsa_priv.h" +static int dsa_master_get_regs_len(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int ret = 0; + int len; + + if (ops->get_regs_len) { + len = ops->get_regs_len(dev); + if (len < 0) + return len; + ret += len; + } + + ret += sizeof(struct ethtool_drvinfo); + ret += sizeof(struct ethtool_regs); + + if (ds->ops->get_regs_len) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return len; + ret += len; + } + + return ret; +} + +static void dsa_master_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_drvinfo *cpu_info; + struct ethtool_regs *cpu_regs; + int port = cpu_dp->index; + int len; + + if (ops->get_regs_len && ops->get_regs) { + len = ops->get_regs_len(dev); + if (len < 0) + return; + regs->len = len; + ops->get_regs(dev, regs, data); + data += regs->len; + } + + cpu_info = (struct ethtool_drvinfo *)data; + strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); + data += sizeof(*cpu_info); + cpu_regs = (struct ethtool_regs *)data; + data += sizeof(*cpu_regs); + + if (ds->ops->get_regs_len && ds->ops->get_regs) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return; + cpu_regs->len = len; + ds->ops->get_regs(ds, port, cpu_regs, data); + } +} + static void dsa_master_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) @@ -147,6 +211,8 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + ops->get_regs_len = dsa_master_get_regs_len; + ops->get_regs = dsa_master_get_regs; ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 26363d72d25b..47ee88163a9d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -165,6 +165,7 @@ static struct sk_buff "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); + kfree_skb(sp->data->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv @@ -211,17 +212,8 @@ static struct sk_buff * for further processing up the network stack. */ kfree_skb(skb); - - skb = skb_copy(stampable_skb, GFP_ATOMIC); - if (!skb) { - dev_err_ratelimited(dp->ds->dev, - "Failed to copy stampable skb\n"); - spin_unlock(&sp->data->meta_lock); - return NULL; - } + skb = stampable_skb; sja1105_transfer_meta(skb, meta); - /* The cached copy will be freed now */ - skb_unref(stampable_skb); spin_unlock(&sp->data->meta_lock); } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d666756be5f1..a999451345f9 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (prev && !IS_ERR(prev)) { + if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 43adfc1641ba..2f01cf6fa0de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0b980e841927..59ded25acd04 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -820,6 +820,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_min_snd_mss_max, }, { + .procname = "tcp_mtu_probe_floor", + .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_min_snd_mss_min, + .extra2 = &tcp_min_snd_mss_max, + }, + { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a0a66321c0ee..f8fa1686f7f3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1162,7 +1162,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; - bool process_backlog = false; + int process_backlog = 0; bool zc = false; long timeo; @@ -1254,9 +1254,10 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - if (process_backlog && sk_flush_backlog(sk)) { - process_backlog = false; - goto restart; + if (unlikely(process_backlog >= 16)) { + process_backlog = 0; + if (sk_flush_backlog(sk)) + goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, @@ -1264,7 +1265,7 @@ new_segment: if (!skb) goto wait_for_memory; - process_backlog = true; + process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c21e8a22fb3b..706cbb3b2986 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3782,6 +3782,49 @@ static void smc_parse_options(const struct tcphdr *th, #endif } +/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped + * value on success. + */ +static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) +{ + const unsigned char *ptr = (const unsigned char *)(th + 1); + int length = (th->doff * 4) - sizeof(struct tcphdr); + u16 mss = 0; + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return mss; + case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ + length--; + continue; + default: + if (length < 2) + return mss; + opsize = *ptr++; + if (opsize < 2) /* "silly options" */ + return mss; + if (opsize > length) + return mss; /* fail on partial options */ + if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) { + u16 in_mss = get_unaligned_be16(ptr); + + if (in_mss) { + if (user_mss && user_mss < in_mss) + in_mss = user_mss; + mss = in_mss; + } + } + ptr += opsize - 2; + length -= opsize; + } + } + return mss; +} + /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. @@ -6422,9 +6465,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, - const struct sk_buff *skb, - const char *proto) +static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; @@ -6444,7 +6485,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + proto, sk->sk_num, msg); return want_cookie; } @@ -6466,6 +6507,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk, } } +/* If a SYN cookie is required and supported, returns a clamped MSS value to be + * used for SYN cookie generation. + */ +u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct tcphdr *th) +{ + struct tcp_sock *tp = tcp_sk(sk); + u16 mss; + + if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + !inet_csk_reqsk_queue_is_full(sk)) + return 0; + + if (!tcp_syn_flood_action(sk, rsk_ops->slab_name)) + return 0; + + if (sk_acceptq_is_full(sk)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + return 0; + } + + mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss); + if (!mss) + mss = af_ops->mss_clamp; + + return mss; +} +EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss); + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) @@ -6487,7 +6558,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, */ if ((net->ipv4.sysctl_tcp_syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); + want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d57641cb3477..fd394ad179a0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1515,6 +1515,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) return sk; } +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, th); + if (mss) { + *cookie = __cookie_v4_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -2637,6 +2652,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c801cd37cc2a..dbd9d2d0ee63 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -154,7 +154,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len); + mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 3d8a1d835471..4849edb62d52 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } +void tcp_update_ulp(struct sock *sk, struct proto *proto) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) { + sk->sk_prot = proto; + return; + } + + if (icsk->icsk_ulp_ops->update) + icsk->icsk_ulp_ops->update(sk, proto); +} + void tcp_cleanup_ulp(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c2049c72f3e5..dd2d0b963260 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3134fbb65d7f..754a484d35df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); - skb_set_inner_ipproto(skb, IPPROTO_IPIP); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, @@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); - skb_set_inner_ipproto(skb, IPPROTO_IPV6); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e49fec767a10..7a5d331cdefa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1951,7 +1951,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) - return; + goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; @@ -2725,10 +2725,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); - if (!res.f6i) { - rcu_read_unlock(); - return; - } + if (!res.f6i) + goto out_unlock; + res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; @@ -2744,10 +2743,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ - if (!arg.match) { - rcu_read_unlock(); - return; - } + if (!arg.match) + goto out_unlock; res.nh = arg.match; } else { @@ -2760,6 +2757,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } +out_unlock: rcu_read_unlock(); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5da069e91cac..87f44d3250ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1063,6 +1063,21 @@ static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) return sk; } +u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, th); + if (mss) { + *cookie = __cookie_v6_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 09e1694b6d34..ebb62a4ebe30 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -512,7 +512,9 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } - case IUCV_DISCONN: /* fall through */ + /* fall through */ + + case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -525,8 +527,9 @@ static void iucv_sock_close(struct sock *sk) iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } + /* fall through */ - case IUCV_CLOSING: /* fall through */ + case IUCV_CLOSING: sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); @@ -535,8 +538,9 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); + /* fall through */ - default: /* fall through */ + default: iucv_sever_path(sk, 1); } @@ -2247,10 +2251,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); break; } - /* fall through and receive non-zero length data */ + /* fall through - and receive non-zero length data */ case (AF_IUCV_FLAG_SHT): /* shutdown request */ - /* fall through and receive zero length data */ + /* fall through - and receive zero length data */ case 0: /* plain data frame */ IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1d0e5904dedf..c54cb59593ef 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = { .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppol2tp_proto = { diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 06aac0aaae64..8dc6580e1787 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1222,7 +1222,6 @@ static void ieee80211_if_setup(struct net_device *dev) static void ieee80211_if_setup_no_queue(struct net_device *dev) { ieee80211_if_setup(dev); - dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e89ed800f012..641876982ab9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2042,6 +2042,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local, ieee80211_regulatory_limit_wmm_params(sdata, ¶ms[ac], ac); } + /* WMM specification requires all 4 ACIs. */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + if (params[ac].cw_min == 0) { + sdata_info(sdata, + "AP has invalid WMM params (missing AC %d), using defaults\n", + ac); + return false; + } + } + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { mlme_dbg(sdata, "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n", diff --git a/net/mac80211/util.c b/net/mac80211/util.c index caa317faee3c..286c7ee35e63 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3856,9 +3856,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, } /* Always allow software iftypes */ - if (local->hw.wiphy->software_iftypes & BIT(iftype) || - (iftype == NL80211_IFTYPE_AP_VLAN && - local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) { + if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) { if (radar_detect) return -EINVAL; return 0; @@ -3893,7 +3891,8 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, if (sdata_iter == sdata || !ieee80211_sdata_running(sdata_iter) || - local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) + cfg80211_iftype_allowed(local->hw.wiphy, + wdev_iter->iftype, 0, 1)) continue; params.iftype_num[wdev_iter->iftype]++; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index ca7ac4a25ada..1d4e63326e68 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -226,7 +226,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, e.id = ip_to_id(map, ip); - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 2e151856ad99..e64d5f9a89dd 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1161,7 +1161,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, return -ENOENT; write_lock_bh(&ip_set_ref_lock); - if (set->ref != 0) { + if (set->ref != 0 || set->ref_netlink != 0) { ret = -IPSET_ERR_REFERENCED; goto out; } diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index faf59b6a998f..24d8f4df4230 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -89,15 +89,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 3d5922c47ec2..8b48e7ce1c2c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -262,7 +262,7 @@ static inline unsigned int ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; __u32 ahash; @@ -493,7 +493,7 @@ static inline unsigned int ip_vs_rs_hashkey(int af, const union nf_inet_addr *addr, __be16 port) { - register unsigned int porth = ntohs(port); + unsigned int porth = ntohs(port); __be32 addr_fold = addr->ip; #ifdef CONFIG_IP_VS_IPV6 diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c8b5a504476c..77c323c36a88 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -160,7 +160,7 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set) /* get weighted least-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *least; int loh, doh; @@ -209,7 +209,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set) /* get weighted most-connection node in the destination set */ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set) { - register struct ip_vs_dest_set_elem *e; + struct ip_vs_dest_set_elem *e; struct ip_vs_dest *dest, *most; int moh, doh; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 605a7cfe7ca7..fe3b7b0c6c66 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7593,6 +7593,11 @@ static struct pernet_operations nf_tables_net_ops = { .exit = nf_tables_exit_net, }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = nft_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init nf_tables_module_init(void) { int err; @@ -7624,6 +7629,7 @@ static int __init nf_tables_module_init(void) goto err5; nft_chain_route_init(); + flow_indr_add_block_ing_cb(&block_ing_entry); return err; err5: rhltable_destroy(&nft_objname_ht); @@ -7640,6 +7646,7 @@ err1: static void __exit nf_tables_module_exit(void) { + flow_indr_del_block_ing_cb(&block_ing_entry); nfnetlink_subsys_unregister(&nf_tables_subsys); unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 64f5fd5f240e..d3c4c9c88bc8 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -171,24 +171,110 @@ static int nft_flow_offload_unbind(struct flow_block_offload *bo, return 0; } +static int nft_block_setup(struct nft_base_chain *basechain, + struct flow_block_offload *bo, + enum flow_block_command cmd) +{ + int err; + + switch (cmd) { + case FLOW_BLOCK_BIND: + err = nft_flow_offload_bind(bo, basechain); + break; + case FLOW_BLOCK_UNBIND: + err = nft_flow_offload_unbind(bo, basechain); + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + +static int nft_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + int err; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) + return err; + + return nft_block_setup(chain, &bo, cmd); +} + +static void nft_indr_block_ing_cmd(struct net_device *dev, + struct nft_base_chain *chain, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + + if (!chain) + return; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); + + nft_block_setup(chain, &bo, cmd); +} + +static int nft_indr_block_offload_cmd(struct nft_base_chain *chain, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct flow_block_offload bo = {}; + struct netlink_ext_ack extack = {}; + + bo.net = dev_net(dev); + bo.block = &chain->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + flow_indr_block_call(dev, &bo, cmd); + + if (list_empty(&bo.cb_list)) + return -EOPNOTSUPP; + + return nft_block_setup(chain, &bo, cmd); +} + #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK static int nft_flow_offload_chain(struct nft_trans *trans, enum flow_block_command cmd) { struct nft_chain *chain = trans->ctx.chain; - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo = {}; struct nft_base_chain *basechain; struct net_device *dev; - int err; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); dev = basechain->ops.dev; - if (!dev || !dev->netdev_ops->ndo_setup_tc) + if (!dev) return -EOPNOTSUPP; /* Only default policy to accept is supported for now. */ @@ -197,26 +283,10 @@ static int nft_flow_offload_chain(struct nft_trans *trans, nft_trans_chain_policy(trans) != NF_ACCEPT) return -EOPNOTSUPP; - bo.command = cmd; - bo.block = &basechain->flow_block; - bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; - bo.extack = &extack; - INIT_LIST_HEAD(&bo.cb_list); - - err = dev->netdev_ops->ndo_setup_tc(dev, FLOW_SETUP_BLOCK, &bo); - if (err < 0) - return err; - - switch (cmd) { - case FLOW_BLOCK_BIND: - err = nft_flow_offload_bind(&bo, basechain); - break; - case FLOW_BLOCK_UNBIND: - err = nft_flow_offload_unbind(&bo, basechain); - break; - } - - return err; + if (dev->netdev_ops->ndo_setup_tc) + return nft_block_offload_cmd(basechain, dev, cmd); + else + return nft_indr_block_offload_cmd(basechain, dev, cmd); } int nft_flow_rule_offload_commit(struct net *net) @@ -266,3 +336,33 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } + +void nft_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) +{ + struct net *net = dev_net(dev); + const struct nft_table *table; + const struct nft_chain *chain; + + list_for_each_entry_rcu(table, &net->nft.tables, list) { + if (table->family != NFPROTO_NETDEV) + continue; + + list_for_each_entry_rcu(chain, &table->chains, list) { + if (nft_is_base_chain(chain)) { + struct nft_base_chain *basechain; + + basechain = nft_base_chain(chain); + if (!strncmp(basechain->dev_name, dev->name, + IFNAMSIZ)) { + nft_indr_block_ing_cmd(dev, basechain, + cb, cb_priv, + command); + return; + } + } + } + } +} diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f1b1d948c07b..f69afb9ff3cb 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -60,24 +60,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->mark; break; case NFT_META_IIF: - if (in == NULL) - goto err; - *dest = in->ifindex; + *dest = in ? in->ifindex : 0; break; case NFT_META_OIF: - if (out == NULL) - goto err; - *dest = out->ifindex; + *dest = out ? out->ifindex : 0; break; case NFT_META_IIFNAME: - if (in == NULL) - goto err; - strncpy((char *)dest, in->name, IFNAMSIZ); + strncpy((char *)dest, in ? in->name : "", IFNAMSIZ); break; case NFT_META_OIFNAME: - if (out == NULL) - goto err; - strncpy((char *)dest, out->name, IFNAMSIZ); + strncpy((char *)dest, out ? out->name : "", IFNAMSIZ); break; case NFT_META_IIFTYPE: if (in == NULL) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 96740d389377..c4f54ad2b98a 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) window = skb->data[20]; + sock_hold(make); skb->sk = make; skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 892287d06c17..65122bbccd27 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -222,6 +222,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; + int error; stats = this_cpu_ptr(dp->stats_percpu); @@ -229,7 +230,6 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; - int error; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; @@ -246,7 +246,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) ovs_flow_stats_update(flow, key->tp.flags, skb); sf_acts = rcu_dereference(flow->sf_acts); - ovs_execute_actions(dp, skb, sf_acts, key); + error = ovs_execute_actions(dp, skb, sf_acts, key); + if (unlikely(error)) + net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; @@ -1047,7 +1050,7 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static struct sw_flow_actions *get_flow_actions(struct net *net, +static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, @@ -1081,12 +1084,13 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, * we should not to return match object with dangling reference * to mask. * */ -static int ovs_nla_init_match_and_action(struct net *net, - struct sw_flow_match *match, - struct sw_flow_key *key, - struct nlattr **a, - struct sw_flow_actions **acts, - bool log) +static noinline_for_stack int +ovs_nla_init_match_and_action(struct net *net, + struct sw_flow_match *match, + struct sw_flow_key *key, + struct nlattr **a, + struct sw_flow_actions **acts, + bool log) { struct sw_flow_mask mask; int error = 0; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index ff74c4bbb9fc..9986d6065c4d 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -105,7 +105,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ESTABLISHED: - trans->cm_connect_complete(conn, event); + if (conn) + trans->cm_connect_complete(conn, event); break; case RDMA_CM_EVENT_REJECTED: @@ -137,6 +138,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: + if (!conn) + break; rdsdebug("DISCONNECT event - dropping connection " "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bea2a02850af..63b26baa108a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1065,6 +1065,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *); /* * proc.c diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 9f2f45c09e58..7666ec72d37e 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -378,7 +378,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9d3ce81cf8ae..9c3ac96f71cb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -437,6 +437,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } /* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + +/* * Make sure all peer records have been discarded. */ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5d3f33ce6d41..bae14438f869 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -226,6 +226,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 8126b26f125e..fd1f7e799e23 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; + u32 index; if (!nla) return -EINVAL; @@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, act, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, act, + ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true); if (ret < 0) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ce36b0f7e1dc..32ac04d77a45 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct tcf_connmark_info *ci; struct tc_connmark *parm; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_CONNMARK_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_connmark_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 621fb22ce2a9..9b9288267a54 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_csum_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b501ce0cf116..33a1a7406e87 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -666,6 +666,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); @@ -681,16 +682,16 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { - err = tcf_idr_create(tn, parm->index, est, a, + err = tcf_idr_create(tn, index, est, a, &act_ct_ops, bind, true); if (err) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 10eb2bb99861..06ef74b74911 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -157,10 +157,10 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; - u32 dscpmask = 0, dscpstatemask; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; @@ -206,12 +206,13 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } /* done the validation:now to the actual action allocation */ - err = tcf_idr_check_alloc(tn, &actparm->index, a, bind); + index = actparm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, actparm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_ctinfo_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, actparm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b2380c5284e6..8f0140c6ca58 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; + u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; @@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); + index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) @@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_gact_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 41d5398dd2f2..92ee853d43e6 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -479,8 +479,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, u8 *saddr = NULL; bool exists = false; int ret = 0; + u32 index; int err; + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); + return -EINVAL; + } + err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) @@ -502,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { kfree(p); return err; @@ -514,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, + ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); kfree(p); return ret; } diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 055faa298c8e..be3f88dfc37e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct net_device *dev; bool exists = false; int ret, err; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); @@ -118,8 +119,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,21 +137,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mirred_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ca2597ce4ac9..0f299e3b618c 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -138,6 +138,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); @@ -153,6 +154,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); + index = parm->index; /* Verify parameters against action type. */ switch (parm->m_action) { @@ -209,7 +211,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -217,10 +219,10 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 45923ebb7a4f..7b858c11b1b5 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; + u32 index; if (nla == NULL) return -EINVAL; @@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_nat_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45e9d6bfddb3..17360c6faeaa 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tcf_pedit *p; int ret = 0, err; int ksize; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); @@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { if (!parm->nkeys) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); ret = -EINVAL; goto out_free; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); goto out_free; } ret = ACT_P_CREATED; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a065f62fa79c..49cec3e64a4d 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; + u32 index; if (nla == NULL) return -EINVAL; @@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, NULL, a, + ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 274d7a0c0e25..595308d60133 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; - u32 psample_group_num, rate; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; @@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f28ddbabff76..33aefa25b545 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct tcf_defact *d; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 215a06705cef..b100870f02a6 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, u16 *queue_mapping = NULL, *ptype = NULL; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 4f07706eff07..7da3518e18ef 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; + u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; - u32 lflags = 0; int ret = 0, err; if (!nla) @@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBMOD_PARMS]); + index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 10dffda1d5cc..6d0debdc9b97 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 flags = 0; u8 tos, ttl; int ret = 0; + u32 index; int err; if (!nla) { @@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); @@ -403,7 +405,7 @@ err_out: if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 9269d350fb8a..a3c9eea1ee8a 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, u8 push_prio = 0; bool exists = false; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); @@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -ERANGE; } @@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { @@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_vlan_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -306,6 +308,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_vlan_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, @@ -315,6 +325,7 @@ static struct tc_action_ops act_vlan_ops = { .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3565d9aa09aa..e0d8b456e9f5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -37,6 +37,7 @@ #include <net/tc_act/tc_skbedit.h> #include <net/tc_act/tc_ct.h> #include <net/tc_act/tc_mpls.h> +#include <net/flow_offload.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -545,235 +546,71 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) } } -static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) -{ - const struct Qdisc_class_ops *cops; - struct Qdisc *qdisc; - - if (!dev_ingress_queue(dev)) - return NULL; - - qdisc = dev_ingress_queue(dev)->qdisc_sleeping; - if (!qdisc) - return NULL; - - cops = qdisc->ops->cl_ops; - if (!cops) - return NULL; - - if (!cops->tcf_block) - return NULL; - - return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); -} - -static struct rhashtable indr_setup_block_ht; - -struct tc_indr_block_dev { - struct rhash_head ht_node; - struct net_device *dev; - unsigned int refcnt; - struct list_head cb_list; - struct tcf_block *block; -}; - -struct tc_indr_block_cb { - struct list_head list; - void *cb_priv; - tc_indr_block_bind_cb_t *cb; - void *cb_ident; -}; - -static const struct rhashtable_params tc_indr_setup_block_ht_params = { - .key_offset = offsetof(struct tc_indr_block_dev, dev), - .head_offset = offsetof(struct tc_indr_block_dev, ht_node), - .key_len = sizeof(struct net_device *), -}; - -static struct tc_indr_block_dev * -tc_indr_block_dev_lookup(struct net_device *dev) -{ - return rhashtable_lookup_fast(&indr_setup_block_ht, &dev, - tc_indr_setup_block_ht_params); -} - -static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev) -{ - struct tc_indr_block_dev *indr_dev; - - indr_dev = tc_indr_block_dev_lookup(dev); - if (indr_dev) - goto inc_ref; - - indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL); - if (!indr_dev) - return NULL; - - INIT_LIST_HEAD(&indr_dev->cb_list); - indr_dev->dev = dev; - indr_dev->block = tc_dev_ingress_block(dev); - if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params)) { - kfree(indr_dev); - return NULL; - } - -inc_ref: - indr_dev->refcnt++; - return indr_dev; -} - -static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev) -{ - if (--indr_dev->refcnt) - return; - - rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node, - tc_indr_setup_block_ht_params); - kfree(indr_dev); -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - if (indr_block_cb->cb == cb && - indr_block_cb->cb_ident == cb_ident) - return indr_block_cb; - return NULL; -} - -static struct tc_indr_block_cb * -tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (indr_block_cb) - return ERR_PTR(-EEXIST); - - indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL); - if (!indr_block_cb) - return ERR_PTR(-ENOMEM); - - indr_block_cb->cb_priv = cb_priv; - indr_block_cb->cb = cb; - indr_block_cb->cb_ident = cb_ident; - list_add(&indr_block_cb->list, &indr_dev->cb_list); - - return indr_block_cb; -} - -static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb) -{ - list_del(&indr_block_cb->list); - kfree(indr_block_cb); -} - static int tcf_block_setup(struct tcf_block *block, struct flow_block_offload *bo); -static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, - struct tc_indr_block_cb *indr_block_cb, +static void tc_indr_block_ing_cmd(struct net_device *dev, + struct tcf_block *block, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, enum flow_block_command command) { struct flow_block_offload bo = { .command = command, .binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, - .net = dev_net(indr_dev->dev), - .block_shared = tcf_block_non_null_shared(indr_dev->block), + .net = dev_net(dev), + .block_shared = tcf_block_non_null_shared(block), }; INIT_LIST_HEAD(&bo.cb_list); - if (!indr_dev->block) + if (!block) return; - bo.block = &indr_dev->block->flow_block; - - indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - tcf_block_setup(indr_dev->block, &bo); -} - -int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; - int err; - - indr_dev = tc_indr_block_dev_get(dev); - if (!indr_dev) - return -ENOMEM; - - indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident); - err = PTR_ERR_OR_ZERO(indr_block_cb); - if (err) - goto err_dev_put; + bo.block = &block->flow_block; - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND); - return 0; + cb(dev, cb_priv, TC_SETUP_BLOCK, &bo); -err_dev_put: - tc_indr_block_dev_put(indr_dev); - return err; + tcf_block_setup(block, &bo); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register); -int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static struct tcf_block *tc_dev_ingress_block(struct net_device *dev) { - int err; - - rtnl_lock(); - err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident); - rtnl_unlock(); + const struct Qdisc_class_ops *cops; + struct Qdisc *qdisc; - return err; -} -EXPORT_SYMBOL_GPL(tc_indr_block_cb_register); + if (!dev_ingress_queue(dev)) + return NULL; -void __tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) -{ - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; + qdisc = dev_ingress_queue(dev)->qdisc_sleeping; + if (!qdisc) + return NULL; - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; + cops = qdisc->ops->cl_ops; + if (!cops) + return NULL; - indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident); - if (!indr_block_cb) - return; + if (!cops->tcf_block) + return NULL; - /* Send unbind message if required to free any block cbs. */ - tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND); - tc_indr_block_cb_del(indr_block_cb); - tc_indr_block_dev_put(indr_dev); + return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL); } -EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister); -void tc_indr_block_cb_unregister(struct net_device *dev, - tc_indr_block_bind_cb_t *cb, void *cb_ident) +static void tc_indr_block_get_and_ing_cmd(struct net_device *dev, + flow_indr_block_bind_cb_t *cb, + void *cb_priv, + enum flow_block_command command) { - rtnl_lock(); - __tc_indr_block_cb_unregister(dev, cb, cb_ident); - rtnl_unlock(); + struct tcf_block *block = tc_dev_ingress_block(dev); + + tc_indr_block_ing_cmd(dev, block, cb, cb_priv, command); } -EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister); -static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, +static void tc_indr_block_call(struct tcf_block *block, + struct net_device *dev, struct tcf_block_ext_info *ei, enum flow_block_command command, struct netlink_ext_ack *extack) { - struct tc_indr_block_cb *indr_block_cb; - struct tc_indr_block_dev *indr_dev; struct flow_block_offload bo = { .command = command, .binder_type = ei->binder_type, @@ -784,16 +621,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, }; INIT_LIST_HEAD(&bo.cb_list); - indr_dev = tc_indr_block_dev_lookup(dev); - if (!indr_dev) - return; - - indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL; - - list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list) - indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, - &bo); - + flow_indr_block_call(dev, &bo, command); tcf_block_setup(block, &bo); } @@ -3205,6 +3033,12 @@ int tc_setup_flow_action(struct flow_action *flow_action, } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + entry->dev = tcf_mirred_dev(act); } else if (is_tcf_vlan(act)) { switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: @@ -3294,6 +3128,9 @@ int tc_setup_flow_action(struct flow_action *flow_action, default: goto err_out; } + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); } else { goto err_out; } @@ -3346,6 +3183,11 @@ static struct pernet_operations tcf_net_ops = { .size = sizeof(struct tcf_net), }; +static struct flow_indr_block_ing_entry block_ing_entry = { + .cb = tc_indr_block_get_and_ing_cmd, + .list = LIST_HEAD_INIT(block_ing_entry.list), +}; + static int __init tc_filter_init(void) { int err; @@ -3358,10 +3200,7 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - err = rhashtable_init(&indr_setup_block_ht, - &tc_indr_setup_block_ht_params); - if (err) - goto err_rhash_setup_block_ht; + flow_indr_add_block_ing_cb(&block_ing_entry); rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, RTNL_FLAG_DOIT_UNLOCKED); @@ -3376,8 +3215,6 @@ static int __init tc_filter_init(void) return 0; -err_rhash_setup_block_ht: - unregister_pernet_subsys(&tcf_net_ops); err_register_pernet_subsys: destroy_workqueue(tc_filter_wq); return err; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 25ef172c23df..30169b3adbbb 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); - if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..c261c0a18868 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -45,7 +45,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -173,7 +172,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -211,7 +211,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -286,7 +285,6 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct sk_buff *skb; struct fq_codel_flow *flow; struct list_head *head; - u32 prev_drop_count, prev_ecn_mark; begin: head = &q->new_flows; @@ -303,16 +301,10 @@ begin: goto begin; } - prev_drop_count = q->cstats.drop_count; - prev_ecn_mark = q->cstats.ecn_mark; - skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams, &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -658,7 +650,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c39db507ba3f..046fd2c102b4 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -677,10 +677,6 @@ static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; -static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { - [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, -}; - static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 2f7e88c46dd2..12503e16fa96 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -985,7 +985,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Walk through the addrs buffer and count the number of addresses. */ @@ -1304,7 +1304,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Allow security module to validate connectx addresses. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 302e355f2ebc..5b932583e407 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -263,7 +263,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, /* Check if socket is already active */ rc = -EINVAL; - if (sk->sk_state != SMC_INIT) + if (sk->sk_state != SMC_INIT || smc->connect_nonblock) goto out_rel; smc->clcsock->sk->sk_reuse = sk->sk_reuse; @@ -1390,7 +1390,8 @@ static int smc_listen(struct socket *sock, int backlog) lock_sock(sk); rc = -EINVAL; - if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN)) + if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || + smc->connect_nonblock) goto out; rc = 0; @@ -1518,7 +1519,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; if (msg->msg_flags & MSG_FASTOPEN) { - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { @@ -1732,14 +1733,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, } break; case TCP_NODELAY: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } break; case TCP_CORK: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (!val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 1336f3cdad38..34f3e5641438 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -406,8 +406,10 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); } - if (dests->local) + if (dests->local) { + tipc_loopback_trace(net, &localq); tipc_sk_mcast_rcv(net, &localq, &inputq); + } exit: /* This queue should normally be empty by now */ __skb_queue_purge(pkts); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a809c0ec8d15..0214aa1c4427 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -389,6 +389,11 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev_put(dev); return -EINVAL; } + if (dev == net->loopback_dev) { + dev_put(dev); + pr_info("Enabling <%s> not permitted\n", b->name); + return -EINVAL; + } /* Autoconfigure own node identity if needed */ if (!tipc_own_id(net) && hwaddr_len <= NODE_ID_LEN) { @@ -674,6 +679,65 @@ void tipc_bearer_stop(struct net *net) } } +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts) +{ + struct net_device *dev = net->loopback_dev; + struct sk_buff *skb, *_skb; + int exp; + + skb_queue_walk(pkts, _skb) { + skb = pskb_copy(_skb, GFP_ATOMIC); + if (!skb) + continue; + + exp = SKB_DATA_ALIGN(dev->hard_header_len - skb_headroom(skb)); + if (exp > 0 && pskb_expand_head(skb, exp, 0, GFP_ATOMIC)) { + kfree_skb(skb); + continue; + } + + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_TIPC, dev->dev_addr, + dev->dev_addr, skb->len); + skb->dev = dev; + skb->pkt_type = PACKET_HOST; + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->protocol = eth_type_trans(skb, dev); + netif_rx_ni(skb); + } +} + +static int tipc_loopback_rcv_pkt(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *od) +{ + consume_skb(skb); + return NET_RX_SUCCESS; +} + +int tipc_attach_loopback(struct net *net) +{ + struct net_device *dev = net->loopback_dev; + struct tipc_net *tn = tipc_net(net); + + if (!dev) + return -ENODEV; + + dev_hold(dev); + tn->loopback_pt.dev = dev; + tn->loopback_pt.type = htons(ETH_P_TIPC); + tn->loopback_pt.func = tipc_loopback_rcv_pkt; + dev_add_pack(&tn->loopback_pt); + return 0; +} + +void tipc_detach_loopback(struct net *net) +{ + struct tipc_net *tn = tipc_net(net); + + dev_remove_pack(&tn->loopback_pt); + dev_put(net->loopback_dev); +} + /* Caller should hold rtnl_lock to protect the bearer */ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, struct tipc_bearer *bearer, int nlflags) diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 7f4c569594a5..ea0f3c49cbed 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -232,6 +232,16 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct tipc_media_addr *dst); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); +int tipc_attach_loopback(struct net *net); +void tipc_detach_loopback(struct net *net); + +static inline void tipc_loopback_trace(struct net *net, + struct sk_buff_head *pkts) +{ + if (unlikely(dev_nit_active(net->loopback_dev))) + tipc_clone_to_loopback(net, pkts); +} /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) diff --git a/net/tipc/core.c b/net/tipc/core.c index c8370722f0bb..23cb379a93d6 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -82,6 +82,10 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_bclink; + err = tipc_attach_loopback(net); + if (err) + goto out_bclink; + return 0; out_bclink: @@ -94,6 +98,7 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { + tipc_detach_loopback(net); tipc_net_stop(net); tipc_bcast_stop(net); tipc_nametbl_stop(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 7a68e1b6a066..60d829581068 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -125,6 +125,9 @@ struct tipc_net { /* Cluster capabilities */ u16 capabilities; + + /* Tracing of node internal messages */ + struct packet_type loopback_pt; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d86030ef1232..e135d4e11231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -55,6 +55,7 @@ struct tipc_nl_compat_msg { int rep_type; int rep_size; int req_type; + int req_size; struct net *net; struct sk_buff *rep; struct tlv_desc *req; @@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, int err; struct sk_buff *arg; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; msg->rep = tipc_tlv_alloc(msg->rep_size); @@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, { int err; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; err = __tipc_nl_compat_doit(cmd, msg); @@ -1278,8 +1281,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) goto send; } - len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (!len || !TLV_OK(msg.req, len)) { + msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); + if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/node.c b/net/tipc/node.c index 7ca019001f7c..1bdcf0fc1a4d 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1443,6 +1443,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, int rc; if (in_own_node(net, dnode)) { + tipc_loopback_trace(net, list); tipc_sk_rcv(net, list); return 0; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index dd8537f988c4..83ae41d7e554 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk_set_unreturnable(tsk, true); if (sock->type == SOCK_DGRAM) tsk_set_unreliable(tsk, true); - __skb_queue_head_init(&tsk->mc_method.deferredq); } - + __skb_queue_head_init(&tsk->mc_method.deferredq); trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " "); return 0; } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index ca8ac96d22a9..3a12fc18239b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -40,6 +40,7 @@ #include "socket.h" #include "addr.h" #include "msg.h" +#include "bearer.h" #include <net/sock.h> #include <linux/module.h> @@ -608,6 +609,7 @@ static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); skb_queue_head_init(&evtq); __skb_queue_tail(&evtq, skb); + tipc_loopback_trace(net, &evtq); tipc_sk_rcv(net, &evtq); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 4674e57e66b0..9cbbae606ced 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,24 +261,9 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } -static void tls_sk_proto_close(struct sock *sk, long timeout) +static void tls_sk_proto_cleanup(struct sock *sk, + struct tls_context *ctx, long timeo) { - struct tls_context *ctx = tls_get_ctx(sk); - long timeo = sock_sndtimeo(sk, 0); - void (*sk_proto_close)(struct sock *sk, long timeout); - bool free_ctx = false; - - lock_sock(sk); - sk_proto_close = ctx->sk_proto_close; - - if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { - free_ctx = true; - goto skip_tx_cleanup; - } - if (unlikely(sk->sk_write_pending) && !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); @@ -287,7 +272,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (ctx->tx_conf == TLS_SW) { kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); - tls_sw_free_resources_tx(sk); + tls_sw_release_resources_tx(sk); #ifdef CONFIG_TLS_DEVICE } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); @@ -295,26 +280,44 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } if (ctx->rx_conf == TLS_SW) - tls_sw_free_resources_rx(sk); + tls_sw_release_resources_rx(sk); #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) tls_device_offload_cleanup_rx(sk); - - if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) { -#else - { #endif - tls_ctx_free(ctx); - ctx = NULL; - } +} -skip_tx_cleanup: +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + bool free_ctx; + + if (ctx->tx_conf == TLS_SW) + tls_sw_cancel_work_tx(ctx); + + lock_sock(sk); + free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; + + if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) + tls_sk_proto_cleanup(sk, ctx, timeo); + + write_lock_bh(&sk->sk_callback_lock); + if (free_ctx) + icsk->icsk_ulp_data = NULL; + sk->sk_prot = ctx->sk_proto; + write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); - sk_proto_close(sk, timeout); - /* free ctx for TLS_HW_RECORD, used by tcp_set_state - * for sk->sk_prot->unhash [tls_hw_unhash] - */ + if (ctx->tx_conf == TLS_SW) + tls_sw_free_ctx_tx(ctx); + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) + tls_sw_strparser_done(ctx); + if (ctx->rx_conf == TLS_SW) + tls_sw_free_ctx_rx(ctx); + ctx->sk_proto_close(sk, timeout); + if (free_ctx) tls_ctx_free(ctx); } @@ -526,6 +529,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 1); + if (rc) + goto err_crypto_info; conf = TLS_SW; } } else { @@ -537,13 +542,13 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 0); + if (rc) + goto err_crypto_info; conf = TLS_SW; } + tls_sw_strparser_arm(sk, ctx); } - if (rc) - goto err_crypto_info; - if (tx) ctx->tx_conf = conf; else @@ -607,6 +612,7 @@ static struct tls_context *create_ctx(struct sock *sk) ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + ctx->unhash = sk->sk_prot->unhash; return ctx; } @@ -764,7 +770,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) @@ -773,7 +778,7 @@ static int tls_init(struct sock *sk) int rc = 0; if (tls_hw_prot(sk)) - goto out; + return 0; /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. @@ -784,21 +789,38 @@ static int tls_init(struct sock *sk) if (sk->sk_state != TCP_ESTABLISHED) return -ENOTSUPP; + tls_build_proto(sk); + /* allocate tls context */ + write_lock_bh(&sk->sk_callback_lock); ctx = create_ctx(sk); if (!ctx) { rc = -ENOMEM; goto out; } - tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: + write_unlock_bh(&sk->sk_callback_lock); return rc; } +static void tls_update(struct sock *sk, struct proto *p) +{ + struct tls_context *ctx; + + ctx = tls_get_ctx(sk); + if (likely(ctx)) { + ctx->sk_proto_close = p->close; + ctx->sk_proto = p; + } else { + sk->sk_prot = p; + } +} + void tls_register_device(struct tls_device *device) { spin_lock_bh(&device_spinlock); @@ -819,6 +841,7 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", .owner = THIS_MODULE, .init = tls_init, + .update = tls_update, }; static int __init tls_register(void) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 53b4ad94e74a..91d21b048a9b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2054,7 +2054,16 @@ static void tls_data_ready(struct sock *sk) } } -void tls_sw_free_resources_tx(struct sock *sk) +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask); + set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); + cancel_delayed_work_sync(&ctx->tx_work.work); +} + +void tls_sw_release_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); @@ -2065,11 +2074,6 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - release_sock(sk); - cancel_delayed_work_sync(&ctx->tx_work.work); - lock_sock(sk); - - /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); /* Free up un-sent records in tx_list. First, free @@ -2092,6 +2096,11 @@ void tls_sw_free_resources_tx(struct sock *sk) crypto_free_aead(ctx->aead_send); tls_free_open_rec(sk); +} + +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); kfree(ctx); } @@ -2110,25 +2119,40 @@ void tls_sw_release_resources_rx(struct sock *sk) skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); - write_lock_bh(&sk->sk_callback_lock); - sk->sk_data_ready = ctx->saved_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - release_sock(sk); - strp_done(&ctx->strp); - lock_sock(sk); + /* If tls_sw_strparser_arm() was not called (cleanup paths) + * we still want to strp_stop(), but sk->sk_data_ready was + * never swapped. + */ + if (ctx->saved_data_ready) { + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = ctx->saved_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + } } } -void tls_sw_free_resources_rx(struct sock *sk) +void tls_sw_strparser_done(struct tls_context *tls_ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - tls_sw_release_resources_rx(sk); + strp_done(&ctx->strp); +} + +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); kfree(ctx); } +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_sw_release_resources_rx(sk); + tls_sw_free_ctx_rx(tls_ctx); +} + /* The work handler to transmitt the encrypted records in tx_list */ static void tx_work_handler(struct work_struct *work) { @@ -2137,11 +2161,17 @@ static void tx_work_handler(struct work_struct *work) struct tx_work, work); struct sock *sk = tx_work->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_sw_context_tx *ctx; - if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + if (unlikely(!tls_ctx)) return; + ctx = tls_sw_ctx_tx(tls_ctx); + if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)) + return; + + if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + return; lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); @@ -2160,6 +2190,18 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) } } +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx); + + write_lock_bh(&sk->sk_callback_lock); + rx_ctx->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = tls_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&rx_ctx->strp); +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2357,13 +2399,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cb.parse_msg = tls_read_size; strp_init(&sw_ctx_rx->strp, sk, &cb); - - write_lock_bh(&sk->sk_callback_lock); - sw_ctx_rx->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = tls_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - - strp_check_rcv(&sw_ctx_rx->strp); } goto out; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 2a1719c0f8d2..261521d286d6 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -312,6 +312,11 @@ static void hvs_close_connection(struct vmbus_channel *chan) lock_sock(sk); hvs_do_close_lock_held(vsock_sk(sk), true); release_sock(sk); + + /* Release the refcnt for the channel that's opened in + * hvs_open_connection(). + */ + sock_put(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -407,6 +412,9 @@ static void hvs_open_connection(struct vmbus_channel *chan) } set_per_channel_state(chan, conn_from_host ? new : sk); + + /* This reference will be dropped by hvs_close_connection(). */ + sock_hold(conn_from_host ? new : sk); vmbus_set_chn_rescind_callback(chan, hvs_close_connection); /* Set the pending send size to max packet size to always get diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 1af56df30276..3c54bb6b925a 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -13,49 +13,23 @@ #define D_SUBMODULE debugfs #include "debug-levels.h" - -#define __debugfs_register(prefix, name, parent) \ -do { \ - result = d_level_register_debugfs(prefix, name, parent); \ - if (result < 0) \ - goto error; \ -} while (0) - - -int wimax_debugfs_add(struct wimax_dev *wimax_dev) +void wimax_debugfs_add(struct wimax_dev *wimax_dev) { - int result; struct net_device *net_dev = wimax_dev->net_dev; - struct device *dev = net_dev->dev.parent; struct dentry *dentry; char buf[128]; snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name); dentry = debugfs_create_dir(buf, NULL); - result = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - if (result == -ENODEV) - result = 0; /* No debugfs support */ - else - dev_err(dev, "Can't create debugfs dentry: %d\n", - result); - goto out; - } wimax_dev->debugfs_dentry = dentry; - __debugfs_register("wimax_dl_", debugfs, dentry); - __debugfs_register("wimax_dl_", id_table, dentry); - __debugfs_register("wimax_dl_", op_msg, dentry); - __debugfs_register("wimax_dl_", op_reset, dentry); - __debugfs_register("wimax_dl_", op_rfkill, dentry); - __debugfs_register("wimax_dl_", op_state_get, dentry); - __debugfs_register("wimax_dl_", stack, dentry); - result = 0; -out: - return result; -error: - debugfs_remove_recursive(wimax_dev->debugfs_dentry); - return result; + d_level_register_debugfs("wimax_dl_", debugfs, dentry); + d_level_register_debugfs("wimax_dl_", id_table, dentry); + d_level_register_debugfs("wimax_dl_", op_msg, dentry); + d_level_register_debugfs("wimax_dl_", op_reset, dentry); + d_level_register_debugfs("wimax_dl_", op_rfkill, dentry); + d_level_register_debugfs("wimax_dl_", op_state_get, dentry); + d_level_register_debugfs("wimax_dl_", stack, dentry); } void wimax_debugfs_rm(struct wimax_dev *wimax_dev) diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 1ba99d65feca..4b9b1c5e8f3a 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -481,12 +481,7 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) /* Set up user-space interaction */ mutex_lock(&wimax_dev->mutex); wimax_id_table_add(wimax_dev); - result = wimax_debugfs_add(wimax_dev); - if (result < 0) { - dev_err(dev, "cannot initialize debugfs: %d\n", - result); - goto error_debugfs_add; - } + wimax_debugfs_add(wimax_dev); __wimax_state_set(wimax_dev, WIMAX_ST_DOWN); mutex_unlock(&wimax_dev->mutex); @@ -498,10 +493,6 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev) d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev); return 0; -error_debugfs_add: - wimax_id_table_rm(wimax_dev); - mutex_unlock(&wimax_dev->mutex); - wimax_rfkill_rm(wimax_dev); error_rfkill_add: d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n", wimax_dev, net_dev, result); diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h index e819a09337ee..40751207296c 100644 --- a/net/wimax/wimax-internal.h +++ b/net/wimax/wimax-internal.h @@ -57,13 +57,10 @@ void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state) void __wimax_state_change(struct wimax_dev *, enum wimax_st); #ifdef CONFIG_DEBUG_FS -int wimax_debugfs_add(struct wimax_dev *); +void wimax_debugfs_add(struct wimax_dev *); void wimax_debugfs_rm(struct wimax_dev *); #else -static inline int wimax_debugfs_add(struct wimax_dev *wimax_dev) -{ - return 0; -} +static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {} static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {} #endif diff --git a/net/wireless/core.c b/net/wireless/core.c index 742986c73490..a599469b8157 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1405,10 +1405,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, } break; case NETDEV_PRE_UP: - if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) && - !(wdev->iftype == NL80211_IFTYPE_AP_VLAN && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP && - wdev->use_4addr)) + if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype, + wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1a107f29016b..92e06482563c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3538,9 +3538,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return err; } - if (!(rdev->wiphy.interface_modes & (1 << type)) && - !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP)) + if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0)) return -EOPNOTSUPP; err = nl80211_parse_mon_options(rdev, type, info, ¶ms); diff --git a/net/wireless/util.c b/net/wireless/util.c index 1c39d6a2e850..d0e35b7b9e35 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1697,7 +1697,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && - !(wiphy->software_iftypes & BIT(iftype))) + !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } @@ -1719,7 +1719,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { - if (wiphy->software_iftypes & BIT(iftype)) + if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; @@ -2072,3 +2072,26 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); + +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif) + +{ + bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; + + switch (check_swif) { + case 0: + if (is_vlan && is_4addr) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->interface_modes & BIT(iftype); + case 1: + if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->software_iftypes & BIT(iftype); + default: + break; + } + + return false; +} +EXPORT_SYMBOL(cfg80211_iftype_allowed); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 83de74ca729a..a0607969f8c0 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -14,6 +14,7 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/idr.h> +#include <linux/highmem.h> #include "xdp_umem.h" #include "xsk_queue.h" @@ -164,6 +165,14 @@ void xdp_umem_clear_dev(struct xdp_umem *umem) umem->zc = false; } +static void xdp_umem_unmap_pages(struct xdp_umem *umem) +{ + unsigned int i; + + for (i = 0; i < umem->npgs; i++) + kunmap(umem->pgs[i]); +} + static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unsigned int i; @@ -207,6 +216,7 @@ static void xdp_umem_release(struct xdp_umem *umem) xsk_reuseq_destroy(umem); + xdp_umem_unmap_pages(umem); xdp_umem_unpin_pages(umem); kfree(umem->pages); @@ -369,7 +379,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) } for (i = 0; i < umem->npgs; i++) - umem->pages[i].addr = page_address(umem->pgs[i]); + umem->pages[i].addr = kmap(umem->pgs[i]); return 0; diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 2dd1d39b152a..8ee47699a870 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -18,9 +18,6 @@ #include <libbpf.h> #include "bpf_load.h" #include "perf-sys.h" -#include "trace_helpers.h" - -static int pmu_fd; static __u64 time_get_ns(void) { @@ -31,12 +28,12 @@ static __u64 time_get_ns(void) } static __u64 start_time; +static __u64 cnt; #define MAX_CNT 100000ll -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { - static __u64 cnt; struct { __u64 pid; __u64 cookie; @@ -45,7 +42,7 @@ static int print_bpf_output(void *data, int size) if (e->cookie != 0x12345678) { printf("BUG pid %llx cookie %llx sized %d\n", e->pid, e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + return; } cnt++; @@ -53,30 +50,14 @@ static int print_bpf_output(void *data, int size) if (cnt == MAX_CNT) { printf("recv %lld events per sec\n", MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - return LIBBPF_PERF_EVENT_DONE; + return; } - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(void) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - - pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); - - assert(pmu_fd >= 0); - assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0); - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); } int main(int argc, char **argv) { + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb; char filename[256]; FILE *f; int ret; @@ -88,16 +69,20 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(); - - if (perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd[0], 8, &pb_opts); + ret = libbpf_get_error(pb); + if (ret) { + printf("failed to setup perf_buffer: %d\n", ret); return 1; + } f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r"); (void) f; start_time = time_get_ns(); - ret = perf_event_poller(pmu_fd, print_bpf_output); + while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { + } kill(0, SIGINT); return ret; } diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c index a7e94e7ff87d..701a30f258b1 100644 --- a/samples/bpf/xdp_fwd_kern.c +++ b/samples/bpf/xdp_fwd_kern.c @@ -23,7 +23,8 @@ #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) -struct bpf_map_def SEC("maps") tx_port = { +/* For TX-traffic redirect requires net_device ifindex to be in this devmap */ +struct bpf_map_def SEC("maps") xdp_tx_ports = { .type = BPF_MAP_TYPE_DEVMAP, .key_size = sizeof(int), .value_size = sizeof(int), @@ -102,14 +103,34 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) fib_params.ifindex = ctx->ingress_ifindex; rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags); - - /* verify egress index has xdp support - * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with - * cannot pass map_type 14 into func bpf_map_lookup_elem#1: - * NOTE: without verification that egress index supports XDP - * forwarding packets are dropped. + /* + * Some rc (return codes) from bpf_fib_lookup() are important, + * to understand how this XDP-prog interacts with network stack. + * + * BPF_FIB_LKUP_RET_NO_NEIGH: + * Even if route lookup was a success, then the MAC-addresses are also + * needed. This is obtained from arp/neighbour table, but if table is + * (still) empty then BPF_FIB_LKUP_RET_NO_NEIGH is returned. To avoid + * doing ARP lookup directly from XDP, then send packet to normal + * network stack via XDP_PASS and expect it will do ARP resolution. + * + * BPF_FIB_LKUP_RET_FWD_DISABLED: + * The bpf_fib_lookup respect sysctl net.ipv{4,6}.conf.all.forwarding + * setting, and will return BPF_FIB_LKUP_RET_FWD_DISABLED if not + * enabled this on ingress device. */ - if (rc == 0) { + if (rc == BPF_FIB_LKUP_RET_SUCCESS) { + /* Verify egress index has been configured as TX-port. + * (Note: User can still have inserted an egress ifindex that + * doesn't support XDP xmit, which will result in packet drops). + * + * Note: lookup in devmap supported since 0cdbb4b09a0. + * If not supported will fail with: + * cannot pass map_type 14 into func bpf_map_lookup_elem#1: + */ + if (!bpf_map_lookup_elem(&xdp_tx_ports, &fib_params.ifindex)) + return XDP_PASS; + if (h_proto == htons(ETH_P_IP)) ip_decrease_ttl(iph); else if (h_proto == htons(ETH_P_IPV6)) @@ -117,7 +138,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags) memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN); memcpy(eth->h_source, fib_params.smac, ETH_ALEN); - return bpf_redirect_map(&tx_port, fib_params.ifindex, 0); + return bpf_redirect_map(&xdp_tx_ports, fib_params.ifindex, 0); } return XDP_PASS; diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 5b46ee12c696..97ff1dad7669 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -27,14 +27,20 @@ #include "libbpf.h" #include <bpf/bpf.h> - -static int do_attach(int idx, int fd, const char *name) +static int do_attach(int idx, int prog_fd, int map_fd, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, fd, 0); - if (err < 0) + err = bpf_set_link_xdp_fd(idx, prog_fd, 0); + if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); + return err; + } + + /* Adding ifindex as a possible egress TX port */ + err = bpf_map_update_elem(map_fd, &idx, &idx, 0); + if (err) + printf("ERROR: failed using device %s as TX-port\n", name); return err; } @@ -47,6 +53,9 @@ static int do_detach(int idx, const char *name) if (err < 0) printf("ERROR: failed to detach program from %s\n", name); + /* TODO: Remember to cleanup map, when adding use of shared map + * bpf_map_delete_elem((map_fd, &idx); + */ return err; } @@ -67,10 +76,10 @@ int main(int argc, char **argv) }; const char *prog_name = "xdp_fwd"; struct bpf_program *prog; + int prog_fd, map_fd = -1; char filename[PATH_MAX]; struct bpf_object *obj; int opt, i, idx, err; - int prog_fd, map_fd; int attach = 1; int ret = 0; @@ -103,8 +112,14 @@ int main(int argc, char **argv) return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + err = bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd); + if (err) { + printf("Does kernel support devmap lookup?\n"); + /* If not, the error message will be: + * "cannot pass map_type 14 into func bpf_map_lookup_elem#1" + */ return 1; + } prog = bpf_object__find_program_by_title(obj, prog_name); prog_fd = bpf_program__fd(prog); @@ -113,16 +128,12 @@ int main(int argc, char **argv) return 1; } map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj, - "tx_port")); + "xdp_tx_ports")); if (map_fd < 0) { printf("map not found: %s\n", strerror(map_fd)); return 1; } } - if (attach) { - for (i = 1; i < 64; ++i) - bpf_map_update_elem(map_fd, &i, &i, 0); - } for (i = optind; i < argc; ++i) { idx = if_nametoindex(argv[i]); @@ -138,7 +149,7 @@ int main(int argc, char **argv) if (err) ret = err; } else { - err = do_attach(idx, prog_fd, argv[i]); + err = do_attach(idx, prog_fd, map_fd, argv[i]); if (err) ret = err; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index dc66345a929a..3002714e3cd5 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -17,14 +17,13 @@ #include <linux/if_link.h> #include "perf-sys.h" -#include "trace_helpers.h" #define MAX_CPUS 128 -static int pmu_fds[MAX_CPUS], if_idx; -static struct perf_event_mmap_page *headers[MAX_CPUS]; +static int if_idx; static char *if_name; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static __u32 prog_id; +static struct perf_buffer *pb = NULL; static int do_attach(int idx, int fd, const char *name) { @@ -73,7 +72,7 @@ static int do_detach(int idx, const char *name) #define SAMPLE_SIZE 64 -static int print_bpf_output(void *data, int size) +static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) { struct { __u16 cookie; @@ -83,45 +82,20 @@ static int print_bpf_output(void *data, int size) int i; if (e->cookie != 0xdead) { - printf("BUG cookie %x sized %d\n", - e->cookie, size); - return LIBBPF_PERF_EVENT_ERROR; + printf("BUG cookie %x sized %d\n", e->cookie, size); + return; } printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len); for (i = 0; i < 14 && i < e->pkt_len; i++) printf("%02x ", e->pkt_data[i]); printf("\n"); - - return LIBBPF_PERF_EVENT_CONT; -} - -static void test_bpf_perf_event(int map_fd, int num) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - .wakeup_events = 1, /* get an fd notification for every event */ - }; - int i; - - for (i = 0; i < num; i++) { - int key = i; - - pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/, - -1/*group_fd*/, 0); - - assert(pmu_fds[i] >= 0); - assert(bpf_map_update_elem(map_fd, &key, - &pmu_fds[i], BPF_ANY) == 0); - ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0); - } } static void sig_handler(int signo) { do_detach(if_idx, if_name); + perf_buffer__free(pb); exit(0); } @@ -140,13 +114,13 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; + struct perf_buffer_opts pb_opts = {}; const char *optstr = "F"; int prog_fd, map_fd, opt; struct bpf_object *obj; struct bpf_map *map; char filename[256]; - int ret, err, i; - int numcpus; + int ret, err; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -169,10 +143,6 @@ int main(int argc, char **argv) return 1; } - numcpus = get_nprocs(); - if (numcpus > MAX_CPUS) - numcpus = MAX_CPUS; - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; @@ -211,14 +181,17 @@ int main(int argc, char **argv) return 1; } - test_bpf_perf_event(map_fd, numcpus); + pb_opts.sample_cb = print_bpf_output; + pb = perf_buffer__new(map_fd, 8, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + perror("perf_buffer setup failed"); + return 1; + } - for (i = 0; i < numcpus; i++) - if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0) - return 1; + while ((ret = perf_buffer__poll(pb, 1000)) >= 0) { + } - ret = perf_event_poller_multi(pmu_fds, headers, numcpus, - print_bpf_output); kill(0, SIGINT); return ret; } diff --git a/samples/vfio-mdev/mdpy-defs.h b/samples/vfio-mdev/mdpy-defs.h index 96b3b1b49d34..eb26421b6429 100644 --- a/samples/vfio-mdev/mdpy-defs.h +++ b/samples/vfio-mdev/mdpy-defs.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Simple pci display device. * diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 77c742fa4fb1..4b0432e095ae 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -190,9 +190,6 @@ echo-cmd = $(if $($(quiet)cmd_$(1)),\ # printing commands cmd = @set -e; $(echo-cmd) $(cmd_$(1)) -# Add $(obj)/ for paths that are not absolute -objectify = $(foreach o,$(1),$(if $(filter /%,$(o)),$(o),$(obj)/$(o))) - ### # if_changed - execute command if any prerequisite is newer than # target, or command line has changed diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 8a5c4d645eb1..4bbf4fc163a2 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -25,7 +25,7 @@ failure = $(if-success,$(1),n,y) # $(cc-option,<flag>) # Return y if the compiler supports <flag>, n otherwise -cc-option = $(success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null) +cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /dev/null) # $(ld-option,<flag>) # Return y if the linker supports <flag>, n otherwise diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5241d0751eb0..41c50f9461e5 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -45,7 +45,6 @@ subdir-ym := $(sort $(subdir-y) $(subdir-m)) multi-used-y := $(sort $(foreach m,$(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y))), $(m)))) multi-used-m := $(sort $(foreach m,$(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m))), $(m)))) multi-used := $(multi-used-y) $(multi-used-m) -single-used-m := $(sort $(filter-out $(multi-used-m),$(obj-m))) # $(subdir-obj-y) is the list of objects in $(obj-y) which uses dir/ to # tell kbuild to descend @@ -91,7 +90,6 @@ lib-y := $(addprefix $(obj)/,$(lib-y)) subdir-obj-y := $(addprefix $(obj)/,$(subdir-obj-y)) real-obj-y := $(addprefix $(obj)/,$(real-obj-y)) real-obj-m := $(addprefix $(obj)/,$(real-obj-m)) -single-used-m := $(addprefix $(obj)/,$(single-used-m)) multi-used-m := $(addprefix $(obj)/,$(multi-used-m)) subdir-ym := $(addprefix $(obj)/,$(subdir-ym)) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 6b19c1a4eae5..92ed02d7cd5e 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -38,12 +38,39 @@ # symbols in the final module linking stage # KBUILD_MODPOST_NOFINAL can be set to skip the final link of modules. # This is solely useful to speed up test compiles -PHONY := _modpost -_modpost: __modpost + +PHONY := __modpost +__modpost: include include/config/auto.conf include scripts/Kbuild.include +kernelsymfile := $(objtree)/Module.symvers +modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers + +MODPOST = scripts/mod/modpost \ + $(if $(CONFIG_MODVERSIONS),-m) \ + $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ + $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \ + $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \ + $(if $(KBUILD_EXTMOD),$(addprefix -e ,$(KBUILD_EXTRA_SYMBOLS))) \ + $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \ + $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ + $(if $(KBUILD_MODPOST_WARN),-w) + +ifdef MODPOST_VMLINUX + +__modpost: vmlinux.o + +quiet_cmd_modpost = MODPOST $@ + cmd_modpost = $(MODPOST) $@ + +PHONY += vmlinux.o +vmlinux.o: + $(call cmd,modpost) + +else + # When building external modules load the Kbuild file to retrieve EXTRA_SYMBOLS info ifneq ($(KBUILD_EXTMOD),) @@ -58,50 +85,27 @@ endif include scripts/Makefile.lib -kernelsymfile := $(objtree)/Module.symvers -modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers - modorder := $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/)modules.order -# Step 1), find all modules listed in modules.order -ifdef CONFIG_MODULES +# find all modules listed in modules.order modules := $(sort $(shell cat $(modorder))) -endif # Stop after building .o files if NOFINAL is set. Makes compile tests quicker -_modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules)) - -# Step 2), invoke modpost -# Includes step 3,4 -modpost = scripts/mod/modpost \ - $(if $(CONFIG_MODVERSIONS),-m) \ - $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a,) \ - $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \ - $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \ - $(if $(KBUILD_EXTRA_SYMBOLS), $(patsubst %, -e %,$(KBUILD_EXTRA_SYMBOLS))) \ - $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \ - $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ - $(if $(KBUILD_MODPOST_WARN),-w) - -MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS))) +__modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules)) + @: -# We can go over command line length here, so be careful. -quiet_cmd_modpost = MODPOST $(words $(filter-out vmlinux FORCE, $^)) modules - cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(modpost) $(MODPOST_OPT) -s -T - +MODPOST += $(subst -i,-n,$(filter -i,$(MAKEFLAGS))) -s -T - $(wildcard vmlinux) -PHONY += __modpost -__modpost: $(modules:.ko=.o) FORCE - $(call cmd,modpost) $(wildcard vmlinux) - -quiet_cmd_kernel-mod = MODPOST $@ - cmd_kernel-mod = $(modpost) $@ +# We can go over command line length here, so be careful. +quiet_cmd_modpost = MODPOST $(words $(modules)) modules + cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(MODPOST) -vmlinux.o: FORCE - $(call cmd,kernel-mod) +PHONY += modules-modpost +modules-modpost: + $(call cmd,modpost) # Declare generated files as targets for modpost -$(modules:.ko=.mod.c): __modpost ; - +$(modules:.ko=.mod.c): modules-modpost # Step 5), compile all *.mod.c files @@ -145,10 +149,10 @@ FORCE: # optimization, we don't need to read them if the target does not # exist, we will rebuild anyway in that case. -cmd_files := $(wildcard $(foreach f,$(sort $(targets)),$(dir $(f)).$(notdir $(f)).cmd)) +existing-targets := $(wildcard $(sort $(targets))) + +-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd) -ifneq ($(cmd_files),) - include $(cmd_files) endif .PHONY: $(PHONY) diff --git a/scripts/gen_compile_commands.py b/scripts/gen_compile_commands.py index 7915823b92a5..c458696ef3a7 100755 --- a/scripts/gen_compile_commands.py +++ b/scripts/gen_compile_commands.py @@ -21,9 +21,9 @@ _LINE_PATTERN = r'^cmd_[^ ]*\.o := (.* )([^ ]*\.c)$' _VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'] # A kernel build generally has over 2000 entries in its compile_commands.json -# database. If this code finds 500 or fewer, then warn the user that they might +# database. If this code finds 300 or fewer, then warn the user that they might # not have all the .cmd files, and they might need to compile the kernel. -_LOW_COUNT_THRESHOLD = 500 +_LOW_COUNT_THRESHOLD = 300 def parse_arguments(): diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh index 47f6f3ea0771..bbaf29386995 100755 --- a/scripts/headers_install.sh +++ b/scripts/headers_install.sh @@ -23,6 +23,12 @@ TMPFILE=$OUTFILE.tmp trap 'rm -f $OUTFILE $TMPFILE' EXIT +# SPDX-License-Identifier with GPL variants must have "WITH Linux-syscall-note" +if [ -n "$(sed -n -e "/SPDX-License-Identifier:.*GPL-/{/WITH Linux-syscall-note/!p}" $INFILE)" ]; then + echo "error: $INFILE: missing \"WITH Linux-syscall-note\" for SPDX-License-Identifier" >&2 + exit 1 +fi + sed -E -e ' s/([[:space:](])(__user|__force|__iomem)[[:space:]]/\1/g s/__attribute_const__([[:space:]]|$)/\1/g diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 1134892599da..3569d2dec37c 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -848,6 +848,7 @@ int conf_write(const char *name) const char *str; char tmpname[PATH_MAX + 1], oldname[PATH_MAX + 1]; char *env; + int i; bool need_newline = false; if (!name) @@ -930,6 +931,9 @@ next: } fclose(out); + for_all_symbols(i, sym) + sym->flags &= ~SYMBOL_WRITTEN; + if (*tmpname) { if (is_same(name, tmpname)) { conf_message("No change to %s", name); diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index a7124f895b24..c31193340108 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -56,8 +56,8 @@ modpost_link() } # Link of vmlinux -# ${1} - optional extra .o files -# ${2} - output file +# ${1} - output file +# ${@:2} - optional extra .o files vmlinux_link() { local lds="${objtree}/${KBUILD_LDS}" @@ -70,9 +70,9 @@ vmlinux_link() --start-group \ ${KBUILD_VMLINUX_LIBS} \ --end-group \ - ${1}" + ${@:2}" - ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \ + ${LD} ${KBUILD_LDFLAGS} ${LDFLAGS_vmlinux} -o ${1} \ -T ${lds} ${objects} else objects="-Wl,--whole-archive \ @@ -81,9 +81,9 @@ vmlinux_link() -Wl,--start-group \ ${KBUILD_VMLINUX_LIBS} \ -Wl,--end-group \ - ${1}" + ${@:2}" - ${CC} ${CFLAGS_vmlinux} -o ${2} \ + ${CC} ${CFLAGS_vmlinux} -o ${1} \ -Wl,-T,${lds} \ ${objects} \ -lutil -lrt -lpthread @@ -92,23 +92,34 @@ vmlinux_link() } # generate .BTF typeinfo from DWARF debuginfo +# ${1} - vmlinux image +# ${2} - file to dump raw BTF data into gen_btf() { - local pahole_ver; + local pahole_ver + local bin_arch if ! [ -x "$(command -v ${PAHOLE})" ]; then info "BTF" "${1}: pahole (${PAHOLE}) is not available" - return 0 + return 1 fi pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/') if [ "${pahole_ver}" -lt "113" ]; then info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13" - return 0 + return 1 fi - info "BTF" ${1} + info "BTF" ${2} + vmlinux_link ${1} LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1} + + # dump .BTF section into raw binary file to link with final vmlinux + bin_arch=$(${OBJDUMP} -f ${1} | grep architecture | \ + cut -d, -f1 | cut -d' ' -f2) + ${OBJCOPY} --dump-section .BTF=.btf.vmlinux.bin ${1} 2>/dev/null + ${OBJCOPY} -I binary -O ${CONFIG_OUTPUT_FORMAT} -B ${bin_arch} \ + --rename-section .data=.BTF .btf.vmlinux.bin ${2} } # Create ${2} .o file with all symbols from the ${1} object file @@ -153,6 +164,7 @@ sortextable() # Delete output files in case of error cleanup() { + rm -f .btf.* rm -f .tmp_System.map rm -f .tmp_kallsyms* rm -f .tmp_vmlinux* @@ -210,11 +222,18 @@ info LD vmlinux.o modpost_link vmlinux.o # modpost vmlinux.o to check for section mismatches -${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o +${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1 info MODINFO modules.builtin.modinfo ${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo +btf_vmlinux_bin_o="" +if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then + if gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then + btf_vmlinux_bin_o=.btf.vmlinux.bin.o + fi +fi + kallsymso="" kallsyms_vmlinux="" if [ -n "${CONFIG_KALLSYMS}" ]; then @@ -246,11 +265,11 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsyms_vmlinux=.tmp_vmlinux2 # step 1 - vmlinux_link "" .tmp_vmlinux1 + vmlinux_link .tmp_vmlinux1 ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux1 .tmp_kallsyms1.o # step 2 - vmlinux_link .tmp_kallsyms1.o .tmp_vmlinux2 + vmlinux_link .tmp_vmlinux2 .tmp_kallsyms1.o ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux2 .tmp_kallsyms2.o # step 3 @@ -261,18 +280,13 @@ if [ -n "${CONFIG_KALLSYMS}" ]; then kallsymso=.tmp_kallsyms3.o kallsyms_vmlinux=.tmp_vmlinux3 - vmlinux_link .tmp_kallsyms2.o .tmp_vmlinux3 - + vmlinux_link .tmp_vmlinux3 .tmp_kallsyms2.o ${btf_vmlinux_bin_o} kallsyms .tmp_vmlinux3 .tmp_kallsyms3.o fi fi info LD vmlinux -vmlinux_link "${kallsymso}" vmlinux - -if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then - gen_btf vmlinux -fi +vmlinux_link vmlinux "${kallsymso}" "${btf_vmlinux_bin_o}" if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then info SORTEX vmlinux diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install index f230e65329a2..3b638c0e1a4f 100755 --- a/scripts/sphinx-pre-install +++ b/scripts/sphinx-pre-install @@ -83,6 +83,17 @@ sub check_missing(%) foreach my $prog (sort keys %missing) { my $is_optional = $missing{$prog}; + # At least on some LTS distros like CentOS 7, texlive doesn't + # provide all packages we need. When such distros are + # detected, we have to disable PDF output. + # + # So, we need to ignore the packages that distros would + # need for LaTeX to work + if ($is_optional == 2 && !$pdf) { + $optional--; + next; + } + if ($is_optional) { print "Warning: better to also install \"$prog\".\n"; } else { @@ -333,10 +344,13 @@ sub give_debian_hints() if ($pdf) { check_missing_file("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", - "fonts-dejavu", 1); + "fonts-dejavu", 2); + + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc", + "fonts-noto-cjk", 2); } - check_program("dvipng", 1) if ($pdf); + check_program("dvipng", 2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -363,6 +377,7 @@ sub give_redhat_hints() my @fedora_tex_pkgs = ( "texlive-collection-fontsrecommended", "texlive-collection-latex", + "texlive-xecjk", "dejavu-sans-fonts", "dejavu-serif-fonts", "dejavu-sans-mono-fonts", @@ -371,22 +386,45 @@ sub give_redhat_hints() # # Checks valid for RHEL/CentOS version 7.x. # - if (! $system_release =~ /Fedora/) { + my $old = 0; + my $rel; + $rel = $1 if ($system_release =~ /release\s+(\d+)/); + + if (!($system_release =~ /Fedora/)) { $map{"virtualenv"} = "python-virtualenv"; - } - my $release; + if ($rel && $rel < 8) { + $old = 1; + $pdf = 0; + + printf("Note: texlive packages on RHEL/CENTOS <= 7 are incomplete. Can't support PDF output\n"); + printf("If you want to build PDF, please read:\n"); + printf("\thttps://www.systutorials.com/241660/how-to-install-tex-live-on-centos-7-linux/\n"); + } + } else { + if ($rel && $rel < 26) { + $old = 1; + } + } + if (!$rel) { + printf("Couldn't identify release number\n"); + $old = 1; + $pdf = 0; + } - $release = $1 if ($system_release =~ /Fedora\s+release\s+(\d+)/); + if ($pdf) { + check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc", + "google-noto-sans-cjk-ttc-fonts", 2); + } - check_rpm_missing(\@fedora26_opt_pkgs, 1) if ($pdf && $release >= 26); - check_rpm_missing(\@fedora_tex_pkgs, 1) if ($pdf); - check_missing_tex(1) if ($pdf); + check_rpm_missing(\@fedora26_opt_pkgs, 2) if ($pdf && !$old); + check_rpm_missing(\@fedora_tex_pkgs, 2) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); - if ($release >= 18) { + if (!$old) { # dnf, for Fedora 18+ printf("You should run:\n\n\tsudo dnf install -y $install\n"); } else { @@ -425,8 +463,15 @@ sub give_opensuse_hints() "texlive-zapfding", ); - check_rpm_missing(\@suse_tex_pkgs, 1) if ($pdf); - check_missing_tex(1) if ($pdf); + $map{"latexmk"} = "texlive-latexmk-bin"; + + # FIXME: add support for installing CJK fonts + # + # I tried hard, but was unable to find a way to install + # "Noto Sans CJK SC" on openSUSE + + check_rpm_missing(\@suse_tex_pkgs, 2) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -450,7 +495,14 @@ sub give_mageia_hints() "texlive-fontsextra", ); - check_rpm_missing(\@tex_pkgs, 1) if ($pdf); + $map{"latexmk"} = "texlive-collection-basic"; + + if ($pdf) { + check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc", + "google-noto-sans-cjk-ttc-fonts", 2); + } + + check_rpm_missing(\@tex_pkgs, 2) if ($pdf); check_missing(\%map); return if (!$need && !$optional); @@ -473,7 +525,13 @@ sub give_arch_linux_hints() "texlive-latexextra", "ttf-dejavu", ); - check_pacman_missing(\@archlinux_tex_pkgs, 1) if ($pdf); + check_pacman_missing(\@archlinux_tex_pkgs, 2) if ($pdf); + + if ($pdf) { + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc", + "noto-fonts-cjk", 2); + } + check_missing(\%map); return if (!$need && !$optional); @@ -492,15 +550,31 @@ sub give_gentoo_hints() ); check_missing_file("/usr/share/fonts/dejavu/DejaVuSans.ttf", - "media-fonts/dejavu", 1) if ($pdf); + "media-fonts/dejavu", 2) if ($pdf); + + if ($pdf) { + check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJKsc-Regular.otf", + "media-fonts/noto-cjk", 2); + } check_missing(\%map); return if (!$need && !$optional); printf("You should run:\n\n"); - printf("\tsudo su -c 'echo \"media-gfx/imagemagick svg png\" > /etc/portage/package.use/imagemagick'\n"); - printf("\tsudo su -c 'echo \"media-gfx/graphviz cairo pdf\" > /etc/portage/package.use/graphviz'\n"); + + my $imagemagick = "media-gfx/imagemagick svg png"; + my $cairo = "media-gfx/graphviz cairo pdf"; + my $portage_imagemagick = "/etc/portage/package.use/imagemagick"; + my $portage_cairo = "/etc/portage/package.use/graphviz"; + + if (qx(cat $portage_imagemagick) ne "$imagemagick\n") { + printf("\tsudo su -c 'echo \"$imagemagick\" > $portage_imagemagick'\n") + } + if (qx(cat $portage_cairo) ne "$cairo\n") { + printf("\tsudo su -c 'echo \"$cairo\" > $portage_cairo'\n"); + } + printf("\tsudo emerge --ask $install\n"); } @@ -560,7 +634,7 @@ sub check_distros() my %map = ( "sphinx-build" => "sphinx" ); - check_missing_tex(1) if ($pdf); + check_missing_tex(2) if ($pdf); check_missing(\%map); print "I don't know distro $system_release.\n"; print "So, I can't provide you a hint with the install procedure.\n"; @@ -589,11 +663,13 @@ sub check_needs() check_program("make", 0); check_program("gcc", 0); check_python_module("sphinx_rtd_theme", 1) if (!$virtualenv); - check_program("xelatex", 1) if ($pdf); check_program("dot", 1); check_program("convert", 1); - check_program("rsvg-convert", 1) if ($pdf); - check_program("latexmk", 1) if ($pdf); + + # Extra PDF files - should use 2 for is_optional + check_program("xelatex", 2) if ($pdf); + check_program("rsvg-convert", 2) if ($pdf); + check_program("latexmk", 2) if ($pdf); check_distros(); diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index a1ffe2eb4d5f..af4c979b38ee 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -61,6 +61,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF bool "zero-init structs passed by reference (strong)" depends on GCC_PLUGINS + depends on !(KASAN && KASAN_STACK=1) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any structures on the stack that may @@ -70,9 +71,15 @@ choice exposures, like CVE-2017-1000410: https://git.kernel.org/linus/06e7e776ca4d3654 + As a side-effect, this keeps a lot of variables on the + stack that can otherwise be optimized out, so combining + this with CONFIG_KASAN_STACK can lead to a stack overflow + and is disallowed. + config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL bool "zero-init anything passed by reference (very strong)" depends on GCC_PLUGINS + depends on !(KASAN && KASAN_STACK=1) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any stack variables that may be passed diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 624ccc6ac744..f8efaa9f647c 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -272,6 +272,8 @@ static int rangetr_cmp(struct hashtab *h, const void *k1, const void *k2) return v; } +static int (*destroy_f[SYM_NUM]) (void *key, void *datum, void *datap); + /* * Initialize a policy database structure. */ @@ -319,8 +321,10 @@ static int policydb_init(struct policydb *p) out: hashtab_destroy(p->filename_trans); hashtab_destroy(p->range_tr); - for (i = 0; i < SYM_NUM; i++) + for (i = 0; i < SYM_NUM; i++) { + hashtab_map(p->symtab[i].table, destroy_f[i], NULL); hashtab_destroy(p->symtab[i].table); + } return rc; } diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index e63a90ff2728..1f0a6eaa2d6a 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -286,6 +286,11 @@ static int sidtab_reverse_lookup(struct sidtab *s, struct context *context, ++count; } + /* bail out if we already reached max entries */ + rc = -EOVERFLOW; + if (count >= SIDTAB_MAX) + goto out_unlock; + /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c index 7b977b753a03..7985dd8198b6 100644 --- a/sound/ac97/bus.c +++ b/sound/ac97/bus.c @@ -122,17 +122,12 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx, vendor_id); ret = device_add(&codec->dev); - if (ret) - goto err_free_codec; + if (ret) { + put_device(&codec->dev); + return ret; + } return 0; -err_free_codec: - of_node_put(codec->dev.of_node); - put_device(&codec->dev); - kfree(codec); - ac97_ctrl->codecs[idx] = NULL; - - return ret; } unsigned int snd_ac97_bus_scan_one(struct ac97_controller *adrv, diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 99b882158705..41905afada63 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -574,10 +574,7 @@ snd_compr_set_params(struct snd_compr_stream *stream, unsigned long arg) stream->metadata_set = false; stream->next_track = false; - if (stream->direction == SND_COMPRESS_PLAYBACK) - stream->runtime->state = SNDRV_PCM_STATE_SETUP; - else - stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + stream->runtime->state = SNDRV_PCM_STATE_SETUP; } else { return -EPERM; } @@ -693,8 +690,17 @@ static int snd_compr_start(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state != SNDRV_PCM_STATE_PREPARED) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_SETUP: + if (stream->direction != SND_COMPRESS_CAPTURE) + return -EPERM; + break; + case SNDRV_PCM_STATE_PREPARED: + break; + default: return -EPERM; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_START); if (!retval) stream->runtime->state = SNDRV_PCM_STATE_RUNNING; @@ -705,9 +711,15 @@ static int snd_compr_stop(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: return -EPERM; + default: + break; + } + retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP); if (!retval) { snd_compr_drain_notify(stream); @@ -795,9 +807,17 @@ static int snd_compr_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; + default: + break; + } retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN); if (retval) { @@ -817,6 +837,10 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING) return -EPERM; + /* next track doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) + return -EPERM; + /* you can signal next track if this is intended to be a gapless stream * and current track metadata is set */ @@ -834,9 +858,23 @@ static int snd_compr_next_track(struct snd_compr_stream *stream) static int snd_compr_partial_drain(struct snd_compr_stream *stream) { int retval; - if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED || - stream->runtime->state == SNDRV_PCM_STATE_SETUP) + + switch (stream->runtime->state) { + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_PREPARED: + case SNDRV_PCM_STATE_PAUSED: + return -EPERM; + case SNDRV_PCM_STATE_XRUN: + return -EPIPE; + default: + break; + } + + /* partial drain doesn't have any meaning for capture streams */ + if (stream->direction == SND_COMPRESS_CAPTURE) return -EPERM; + /* stream can be drained only when next track has been signalled */ if (stream->next_track == false) return -EPERM; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 860543a4c840..703857aab00f 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -77,7 +77,7 @@ void snd_pcm_group_init(struct snd_pcm_group *group) spin_lock_init(&group->lock); mutex_init(&group->mutex); INIT_LIST_HEAD(&group->substreams); - refcount_set(&group->refs, 0); + refcount_set(&group->refs, 1); } /* define group lock helpers */ @@ -1096,8 +1096,7 @@ static void snd_pcm_group_unref(struct snd_pcm_group *group, if (!group) return; - do_free = refcount_dec_and_test(&group->refs) && - list_empty(&group->substreams); + do_free = refcount_dec_and_test(&group->refs); snd_pcm_group_unlock(group, substream->pcm->nonatomic); if (do_free) kfree(group); @@ -1874,6 +1873,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, if (!to_check) break; /* all drained */ init_waitqueue_entry(&wait, current); + set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); if (runtime->no_period_wakeup) @@ -1886,7 +1886,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream, } tout = msecs_to_jiffies(tout * 1000); } - tout = schedule_timeout_interruptible(tout); + tout = schedule_timeout(tout); snd_pcm_stream_lock_irq(substream); group = snd_pcm_stream_group_ref(substream); @@ -2020,6 +2020,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) snd_pcm_group_lock_irq(target_group, nonatomic); snd_pcm_stream_lock(substream1); snd_pcm_group_assign(substream1, target_group); + refcount_inc(&target_group->refs); snd_pcm_stream_unlock(substream1); snd_pcm_group_unlock_irq(target_group, nonatomic); _end: @@ -2056,13 +2057,14 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) snd_pcm_group_lock_irq(group, nonatomic); relink_to_local(substream); + refcount_dec(&group->refs); /* detach the last stream, too */ if (list_is_singular(&group->substreams)) { relink_to_local(list_first_entry(&group->substreams, struct snd_pcm_substream, link_list)); - do_free = !refcount_read(&group->refs); + do_free = refcount_dec_and_test(&group->refs); } snd_pcm_group_unlock_irq(group, nonatomic); diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 1192c7561d62..3c2db3816029 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -136,10 +136,12 @@ int snd_hdac_i915_init(struct hdac_bus *bus) if (!acomp) return -ENODEV; if (!acomp->ops) { - request_module("i915"); - /* 60s timeout */ - wait_for_completion_timeout(&bind_complete, - msecs_to_jiffies(60 * 1000)); + if (!IS_ENABLED(CONFIG_MODULES) || + !request_module("i915")) { + /* 60s timeout */ + wait_for_completion_timeout(&bind_complete, + msecs_to_jiffies(60 * 1000)); + } } if (!acomp->ops) { dev_info(bus->dev, "couldn't bind with audio component\n"); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index e30e86ca6b72..51f10ed9bc43 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2942,7 +2942,7 @@ static int hda_codec_runtime_resume(struct device *dev) static int hda_codec_force_resume(struct device *dev) { struct hda_codec *codec = dev_to_hda_codec(dev); - bool forced_resume = !codec->relaxed_resume; + bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used; int ret; /* The get/put pair below enforces the runtime resume even if the diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index cb8b0945547c..1e14d7270adf 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -313,11 +313,10 @@ enum { #define AZX_DCAPS_INTEL_SKYLAKE \ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_SYNC_WRITE |\ AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) -#define AZX_DCAPS_INTEL_BROXTON \ - (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\ - AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT) +#define AZX_DCAPS_INTEL_BROXTON AZX_DCAPS_INTEL_SKYLAKE /* quirks for ATI SB / AMD Hudson */ #define AZX_DCAPS_PRESET_ATI_SB \ diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4f8d0845ee1e..f299f137eaea 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1083,6 +1083,7 @@ static int patch_conexant_auto(struct hda_codec *codec) */ static const struct hda_device_id snd_hda_id_conexant[] = { + HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto), HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto), diff --git a/sound/usb/helper.c b/sound/usb/helper.c index 71d5f540334a..4c12cc5b53fd 100644 --- a/sound/usb/helper.c +++ b/sound/usb/helper.c @@ -72,7 +72,7 @@ int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe) struct usb_host_endpoint *ep; ep = usb_pipe_endpoint(dev, pipe); - if (usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)]) + if (!ep || usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)]) return -EINVAL; return 0; } diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index f0662bd4e50f..27bf61c177c0 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -368,7 +368,7 @@ static const struct line6_properties podhd_properties_table[] = { .name = "POD HD500", .capabilities = LINE6_CAP_PCM | LINE6_CAP_HWMON, - .altsetting = 1, + .altsetting = 0, .ep_ctrl_r = 0x81, .ep_ctrl_w = 0x01, .ep_audio_r = 0x86, diff --git a/sound/usb/line6/variax.c b/sound/usb/line6/variax.c index 0d24c72c155f..ed158f04de80 100644 --- a/sound/usb/line6/variax.c +++ b/sound/usb/line6/variax.c @@ -244,5 +244,5 @@ static struct usb_driver variax_driver = { module_usb_driver(variax_driver); -MODULE_DESCRIPTION("Vairax Workbench USB driver"); +MODULE_DESCRIPTION("Variax Workbench USB driver"); MODULE_LICENSE("GPL"); diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 4602464ebdfb..a4217c1a5d01 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -214,6 +214,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) + /* Higher values mean better protection. */ +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index d819a3e8b552..9a507716ae2f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -229,6 +229,16 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_FW | ((r) & 0xffff)) #define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h index f33105bc5ca6..8601d824a9c6 100644 --- a/tools/arch/powerpc/include/uapi/asm/mman.h +++ b/tools/arch/powerpc/include/uapi/asm/mman.h @@ -4,12 +4,8 @@ #define MAP_DENYWRITE 0x0800 #define MAP_EXECUTABLE 0x1000 #define MAP_GROWSDOWN 0x0100 -#define MAP_HUGETLB 0x40000 #define MAP_LOCKED 0x80 -#define MAP_NONBLOCK 0x10000 #define MAP_NORESERVE 0x40 -#define MAP_POPULATE 0x8000 -#define MAP_STACK 0x20000 #include <uapi/asm-generic/mman-common.h> /* MAP_32BIT is undefined on powerpc, fix it for perf */ #define MAP_32BIT 0 diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h index 38920eed8cbf..7b94dccc843d 100644 --- a/tools/arch/sparc/include/uapi/asm/mman.h +++ b/tools/arch/sparc/include/uapi/asm/mman.h @@ -4,12 +4,8 @@ #define MAP_DENYWRITE 0x0800 #define MAP_EXECUTABLE 0x1000 #define MAP_GROWSDOWN 0x0200 -#define MAP_HUGETLB 0x40000 #define MAP_LOCKED 0x100 -#define MAP_NONBLOCK 0x10000 #define MAP_NORESERVE 0x40 -#define MAP_POPULATE 0x8000 -#define MAP_STACK 0x20000 #include <uapi/asm-generic/mman-common.h> /* MAP_32BIT is undefined on sparc, fix it for perf */ #define MAP_32BIT 0 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index d6ab5b4d15e5..503d3f42da16 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,10 +378,11 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; -#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) -#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) -#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) -#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */ @@ -432,4 +433,17 @@ struct kvm_nested_state { } data; }; +/* for KVM_CAP_PMU_EVENT_FILTER */ +struct kvm_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 pad[4]; + __u64 events[0]; +}; + +#define KVM_PMU_EVENT_ALLOW 0 +#define KVM_PMU_EVENT_DENY 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index d213ec5c3766..f0b0c90dd398 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -146,7 +146,6 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 -#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 585f270c2d25..06a28b07787d 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -20,8 +20,8 @@ SYNOPSIS CGROUP COMMANDS =============== -| **bpftool** **cgroup { show | list }** *CGROUP* -| **bpftool** **cgroup tree** [*CGROUP_ROOT*] +| **bpftool** **cgroup { show | list }** *CGROUP* [**effective**] +| **bpftool** **cgroup tree** [*CGROUP_ROOT*] [**effective**] | **bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] | **bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* | **bpftool** **cgroup help** @@ -35,13 +35,17 @@ CGROUP COMMANDS DESCRIPTION =========== - **bpftool cgroup { show | list }** *CGROUP* + **bpftool cgroup { show | list }** *CGROUP* [**effective**] List all programs attached to the cgroup *CGROUP*. Output will start with program ID followed by attach type, attach flags and program name. - **bpftool cgroup tree** [*CGROUP_ROOT*] + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + + **bpftool cgroup tree** [*CGROUP_ROOT*] [**effective**] Iterate over all cgroups in *CGROUP_ROOT* and list all attached programs. If *CGROUP_ROOT* is not specified, bpftool uses cgroup v2 mountpoint. @@ -50,6 +54,10 @@ DESCRIPTION commands: it starts with absolute cgroup path, followed by program ID, attach type, attach flags and program name. + If **effective** is specified retrieve effective programs that + will execute for events within a cgroup. This includes + inherited along with attached ones. + **bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*] Attach program *PROG* to the cgroup *CGROUP* with attach type *ATTACH_TYPE* and optional *ATTACH_FLAGS*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 490b4501cb6e..61d1d270eb5e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -46,7 +46,7 @@ MAP COMMANDS | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** | | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** | | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** -| | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index a7afea4dec47..4c9d1ffc3fc7 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -52,14 +52,14 @@ ifneq ($(EXTRA_LDFLAGS),) LDFLAGS += $(EXTRA_LDFLAGS) endif -LIBS = -lelf $(LIBBPF) +LIBS = -lelf -lz $(LIBBPF) INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray -FEATURE_DISPLAY = libbfd disassembler-four-args +FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib +FEATURE_DISPLAY = libbfd disassembler-four-args zlib check_feat := 1 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall @@ -111,6 +111,8 @@ OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< +$(OUTPUT)feature.o: | zdep + $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ $(LIBS) @@ -149,6 +151,9 @@ doc-uninstall: FORCE: -.PHONY: all FORCE clean install uninstall +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + +.PHONY: all FORCE clean install uninstall zdep .PHONY: doc doc-clean doc-install doc-uninstall .DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index c8f42e1fcbc9..df16c5415444 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -489,8 +489,8 @@ _bpftool() perf_event_array percpu_hash percpu_array \ stack_trace cgroup_array lru_hash \ lru_percpu_hash lpm_trie array_of_maps \ - hash_of_maps devmap sockmap cpumap xskmap \ - sockhash cgroup_storage reuseport_sockarray \ + hash_of_maps devmap devmap_hash sockmap cpumap \ + xskmap sockhash cgroup_storage reuseport_sockarray \ percpu_cgroup_storage queue stack' -- \ "$cur" ) ) return 0 @@ -710,12 +710,15 @@ _bpftool() ;; cgroup) case $command in - show|list) - _filedir - return 0 - ;; - tree) - _filedir + show|list|tree) + case $cword in + 3) + _filedir + ;; + 4) + COMPREPLY=( $( compgen -W 'effective' -- "$cur" ) ) + ;; + esac return 0 ;; attach|detach) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index f3c05b08c68c..44352b5aca85 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -29,6 +29,8 @@ " recvmsg4 | recvmsg6 | sysctl |\n" \ " getsockopt | setsockopt }" +static unsigned int query_flags; + static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", [BPF_CGROUP_INET_EGRESS] = "egress", @@ -107,7 +109,8 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) __u32 prog_cnt = 0; int ret; - ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, NULL, + NULL, &prog_cnt); if (ret) return -1; @@ -125,8 +128,8 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int ret; prog_cnt = ARRAY_SIZE(prog_ids); - ret = bpf_prog_query(cgroup_fd, type, 0, &attach_flags, prog_ids, - &prog_cnt); + ret = bpf_prog_query(cgroup_fd, type, query_flags, &attach_flags, + prog_ids, &prog_cnt); if (ret) return ret; @@ -158,20 +161,34 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + const char *path; int cgroup_fd; int ret = -1; - if (argc < 1) { - p_err("too few parameters for cgroup show"); - goto exit; - } else if (argc > 1) { - p_err("too many parameters for cgroup show"); - goto exit; + query_flags = 0; + + if (!REQ_ARGS(1)) + return -1; + path = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } } - cgroup_fd = open(argv[0], O_RDONLY); + cgroup_fd = open(path, O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[0]); + p_err("can't open cgroup %s", path); goto exit; } @@ -294,26 +311,37 @@ static char *find_cgroup_root(void) static int do_show_tree(int argc, char **argv) { - char *cgroup_root; + char *cgroup_root, *cgroup_alloced = NULL; int ret; - switch (argc) { - case 0: - cgroup_root = find_cgroup_root(); - if (!cgroup_root) { + query_flags = 0; + + if (!argc) { + cgroup_alloced = find_cgroup_root(); + if (!cgroup_alloced) { p_err("cgroup v2 isn't mounted"); return -1; } - break; - case 1: - cgroup_root = argv[0]; - break; - default: - p_err("too many parameters for cgroup tree"); - return -1; + cgroup_root = cgroup_alloced; + } else { + cgroup_root = GET_ARG(); + + while (argc) { + if (is_prefix(*argv, "effective")) { + if (query_flags & BPF_F_QUERY_EFFECTIVE) { + p_err("duplicated argument: %s", *argv); + return -1; + } + query_flags |= BPF_F_QUERY_EFFECTIVE; + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'effective', got: '%s'?", + *argv); + return -1; + } + } } - if (json_output) jsonw_start_array(json_wtr); else @@ -338,8 +366,7 @@ static int do_show_tree(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); - if (argc == 0) - free(cgroup_root); + free(cgroup_alloced); return ret; } @@ -459,8 +486,8 @@ static int do_help(int argc, char **argv) } fprintf(stderr, - "Usage: %s %s { show | list } CGROUP\n" - " %s %s tree [CGROUP_ROOT]\n" + "Usage: %s %s { show | list } CGROUP [**effective**]\n" + " %s %s tree [CGROUP_ROOT] [**effective**]\n" " %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index d672d9086fff..03bdc5b3ac49 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -14,6 +14,7 @@ #include <bpf.h> #include <libbpf.h> +#include <zlib.h> #include "main.h" @@ -284,34 +285,32 @@ static void probe_jit_limit(void) } } -static char *get_kernel_config_option(FILE *fd, const char *option) +static bool read_next_kernel_config_option(gzFile file, char *buf, size_t n, + char **value) { - size_t line_n = 0, optlen = strlen(option); - char *res, *strval, *line = NULL; - ssize_t n; + char *sep; - rewind(fd); - while ((n = getline(&line, &line_n, fd)) > 0) { - if (strncmp(line, option, optlen)) + while (gzgets(file, buf, n)) { + if (strncmp(buf, "CONFIG_", 7)) continue; - /* Check we have at least '=', value, and '\n' */ - if (strlen(line) < optlen + 3) - continue; - if (*(line + optlen) != '=') + + sep = strchr(buf, '='); + if (!sep) continue; /* Trim ending '\n' */ - line[strlen(line) - 1] = '\0'; + buf[strlen(buf) - 1] = '\0'; + + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) + continue; - /* Copy and return config option value */ - strval = line + optlen + 1; - res = strdup(strval); - free(line); - return res; + *value = sep + 1; + return true; } - free(line); - return NULL; + return false; } static void probe_kernel_image_config(void) @@ -386,59 +385,61 @@ static void probe_kernel_image_config(void) /* test_bpf module for BPF tests */ "CONFIG_TEST_BPF", }; - char *value, *buf = NULL; + char *values[ARRAY_SIZE(options)] = { }; struct utsname utsn; char path[PATH_MAX]; - size_t i, n; - ssize_t ret; - FILE *fd; + gzFile file = NULL; + char buf[4096]; + char *value; + size_t i; - if (uname(&utsn)) - goto no_config; + if (!uname(&utsn)) { + snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); - snprintf(path, sizeof(path), "/boot/config-%s", utsn.release); + /* gzopen also accepts uncompressed files. */ + file = gzopen(path, "r"); + } - fd = fopen(path, "r"); - if (!fd && errno == ENOENT) { - /* Some distributions put the config file at /proc/config, give - * it a try. - * Sometimes it is also at /proc/config.gz but we do not try - * this one for now, it would require linking against libz. + if (!file) { + /* Some distributions build with CONFIG_IKCONFIG=y and put the + * config file at /proc/config.gz. */ - fd = fopen("/proc/config", "r"); + file = gzopen("/proc/config.gz", "r"); } - if (!fd) { + if (!file) { p_info("skipping kernel config, can't open file: %s", strerror(errno)); - goto no_config; + goto end_parse; } /* Sanity checks */ - ret = getline(&buf, &n, fd); - ret = getline(&buf, &n, fd); - if (!buf || !ret) { + if (!gzgets(file, buf, sizeof(buf)) || + !gzgets(file, buf, sizeof(buf))) { p_info("skipping kernel config, can't read from file: %s", strerror(errno)); - free(buf); - goto no_config; + goto end_parse; } if (strcmp(buf, "# Automatically generated file; DO NOT EDIT.\n")) { p_info("skipping kernel config, can't find correct file"); - free(buf); - goto no_config; + goto end_parse; } - free(buf); - for (i = 0; i < ARRAY_SIZE(options); i++) { - value = get_kernel_config_option(fd, options[i]); - print_kernel_option(options[i], value); - free(value); + while (read_next_kernel_config_option(file, buf, sizeof(buf), &value)) { + for (i = 0; i < ARRAY_SIZE(options); i++) { + if (values[i] || strcmp(buf, options[i])) + continue; + + values[i] = strdup(value); + } } - fclose(fd); - return; -no_config: - for (i = 0; i < ARRAY_SIZE(options); i++) - print_kernel_option(options[i], NULL); +end_parse: + if (file) + gzclose(file); + + for (i = 0; i < ARRAY_SIZE(options); i++) { + print_kernel_option(options[i], values[i]); + free(values[i]); + } } static bool probe_bpf_syscall(const char *define_prefix) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 5da5a7311f13..bfbbc6b4cb83 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -37,6 +37,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", [BPF_MAP_TYPE_XSKMAP] = "xskmap", @@ -1271,7 +1272,7 @@ static int do_help(int argc, char **argv) " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" " percpu_array | stack_trace | cgroup_array | lru_hash |\n" " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" - " devmap | sockmap | cpumap | xskmap | sockhash |\n" + " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index abd238d0f7a4..63b1f506ea67 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -19,15 +19,18 @@ #define MAP_TYPE 0x0f /* Mask for type of mapping */ #define MAP_FIXED 0x10 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20 /* don't use a file */ -#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED -# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be uninitialized */ -#else -# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */ -#endif -/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */ +/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */ +#define MAP_POPULATE 0x008000 /* populate (prefault) pagetables */ +#define MAP_NONBLOCK 0x010000 /* do not block on IO */ +#define MAP_STACK 0x020000 /* give out an address that is best suited for process/thread stacks */ +#define MAP_HUGETLB 0x040000 /* create a huge page mapping */ +#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be + * uninitialized */ + /* * Flags for mlock */ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 36c197fc44a0..406f7718f9ad 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -9,13 +9,11 @@ #define MAP_EXECUTABLE 0x1000 /* mark it as an executable */ #define MAP_LOCKED 0x2000 /* pages are locked */ #define MAP_NORESERVE 0x4000 /* don't check for reservations */ -#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ -#define MAP_NONBLOCK 0x10000 /* do not block on IO */ -#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ -#define MAP_HUGETLB 0x40000 /* create a huge page mapping */ -#define MAP_SYNC 0x80000 /* perform synchronous page faults for the mapping */ -/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */ +/* + * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h + * for MAP_HUGETLB usage + */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a87904daf103..1be0e798e362 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -844,9 +844,15 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig) __SYSCALL(__NR_fsmount, sys_fsmount) #define __NR_fspick 433 __SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) +#ifdef __ARCH_WANT_SYS_CLONE3 +#define __NR_clone3 435 +__SYSCALL(__NR_clone3, sys_clone3) +#endif #undef __NR_syscalls -#define __NR_syscalls 434 +#define __NR_syscalls 436 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 661d73f9a919..8a5b2f8f8eb9 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -50,6 +50,7 @@ typedef unsigned int drm_handle_t; #else /* One of the BSDs */ +#include <stdint.h> #include <sys/ioccom.h> #include <sys/types.h> typedef int8_t __s8; diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 3a73f5316766..328d05e77d9f 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -136,6 +136,8 @@ enum drm_i915_gem_engine_class { struct i915_engine_class_instance { __u16 engine_class; /* see enum drm_i915_gem_engine_class */ __u16 engine_instance; +#define I915_ENGINE_CLASS_INVALID_NONE -1 +#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 }; /** @@ -355,6 +357,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_PERF_ADD_CONFIG 0x37 #define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_I915_QUERY 0x39 +#define DRM_I915_GEM_VM_CREATE 0x3a +#define DRM_I915_GEM_VM_DESTROY 0x3b /* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) @@ -415,6 +419,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) #define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query) +#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control) +#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -598,6 +604,12 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_MMAP_GTT_COHERENT 52 +/* + * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel + * execution through use of explicit fence support. + * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT. + */ +#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53 /* Must be kept compact -- no holes and well documented */ typedef struct drm_i915_getparam { @@ -1120,7 +1132,16 @@ struct drm_i915_gem_execbuffer2 { */ #define I915_EXEC_FENCE_ARRAY (1<<19) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) +/* + * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent + * a sync_file fd to wait upon (in a nonblocking manner) prior to executing + * the batch. + * + * Returns -EINVAL if the sync_file fd cannot be found. + */ +#define I915_EXEC_FENCE_SUBMIT (1 << 20) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1464,8 +1485,9 @@ struct drm_i915_gem_context_create_ext { __u32 ctx_id; /* output: id of new context*/ __u32 flags; #define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0) +#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1) #define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \ - (-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1)) + (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1)) __u64 extensions; }; @@ -1507,6 +1529,41 @@ struct drm_i915_gem_context_param { * On creation, all new contexts are marked as recoverable. */ #define I915_CONTEXT_PARAM_RECOVERABLE 0x8 + + /* + * The id of the associated virtual memory address space (ppGTT) of + * this context. Can be retrieved and passed to another context + * (on the same fd) for both to use the same ppGTT and so share + * address layouts, and avoid reloading the page tables on context + * switches between themselves. + * + * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY. + */ +#define I915_CONTEXT_PARAM_VM 0x9 + +/* + * I915_CONTEXT_PARAM_ENGINES: + * + * Bind this context to operate on this subset of available engines. Henceforth, + * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as + * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0] + * and upwards. Slots 0...N are filled in using the specified (class, instance). + * Use + * engine_class: I915_ENGINE_CLASS_INVALID, + * engine_instance: I915_ENGINE_CLASS_INVALID_NONE + * to specify a gap in the array that can be filled in later, e.g. by a + * virtual engine used for load balancing. + * + * Setting the number of engines bound to the context to 0, by passing a zero + * sized argument, will revert back to default settings. + * + * See struct i915_context_param_engines. + * + * Extensions: + * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) + * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + */ +#define I915_CONTEXT_PARAM_ENGINES 0xa /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -1540,9 +1597,10 @@ struct drm_i915_gem_context_param_sseu { struct i915_engine_class_instance engine; /* - * Unused for now. Must be cleared to zero. + * Unknown flags must be cleared to zero. */ __u32 flags; +#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0) /* * Mask of slices to enable for the context. Valid values are a subset @@ -1570,12 +1628,115 @@ struct drm_i915_gem_context_param_sseu { __u32 rsvd; }; +/* + * i915_context_engines_load_balance: + * + * Enable load balancing across this set of engines. + * + * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when + * used will proxy the execbuffer request onto one of the set of engines + * in such a way as to distribute the load evenly across the set. + * + * The set of engines must be compatible (e.g. the same HW class) as they + * will share the same logical GPU context and ring. + * + * To intermix rendering with the virtual engine and direct rendering onto + * the backing engines (bypassing the load balancing proxy), the context must + * be defined to use a single timeline for all engines. + */ +struct i915_context_engines_load_balance { + struct i915_user_extension base; + + __u16 engine_index; + __u16 num_siblings; + __u32 flags; /* all undefined flags must be zero */ + + __u64 mbz64; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 num_siblings; \ + __u32 flags; \ + __u64 mbz64; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/* + * i915_context_engines_bond: + * + * Constructed bonded pairs for execution within a virtual engine. + * + * All engines are equal, but some are more equal than others. Given + * the distribution of resources in the HW, it may be preferable to run + * a request on a given subset of engines in parallel to a request on a + * specific engine. We enable this selection of engines within a virtual + * engine by specifying bonding pairs, for any given master engine we will + * only execute on one of the corresponding siblings within the virtual engine. + * + * To execute a request in parallel on the master engine and a sibling requires + * coordination with a I915_EXEC_FENCE_SUBMIT. + */ +struct i915_context_engines_bond { + struct i915_user_extension base; + + struct i915_engine_class_instance master; + + __u16 virtual_index; /* index of virtual engine in ctx->engines[] */ + __u16 num_bonds; + + __u64 flags; /* all undefined flags must be zero */ + __u64 mbz64[4]; /* reserved for future use; must be zero */ + + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \ + struct i915_user_extension base; \ + struct i915_engine_class_instance master; \ + __u16 virtual_index; \ + __u16 num_bonds; \ + __u64 flags; \ + __u64 mbz64[4]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +struct i915_context_param_engines { + __u64 extensions; /* linked chain of extension blocks, 0 terminates */ +#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ +#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ + struct i915_engine_class_instance engines[0]; +} __attribute__((packed)); + +#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ + __u64 extensions; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + struct drm_i915_gem_context_create_ext_setparam { #define I915_CONTEXT_CREATE_EXT_SETPARAM 0 struct i915_user_extension base; struct drm_i915_gem_context_param param; }; +struct drm_i915_gem_context_create_ext_clone { +#define I915_CONTEXT_CREATE_EXT_CLONE 1 + struct i915_user_extension base; + __u32 clone_id; + __u32 flags; +#define I915_CONTEXT_CLONE_ENGINES (1u << 0) +#define I915_CONTEXT_CLONE_FLAGS (1u << 1) +#define I915_CONTEXT_CLONE_SCHEDATTR (1u << 2) +#define I915_CONTEXT_CLONE_SSEU (1u << 3) +#define I915_CONTEXT_CLONE_TIMELINE (1u << 4) +#define I915_CONTEXT_CLONE_VM (1u << 5) +#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1) + __u64 rsvd; +}; + struct drm_i915_gem_context_destroy { __u32 ctx_id; __u32 pad; @@ -1821,6 +1982,7 @@ struct drm_i915_perf_oa_config { struct drm_i915_query_item { __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 /* Must be kept compact -- no holes and well documented */ /* @@ -1919,6 +2081,47 @@ struct drm_i915_query_topology_info { __u8 data[]; }; +/** + * struct drm_i915_engine_info + * + * Describes one engine and it's capabilities as known to the driver. + */ +struct drm_i915_engine_info { + /** Engine class and instance. */ + struct i915_engine_class_instance engine; + + /** Reserved field. */ + __u32 rsvd0; + + /** Engine flags. */ + __u64 flags; + + /** Capabilities of this engine. */ + __u64 capabilities; +#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) +#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + + /** Reserved fields. */ + __u64 rsvd1[4]; +}; + +/** + * struct drm_i915_query_engine_info + * + * Engine info query enumerates all engines known to the driver by filling in + * an array of struct drm_i915_engine_info structures. + */ +struct drm_i915_query_engine_info { + /** Number of struct drm_i915_engine_info structs following. */ + __u32 num_engines; + + /** MBZ */ + __u32 rsvd[3]; + + /** Marker for drm_i915_engine_info structures. */ + struct drm_i915_engine_info engines[]; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4e455018da65..4393bd4b2419 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -134,6 +134,7 @@ enum bpf_map_type { BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, }; /* Note that tracing related programs such as @@ -1571,8 +1572,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). @@ -2710,6 +2714,33 @@ union bpf_attr { * **-EPERM** if no permission to send the *sig*. * * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2821,7 +2852,8 @@ union bpf_attr { FN(strtoul), \ FN(sk_storage_get), \ FN(sk_storage_delete), \ - FN(send_signal), + FN(send_signal), \ + FN(tcp_gen_syncookie), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3504,6 +3536,10 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + struct bpf_flow_keys { __u16 nhoff; __u16 thoff; @@ -3525,6 +3561,8 @@ struct bpf_flow_keys { __u32 ipv6_dst[4]; /* in6_addr; network order */ }; }; + __u32 flags; + __be32 flow_label; }; struct bpf_func_info { diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 7d113a9602f0..4a8c02cafa9a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -695,6 +695,7 @@ enum { IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ __IFLA_VF_MAX, }; @@ -705,6 +706,10 @@ struct ifla_vf_mac { __u8 mac[32]; /* MAX_ADDR_LEN */ }; +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + struct ifla_vf_vlan { __u32 vf; __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c2152f3dd02d..5e3f12d5359e 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -116,7 +116,7 @@ struct kvm_irq_level { * ACPI gsi notion of irq. * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. - * For ARM: See Documentation/virtual/kvm/api.txt + * For ARM: See Documentation/virt/kvm/api.txt */ union { __u32 irq; @@ -995,6 +995,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_SVE 170 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172 +#define KVM_CAP_PMU_EVENT_FILTER 173 #ifdef KVM_CAP_IRQ_ROUTING @@ -1085,7 +1086,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emulation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virt/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) @@ -1329,6 +1330,8 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* Available with KVM_CAP_PPC_GET_CPU_CHAR */ #define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) +/* Available with KVM_CAP_PMU_EVENT_FILTER */ +#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index ed4ee170bee2..b3105ac1381a 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_SCHED_H #define _UAPI_LINUX_SCHED_H +#include <linux/types.h> + /* * cloning flags: */ @@ -32,6 +34,20 @@ #define CLONE_IO 0x80000000 /* Clone io context */ /* + * Arguments for the clone3 syscall + */ +struct clone_args { + __aligned_u64 flags; + __aligned_u64 pidfd; + __aligned_u64 child_tid; + __aligned_u64 parent_tid; + __aligned_u64 exit_signal; + __aligned_u64 stack; + __aligned_u64 stack_size; + __aligned_u64 tls; +}; + +/* * Scheduling policies */ #define SCHED_NORMAL 0 @@ -51,9 +67,21 @@ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 +#define SCHED_FLAG_KEEP_POLICY 0x08 +#define SCHED_FLAG_KEEP_PARAMS 0x10 +#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20 +#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40 + +#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \ + SCHED_FLAG_KEEP_PARAMS) + +#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \ + SCHED_FLAG_UTIL_CLAMP_MAX) #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ - SCHED_FLAG_DL_OVERRUN) + SCHED_FLAG_DL_OVERRUN | \ + SCHED_FLAG_KEEP_ALL | \ + SCHED_FLAG_UTIL_CLAMP) #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h index 964e87217be4..78efe870c2b7 100644 --- a/tools/include/uapi/linux/usbdevice_fs.h +++ b/tools/include/uapi/linux/usbdevice_fs.h @@ -76,6 +76,26 @@ struct usbdevfs_connectinfo { unsigned char slow; }; +struct usbdevfs_conninfo_ex { + __u32 size; /* Size of the structure from the kernel's */ + /* point of view. Can be used by userspace */ + /* to determine how much data can be */ + /* used/trusted. */ + __u32 busnum; /* USB bus number, as enumerated by the */ + /* kernel, the device is connected to. */ + __u32 devnum; /* Device address on the bus. */ + __u32 speed; /* USB_SPEED_* constants from ch9.h */ + __u8 num_ports; /* Number of ports the device is connected */ + /* to on the way to the root hub. It may */ + /* be bigger than size of 'ports' array so */ + /* userspace can detect overflows. */ + __u8 ports[7]; /* List of ports on the way from the root */ + /* hub to the device. Current limit in */ + /* USB specification is 7 tiers (root hub, */ + /* 5 intermediate hubs, device), which */ + /* gives at most 6 port entries. */ +}; + #define USBDEVFS_URB_SHORT_NOT_OK 0x01 #define USBDEVFS_URB_ISO_ASAP 0x02 #define USBDEVFS_URB_BULK_CONTINUATION 0x04 @@ -137,6 +157,7 @@ struct usbdevfs_hub_portinfo { #define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10 #define USBDEVFS_CAP_MMAP 0x20 #define USBDEVFS_CAP_DROP_PRIVILEGES 0x40 +#define USBDEVFS_CAP_CONNINFO_EX 0x80 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */ @@ -197,5 +218,10 @@ struct usbdevfs_streams { #define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams) #define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32) #define USBDEVFS_GET_SPEED _IO('U', 31) +/* + * Returns struct usbdevfs_conninfo_ex; length is variable to allow + * extending size of the data returned. + */ +#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) #endif /* _UAPI_LINUX_USBDEVICE_FS_H */ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 467224feb43b..1aa189a9112a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include <endian.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -19,13 +20,6 @@ #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff -#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ - ((k) == BTF_KIND_VOLATILE) || \ - ((k) == BTF_KIND_CONST) || \ - ((k) == BTF_KIND_RESTRICT)) - -#define IS_VAR(k) ((k) == BTF_KIND_VAR) - static struct btf_type btf_void; struct btf { @@ -42,47 +36,6 @@ struct btf { int fd; }; -struct btf_ext_info { - /* - * info points to the individual info section (e.g. func_info and - * line_info) from the .BTF.ext. It does not include the __u32 rec_size. - */ - void *info; - __u32 rec_size; - __u32 len; -}; - -struct btf_ext { - union { - struct btf_ext_header *hdr; - void *data; - }; - struct btf_ext_info func_info; - struct btf_ext_info line_info; - __u32 data_size; -}; - -struct btf_ext_info_sec { - __u32 sec_name_off; - __u32 num_info; - /* Followed by num_info * record_size number of bytes */ - __u8 data[0]; -}; - -/* The minimum bpf_func_info checked by the loader */ -struct bpf_func_info_min { - __u32 insn_off; - __u32 type_id; -}; - -/* The minimum bpf_line_info checked by the loader */ -struct bpf_line_info_min { - __u32 insn_off; - __u32 file_name_off; - __u32 line_off; - __u32 line_col; -}; - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -192,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf) static int btf_type_size(struct btf_type *t) { int base_size = sizeof(struct btf_type); - __u16 vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = btf_vlen(t); - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_FWD: case BTF_KIND_CONST: case BTF_KIND_VOLATILE: @@ -219,7 +172,7 @@ static int btf_type_size(struct btf_type *t) case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); default: - pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; } } @@ -263,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) static bool btf_type_is_void(const struct btf_type *t) { - return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return t == &btf_void || btf_is_fwd(t); } static bool btf_type_is_void_or_null(const struct btf_type *t) @@ -284,7 +237,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: @@ -303,7 +256,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) type_id = t->type; break; case BTF_KIND_ARRAY: - array = (const struct btf_array *)(t + 1); + array = btf_array(t); if (nelems && array->nelems > UINT32_MAX / nelems) return -E2BIG; nelems *= array->nelems; @@ -334,8 +287,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - (IS_MODIFIER(BTF_INFO_KIND(t->info)) || - IS_VAR(BTF_INFO_KIND(t->info)))) { + (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -419,9 +371,9 @@ done: static bool btf_check_endianness(const GElf_Ehdr *ehdr) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" @@ -554,11 +506,11 @@ static int compare_vsi_off(const void *_a, const void *_b) static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, struct btf_type *t) { - __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + __u32 size = 0, off = 0, i, vars = btf_vlen(t); const char *name = btf__name_by_offset(btf, t->name_off); const struct btf_type *t_var; struct btf_var_secinfo *vsi; - struct btf_var *var; + const struct btf_var *var; int ret; if (!name) { @@ -574,12 +526,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, t->size = size; - for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); - i < vars; i++, vsi++) { + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { t_var = btf__type_by_id(btf, vsi->type); - var = (struct btf_var *)(t_var + 1); + var = btf_var(t_var); - if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + if (!btf_is_var(t_var)) { pr_debug("Non-VAR type seen in section %s\n", name); return -EINVAL; } @@ -595,7 +546,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, ret = bpf_object__variable_offset(obj, name, &off); if (ret) { - pr_debug("No offset found in symbol table for VAR %s\n", name); + pr_debug("No offset found in symbol table for VAR %s\n", + name); return -ENOENT; } @@ -619,7 +571,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) * is section size and global variable offset. We use * the info from the ELF itself for this purpose. */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + if (btf_is_datasec(t)) { err = btf_fixup_datasec(obj, btf, t); if (err) break; @@ -774,14 +726,13 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, return -EINVAL; } - if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(container_type->info) < 2) { + if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { pr_warning("map:%s container_name:%s is an invalid container struct\n", map_name, container_name); return -EINVAL; } - key = (struct btf_member *)(container_type + 1); + key = btf_members(container_type); value = key + 1; key_size = btf__resolve_size(btf, key->type); @@ -831,6 +782,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* The start of the info sec (including the __u32 record_size). */ void *info; + if (ext_sec->len == 0) + return 0; + if (ext_sec->off & 0x03) { pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", ext_sec->desc); @@ -934,11 +888,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } +static int btf_ext_setup_offset_reloc(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->offset_reloc_off, + .len = btf_ext->hdr->offset_reloc_len, + .min_rec_size = sizeof(struct bpf_offset_reloc), + .ext_info = &btf_ext->offset_reloc_info, + .desc = "offset_reloc", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) { const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - if (data_size < offsetof(struct btf_ext_header, func_info_off) || + if (data_size < offsetofend(struct btf_ext_header, hdr_len) || data_size < hdr->hdr_len) { pr_debug("BTF.ext header not found"); return -EINVAL; @@ -996,6 +963,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, line_info_len)) + goto done; err = btf_ext_setup_func_info(btf_ext); if (err) goto done; @@ -1004,6 +974,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, offset_reloc_len)) + goto done; + err = btf_ext_setup_offset_reloc(btf_ext); + if (err) + goto done; + done: if (err) { btf_ext__free(btf_ext); @@ -1440,10 +1417,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, d->map[0] = 0; for (i = 1; i <= btf->nr_types; i++) { struct btf_type *t = d->btf->types[i]; - __u16 kind = BTF_INFO_KIND(t->info); /* VAR and DATASEC are never deduped and are self-canonical */ - if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + if (btf_is_var(t) || btf_is_datasec(t)) d->map[i] = i; else d->map[i] = BTF_UNPROCESSED_ID; @@ -1484,11 +1460,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) if (r) return r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *m = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1499,8 +1475,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_ENUM: { - struct btf_enum *m = (struct btf_enum *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_enum *m = btf_enum(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1511,8 +1487,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *m = btf_params(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1801,16 +1777,16 @@ static long btf_hash_enum(struct btf_type *t) /* Check structural equality of two ENUMs. */ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) { - struct btf_enum *m1, *m2; + const struct btf_enum *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_enum *)(t1 + 1); - m2 = (struct btf_enum *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_enum(t1); + m2 = btf_enum(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->val != m2->val) return false; @@ -1822,8 +1798,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) static inline bool btf_is_enum_fwd(struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && - BTF_INFO_VLEN(t->info) == 0; + return btf_is_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -1843,8 +1818,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_struct(struct btf_type *t) { - struct btf_member *member = (struct btf_member *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1864,16 +1839,16 @@ static long btf_hash_struct(struct btf_type *t) */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) { - struct btf_member *m1, *m2; + const struct btf_member *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_member *)(t1 + 1); - m2 = (struct btf_member *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->offset != m2->offset) return false; @@ -1890,7 +1865,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_array(struct btf_type *t) { - struct btf_array *info = (struct btf_array *)(t + 1); + const struct btf_array *info = btf_array(t); long h = btf_hash_common(t); h = hash_combine(h, info->type); @@ -1908,13 +1883,13 @@ static long btf_hash_array(struct btf_type *t) */ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; + const struct btf_array *info1, *info2; if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); + info1 = btf_array(t1); + info2 = btf_array(t2); return info1->type == info2->type && info1->index_type == info2->index_type && info1->nelems == info2->nelems; @@ -1927,14 +1902,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; - if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); - return info1->nelems == info2->nelems; + return btf_array(t1)->nelems == btf_array(t2)->nelems; } /* @@ -1944,8 +1915,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_fnproto(struct btf_type *t) { - struct btf_param *member = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1966,16 +1937,16 @@ static long btf_hash_fnproto(struct btf_type *t) */ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->type != m2->type) return false; @@ -1992,7 +1963,7 @@ static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; @@ -2000,9 +1971,9 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) if (t1->name_off != t2->name_off || t1->info != t2->info) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off) return false; @@ -2028,7 +1999,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) __u32 cand_id; long h; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2141,13 +2112,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) { __u32 orig_type_id = type_id; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) type_id = d->map[type_id]; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; return orig_type_id; @@ -2156,7 +2127,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) static inline __u16 btf_fwd_kind(struct btf_type *t) { - return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT; + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } /* @@ -2277,8 +2248,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, cand_type = d->btf->types[cand_id]; canon_type = d->btf->types[canon_id]; - cand_kind = BTF_INFO_KIND(cand_type->info); - canon_kind = BTF_INFO_KIND(canon_type->info); + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); if (cand_type->name_off != canon_type->name_off) return 0; @@ -2327,12 +2298,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { - struct btf_array *cand_arr, *canon_arr; + const struct btf_array *cand_arr, *canon_arr; if (!btf_compat_array(cand_type, canon_type)) return 0; - cand_arr = (struct btf_array *)(cand_type + 1); - canon_arr = (struct btf_array *)(canon_type + 1); + cand_arr = btf_array(cand_type); + canon_arr = btf_array(canon_type); eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type); if (eq <= 0) @@ -2342,14 +2313,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *cand_m, *canon_m; + const struct btf_member *cand_m, *canon_m; __u16 vlen; if (!btf_shallow_equal_struct(cand_type, canon_type)) return 0; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_m = (struct btf_member *)(cand_type + 1); - canon_m = (struct btf_member *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_m = btf_members(cand_type); + canon_m = btf_members(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); if (eq <= 0) @@ -2362,7 +2333,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, } case BTF_KIND_FUNC_PROTO: { - struct btf_param *cand_p, *canon_p; + const struct btf_param *cand_p, *canon_p; __u16 vlen; if (!btf_compat_fnproto(cand_type, canon_type)) @@ -2370,9 +2341,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); if (eq <= 0) return eq; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_p = (struct btf_param *)(cand_type + 1); - canon_p = (struct btf_param *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_p = btf_params(cand_type); + canon_p = btf_params(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); if (eq <= 0) @@ -2427,8 +2398,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) targ_type_id = d->hypot_map[cand_type_id]; t_id = resolve_type_id(d, targ_type_id); c_id = resolve_type_id(d, cand_type_id); - t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info); - c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info); + t_kind = btf_kind(d->btf->types[t_id]); + c_kind = btf_kind(d->btf->types[c_id]); /* * Resolve FWD into STRUCT/UNION. * It's ok to resolve FWD into STRUCT/UNION that's not yet @@ -2497,7 +2468,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) return 0; t = d->btf->types[type_id]; - kind = BTF_INFO_KIND(t->info); + kind = btf_kind(t); if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) return 0; @@ -2592,7 +2563,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) t = d->btf->types[type_id]; d->map[type_id] = BTF_IN_PROGRESS_ID; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2616,7 +2587,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *info = (struct btf_array *)(t + 1); + struct btf_array *info = btf_array(t); ref_type_id = btf_dedup_ref_type(d, info->type); if (ref_type_id < 0) @@ -2650,8 +2621,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) return ref_type_id; t->type = ref_type_id; - vlen = BTF_INFO_VLEN(t->info); - param = (struct btf_param *)(t + 1); + vlen = btf_vlen(t); + param = btf_params(t); for (i = 0; i < vlen; i++) { ref_type_id = btf_dedup_ref_type(d, param->type); if (ref_type_id < 0) @@ -2791,7 +2762,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) struct btf_type *t = d->btf->types[type_id]; int i, r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: break; @@ -2811,7 +2782,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *arr_info = (struct btf_array *)(t + 1); + struct btf_array *arr_info = btf_array(t); r = btf_dedup_remap_type_id(d, arr_info->type); if (r < 0) @@ -2826,8 +2797,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *member = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *member = btf_members(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, member->type); @@ -2840,8 +2811,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_FUNC_PROTO: { - struct btf_param *param = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *param = btf_params(t); + __u16 vlen = btf_vlen(t); r = btf_dedup_remap_type_id(d, t->type); if (r < 0) @@ -2859,8 +2830,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_DATASEC: { - struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_var_secinfo *var = btf_var_secinfos(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, var->type); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 88a52ae56fc6..9cb44b4fbf60 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -5,6 +5,7 @@ #define __LIBBPF_BTF_H #include <stdarg.h> +#include <linux/btf.h> #include <linux/types.h> #ifdef __cplusplus @@ -57,6 +58,10 @@ struct btf_ext_header { __u32 func_info_len; __u32 line_info_off; __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 offset_reloc_off; + __u32 offset_reloc_len; }; LIBBPF_API void btf__free(struct btf *btf); @@ -120,6 +125,183 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +/* + * A set of helpers for easier BTF types handling + */ +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline __u16 btf_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_struct(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_STRUCT; +} + +static inline bool btf_is_union(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNION; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +static inline bool btf_is_typedef(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_is_volatile(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VOLATILE; +} + +static inline bool btf_is_const(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_CONST; +} + +static inline bool btf_is_restrict(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_mod(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_VOLATILE || + kind == BTF_KIND_CONST || + kind == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_func(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC; +} + +static inline bool btf_is_func_proto(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC_PROTO; +} + +static inline bool btf_is_var(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VAR; +} + +static inline bool btf_is_datasec(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DATASEC; +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* Get bit offset of a member with specified index. */ +static inline __u32 btf_member_bit_offset(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; +} +/* + * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or + * BTF_KIND_UNION. If member is not a bitfield, zero is returned. + */ +static inline __u32 btf_member_bitfield_size(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; +} + +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + +static inline struct btf_var *btf_var(const struct btf_type *t) +{ + return (struct btf_var *)(t + 1); +} + +static inline struct btf_var_secinfo * +btf_var_secinfos(const struct btf_type *t) +{ + return (struct btf_var_secinfo *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 7065bb5b2752..715967762312 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -100,21 +100,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx) return strcmp(a, b) == 0; } -static __u16 btf_kind_of(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info); -} - -static __u16 btf_vlen_of(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_kflag_of(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) { return btf__name_by_offset(d->btf, name_off); @@ -349,7 +334,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) */ struct btf_dump_type_aux_state *tstate = &d->type_states[id]; const struct btf_type *t; - __u16 kind, vlen; + __u16 vlen; int err, i; /* return true, letting typedefs know that it's ok to be emitted */ @@ -357,18 +342,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); if (tstate->order_state == ORDERING) { /* type loop, but resolvable through fwd declaration */ - if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) && - through_ptr && t->name_off != 0) + if (btf_is_composite(t) && through_ptr && t->name_off != 0) return 0; pr_warning("unsatisfiable type cycle, id:[%u]\n", id); return -ELOOP; } - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_INT: tstate->order_state = ORDERED; return 0; @@ -378,14 +361,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERED; return err; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); - return btf_dump_order_type(d, a->type, through_ptr); - } case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); + const struct btf_member *m = btf_members(t); /* * struct/union is part of strong link, only if it's embedded * (so no ptr in a path) or it's anonymous (so has to be @@ -396,7 +377,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERING; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, m++) { err = btf_dump_order_type(d, m->type, false); if (err < 0) @@ -447,7 +428,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); + const struct btf_param *p = btf_params(t); bool is_strong; err = btf_dump_order_type(d, t->type, through_ptr); @@ -455,7 +436,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err; is_strong = err > 0; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, p++) { err = btf_dump_order_type(d, p->type, through_ptr); if (err < 0) @@ -553,7 +534,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) return; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); if (top_level_def && t->name_off == 0) { pr_warning("unexpected nameless definition, id:[%u]\n", id); @@ -618,12 +599,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_RESTRICT: btf_dump_emit_type(d, t->type, cont_id); break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - btf_dump_emit_type(d, a->type, cont_id); + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); break; - } case BTF_KIND_FWD: btf_dump_emit_fwd_def(d, id, t); btf_dump_printf(d, ";\n\n"); @@ -656,8 +634,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) * applicable */ if (top_level_def || t->name_off == 0) { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, new_cont_id; new_cont_id = t->name_off == 0 ? cont_id : id; @@ -678,8 +656,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } break; case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_type(d, t->type, cont_id); @@ -696,7 +674,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) static int btf_align_of(const struct btf *btf, __u32 id) { const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind_of(t); + __u16 kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -709,15 +687,12 @@ static int btf_align_of(const struct btf *btf, __u32 id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - return btf_align_of(btf, a->type); - } + case BTF_KIND_ARRAY: + return btf_align_of(btf, btf_array(t)->type); case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); int i, align = 1; for (i = 0; i < vlen; i++, m++) @@ -726,7 +701,7 @@ static int btf_align_of(const struct btf *btf, __u32 id) return align; } default: - pr_warning("unsupported BTF_KIND:%u\n", btf_kind_of(t)); + pr_warning("unsupported BTF_KIND:%u\n", btf_kind(t)); return 1; } } @@ -737,20 +712,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_member *m; int align, i, bit_sz; __u16 vlen; - bool kflag; align = btf_align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ if (t->size % align) return true; - m = (void *)(t + 1); - kflag = btf_kflag_of(t); - vlen = btf_vlen_of(t); + m = btf_members(t); + vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { align = btf_align_of(btf, m->type); - bit_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; + bit_sz = btf_member_bitfield_size(t, i); if (bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -807,7 +780,7 @@ static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { btf_dump_printf(d, "%s %s", - btf_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union", + btf_is_struct(t) ? "struct" : "union", btf_dump_type_name(d, id)); } @@ -816,12 +789,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, const struct btf_type *t, int lvl) { - const struct btf_member *m = (void *)(t + 1); - bool kflag = btf_kflag_of(t), is_struct; + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); int align, i, packed, off = 0; - __u16 vlen = btf_vlen_of(t); + __u16 vlen = btf_vlen(t); - is_struct = btf_kind_of(t) == BTF_KIND_STRUCT; packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; align = packed ? 1 : btf_align_of(d->btf, id); @@ -835,8 +807,8 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, int m_off, m_sz; fname = btf_name_of(d, m->name_off); - m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; - m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; + m_sz = btf_member_bitfield_size(t, i); + m_off = btf_member_bit_offset(t, i); align = packed ? 1 : btf_align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); @@ -870,8 +842,8 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, const struct btf_type *t, int lvl) { - const struct btf_enum *v = (void *)(t+1); - __u16 vlen = btf_vlen_of(t); + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); const char *name; size_t dup_cnt; int i; @@ -905,7 +877,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, { const char *name = btf_dump_type_name(d, id); - if (btf_kflag_of(t)) + if (btf_kflag(t)) btf_dump_printf(d, "union %s", name); else btf_dump_printf(d, "struct %s", name); @@ -987,7 +959,6 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, struct id_stack decl_stack; const struct btf_type *t; int err, stack_start; - __u16 kind; stack_start = d->decl_stack_cnt; for (;;) { @@ -1008,8 +979,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, break; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_PTR: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -1017,12 +987,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_FUNC_PROTO: id = t->type; break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - id = a->type; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; break; - } case BTF_KIND_INT: case BTF_KIND_ENUM: case BTF_KIND_FWD: @@ -1032,7 +999,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, goto done; default: pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n", - kind, id); + btf_kind(t), id); goto done; } } @@ -1070,7 +1037,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) id = decl_stack->ids[decl_stack->cnt - 1]; t = btf__type_by_id(d->btf, id); - switch (btf_kind_of(t)) { + switch (btf_kind(t)) { case BTF_KIND_VOLATILE: btf_dump_printf(d, "volatile "); break; @@ -1087,20 +1054,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) } } -static bool btf_is_mod_kind(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - - switch (btf_kind_of(t)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return true; - default: - return false; - } -} - static void btf_dump_emit_name(const struct btf_dump *d, const char *name, bool last_was_ptr) { @@ -1139,7 +1092,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -1185,7 +1138,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_printf(d, " restrict"); break; case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + const struct btf_array *a = btf_array(t); const struct btf_type *next_t; __u32 next_id; bool multidim; @@ -1201,7 +1154,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, */ while (decls->cnt) { next_id = decls->ids[decls->cnt - 1]; - if (btf_is_mod_kind(d->btf, next_id)) + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) decls->cnt--; else break; @@ -1214,7 +1168,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } next_t = btf__type_by_id(d->btf, next_id); - multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY; + multidim = btf_is_array(next_t); /* we need space if we have named non-pointer */ if (fname[0] && !last_was_ptr) btf_dump_printf(d, " "); @@ -1228,8 +1182,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_mods(d, decls); diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index 03748a742146..bae8879cdf58 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -10,6 +10,11 @@ #include <stdbool.h> #include <stddef.h> +#ifdef __GLIBC__ +#include <bits/wordsize.h> +#else +#include <bits/reg.h> +#endif #include "libbpf_internal.h" static inline size_t hash_bits(size_t h, int bits) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 794dd5064ae8..2233f919dd88 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -20,6 +20,7 @@ #include <inttypes.h> #include <string.h> #include <unistd.h> +#include <endian.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> @@ -38,6 +39,7 @@ #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> +#include <sys/utsname.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> @@ -47,6 +49,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" +#include "hashmap.h" #ifndef EM_BPF #define EM_BPF 247 @@ -74,9 +77,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format, static libbpf_print_fn_t __libbpf_pr = __base_pr; -void libbpf_set_print(libbpf_print_fn_t fn) +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { + libbpf_print_fn_t old_print_fn = __libbpf_pr; + __libbpf_pr = fn; + return old_print_fn; } __printf(2, 3) @@ -612,10 +618,10 @@ errout: static int bpf_object__check_endianness(struct bpf_object *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) return 0; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) return 0; #else @@ -1012,23 +1018,21 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } -static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, - __u32 id) +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) { const struct btf_type *t = btf__type_by_id(btf, id); - while (true) { - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - case BTF_KIND_TYPEDEF: - t = btf__type_by_id(btf, t->type); - break; - default: - return t; - } + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); } + + return t; } /* @@ -1041,14 +1045,14 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, static bool get_map_field_int(const char *map_name, const struct btf *btf, const struct btf_type *def, const struct btf_member *m, __u32 *res) { - const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); const char *name = btf__name_by_offset(btf, m->name_off); const struct btf_array *arr_info; const struct btf_type *arr_t; - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': attr '%s': expected PTR, got %u.\n", - map_name, name, BTF_INFO_KIND(t->info)); + map_name, name, btf_kind(t)); return false; } @@ -1058,12 +1062,12 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, map_name, name, t->type); return false; } - if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) { + if (!btf_is_array(arr_t)) { pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n", - map_name, name, BTF_INFO_KIND(arr_t->info)); + map_name, name, btf_kind(arr_t)); return false; } - arr_info = (const void *)(arr_t + 1); + arr_info = btf_array(arr_t); *res = arr_info->nelems; return true; } @@ -1081,11 +1085,11 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, struct bpf_map *map; int vlen, i; - vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + vi = btf_var_secinfos(sec) + var_idx; var = btf__type_by_id(obj->btf, vi->type); - var_extra = (const void *)(var + 1); + var_extra = btf_var(var); map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = BTF_INFO_VLEN(var->info); + vlen = btf_vlen(var); if (map_name == NULL || map_name[0] == '\0') { pr_warning("map #%d: empty name.\n", var_idx); @@ -1095,9 +1099,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_warning("map '%s' BTF data is corrupted.\n", map_name); return -EINVAL; } - if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + if (!btf_is_var(var)) { pr_warning("map '%s': unexpected var kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && @@ -1107,10 +1111,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return -EOPNOTSUPP; } - def = skip_mods_and_typedefs(obj->btf, var->type); - if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { pr_warning("map '%s': unexpected def kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + map_name, btf_kind(var)); return -EINVAL; } if (def->size > vi->size) { @@ -1133,8 +1137,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - vlen = BTF_INFO_VLEN(def->info); - m = (const void *)(def + 1); + vlen = btf_vlen(def); + m = btf_members(def); for (i = 0; i < vlen; i++, m++) { const char *name = btf__name_by_offset(obj->btf, m->name_off); @@ -1184,9 +1188,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': key spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1227,9 +1231,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + if (!btf_is_ptr(t)) { pr_warning("map '%s': value spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + map_name, btf_kind(t)); return -EINVAL; } sz = btf__resolve_size(obj->btf, t->type); @@ -1290,7 +1294,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) nr_types = btf__get_nr_types(obj->btf); for (i = 1; i <= nr_types; i++) { t = btf__type_by_id(obj->btf, i); - if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + if (!btf_is_datasec(t)) continue; name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { @@ -1304,7 +1308,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) return -ENOENT; } - vlen = BTF_INFO_VLEN(sec->info); + vlen = btf_vlen(sec); for (i = 0; i < vlen; i++) { err = bpf_object__init_user_btf_map(obj, sec, i, obj->efile.btf_maps_shndx, @@ -1365,24 +1369,27 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - __u16 kind; if (!obj->btf || (has_func && has_datasec)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - kind = BTF_INFO_KIND(t->info); - if (!has_datasec && kind == BTF_KIND_VAR) { + if (!has_datasec && btf_is_var(t)) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); - t->size = sizeof(int); - *(int *)(t+1) = BTF_INT_ENC(0, 0, 32); - } else if (!has_datasec && kind == BTF_KIND_DATASEC) { + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { /* replace DATASEC with STRUCT */ - struct btf_var_secinfo *v = (void *)(t + 1); - struct btf_member *m = (void *)(t + 1); + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); struct btf_type *vt; char *name; @@ -1393,7 +1400,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) name++; } - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); for (j = 0; j < vlen; j++, v++, m++) { /* order of field assignments is important */ @@ -1403,12 +1410,12 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) vt = (void *)btf__type_by_id(btf, v->type); m->name_off = vt->name_off; } - } else if (!has_func && kind == BTF_KIND_FUNC_PROTO) { + } else if (!has_func && btf_is_func_proto(t)) { /* replace FUNC_PROTO with ENUM */ - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); t->size = sizeof(__u32); /* kernel enforced */ - } else if (!has_func && kind == BTF_KIND_FUNC) { + } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); } @@ -1500,6 +1507,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) BTF_ELF_SEC, err); btf__free(obj->btf); obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + if (bpf_object__is_btf_mandatory(obj)) return err; } @@ -1760,15 +1773,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, (long long) sym.st_value, sym.st_name, name); shdr_idx = sym.st_shndx; + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n", + insn_idx, shdr_idx); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n", + name, shdr_idx, insn_idx, + insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { pr_warning("incorrect bpf_call opcode\n"); @@ -2282,6 +2302,894 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, return 0; } +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field byte offset represented by spec */ + __u32 offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_offset_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field offset (in bytes), specified by accessor string. Low-level spec + * captures every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset = access_idx * sz; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + if (btf_member_bitfield_size(t, access_idx)) + return -EINVAL; + + offset = btf_member_bit_offset(t, access_idx); + if (offset % 8) + return -EINVAL; + spec->offset += offset / 8; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->offset += access_idx * sz; + } else { + pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating offset to the compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible; + * - any two PTRs are always compatible; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and bitness should match, signedness is ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_FWD: + case BTF_KIND_PTR: + return 1; + case BTF_KIND_ENUM: + return local_type->size == targ_type->size; + case BTF_KIND_INT: + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0 && + local_type->size == targ_type->size && + btf_int_bits(local_type) == btf_int_bits(targ_type); + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 offset; + + /* bitfield relocations not supported */ + if (btf_member_bitfield_size(targ_type, i)) + continue; + offset = btf_member_bit_offset(targ_type, i); + if (offset % 8) + continue; + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->offset += offset / 8; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->offset -= offset / 8; + spec->raw_len--; + } + + return 0; +} + +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->offset += local_acc->idx * sz; + } + } + + return 1; +} + +/* + * Patch relocatable BPF instruction. + * Expected insn->imm value is provided for validation, as well as the new + * relocated value. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + * 3. *(rX) = <imm> (indirect memory assignment with immediate operand). + * + * If actual insn->imm value is wrong, bail out. + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off, + __u32 orig_off, __u32 new_off) +{ + struct bpf_insn *insn; + int insn_idx; + __u8 class; + + if (insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = insn_off / sizeof(struct bpf_insn); + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (insn->imm != orig_off) + return -EINVAL; + insn->imm = new_off; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n", + bpf_program__title(prog, false), + insn_idx, orig_off, new_off); + } else { + pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warning("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u @ &x", spec->offset); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is not error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_offset_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_offset(struct bpf_program *prog, + const struct bpf_offset_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warning("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warning("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warning("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.offset != targ_spec.offset) { + /* if there are many candidates, they should all + * resolve to the same offset + */ + pr_warning("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.offset, + targ_spec.offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + cand_ids->len = j; + if (cand_ids->len == 0) { + pr_warning("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + err = bpf_core_reloc_insn(prog, relo->insn_off, + local_spec.offset, targ_spec.offset); + if (err) { + pr_warning("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_offsets(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_offset_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warning("failed to get target BTF: %ld\n", + PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->offset_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warning("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_offset(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warning("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->offset_reloc_info.len) + err = bpf_core_reloc_offsets(obj, targ_btf_path); + + return err; +} + static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) @@ -2389,14 +3297,21 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; } - static int -bpf_object__relocate(struct bpf_object *obj) +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i; int err; + if (obj->btf_ext) { + err = bpf_object__relocate_core(obj, targ_btf_path); + if (err) { + pr_warning("failed to perform CO-RE relocations: %d\n", + err); + return err; + } + } for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; @@ -2797,7 +3712,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; @@ -4507,13 +5422,13 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const struct perf_buffer_opts *opts) { struct perf_buffer_params p = {}; - struct perf_event_attr attr = { - .config = PERF_COUNT_SW_BPF_OUTPUT, - .type = PERF_TYPE_SOFTWARE, - .sample_type = PERF_SAMPLE_RAW, - .sample_period = 1, - .wakeup_events = 1, - }; + struct perf_event_attr attr = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; p.attr = &attr; p.sample_cb = opts ? opts->sample_cb : NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5cbf459ece0b..e8f70977d137 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -57,7 +57,7 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); -LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; @@ -92,6 +92,7 @@ LIBBPF_API void bpf_object__close(struct bpf_object *object); struct bpf_object_load_attr { struct bpf_object *obj; int log_level; + const char *target_btf_path; }; /* Load/unload object into/from kernel */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2ac29bd36226..2e83a34f8c79 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -29,6 +29,10 @@ #ifndef max # define max(x, y) ((x) < (y) ? (y) : (x)) #endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif extern void libbpf_print(enum libbpf_print_level level, const char *format, ...) @@ -46,4 +50,105 @@ do { \ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +struct btf_ext_info { + /* + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. + */ + void *info; + __u32 rec_size; + __u32 len; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + for (sec = (seg)->info; \ + (void *)sec < (seg)->info + (seg)->len; \ + sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \ + (seg)->rec_size * sec->num_info) + +#define for_each_btf_ext_rec(seg, sec, i, rec) \ + for (i = 0, rec = (void *)&(sec)->data; \ + i < (sec)->num_info; \ + i++, rec = (void *)rec + (seg)->rec_size) + +struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; + struct btf_ext_info func_info; + struct btf_ext_info line_info; + struct btf_ext_info offset_reloc_info; + __u32 data_size; +}; + +struct btf_ext_info_sec { + __u32 sec_name_off; + __u32 num_info; + /* Followed by num_info * record_size number of bytes */ + __u8 data[0]; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_off; + __u32 type_id; +}; + +/* The minimum bpf_line_info checked by the loader */ +struct bpf_line_info_min { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +/* The minimum bpf_offset_reloc checked by the loader + * + * Offset relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual offset; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * offset; + * - access_str_off - offset into corresponding .BTF string section. String + * itself encodes an accessed field using a sequence of field and array + * indicies, separated by colon (:). It's conceptually very close to LLVM's + * getelementptr ([0]) instruction's arguments for identifying offset to + * a field. + * + * Example to provide a better feel. + * + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int x = &s->a; // encoded as "0:0" (a is field #0) + * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit offset relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_offset_reloc { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; +}; + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ace1a0708d99..4b0b0364f5fc 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -244,6 +244,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_XSKMAP: diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 5007b5d4fd2c..680e63066cf3 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -317,17 +317,16 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) static int xsk_get_max_queues(struct xsk_socket *xsk) { - struct ethtool_channels channels; - struct ifreq ifr; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; int fd, err, ret; fd = socket(AF_INET, SOCK_DGRAM, 0); if (fd < 0) return -errno; - channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { @@ -335,7 +334,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (channels.max_combined == 0 || errno == EOPNOTSUPP) + if (err || channels.max_combined == 0) /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ @@ -517,7 +516,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5f26620f13f5..176f2f084060 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1946,6 +1946,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct alternative *alt; struct instruction *insn, *next_insn; struct section *sec; + u8 visited; int ret; insn = first; @@ -1972,12 +1973,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + visited = 1 << state.uaccess; if (insn->visited) { if (!insn->hint && !insn_state_match(insn, &state)) return 1; - /* If we were here with AC=0, but now have AC=1, go again */ - if (insn->state.uaccess || !state.uaccess) + if (insn->visited & visited) return 0; } @@ -2024,7 +2025,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } else insn->state = state; - insn->visited = true; + insn->visited |= visited; if (!insn->ignore_alts) { bool skip_orig = false; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index b881fafcf55d..6d875ca6fce0 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -33,8 +33,9 @@ struct instruction { unsigned int len; enum insn_type type; unsigned long immediate; - bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; + bool alt_group, dead_end, ignore, hint, save, restore, ignore_alts; bool retpoline_safe; + u8 visited; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index d4e2e18a5881..caaab28f8400 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -228,11 +228,11 @@ OPTIONS With the metric option perf script can compute metrics for sampling periods, similar to perf stat. This requires - specifying a group with multiple metrics with the :S option + specifying a group with multiple events defining metrics with the :S option for perf record. perf will sample on the first event, and - compute metrics for all the events in the group. Please note + print computed metrics for all the events in the group. Please note that the metric computed is averaged over the whole sampling - period, not just for the sample point. + period (since the last sample), not just for the sample point. For sample events it's possible to display misc field with -F +misc option, following letters are displayed for each bit: @@ -384,7 +384,7 @@ include::itrace.txt[] perf script --time 0%-10%,30%-40% --max-blocks:: - Set the maximum number of program blocks to print with brstackasm for + Set the maximum number of program blocks to print with brstackinsn for each sample. --reltime:: diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index 5f54feb19977..d030c87ed9f5 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -126,7 +126,7 @@ vendor,family,model,stepping. For example: GenuineIntel,6,69,1 HEADER_TOTAL_MEM = 10, -An uint64_t with the total memory in bytes. +An uint64_t with the total memory in kilobytes. HEADER_CMDLINE = 11, diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index b4e6f9e6204a..c29976eca4a8 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -355,6 +355,8 @@ 431 common fsconfig __x64_sys_fsconfig 432 common fsmount __x64_sys_fsmount 433 common fspick __x64_sys_fspick +434 common pidfd_open __x64_sys_pidfd_open +435 common clone3 __x64_sys_clone3/ptregs # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 6418782951a4..3d0ffd41fb55 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -698,6 +698,16 @@ __cmd_probe(int argc, const char **argv) ret = perf_add_probe_events(params.events, params.nevents); if (ret < 0) { + + /* + * When perf_add_probe_events() fails it calls + * cleanup_perf_probe_events(pevs, npevs), i.e. + * cleanup_perf_probe_events(params.events, params.nevents), which + * will call clear_perf_probe_event(), so set nevents to zero + * to avoid cleanup_params() to call clear_perf_probe_event() again + * on the same pevs. + */ + params.nevents = 0; pr_err_with_code(" Error: Failed to add events.", ret); return ret; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8f24865596af..0140ddb8dd0b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1059,7 +1059,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (ip == end) { - printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp, + printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp, &total_cycles); if (PRINT_FIELD(SRCCODE)) printed += print_srccode(thread, x.cpumode, ip); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b55a534b4de0..352cf39d7c2f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -607,7 +607,13 @@ try_again: * group leaders. */ read_counters(&(struct timespec) { .tv_nsec = t1-t0 }); - perf_evlist__close(evsel_list); + + /* + * We need to keep evsel_list alive, because it's processed + * later the evsel_list will be closed after. + */ + if (!STAT_RECORD) + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } @@ -1997,6 +2003,7 @@ int cmd_stat(int argc, const char **argv) perf_session__write_header(perf_stat.session, evsel_list, fd, true); } + perf_evlist__close(evsel_list); perf_session__delete(perf_stat.session); } diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh index 930b80f422e8..aa597ae53747 100755 --- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh +++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh @@ -3,10 +3,13 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ +# also as: +# #define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len) + printf "static const char *usbdevfs_ioctl_cmds[] = {\n" -regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" -egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \ - sed -r "s/$regex/\2 \1/g" | \ +regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*" +egrep "$regex" ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \ + sed -r "s/$regex/\4 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" printf "#if 0\n" diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ebb46da4dfe5..52459dd5ad0c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1291,6 +1291,7 @@ static void perf_evsel__free_id(struct perf_evsel *evsel) xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; zfree(&evsel->id); + evsel->ids = 0; } static void perf_evsel__free_config_terms(struct perf_evsel *evsel) @@ -2077,6 +2078,7 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__close_fd(evsel); perf_evsel__free_fd(evsel); + perf_evsel__free_id(evsel); } int perf_evsel__open_per_cpu(struct perf_evsel *evsel, diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index c24db7f4909c..1903d7ec9797 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3559,6 +3559,13 @@ int perf_session__read_header(struct perf_session *session) data->file.path); } + if (f_header.attr_size == 0) { + pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n" + "Was the 'perf record' command properly terminated?\n", + data->file.path); + return -EINVAL; + } + nr_attrs = f_header.attrs.size / f_header.attr_size; lseek(fd, f_header.attrs.offset, SEEK_SET); @@ -3639,7 +3646,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool, size += sizeof(struct perf_event_header); size += ids * sizeof(u64); - ev = malloc(size); + ev = zalloc(size); if (ev == NULL) return -ENOMEM; @@ -3747,7 +3754,7 @@ int perf_event__process_feature(struct perf_session *session, return 0; ff.buf = (void *)fe->data; - ff.size = event->header.size - sizeof(event->header); + ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; if (feat_ops[feat].process(&ff, NULL)) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index cd1eb73cfe83..8394d48f8b32 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2230,6 +2230,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev) field = next; } } + pev->nargs = 0; zfree(&pev->args); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d0fd6c614e68..37efa1f43d8b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -36,10 +36,16 @@ static int perf_session__process_compressed_event(struct perf_session *session, void *src; size_t decomp_size, src_size; u64 decomp_last_rem = 0; - size_t decomp_len = session->header.env.comp_mmap_len; + size_t mmap_len, decomp_len = session->header.env.comp_mmap_len; struct decomp *decomp, *decomp_last = session->decomp_last; - decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE, + if (decomp_last) { + decomp_last_rem = decomp_last->size - decomp_last->head; + decomp_len += decomp_last_rem; + } + + mmap_len = sizeof(struct decomp) + decomp_len; + decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (decomp == MAP_FAILED) { pr_err("Couldn't allocate memory for decompression\n"); @@ -47,10 +53,10 @@ static int perf_session__process_compressed_event(struct perf_session *session, } decomp->file_pos = file_offset; + decomp->mmap_len = mmap_len; decomp->head = 0; - if (decomp_last) { - decomp_last_rem = decomp_last->size - decomp_last->head; + if (decomp_last_rem) { memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem); decomp->size = decomp_last_rem; } @@ -61,7 +67,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size, &(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem); if (!decomp_size) { - munmap(decomp, sizeof(struct decomp) + decomp_len); + munmap(decomp, mmap_len); pr_err("Couldn't decompress data\n"); return -1; } @@ -255,15 +261,15 @@ static void perf_session__delete_threads(struct perf_session *session) static void perf_session__release_decomp_events(struct perf_session *session) { struct decomp *next, *decomp; - size_t decomp_len; + size_t mmap_len; next = session->decomp; - decomp_len = session->header.env.comp_mmap_len; do { decomp = next; if (decomp == NULL) break; next = decomp->next; - munmap(decomp, decomp_len + sizeof(struct decomp)); + mmap_len = decomp->mmap_len; + munmap(decomp, mmap_len); } while (1); } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index dd8920b745bc..863dbad87849 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -46,6 +46,7 @@ struct perf_session { struct decomp { struct decomp *next; u64 file_pos; + size_t mmap_len; u64 head; size_t size; char data[]; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 656065af4971..accb1bf1cfd8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -819,7 +819,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, "stalled cycles per insn", ratio); } else if (have_frontend_stalled) { - print_metric(config, ctxp, NULL, NULL, + out->new_line(config, ctxp); + print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index 23bdb9884576..d2202392ffdb 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -99,8 +99,8 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { - pr_err("failed to decompress (B): %ld -> %ld : %s\n", - src_size, output.size, ZSTD_getErrorName(ret)); + pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n", + src_size, output.size, dst_size, ZSTD_getErrorName(ret)); break; } output.dst = dst + output.pos; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 495066bafbe3..ded7a950dc40 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -32,7 +32,6 @@ EXTRA_WARNINGS += -Wno-system-headers EXTRA_WARNINGS += -Wold-style-definition EXTRA_WARNINGS += -Wpacked EXTRA_WARNINGS += -Wredundant-decls -EXTRA_WARNINGS += -Wshadow EXTRA_WARNINGS += -Wstrict-prototypes EXTRA_WARNINGS += -Wswitch-default EXTRA_WARNINGS += -Wswitch-enum @@ -69,8 +68,16 @@ endif # will do for now and keep the above -Wstrict-aliasing=3 in place # in newer systems. # Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h +# +# See https://lkml.org/lkml/2006/11/28/253 and https://gcc.gnu.org/gcc-4.8/changes.html, +# that takes into account Linus's comments (search for Wshadow) for the reasoning about +# -Wshadow not being interesting before gcc 4.8. + ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3 EXTRA_WARNINGS += -fno-strict-aliasing +EXTRA_WARNINGS += -Wno-shadow +else +EXTRA_WARNINGS += -Wshadow endif ifneq ($(findstring $(MAKEFLAGS), w),w) diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl index 72525426654b..6fd864935319 100755 --- a/tools/testing/ktest/config-bisect.pl +++ b/tools/testing/ktest/config-bisect.pl @@ -663,7 +663,7 @@ while ($#ARGV >= 0) { } else { - die "Unknow option $opt\n"; + die "Unknown option $opt\n"; } } @@ -732,7 +732,7 @@ if ($start) { } } run_command "cp $good_start $good" or die "failed to copy to $good\n"; - run_command "cp $bad_start $bad" or die "faield to copy to $bad\n"; + run_command "cp $bad_start $bad" or die "failed to copy to $bad\n"; } else { if ( ! -f $good ) { die "Can not find file $good\n"; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 11c9c62c3362..29001f944db7 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -57,7 +57,8 @@ TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ test_skb_cgroup_id.sh \ test_flow_dissector.sh \ - test_xdp_vlan.sh \ + test_xdp_vlan_mode_generic.sh \ + test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ test_tcp_check_syncookie.sh \ test_tc_tunnel.sh \ @@ -235,18 +236,12 @@ PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) test_progs.c: $(PROG_TESTS_H) $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_FILES) | $(PROG_TESTS_H) $(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ - echo '#ifdef DECLARE'; \ ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \ - echo '#endif'; \ - echo '#ifdef CALL'; \ - ls *.c 2> /dev/null | \ - sed -e 's@\([^\.]*\)\.c@test_\1();@'; \ - echo '#endif' \ + sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@'; \ ) > $(PROG_TESTS_H)) MAP_TESTS_DIR = $(OUTPUT)/map_tests @@ -256,7 +251,7 @@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h MAP_TESTS_FILES := $(wildcard map_tests/*.c) test_maps.c: $(MAP_TESTS_H) $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) -$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES) +$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_FILES) | $(MAP_TESTS_H) $(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR) $(shell ( cd map_tests/; \ echo '/* Generated header, do not edit */'; \ @@ -277,7 +272,7 @@ VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) -$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: test_verifier.c | $(VERIFIER_TEST_FILES) $(VERIFIER_TESTS_H) $(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f804f210244e..8b503ea142f0 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -228,6 +228,9 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = (void *)BPF_FUNC_sk_storage_delete; static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal; +static long long (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *ip, + int ip_len, void *tcp, int tcp_len) = + (void *) BPF_FUNC_tcp_gen_syncookie; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -501,4 +504,24 @@ struct pt_regs; (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif +/* + * BPF_CORE_READ abstracts away bpf_probe_read() call and captures offset + * relocation for source address using __builtin_preserve_access_index() + * built-in, provided by Clang. + * + * __builtin_preserve_access_index() takes as an argument an expression of + * taking an address of a field within struct/union. It makes compiler emit + * a relocation, which records BTF type ID describing root struct/union and an + * accessor string which describes exact embedded field that was used to take + * an address. See detailed description of this relocation format and + * semantics in comments to struct bpf_offset_reloc in libbpf_internal.h. + * + * This relocation allows libbpf to adjust BPF instruction to use correct + * actual field offset, based on target kernel BTF type that matches original + * (local) BTF, used to record relocation. + */ +#define BPF_CORE_READ(dst, src) \ + bpf_probe_read((dst), sizeof(*(src)), \ + __builtin_preserve_access_index(src)) + #endif diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index cb827383db4d..fb5840a62548 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -106,8 +106,8 @@ void test_bpf_obj_id(void) if (CHECK(err || prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || - (jit_enabled && !prog_infos[i].jited_prog_len) || - (jit_enabled && + (env.jit_enabled && !prog_infos[i].jited_prog_len) || + (env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))) || !prog_infos[i].xlated_prog_len || !memcmp(xlated_insns, zeros, sizeof(zeros)) || @@ -121,7 +121,7 @@ void test_bpf_obj_id(void) err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), - jit_enabled, + env.jit_enabled, prog_infos[i].jited_prog_len, prog_infos[i].xlated_prog_len, !!memcmp(jited_insns, zeros, sizeof(zeros)), diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index e1b55261526f..1a1eae356f81 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -4,12 +4,15 @@ static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { - if (level != LIBBPF_DEBUG) - return vfprintf(stderr, format, args); + if (level != LIBBPF_DEBUG) { + vprintf(format, args); + return 0; + } if (!strstr(format, "verifier log")) return 0; - return vfprintf(stderr, "%s", args); + vprintf("%s", args); + return 0; } static int check_load(const char *file, enum bpf_prog_type type) @@ -30,14 +33,25 @@ static int check_load(const char *file, enum bpf_prog_type type) return err; } +struct scale_test_def { + const char *file; + enum bpf_prog_type attach_type; + bool fails; +}; + void test_bpf_verif_scale(void) { - const char *sched_cls[] = { - "./test_verif_scale1.o", "./test_verif_scale2.o", "./test_verif_scale3.o", - }; - const char *raw_tp[] = { + struct scale_test_def tests[] = { + { "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ }, + + { "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, + { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, + /* full unroll by llvm */ - "./pyperf50.o", "./pyperf100.o", "./pyperf180.o", + { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* partial unroll. llvm will unroll loop ~150 times. * C loop count -> 600. @@ -45,7 +59,7 @@ void test_bpf_verif_scale(void) * 16k insns in loop body. * Total of 5 such loops. Total program size ~82k insns. */ - "./pyperf600.o", + { "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll at all. * C loop count -> 600. @@ -53,48 +67,52 @@ void test_bpf_verif_scale(void) * ~110 insns in loop body. * Total of 5 such loops. Total program size ~1500 insns. */ - "./pyperf600_nounroll.o", + { "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - "./loop1.o", "./loop2.o", + { "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "loop4.o", BPF_PROG_TYPE_SCHED_CLS }, + { "loop5.o", BPF_PROG_TYPE_SCHED_CLS }, /* partial unroll. 19k insn in a loop. * Total program size 20.8k insn. * ~350k processed_insns */ - "./strobemeta.o", + { "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, /* no unroll, tiny loops */ - "./strobemeta_nounroll1.o", - "./strobemeta_nounroll2.o", - }; - const char *cg_sysctl[] = { - "./test_sysctl_loop1.o", "./test_sysctl_loop2.o", - }; - int err, i; + { "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + { "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, - if (verifier_stats) - libbpf_set_print(libbpf_debug_print); + { "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, + { "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL }, - err = check_load("./loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:loop3:%s\n", err ? (error_cnt--, "OK") : "FAIL"); + { "test_xdp_loop.o", BPF_PROG_TYPE_XDP }, + { "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL }, + }; + libbpf_print_fn_t old_print_fn = NULL; + int err, i; - for (i = 0; i < ARRAY_SIZE(sched_cls); i++) { - err = check_load(sched_cls[i], BPF_PROG_TYPE_SCHED_CLS); - printf("test_scale:%s:%s\n", sched_cls[i], err ? "FAIL" : "OK"); + if (env.verifier_stats) { + test__force_log(); + old_print_fn = libbpf_set_print(libbpf_debug_print); } - for (i = 0; i < ARRAY_SIZE(raw_tp); i++) { - err = check_load(raw_tp[i], BPF_PROG_TYPE_RAW_TRACEPOINT); - printf("test_scale:%s:%s\n", raw_tp[i], err ? "FAIL" : "OK"); - } + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct scale_test_def *test = &tests[i]; + + if (!test__start_subtest(test->file)) + continue; - for (i = 0; i < ARRAY_SIZE(cg_sysctl); i++) { - err = check_load(cg_sysctl[i], BPF_PROG_TYPE_CGROUP_SYSCTL); - printf("test_scale:%s:%s\n", cg_sysctl[i], err ? "FAIL" : "OK"); + err = check_load(test->file, test->attach_type); + if (test->fails) { /* expected to fail */ + if (err) + error_cnt--; + else + error_cnt++; + } } - err = check_load("./test_xdp_loop.o", BPF_PROG_TYPE_XDP); - printf("test_scale:test_xdp_loop:%s\n", err ? "FAIL" : "OK"); - err = check_load("./test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL); - printf("test_scale:test_seg6_loop:%s\n", err ? "FAIL" : "OK"); + if (env.verifier_stats) + libbpf_set_print(old_print_fn); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c new file mode 100644 index 000000000000..f3863f976a48 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "progs/core_reloc_types.h" + +#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) + +#define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 42, \ + .b = 0xc001, \ + .c = 0xbeef, \ +} + +#define FLAVORS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_flavors.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" \ + +#define FLAVORS_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .input = FLAVORS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = FLAVORS_DATA(core_reloc_flavors), \ + .output_len = sizeof(struct core_reloc_flavors), \ +} + +#define FLAVORS_ERR_CASE(name) { \ + FLAVORS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define NESTING_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { .a = { .a = 42 } }, \ + .b = { .b = { .b = 0xc001 } }, \ +} + +#define NESTING_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_nesting.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define NESTING_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .input = NESTING_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = NESTING_DATA(core_reloc_nesting), \ + .output_len = sizeof(struct core_reloc_nesting) \ +} + +#define NESTING_ERR_CASE(name) { \ + NESTING_CASE_COMMON(name), \ + .fails = true, \ +} + +#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = { [2] = 1 }, \ + .b = { [1] = { [2] = { [3] = 2 } } }, \ + .c = { [1] = { .c = 3 } }, \ + .d = { [0] = { [0] = { .d = 4 } } }, \ +} + +#define ARRAYS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_arrays.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define ARRAYS_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .input = ARRAYS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) { \ + .a2 = 1, \ + .b123 = 2, \ + .c1c = 3, \ + .d00d = 4, \ + }, \ + .output_len = sizeof(struct core_reloc_arrays_output) \ +} + +#define ARRAYS_ERR_CASE(name) { \ + ARRAYS_CASE_COMMON(name), \ + .fails = true, \ +} + +#define PRIMITIVES_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .a = 1, \ + .b = 2, \ + .c = 3, \ + .d = (void *)4, \ + .f = (void *)5, \ +} + +#define PRIMITIVES_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_primitives.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define PRIMITIVES_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .input = PRIMITIVES_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = PRIMITIVES_DATA(core_reloc_primitives), \ + .output_len = sizeof(struct core_reloc_primitives), \ +} + +#define PRIMITIVES_ERR_CASE(name) { \ + PRIMITIVES_CASE_COMMON(name), \ + .fails = true, \ +} + +#define MODS_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_mods.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = STRUCT_TO_CHAR_PTR(core_reloc_##name) { \ + .a = 1, \ + .b = 2, \ + .c = (void *)3, \ + .d = (void *)4, \ + .e = { [2] = 5 }, \ + .f = { [1] = 6 }, \ + .g = { .x = 7 }, \ + .h = { .y = 8 }, \ + }, \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_mods_output) { \ + .a = 1, .b = 2, .c = 3, .d = 4, \ + .e = 5, .f = 6, .g = 7, .h = 8, \ + }, \ + .output_len = sizeof(struct core_reloc_mods_output), \ +} + +#define PTR_AS_ARR_CASE(name) { \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ptr_as_arr.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o", \ + .input = (const char *)&(struct core_reloc_##name []){ \ + { .a = 1 }, \ + { .a = 2 }, \ + { .a = 3 }, \ + }, \ + .input_len = 3 * sizeof(struct core_reloc_##name), \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_ptr_as_arr) { \ + .a = 3, \ + }, \ + .output_len = sizeof(struct core_reloc_ptr_as_arr), \ +} + +#define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ + .u8_field = 1, \ + .s8_field = 2, \ + .u16_field = 3, \ + .s16_field = 4, \ + .u32_field = 5, \ + .s32_field = 6, \ + .u64_field = 7, \ + .s64_field = 8, \ +} + +#define INTS_CASE_COMMON(name) \ + .case_name = #name, \ + .bpf_obj_file = "test_core_reloc_ints.o", \ + .btf_src_file = "btf__core_reloc_" #name ".o" + +#define INTS_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .input = INTS_DATA(core_reloc_##name), \ + .input_len = sizeof(struct core_reloc_##name), \ + .output = INTS_DATA(core_reloc_ints), \ + .output_len = sizeof(struct core_reloc_ints), \ +} + +#define INTS_ERR_CASE(name) { \ + INTS_CASE_COMMON(name), \ + .fails = true, \ +} + +struct core_reloc_test_case { + const char *case_name; + const char *bpf_obj_file; + const char *btf_src_file; + const char *input; + int input_len; + const char *output; + int output_len; + bool fails; +}; + +static struct core_reloc_test_case test_cases[] = { + /* validate we can find kernel image and use its BTF for relocs */ + { + .case_name = "kernel", + .bpf_obj_file = "test_core_reloc_kernel.o", + .btf_src_file = NULL, /* load from /lib/modules/$(uname -r) */ + .input = "", + .input_len = 0, + .output = "\1", /* true */ + .output_len = 1, + }, + + /* validate BPF program can use multiple flavors to match against + * single target BTF type + */ + FLAVORS_CASE(flavors), + + FLAVORS_ERR_CASE(flavors__err_wrong_name), + + /* various struct/enum nesting and resolution scenarios */ + NESTING_CASE(nesting), + NESTING_CASE(nesting___anon_embed), + NESTING_CASE(nesting___struct_union_mixup), + NESTING_CASE(nesting___extra_nesting), + NESTING_CASE(nesting___dup_compat_types), + + NESTING_ERR_CASE(nesting___err_missing_field), + NESTING_ERR_CASE(nesting___err_array_field), + NESTING_ERR_CASE(nesting___err_missing_container), + NESTING_ERR_CASE(nesting___err_nonstruct_container), + NESTING_ERR_CASE(nesting___err_array_container), + NESTING_ERR_CASE(nesting___err_dup_incompat_types), + NESTING_ERR_CASE(nesting___err_partial_match_dups), + NESTING_ERR_CASE(nesting___err_too_deep), + + /* various array access relocation scenarios */ + ARRAYS_CASE(arrays), + ARRAYS_CASE(arrays___diff_arr_dim), + ARRAYS_CASE(arrays___diff_arr_val_sz), + + ARRAYS_ERR_CASE(arrays___err_too_small), + ARRAYS_ERR_CASE(arrays___err_too_shallow), + ARRAYS_ERR_CASE(arrays___err_non_array), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), + ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + + /* enum/ptr/int handling scenarios */ + PRIMITIVES_CASE(primitives), + PRIMITIVES_CASE(primitives___diff_enum_def), + PRIMITIVES_CASE(primitives___diff_func_proto), + PRIMITIVES_CASE(primitives___diff_ptr_type), + + PRIMITIVES_ERR_CASE(primitives___err_non_enum), + PRIMITIVES_ERR_CASE(primitives___err_non_int), + PRIMITIVES_ERR_CASE(primitives___err_non_ptr), + + /* const/volatile/restrict and typedefs scenarios */ + MODS_CASE(mods), + MODS_CASE(mods___mod_swap), + MODS_CASE(mods___typedefs), + + /* handling "ptr is an array" semantics */ + PTR_AS_ARR_CASE(ptr_as_arr), + PTR_AS_ARR_CASE(ptr_as_arr___diff_sz), + + /* int signedness/sizing/bitfield handling */ + INTS_CASE(ints), + INTS_CASE(ints___bool), + INTS_CASE(ints___reverse_sign), + + INTS_ERR_CASE(ints___err_bitfield), + INTS_ERR_CASE(ints___err_wrong_sz_8), + INTS_ERR_CASE(ints___err_wrong_sz_16), + INTS_ERR_CASE(ints___err_wrong_sz_32), + INTS_ERR_CASE(ints___err_wrong_sz_64), + + /* validate edge cases of capturing relocations */ + { + .case_name = "misc", + .bpf_obj_file = "test_core_reloc_misc.o", + .btf_src_file = "btf__core_reloc_misc.o", + .input = (const char *)&(struct core_reloc_misc_extensible[]){ + { .a = 1 }, + { .a = 2 }, /* not read */ + { .a = 3 }, + }, + .input_len = 4 * sizeof(int), + .output = STRUCT_TO_CHAR_PTR(core_reloc_misc_output) { + .a = 1, + .b = 1, + .c = 0, /* BUG in clang, should be 3 */ + }, + .output_len = sizeof(struct core_reloc_misc_output), + }, +}; + +struct data { + char in[256]; + char out[256]; +}; + +void test_core_reloc(void) +{ + const char *probe_name = "raw_tracepoint/sys_enter"; + struct bpf_object_load_attr load_attr = {}; + struct core_reloc_test_case *test_case; + int err, duration = 0, i, equal; + struct bpf_link *link = NULL; + struct bpf_map *data_map; + struct bpf_program *prog; + struct bpf_object *obj; + const int zero = 0; + struct data data; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + test_case = &test_cases[i]; + + if (!test__start_subtest(test_case->case_name)) + continue; + + obj = bpf_object__open(test_case->bpf_obj_file); + if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", + "failed to open '%s': %ld\n", + test_case->bpf_obj_file, PTR_ERR(obj))) + continue; + + prog = bpf_object__find_program_by_title(obj, probe_name); + if (CHECK(!prog, "find_probe", + "prog '%s' not found\n", probe_name)) + goto cleanup; + bpf_program__set_type(prog, BPF_PROG_TYPE_RAW_TRACEPOINT); + + load_attr.obj = obj; + load_attr.log_level = 0; + load_attr.target_btf_path = test_case->btf_src_file; + err = bpf_object__load_xattr(&load_attr); + if (test_case->fails) { + CHECK(!err, "obj_load_fail", + "should fail to load prog '%s'\n", probe_name); + goto cleanup; + } else { + if (CHECK(err, "obj_load", + "failed to load prog '%s': %d\n", + probe_name, err)) + goto cleanup; + } + + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", + PTR_ERR(link))) + goto cleanup; + + data_map = bpf_object__find_map_by_name(obj, "test_cor.bss"); + if (CHECK(!data_map, "find_data_map", "data map not found\n")) + goto cleanup; + + memset(&data, 0, sizeof(data)); + memcpy(data.in, test_case->input, test_case->input_len); + + err = bpf_map_update_elem(bpf_map__fd(data_map), + &zero, &data, 0); + if (CHECK(err, "update_data_map", + "failed to update .data map: %d\n", err)) + goto cleanup; + + /* trigger test run */ + usleep(1); + + err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data); + if (CHECK(err, "get_result", + "failed to get output data: %d\n", err)) + goto cleanup; + + equal = memcmp(data.out, test_case->output, + test_case->output_len) == 0; + if (CHECK(!equal, "check_result", + "input/output data don't match\n")) { + int j; + + for (j = 0; j < test_case->input_len; j++) { + printf("input byte #%d: 0x%02hhx\n", + j, test_case->input[j]); + } + for (j = 0; j < test_case->output_len; j++) { + printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n", + j, test_case->output[j], data.out[j]); + } + goto cleanup; + } + +cleanup: + if (!IS_ERR_OR_NULL(link)) { + bpf_link__destroy(link); + link = NULL; + } + bpf_object__close(obj); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index c938283ac232..6892b88ae065 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -5,6 +5,10 @@ #include <linux/if_tun.h> #include <sys/uio.h> +#ifndef IP_MF +#define IP_MF 0x2000 +#endif + #define CHECK_FLOW_KEYS(desc, got, expected) \ CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ @@ -16,6 +20,7 @@ "is_encap=%u/%u " \ "ip_proto=0x%x/0x%x " \ "n_proto=0x%x/0x%x " \ + "flow_label=0x%x/0x%x " \ "sport=%u/%u " \ "dport=%u/%u\n", \ got.nhoff, expected.nhoff, \ @@ -26,6 +31,7 @@ got.is_encap, expected.is_encap, \ got.ip_proto, expected.ip_proto, \ got.n_proto, expected.n_proto, \ + got.flow_label, expected.flow_label, \ got.sport, expected.sport, \ got.dport, expected.dport) @@ -35,6 +41,13 @@ struct ipv4_pkt { struct tcphdr tcp; } __packed; +struct ipip_pkt { + struct ethhdr eth; + struct iphdr iph; + struct iphdr iph_inner; + struct tcphdr tcp; +} __packed; + struct svlan_ipv4_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -49,6 +62,18 @@ struct ipv6_pkt { struct tcphdr tcp; } __packed; +struct ipv6_frag_pkt { + struct ethhdr eth; + struct ipv6hdr iph; + struct frag_hdr { + __u8 nexthdr; + __u8 reserved; + __be16 frag_off; + __be32 identification; + } ipf; + struct tcphdr tcp; +} __packed; + struct dvlan_ipv6_pkt { struct ethhdr eth; __u16 vlan_tci; @@ -64,10 +89,13 @@ struct test { union { struct ipv4_pkt ipv4; struct svlan_ipv4_pkt svlan_ipv4; + struct ipip_pkt ipip; struct ipv6_pkt ipv6; + struct ipv6_frag_pkt ipv6_frag; struct dvlan_ipv6_pkt dvlan_ipv6; } pkt; struct bpf_flow_keys keys; + __u32 flags; }; #define VLAN_HLEN 4 @@ -81,6 +109,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -88,6 +118,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -97,6 +129,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN, @@ -104,6 +138,8 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, }, }, { @@ -115,6 +151,8 @@ struct test tests[] = { .iph.protocol = IPPROTO_TCP, .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN, @@ -122,6 +160,8 @@ struct test tests[] = { .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), + .sport = 80, + .dport = 8080, }, }, { @@ -133,6 +173,8 @@ struct test tests[] = { .iph.nexthdr = IPPROTO_TCP, .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, }, .keys = { .nhoff = ETH_HLEN + VLAN_HLEN * 2, @@ -141,8 +183,206 @@ struct test tests[] = { .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, }, }, + { + .name = "ipv4-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv4-no-frag", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.frag_off = __bpf_constant_htons(IP_MF), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + .sport = 80, + .dport = 8080, + }, + .flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG, + }, + { + .name = "ipv6-no-frag", + .pkt.ipv6_frag = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_FRAGMENT, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .ipf.nexthdr = IPPROTO_TCP, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr) + + sizeof(struct frag_hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .is_frag = true, + .is_first_frag = true, + }, + }, + { + .name = "ipv6-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .sport = 80, + .dport = 8080, + .flow_label = __bpf_constant_htonl(0xbeeef), + }, + }, + { + .name = "ipv6-no-flow-label", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .iph.flow_lbl = { 0xb, 0xee, 0xef }, + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + .flow_label = __bpf_constant_htonl(0xbeeef), + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL, + }, + { + .name = "ipip-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = 0, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) + + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + .sport = 80, + .dport = 8080, + }, + }, + { + .name = "ipip-no-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_IPIP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES) - + sizeof(struct iphdr), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_IPIP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + }, }; static int create_tap(const char *ifname) @@ -225,6 +465,13 @@ void test_flow_dissector(void) .data_size_in = sizeof(tests[i].pkt), .data_out = &flow_keys, }; + static struct bpf_flow_keys ctx = {}; + + if (tests[i].flags) { + tattr.ctx_in = &ctx; + tattr.ctx_size_in = sizeof(ctx); + ctx.flags = tests[i].flags; + } err = bpf_prog_test_run_xattr(&tattr); CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || @@ -251,9 +498,20 @@ void test_flow_dissector(void) CHECK(err, "ifup", "err %d errno %d\n", err, errno); for (i = 0; i < ARRAY_SIZE(tests); i++) { - struct bpf_flow_keys flow_keys = {}; + /* Keep in sync with 'flags' from eth_get_headlen. */ + __u32 eth_get_headlen_flags = + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; struct bpf_prog_test_run_attr tattr = {}; - __u32 key = 0; + struct bpf_flow_keys flow_keys = {}; + __u32 key = (__u32)(tests[i].keys.sport) << 16 | + tests[i].keys.dport; + + /* For skb-less case we can't pass input flags; run + * only the tests that have a matching set of flags. + */ + + if (tests[i].flags != eth_get_headlen_flags) + continue; err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); @@ -263,6 +521,9 @@ void test_flow_dissector(void) CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + + err = bpf_map_delete_elem(keys_fd, &key); + CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); } bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index c2a0a9d5591b..3d59b3c841fe 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -1,8 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <pthread.h> +#include <sched.h> +#include <sys/socket.h> #include <test_progs.h> #define MAX_CNT_RAWTP 10ull #define MAX_STACK_RAWTP 100 + +static int duration = 0; + struct get_stack_trace_t { int pid; int kern_stack_size; @@ -13,7 +20,7 @@ struct get_stack_trace_t { struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; }; -static int get_stack_print_output(void *data, int size) +static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) { bool good_kern_stack = false, good_user_stack = false; const char *nonjit_func = "___bpf_prog_run"; @@ -34,7 +41,7 @@ static int get_stack_print_output(void *data, int size) * just assume it is good if the stack is not empty. * This could be improved in the future. */ - if (jit_enabled) { + if (env.jit_enabled) { found = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -51,7 +58,7 @@ static int get_stack_print_output(void *data, int size) } } else { num_stack = e->kern_stack_size / sizeof(__u64); - if (jit_enabled) { + if (env.jit_enabled) { good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { @@ -65,75 +72,76 @@ static int get_stack_print_output(void *data, int size) if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) good_user_stack = true; } - if (!good_kern_stack || !good_user_stack) - return LIBBPF_PERF_EVENT_ERROR; - if (cnt == MAX_CNT_RAWTP) - return LIBBPF_PERF_EVENT_DONE; - - return LIBBPF_PERF_EVENT_CONT; + if (!good_kern_stack) + CHECK(!good_kern_stack, "kern_stack", "corrupted kernel stack\n"); + if (!good_user_stack) + CHECK(!good_user_stack, "user_stack", "corrupted user stack\n"); } void test_get_stack_raw_tp(void) { const char *file = "./test_get_stack_rawtp.o"; - int i, efd, err, prog_fd, pmu_fd, perfmap_fd; - struct perf_event_attr attr = {}; + const char *prog_name = "raw_tracepoint/sys_enter"; + int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP; + struct perf_buffer_opts pb_opts = {}; + struct perf_buffer *pb = NULL; + struct bpf_link *link = NULL; struct timespec tv = {0, 10}; - __u32 key = 0, duration = 0; + struct bpf_program *prog; struct bpf_object *obj; + struct bpf_map *map; + cpu_set_t cpu_set; err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) return; - efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); - if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + prog = bpf_object__find_program_by_title(obj, prog_name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) goto close_prog; - perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); - if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", - perfmap_fd, errno)) + map = bpf_object__find_map_by_name(obj, "perfmap"); + if (CHECK(!map, "bpf_find_map", "not found\n")) goto close_prog; err = load_kallsyms(); if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) goto close_prog; - attr.sample_type = PERF_SAMPLE_RAW; - attr.type = PERF_TYPE_SOFTWARE; - attr.config = PERF_COUNT_SW_BPF_OUTPUT; - pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, - -1/*group_fd*/, 0); - if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, - errno)) + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno)) goto close_prog; - err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); - if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, - errno)) + link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) goto close_prog; - err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", - err, errno)) - goto close_prog; - - err = perf_event_mmap(pmu_fd); - if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + pb_opts.sample_cb = get_stack_print_output; + pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts); + if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) goto close_prog; /* trigger some syscall action */ for (i = 0; i < MAX_CNT_RAWTP; i++) nanosleep(&tv, NULL); - err = perf_event_poller(pmu_fd, get_stack_print_output); - if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) - goto close_prog; + while (exp_cnt > 0) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && CHECK(err < 0, "pb__poll", "err %d\n", err)) + goto close_prog; + exp_cnt -= err; + } goto close_prog_noerr; close_prog: error_cnt++; close_prog_noerr: + if (!IS_ERR_OR_NULL(link)) + bpf_link__destroy(link); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 5633be43828f..4a4f428d1a78 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,15 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> -static int libbpf_debug_print(enum libbpf_print_level level, - const char *format, va_list args) -{ - if (level == LIBBPF_DEBUG) - return 0; - - return vfprintf(stderr, format, args); -} - void test_reference_tracking(void) { const char *file = "./test_sk_lookup_kern.o"; @@ -36,9 +27,11 @@ void test_reference_tracking(void) /* Expect verifier failure if test name has 'fail' */ if (strstr(title, "fail") != NULL) { - libbpf_set_print(NULL); + libbpf_print_fn_t old_print_fn; + + old_print_fn = libbpf_set_print(NULL); err = !bpf_program__load(prog, "GPL", 0); - libbpf_set_print(libbpf_debug_print); + libbpf_set_print(old_print_fn); } else { err = bpf_program__load(prog, "GPL", 0); } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 54218ee3c004..1575f0a1f586 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -203,7 +203,7 @@ static int test_send_signal_nmi(void) if (pmu_fd == -1) { if (errno == ENOENT) { printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", - __func__); + __func__); return 0; } /* Let the test fail with a more informative message */ @@ -219,11 +219,10 @@ void test_send_signal(void) { int ret = 0; - ret |= test_send_signal_tracepoint(); - ret |= test_send_signal_perf(); - ret |= test_send_signal_nmi(); - if (!ret) - printf("test_send_signal:OK\n"); - else - printf("test_send_signal:FAIL\n"); + if (test__start_subtest("send_signal_tracepoint")) + ret |= test_send_signal_tracepoint(); + if (test__start_subtest("send_signal_perf")) + ret |= test_send_signal_perf(); + if (test__start_subtest("send_signal_nmi")) + ret |= test_send_signal_nmi(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 09e6b46f5515..15f7c272edb0 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -75,7 +75,8 @@ void test_xdp_noinline(void) } if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { error_cnt++; - printf("test_xdp_noinline:FAIL:stats %lld %lld\n", bytes, pkts); + printf("test_xdp_noinline:FAIL:stats %lld %lld\n", + bytes, pkts); } out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 5ae485a6af3f..040a44206f29 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -65,8 +65,8 @@ struct { } jmp_table SEC(".maps"); struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1024); __type(key, __u32); __type(value, struct bpf_flow_keys); } last_dissection SEC(".maps"); @@ -74,15 +74,20 @@ struct { static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, int ret) { - struct bpf_flow_keys *val; - __u32 key = 0; + __u32 key = (__u32)(keys->sport) << 16 | keys->dport; + struct bpf_flow_keys val; - val = bpf_map_lookup_elem(&last_dissection, &key); - if (val) - memcpy(val, keys, sizeof(*val)); + memcpy(&val, keys, sizeof(val)); + bpf_map_update_elem(&last_dissection, &key, &val, BPF_ANY); return ret; } +#define IPV6_FLOWLABEL_MASK __bpf_constant_htonl(0x000FFFFF) +static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) +{ + return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; +} + static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, __u16 hdr_size, void *buffer) @@ -153,7 +158,6 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) struct tcphdr *tcp, _tcp; struct udphdr *udp, _udp; - keys->ip_proto = proto; switch (proto) { case IPPROTO_ICMP: icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); @@ -162,9 +166,15 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) return export_flow_keys(keys, BPF_OK); case IPPROTO_IPIP: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); case IPPROTO_IPV6: keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); + return parse_eth_proto(skb, bpf_htons(ETH_P_IPV6)); case IPPROTO_GRE: gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); @@ -184,6 +194,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) keys->thoff += 4; /* Step over sequence number */ keys->is_encap = true; + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP) + return export_flow_keys(keys, BPF_OK); if (gre->proto == bpf_htons(ETH_P_TEB)) { eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), @@ -231,7 +243,6 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->ip_proto = nexthdr; switch (nexthdr) { case IPPROTO_HOPOPTS: case IPPROTO_DSTOPTS: @@ -266,6 +277,7 @@ PROG(IP)(struct __sk_buff *skb) keys->addr_proto = ETH_P_IP; keys->ipv4_src = iph->saddr; keys->ipv4_dst = iph->daddr; + keys->ip_proto = iph->protocol; keys->thoff += iph->ihl << 2; if (data + keys->thoff > data_end) @@ -273,13 +285,20 @@ PROG(IP)(struct __sk_buff *skb) if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { keys->is_frag = true; - if (iph->frag_off & bpf_htons(IP_OFFSET)) + if (iph->frag_off & bpf_htons(IP_OFFSET)) { /* From second fragment on, packets do not have headers * we can parse. */ done = true; - else + } else { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + done = true; + } } if (done) @@ -301,6 +320,11 @@ PROG(IPV6)(struct __sk_buff *skb) memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); keys->thoff += sizeof(struct ipv6hdr); + keys->ip_proto = ip6h->nexthdr; + keys->flow_label = ip6_flowlabel(ip6h); + + if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) + return export_flow_keys(keys, BPF_OK); return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -317,7 +341,8 @@ PROG(IPV6OP)(struct __sk_buff *skb) /* hlen is in 8-octets and does not include the first 8 bytes * of the header */ - skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->thoff += (1 + ip6h->hdrlen) << 3; + keys->ip_proto = ip6h->nexthdr; return parse_ipv6_proto(skb, ip6h->nexthdr); } @@ -333,9 +358,18 @@ PROG(IPV6FR)(struct __sk_buff *skb) keys->thoff += sizeof(*fragh); keys->is_frag = true; - if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) + keys->ip_proto = fragh->nexthdr; + + if (!(fragh->frag_off & bpf_htons(IP6_OFFSET))) { keys->is_first_frag = true; + /* No need to parse fragmented packet unless + * explicitly asked for. + */ + if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) + return export_flow_keys(keys, BPF_OK); + } + return parse_ipv6_proto(skb, fragh->nexthdr); } diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c new file mode 100644 index 000000000000..018ed7fbba3a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c new file mode 100644 index 000000000000..13d662c57014 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_dim.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_dim x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c new file mode 100644 index 000000000000..a351f418c85d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___diff_arr_val_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___diff_arr_val_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c new file mode 100644 index 000000000000..a8735009becc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_non_array.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_non_array x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c new file mode 100644 index 000000000000..2a67c28b1e75 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_shallow.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_shallow x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c new file mode 100644 index 000000000000..1142c08c925f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_too_small.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_too_small x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c new file mode 100644 index 000000000000..795a5b729176 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type1.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type1 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c new file mode 100644 index 000000000000..3af74b837c4d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_wrong_val_type2.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_wrong_val_type2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c new file mode 100644 index 000000000000..b74455b91227 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c new file mode 100644 index 000000000000..7b6035f86ee6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_flavors__err_wrong_name.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_flavors__err_wrong_name x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c new file mode 100644 index 000000000000..7d0f041042c5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c new file mode 100644 index 000000000000..f9359450186e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___bool.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___bool x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c new file mode 100644 index 000000000000..50369e8320a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_bitfield.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_bitfield x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c new file mode 100644 index 000000000000..823bac13d641 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_16.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_16 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c new file mode 100644 index 000000000000..b44f3be18535 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_32.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_32 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c new file mode 100644 index 000000000000..9a3dd2099c0f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_64.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_64 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c new file mode 100644 index 000000000000..9f11ef5f6e88 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___err_wrong_sz_8.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___err_wrong_sz_8 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c new file mode 100644 index 000000000000..aafb1c5819d7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ints___reverse_sign.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ints___reverse_sign x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c new file mode 100644 index 000000000000..ed9ad8b5b4f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_misc.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_misc___a x) {} +void f2(struct core_reloc_misc___b x) {} +void f3(struct core_reloc_misc_extensible x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c new file mode 100644 index 000000000000..124197a2e813 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c new file mode 100644 index 000000000000..f8a6592ca75f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___mod_swap.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___mod_swap x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c new file mode 100644 index 000000000000..5c0d73687247 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_mods___typedefs.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_mods___typedefs x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c new file mode 100644 index 000000000000..4480fcc0f183 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c new file mode 100644 index 000000000000..13e108f76ece --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___anon_embed.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___anon_embed x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c new file mode 100644 index 000000000000..76b54fda5fbb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___dup_compat_types.c @@ -0,0 +1,5 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___dup_compat_types x) {} +void f2(struct core_reloc_nesting___dup_compat_types__2 x) {} +void f3(struct core_reloc_nesting___dup_compat_types__3 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c new file mode 100644 index 000000000000..975fb95db810 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c new file mode 100644 index 000000000000..ad66c67e7980 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_array_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_array_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c new file mode 100644 index 000000000000..35c5f8da6812 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_dup_incompat_types.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_dup_incompat_types__1 x) {} +void f2(struct core_reloc_nesting___err_dup_incompat_types__2 x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c new file mode 100644 index 000000000000..142e332041db --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c new file mode 100644 index 000000000000..efcae167fab9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_missing_field.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_missing_field x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c new file mode 100644 index 000000000000..97aaaedd8ada --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_nonstruct_container.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_nonstruct_container x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c new file mode 100644 index 000000000000..ffde35086e90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_partial_match_dups.c @@ -0,0 +1,4 @@ +#include "core_reloc_types.h" + +void f1(struct core_reloc_nesting___err_partial_match_dups__a x) {} +void f2(struct core_reloc_nesting___err_partial_match_dups__b x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c new file mode 100644 index 000000000000..39a2fadd8e95 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___err_too_deep.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___err_too_deep x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c new file mode 100644 index 000000000000..a09d9dfb20df --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___extra_nesting.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___extra_nesting x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c new file mode 100644 index 000000000000..3d8a1a74012f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_nesting___struct_union_mixup.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_nesting___struct_union_mixup x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c new file mode 100644 index 000000000000..96b90e39242a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c new file mode 100644 index 000000000000..6e87233a3ed0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_enum_def.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_enum_def x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c new file mode 100644 index 000000000000..d9f48e80b9d9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_func_proto.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_func_proto x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c new file mode 100644 index 000000000000..c718f75f8f3b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___diff_ptr_type.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___diff_ptr_type x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c new file mode 100644 index 000000000000..b8a120830891 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_enum.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_enum x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c new file mode 100644 index 000000000000..ad8b3c9aa76f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_int.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_int x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c new file mode 100644 index 000000000000..e20bc1d42d0a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_primitives___err_non_ptr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_primitives___err_non_ptr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..8da52432ba17 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c new file mode 100644 index 000000000000..003acfc9a3e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_ptr_as_arr___diff_sz.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_ptr_as_arr___diff_sz x) {} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h new file mode 100644 index 000000000000..f686a8138d90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -0,0 +1,667 @@ +#include <stdint.h> +#include <stdbool.h> + +/* + * FLAVORS + */ +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* this is not a flavor, as it doesn't have triple underscore */ +struct core_reloc_flavors__err_wrong_name { + int a; + int b; + int c; +}; + +/* + * NESTING + */ +/* original set up, used to record relocations in BPF program */ +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +/* inlined anonymous struct/union instead of named structs in original */ +struct core_reloc_nesting___anon_embed { + int __just_for_padding; + union { + struct { + int a; + } a; + } a; + struct { + union { + int b; + } b; + } b; +}; + +/* different mix of nested structs/unions than in original */ +struct core_reloc_nesting___struct_union_mixup { + int __a; + struct { + int __a; + union { + char __a; + int a; + } a; + } a; + int __b; + union { + int __b; + union { + char __b; + int b; + } b; + } b; +}; + +/* extra anon structs/unions, but still valid a.a.a and b.b.b accessors */ +struct core_reloc_nesting___extra_nesting { + int __padding; + struct { + struct { + struct { + struct { + union { + int a; + } a; + }; + }; + } a; + int __some_more; + struct { + union { + union { + union { + struct { + int b; + }; + } b; + }; + } b; + }; + }; +}; + +/* three flavors of same struct with different structure but same layout for + * a.a.a and b.b.b, thus successfully resolved and relocatable */ +struct core_reloc_nesting___dup_compat_types { + char __just_for_padding; + /* 3 more bytes of padding */ + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + long long __more_padding; + struct { + struct { + int b; /* offset 16 */ + } b; + } b; +}; + +struct core_reloc_nesting___dup_compat_types__2 { + int __aligned_padding; + struct { + int __trickier_noop[0]; + struct { + char __some_more_noops[0]; + int a; /* offset 4 */ + } a; + } a; + int __more_padding; + struct { + struct { + struct { + int __critical_padding; + int b; /* offset 16 */ + } b; + int __does_not_matter; + }; + } b; + int __more_irrelevant_stuff; +}; + +struct core_reloc_nesting___dup_compat_types__3 { + char __correct_padding[4]; + struct { + struct { + int a; /* offset 4 */ + } a; + } a; + /* 8 byte padding due to next struct's alignment */ + struct { + struct { + int b; + } b; + } b __attribute__((aligned(16))); +}; + +/* b.b.b field is missing */ +struct core_reloc_nesting___err_missing_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int x; + } b; + } b; +}; + +/* b.b.b field is an array of integers instead of plain int */ +struct core_reloc_nesting___err_array_field { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b[1]; + } b; + } b; +}; + +/* middle b container is missing */ +struct core_reloc_nesting___err_missing_container { + struct { + struct { + int a; + } a; + } a; + struct { + int x; + } b; +}; + +/* middle b container is referenced through pointer instead of being embedded */ +struct core_reloc_nesting___err_nonstruct_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } *b; + } b; +}; + +/* middle b container is an array of structs instead of plain struct */ +struct core_reloc_nesting___err_array_container { + struct { + struct { + int a; + } a; + } a; + struct { + struct { + int b; + } b[1]; + } b; +}; + +/* two flavors of same struct with incompatible layout for b.b.b */ +struct core_reloc_nesting___err_dup_incompat_types__1 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + struct { + struct { + int b; /* offset 4 */ + } b; + } b; +}; + +struct core_reloc_nesting___err_dup_incompat_types__2 { + struct { + struct { + int a; /* offset 0 */ + } a; + } a; + int __extra_padding; + struct { + struct { + int b; /* offset 8 (!) */ + } b; + } b; +}; + +/* two flavors of same struct having one of a.a.a and b.b.b, but not both */ +struct core_reloc_nesting___err_partial_match_dups__a { + struct { + struct { + int a; + } a; + } a; +}; + +struct core_reloc_nesting___err_partial_match_dups__b { + struct { + struct { + int b; + } b; + } b; +}; + +struct core_reloc_nesting___err_too_deep { + struct { + struct { + int a; + } a; + } a; + /* 65 levels of nestedness for b.b.b */ + struct { + struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + struct { struct { struct { struct { struct { + /* this one is one too much */ + struct { + int b; + }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + }; }; }; }; }; + } b; + } b; +}; + +/* + * ARRAYS + */ +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* bigger array dimensions */ +struct core_reloc_arrays___diff_arr_dim { + int a[7]; + char b[3][4][5]; + struct core_reloc_arrays_substruct c[4]; + struct core_reloc_arrays_substruct d[2][3]; +}; + +/* different size of array's value (struct) */ +struct core_reloc_arrays___diff_arr_val_sz { + int a[5]; + char b[2][3][4]; + struct { + int __padding1; + int c; + int __padding2; + } c[3]; + struct { + int __padding1; + int d; + int __padding2; + } d[1][2]; +}; + +struct core_reloc_arrays___err_too_small { + int a[2]; /* this one is too small */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_too_shallow { + int a[5]; + char b[2][3]; /* this one lacks one dimension */ + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_non_array { + int a; /* not an array */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type1 { + char a[5]; /* char instead of int */ + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +struct core_reloc_arrays___err_wrong_val_type2 { + int a[5]; + char b[2][3][4]; + int c[3]; /* value is not a struct */ + struct core_reloc_arrays_substruct d[1][2]; +}; + +/* + * PRIMITIVES + */ +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___diff_enum_def { + char a; + int b; + void *d; + int (*f)(const char *); + enum { + X = 100, + Y = 200, + } c; /* inline enum def with differing set of values */ +}; + +struct core_reloc_primitives___diff_func_proto { + void (*f)(int); /* incompatible function prototype */ + void *d; + enum core_reloc_primitives_enum c; + int b; + char a; +}; + +struct core_reloc_primitives___diff_ptr_type { + const char * const d; /* different pointee type + modifiers */ + char a; + int b; + enum core_reloc_primitives_enum c; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_enum { + char a[1]; + int b; + int c; /* int instead of enum */ + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_int { + char a[1]; + int *b; /* ptr instead of int */ + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +struct core_reloc_primitives___err_non_ptr { + char a[1]; + int b; + enum core_reloc_primitives_enum c; + int d; /* int instead of ptr */ + int (*f)(const char *); +}; + +/* + * MODS + */ +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +/* a/b, c/d, e/f, and g/h pairs are swapped */ +struct core_reloc_mods___mod_swap { + int b; + int_t a; + char *d; + char_ptr_t c; + int f[3]; + arr_t e; + struct { + int y; + int x; + } h; + core_reloc_mods_substruct_t g; +}; + +typedef int int1_t; +typedef int1_t int2_t; +typedef int2_t int3_t; + +typedef int arr1_t[5]; +typedef arr1_t arr2_t; +typedef arr2_t arr3_t; +typedef arr3_t arr4_t; + +typedef const char * const volatile fancy_char_ptr_t; + +typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; + +/* we need more typedefs */ +struct core_reloc_mods___typedefs { + core_reloc_mods_substruct_tt g; + core_reloc_mods_substruct_tt h; + arr4_t f; + arr4_t e; + fancy_char_ptr_t d; + fancy_char_ptr_t c; + int3_t b; + int3_t a; +}; + +/* + * PTR_AS_ARR + */ +struct core_reloc_ptr_as_arr { + int a; +}; + +struct core_reloc_ptr_as_arr___diff_sz { + int :32; /* padding */ + char __some_more_padding; + int a; +}; + +/* + * INTS + */ +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +/* signed/unsigned types swap */ +struct core_reloc_ints___reverse_sign { + int8_t u8_field; + uint8_t s8_field; + int16_t u16_field; + uint16_t s16_field; + int32_t u32_field; + uint32_t s32_field; + int64_t u64_field; + uint64_t s64_field; +}; + +struct core_reloc_ints___bool { + bool u8_field; /* bool instead of uint8 */ + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_bitfield { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field: 32; /* bitfields are not supported */ + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_8 { + uint16_t u8_field; /* not 8-bit anymore */ + int16_t s8_field; /* not 8-bit anymore */ + + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_16 { + uint8_t u8_field; + int8_t s8_field; + + uint32_t u16_field; /* not 16-bit anymore */ + int32_t s16_field; /* not 16-bit anymore */ + + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_32 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + + uint64_t u32_field; /* not 32-bit anymore */ + int64_t s32_field; /* not 32-bit anymore */ + + uint64_t u64_field; + int64_t s64_field; +}; + +struct core_reloc_ints___err_wrong_sz_64 { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + + uint32_t u64_field; /* not 64-bit anymore */ + int32_t s64_field; /* not 64-bit anymore */ +}; + +/* + * MISC + */ +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* this one extends core_reloc_misc_extensible struct from BPF prog */ +struct core_reloc_misc_extensible { + int a; + int b; + int c; + int d; +}; diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c new file mode 100644 index 000000000000..650859022771 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int combinations(volatile struct __sk_buff* skb) +{ + int ret = 0, i; + +#pragma nounroll + for (i = 0; i < 20; i++) + if (skb->len) + ret |= 1 << i; + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c new file mode 100644 index 000000000000..28d1d668f07c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include "bpf_helpers.h" +#define barrier() __asm__ __volatile__("": : :"memory") + +char _license[] SEC("license") = "GPL"; + +SEC("socket") +int while_true(volatile struct __sk_buff* skb) +{ + int i = 0; + + while (1) { + if (skb->len) + i += 3; + else + i += 7; + if (i == 9) + break; + barrier(); + if (i == 10) + break; + barrier(); + if (i == 13) + break; + barrier(); + if (i == 14) + break; + } + return i; +} diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index 5aeaa284fc47..a68062820410 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) } /* Rewrite destination. */ - if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && - ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 076122c898e9..9a3d1c79e6fe 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#include <string.h> #include <netinet/in.h> +#include <netinet/tcp.h> #include <linux/bpf.h> #include "bpf_helpers.h" @@ -42,6 +44,14 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Not interested in SOL_TCP:TCP_CONGESTION; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ @@ -91,6 +101,18 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } + if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { + /* Always use cubic */ + + if (optval + 5 > optval_end) + return 0; /* EPERM, bounds check */ + + memcpy(optval, "cubic", 5); + ctx->optlen = 5; + + return 1; + } + if (ctx->level != SOL_CUSTOM) return 0; /* EPERM, deny everything except custom level */ diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c new file mode 100644 index 000000000000..bf67f0fdf743 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_arrays_output { + int a2; + char b123; + int c1c; + int d00d; +}; + +struct core_reloc_arrays_substruct { + int c; + int d; +}; + +struct core_reloc_arrays { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_arrays(void *ctx) +{ + struct core_reloc_arrays *in = (void *)&data.in; + struct core_reloc_arrays_output *out = (void *)&data.out; + + /* in->a[2] */ + if (BPF_CORE_READ(&out->a2, &in->a[2])) + return 1; + /* in->b[1][2][3] */ + if (BPF_CORE_READ(&out->b123, &in->b[1][2][3])) + return 1; + /* in->c[1].c */ + if (BPF_CORE_READ(&out->c1c, &in->c[1].c)) + return 1; + /* in->d[0][0].d */ + if (BPF_CORE_READ(&out->d00d, &in->d[0][0].d)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c new file mode 100644 index 000000000000..9fda73e87972 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_flavors { + int a; + int b; + int c; +}; + +/* local flavor with reversed layout */ +struct core_reloc_flavors___reversed { + int c; + int b; + int a; +}; + +/* local flavor with nested/overlapping layout */ +struct core_reloc_flavors___weird { + struct { + int b; + }; + /* a and c overlap in local flavor, but this should still work + * correctly with target original flavor + */ + union { + int a; + int c; + }; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_flavors(void *ctx) +{ + struct core_reloc_flavors *in_orig = (void *)&data.in; + struct core_reloc_flavors___reversed *in_rev = (void *)&data.in; + struct core_reloc_flavors___weird *in_weird = (void *)&data.in; + struct core_reloc_flavors *out = (void *)&data.out; + + /* read a using weird layout */ + if (BPF_CORE_READ(&out->a, &in_weird->a)) + return 1; + /* read b using reversed layout */ + if (BPF_CORE_READ(&out->b, &in_rev->b)) + return 1; + /* read c using original layout */ + if (BPF_CORE_READ(&out->c, &in_orig->c)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c new file mode 100644 index 000000000000..d99233c8008a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ints { + uint8_t u8_field; + int8_t s8_field; + uint16_t u16_field; + int16_t s16_field; + uint32_t u32_field; + int32_t s32_field; + uint64_t u64_field; + int64_t s64_field; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ints(void *ctx) +{ + struct core_reloc_ints *in = (void *)&data.in; + struct core_reloc_ints *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->u8_field, &in->u8_field) || + BPF_CORE_READ(&out->s8_field, &in->s8_field) || + BPF_CORE_READ(&out->u16_field, &in->u16_field) || + BPF_CORE_READ(&out->s16_field, &in->s16_field) || + BPF_CORE_READ(&out->u32_field, &in->u32_field) || + BPF_CORE_READ(&out->s32_field, &in->s32_field) || + BPF_CORE_READ(&out->u64_field, &in->u64_field) || + BPF_CORE_READ(&out->s64_field, &in->s64_field)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c new file mode 100644 index 000000000000..37e02aa3f0c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct task_struct { + int pid; + int tgid; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_kernel(void *ctx) +{ + struct task_struct *task = (void *)bpf_get_current_task(); + uint64_t pid_tgid = bpf_get_current_pid_tgid(); + int pid, tgid; + + if (BPF_CORE_READ(&pid, &task->pid) || + BPF_CORE_READ(&tgid, &task->tgid)) + return 1; + + /* validate pid + tgid matches */ + data.out[0] = (((uint64_t)pid << 32) | tgid) == pid_tgid; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c new file mode 100644 index 000000000000..c59984bd3e23 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_misc_output { + int a, b, c; +}; + +struct core_reloc_misc___a { + int a1; + int a2; +}; + +struct core_reloc_misc___b { + int b1; + int b2; +}; + +/* fixed two first members, can be extended with new fields */ +struct core_reloc_misc_extensible { + int a; + int b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_misc(void *ctx) +{ + struct core_reloc_misc___a *in_a = (void *)&data.in; + struct core_reloc_misc___b *in_b = (void *)&data.in; + struct core_reloc_misc_extensible *in_ext = (void *)&data.in; + struct core_reloc_misc_output *out = (void *)&data.out; + + /* record two different relocations with the same accessor string */ + if (BPF_CORE_READ(&out->a, &in_a->a1) || /* accessor: 0:0 */ + BPF_CORE_READ(&out->b, &in_b->b1)) /* accessor: 0:0 */ + return 1; + + /* Validate relocations capture array-only accesses for structs with + * fixed header, but with potentially extendable tail. This will read + * first 4 bytes of 2nd element of in_ext array of potentially + * variably sized struct core_reloc_misc_extensible. */ + if (BPF_CORE_READ(&out->c, &in_ext[2])) /* accessor: 2 */ + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c new file mode 100644 index 000000000000..f98b942c062b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_mods_output { + int a, b, c, d, e, f, g, h; +}; + +typedef const int int_t; +typedef const char *char_ptr_t; +typedef const int arr_t[7]; + +struct core_reloc_mods_substruct { + int x; + int y; +}; + +typedef struct { + int x; + int y; +} core_reloc_mods_substruct_t; + +struct core_reloc_mods { + int a; + int_t b; + char *c; + char_ptr_t d; + int e[3]; + arr_t f; + struct core_reloc_mods_substruct g; + core_reloc_mods_substruct_t h; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_mods(void *ctx) +{ + struct core_reloc_mods *in = (void *)&data.in; + struct core_reloc_mods_output *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->e, &in->e[2]) || + BPF_CORE_READ(&out->f, &in->f[1]) || + BPF_CORE_READ(&out->g, &in->g.x) || + BPF_CORE_READ(&out->h, &in->h.y)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c new file mode 100644 index 000000000000..3ca30cec2b39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_nesting_substruct { + int a; +}; + +union core_reloc_nesting_subunion { + int b; +}; + +/* int a.a.a and b.b.b accesses */ +struct core_reloc_nesting { + union { + struct core_reloc_nesting_substruct a; + } a; + struct { + union core_reloc_nesting_subunion b; + } b; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_nesting(void *ctx) +{ + struct core_reloc_nesting *in = (void *)&data.in; + struct core_reloc_nesting *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a.a.a, &in->a.a.a)) + return 1; + if (BPF_CORE_READ(&out->b.b.b, &in->b.b.b)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c new file mode 100644 index 000000000000..add52f23ab35 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +enum core_reloc_primitives_enum { + A = 0, + B = 1, +}; + +struct core_reloc_primitives { + char a; + int b; + enum core_reloc_primitives_enum c; + void *d; + int (*f)(const char *); +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_primitives(void *ctx) +{ + struct core_reloc_primitives *in = (void *)&data.in; + struct core_reloc_primitives *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in->a) || + BPF_CORE_READ(&out->b, &in->b) || + BPF_CORE_READ(&out->c, &in->c) || + BPF_CORE_READ(&out->d, &in->d) || + BPF_CORE_READ(&out->f, &in->f)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c new file mode 100644 index 000000000000..526b7ddc7ea1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <linux/bpf.h> +#include <stdint.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; + +static volatile struct data { + char in[256]; + char out[256]; +} data; + +struct core_reloc_ptr_as_arr { + int a; +}; + +SEC("raw_tracepoint/sys_enter") +int test_core_ptr_as_arr(void *ctx) +{ + struct core_reloc_ptr_as_arr *in = (void *)&data.in; + struct core_reloc_ptr_as_arr *out = (void *)&data.out; + + if (BPF_CORE_READ(&out->a, &in[2].a)) + return 1; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 33254b771384..f8ffa3f3d44b 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -55,7 +55,7 @@ struct { __type(value, raw_stack_trace_t); } rawdata_map SEC(".maps"); -SEC("tracepoint/raw_syscalls/sys_enter") +SEC("raw_tracepoint/sys_enter") int bpf_prog1(void *ctx) { int max_len, max_buildid_len, usize, ksize, total_size; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index 1ab095bcacd8..d8803dfa8d32 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -19,10 +19,29 @@ struct bpf_map_def SEC("maps") results = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = 1, + .value_size = sizeof(__u32), + .max_entries = 3, }; +static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, + void *iph, __u32 ip_size, + struct tcphdr *tcph) +{ + __u32 thlen = tcph->doff * 4; + + if (tcph->syn && !tcph->ack) { + // packet should only have an MSS option + if (thlen != 24) + return 0; + + if ((void *)tcph + thlen > data_end) + return 0; + + return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen); + } + return 0; +} + static __always_inline void check_syncookie(void *ctx, void *data, void *data_end) { @@ -33,8 +52,10 @@ static __always_inline void check_syncookie(void *ctx, void *data, struct ipv6hdr *ipv6h; struct tcphdr *tcph; int ret; + __u32 key_mss = 2; + __u32 key_gen = 1; __u32 key = 0; - __u64 value = 1; + __s64 seq_mss; ethh = data; if (ethh + 1 > data_end) @@ -66,6 +87,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h), tcph, sizeof(*tcph)); break; @@ -95,6 +119,9 @@ static __always_inline void check_syncookie(void *ctx, void *data, if (sk->state != BPF_TCP_LISTEN) goto release; + seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h), + tcph); + ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h), tcph, sizeof(*tcph)); break; @@ -103,8 +130,19 @@ static __always_inline void check_syncookie(void *ctx, void *data, return; } - if (ret == 0) - bpf_map_update_elem(&results, &key, &value, 0); + if (seq_mss > 0) { + __u32 cookie = (__u32)seq_mss; + __u32 mss = seq_mss >> 32; + + bpf_map_update_elem(&results, &key_gen, &cookie, 0); + bpf_map_update_elem(&results, &key_mss, &mss, 0); + } + + if (ret == 0) { + __u32 cookie = bpf_ntohl(tcph->ack_seq) - 1; + + bpf_map_update_elem(&results, &key, &cookie, 0); + } release: bpf_sk_release(sk); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 5443b9bd75ed..e1f1becda529 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -508,6 +508,21 @@ static void test_devmap(unsigned int task, void *data) close(fd); } +static void test_devmap_hash(unsigned int task, void *data) +{ + int fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create devmap_hash '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + static void test_queuemap(unsigned int task, void *data) { const int MAP_SIZE = 32; @@ -1684,6 +1699,7 @@ static void run_all_tests(void) test_arraymap_percpu_many_keys(); test_devmap(0, NULL); + test_devmap_hash(0, NULL); test_sockmap(0, NULL); test_map_large(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index dae0819b1141..12895d03d58b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -3,10 +3,107 @@ */ #include "test_progs.h" #include "bpf_rlimit.h" +#include <argp.h> +#include <string.h> +/* defined in test_progs.h */ +struct test_env env; int error_cnt, pass_cnt; -bool jit_enabled; -bool verifier_stats = false; + +struct prog_test_def { + const char *test_name; + int test_num; + void (*run_test)(void); + bool force_log; + int pass_cnt; + int error_cnt; + bool tested; + + const char *subtest_name; + int subtest_num; + + /* store counts before subtest started */ + int old_pass_cnt; + int old_error_cnt; +}; + +static bool should_run(struct test_selector *sel, int num, const char *name) +{ + if (sel->name && sel->name[0] && !strstr(name, sel->name)) + return false; + + if (!sel->num_set) + return true; + + return num < sel->num_set_len && sel->num_set[num]; +} + +static void dump_test_log(const struct prog_test_def *test, bool failed) +{ + if (stdout == env.stdout) + return; + + fflush(stdout); /* exports env.log_buf & env.log_cnt */ + + if (env.verbose || test->force_log || failed) { + if (env.log_cnt) { + fprintf(env.stdout, "%s", env.log_buf); + if (env.log_buf[env.log_cnt - 1] != '\n') + fprintf(env.stdout, "\n"); + } + } + + fseeko(stdout, 0, SEEK_SET); /* rewind */ +} + +void test__end_subtest() +{ + struct prog_test_def *test = env.test; + int sub_error_cnt = error_cnt - test->old_error_cnt; + + if (sub_error_cnt) + env.fail_cnt++; + else + env.sub_succ_cnt++; + + dump_test_log(test, sub_error_cnt); + + fprintf(env.stdout, "#%d/%d %s:%s\n", + test->test_num, test->subtest_num, + test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); +} + +bool test__start_subtest(const char *name) +{ + struct prog_test_def *test = env.test; + + if (test->subtest_name) { + test__end_subtest(); + test->subtest_name = NULL; + } + + test->subtest_num++; + + if (!name || !name[0]) { + fprintf(env.stderr, + "Subtest #%d didn't provide sub-test name!\n", + test->subtest_num); + return false; + } + + if (!should_run(&env.subtest_selector, test->subtest_num, name)) + return false; + + test->subtest_name = name; + env.test->old_pass_cnt = pass_cnt; + env.test->old_error_cnt = error_cnt; + + return true; +} + +void test__force_log() { + env.test->force_log = true; +} struct ipv4_packet pkt_v4 = { .eth.h_proto = __bpf_constant_htons(ETH_P_IP), @@ -156,23 +253,276 @@ void *spin_lock_thread(void *arg) pthread_exit(arg); } -#define DECLARE +/* extern declarations for test funcs */ +#define DEFINE_TEST(name) extern void test_##name(); +#include <prog_tests/tests.h> +#undef DEFINE_TEST + +static struct prog_test_def prog_test_defs[] = { +#define DEFINE_TEST(name) { \ + .test_name = #name, \ + .run_test = &test_##name, \ +}, #include <prog_tests/tests.h> -#undef DECLARE +#undef DEFINE_TEST +}; +const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); + +const char *argp_program_version = "test_progs 0.1"; +const char *argp_program_bug_address = "<[email protected]>"; +const char argp_program_doc[] = "BPF selftests test runner"; + +enum ARG_KEYS { + ARG_TEST_NUM = 'n', + ARG_TEST_NAME = 't', + ARG_VERIFIER_STATS = 's', + ARG_VERBOSE = 'v', +}; + +static const struct argp_option opts[] = { + { "num", ARG_TEST_NUM, "NUM", 0, + "Run test number NUM only " }, + { "name", ARG_TEST_NAME, "NAME", 0, + "Run tests with names containing NAME" }, + { "verifier-stats", ARG_VERIFIER_STATS, NULL, 0, + "Output verifier statistics", }, + { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, + "Verbose output (use -vv for extra verbose output)" }, + {}, +}; + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (!env.very_verbose && level == LIBBPF_DEBUG) + return 0; + vprintf(format, args); + return 0; +} + +int parse_num_list(const char *s, struct test_selector *sel) +{ + int i, set_len = 0, num, start = 0, end = -1; + bool *set = NULL, *tmp, parsing_end = false; + char *next; + + while (s[0]) { + errno = 0; + num = strtol(s, &next, 10); + if (errno) + return -errno; + + if (parsing_end) + end = num; + else + start = num; + + if (!parsing_end && *next == '-') { + s = next + 1; + parsing_end = true; + continue; + } else if (*next == ',') { + parsing_end = false; + s = next + 1; + end = num; + } else if (*next == '\0') { + parsing_end = false; + s = next; + end = num; + } else { + return -EINVAL; + } + + if (start > end) + return -EINVAL; -int main(int ac, char **av) + if (end + 1 > set_len) { + set_len = end + 1; + tmp = realloc(set, set_len); + if (!tmp) { + free(set); + return -ENOMEM; + } + set = tmp; + } + for (i = start; i <= end; i++) { + set[i] = true; + } + + } + + if (!set) + return -EINVAL; + + sel->num_set = set; + sel->num_set_len = set_len; + + return 0; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + struct test_env *env = state->input; + + switch (key) { + case ARG_TEST_NUM: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + if (parse_num_list(subtest_str + 1, + &env->subtest_selector)) { + fprintf(stderr, + "Failed to parse subtest numbers.\n"); + return -EINVAL; + } + } + if (parse_num_list(arg, &env->test_selector)) { + fprintf(stderr, "Failed to parse test numbers.\n"); + return -EINVAL; + } + break; + } + case ARG_TEST_NAME: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + env->subtest_selector.name = strdup(subtest_str + 1); + if (!env->subtest_selector.name) + return -ENOMEM; + } + env->test_selector.name = strdup(arg); + if (!env->test_selector.name) + return -ENOMEM; + break; + } + case ARG_VERIFIER_STATS: + env->verifier_stats = true; + break; + case ARG_VERBOSE: + if (arg) { + if (strcmp(arg, "v") == 0) { + env->very_verbose = true; + } else { + fprintf(stderr, + "Unrecognized verbosity setting ('%s'), only -v and -vv are supported\n", + arg); + return -EINVAL; + } + } + env->verbose = true; + break; + case ARGP_KEY_ARG: + argp_usage(state); + break; + case ARGP_KEY_END: + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +static void stdio_hijack(void) { +#ifdef __GLIBC__ + env.stdout = stdout; + env.stderr = stderr; + + if (env.verbose) { + /* nothing to do, output to stdout by default */ + return; + } + + /* stdout and stderr -> buffer */ + fflush(stdout); + + stdout = open_memstream(&env.log_buf, &env.log_cnt); + if (!stdout) { + stdout = env.stdout; + perror("open_memstream"); + return; + } + + stderr = stdout; +#endif +} + +static void stdio_restore(void) +{ +#ifdef __GLIBC__ + if (stdout == env.stdout) + return; + + fclose(stdout); + free(env.log_buf); + + env.log_buf = NULL; + env.log_cnt = 0; + + stdout = env.stdout; + stderr = env.stderr; +#endif +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + int err, i; + + err = argp_parse(&argp, argc, argv, 0, NULL, &env); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + srand(time(NULL)); - jit_enabled = is_jit_enabled(); + env.jit_enabled = is_jit_enabled(); - if (ac == 2 && strcmp(av[1], "-s") == 0) - verifier_stats = true; + stdio_hijack(); + for (i = 0; i < prog_test_cnt; i++) { + struct prog_test_def *test = &prog_test_defs[i]; + int old_pass_cnt = pass_cnt; + int old_error_cnt = error_cnt; -#define CALL -#include <prog_tests/tests.h> -#undef CALL + env.test = test; + test->test_num = i + 1; + + if (!should_run(&env.test_selector, + test->test_num, test->test_name)) + continue; + + test->run_test(); + /* ensure last sub-test is finalized properly */ + if (test->subtest_name) + test__end_subtest(); + + test->tested = true; + test->pass_cnt = pass_cnt - old_pass_cnt; + test->error_cnt = error_cnt - old_error_cnt; + if (test->error_cnt) + env.fail_cnt++; + else + env.succ_cnt++; + + dump_test_log(test, test->error_cnt); + + fprintf(env.stdout, "#%d %s:%s\n", + test->test_num, test->test_name, + test->error_cnt ? "FAIL" : "OK"); + } + stdio_restore(); + printf("Summary: %d/%d PASSED, %d FAILED\n", + env.succ_cnt, env.sub_succ_cnt, env.fail_cnt); + + free(env.test_selector.num_set); + free(env.subtest_selector.num_set); - printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 49e0f7d85643..37d427f5a1e5 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -38,9 +38,40 @@ typedef __u16 __sum16; #include "trace_helpers.h" #include "flow_dissector_load.h" -extern int error_cnt, pass_cnt; -extern bool jit_enabled; -extern bool verifier_stats; +struct prog_test_def; + +struct test_selector { + const char *name; + bool *num_set; + int num_set_len; +}; + +struct test_env { + struct test_selector test_selector; + struct test_selector subtest_selector; + bool verifier_stats; + bool verbose; + bool very_verbose; + + bool jit_enabled; + + struct prog_test_def *test; + FILE *stdout; + FILE *stderr; + char *log_buf; + size_t log_cnt; + + int succ_cnt; /* successful tests */ + int sub_succ_cnt; /* successful sub-tests */ + int fail_cnt; /* total failed tests + sub-tests */ +}; + +extern int error_cnt; +extern int pass_cnt; +extern struct test_env env; + +extern void test__force_log(); +extern bool test__start_subtest(const char *name); #define MAGIC_BYTES 123 @@ -68,7 +99,8 @@ extern struct ipv6_packet pkt_v6; printf(format); \ } else { \ pass_cnt++; \ - printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ + printf("%s:PASS:%s %d nsec\n", \ + __func__, tag, duration); \ } \ __ret; \ }) diff --git a/tools/testing/selftests/bpf/test_sockopt_sk.c b/tools/testing/selftests/bpf/test_sockopt_sk.c index 036b652e5ca9..e4f6055d92e9 100644 --- a/tools/testing/selftests/bpf/test_sockopt_sk.c +++ b/tools/testing/selftests/bpf/test_sockopt_sk.c @@ -6,6 +6,7 @@ #include <sys/types.h> #include <sys/socket.h> #include <netinet/in.h> +#include <netinet/tcp.h> #include <linux/filter.h> #include <bpf/bpf.h> @@ -25,6 +26,7 @@ static int getsetsockopt(void) union { char u8[4]; __u32 u32; + char cc[16]; /* TCP_CA_NAME_MAX */ } buf = {}; socklen_t optlen; @@ -115,6 +117,29 @@ static int getsetsockopt(void) goto err; } + /* TCP_CONGESTION can extend the string */ + + strcpy(buf.cc, "nv"); + err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv")); + if (err) { + log_err("Failed to call setsockopt(TCP_CONGESTION)"); + goto err; + } + + + optlen = sizeof(buf.cc); + err = getsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(TCP_CONGESTION)"); + goto err; + } + + if (strcmp(buf.cc, "cubic") != 0) { + log_err("Unexpected getsockopt(TCP_CONGESTION) %s != %s", + buf.cc, "cubic"); + goto err; + } + close(fd); return 0; err: diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index d48e51716d19..9b3617d770a5 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -37,6 +37,9 @@ setup() ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 + ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0 + ns1_exec sysctl -w net.ipv4.tcp_timestamps=0 + ns1_exec sysctl -w net.ipv4.tcp_sack=0 wait_for_ip 127.0.0.1 wait_for_ip ::1 diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index 87829c86c746..b9e991d43155 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -2,6 +2,7 @@ // Copyright (c) 2018 Facebook // Copyright (c) 2019 Cloudflare +#include <limits.h> #include <string.h> #include <stdlib.h> #include <unistd.h> @@ -77,7 +78,7 @@ out: return fd; } -static int get_map_fd_by_prog_id(int prog_id) +static int get_map_fd_by_prog_id(int prog_id, bool *xdp) { struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); @@ -104,6 +105,8 @@ static int get_map_fd_by_prog_id(int prog_id) goto err; } + *xdp = info.type == BPF_PROG_TYPE_XDP; + map_fd = bpf_map_get_fd_by_id(map_ids[0]); if (map_fd < 0) log_err("Failed to get fd by map id %d", map_ids[0]); @@ -113,18 +116,32 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd) +static int run_test(int server_fd, int results_fd, bool xdp) { int client = -1, srv_client = -1; int ret = 0; __u32 key = 0; - __u64 value = 0; + __u32 key_gen = 1; + __u32 key_mss = 2; + __u32 value = 0; + __u32 value_gen = 0; + __u32 value_mss = 0; if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) { log_err("Can't clear results"); goto err; } + if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + + if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) { + log_err("Can't clear results"); + goto err; + } + client = connect_to_server(server_fd); if (client == -1) goto err; @@ -140,8 +157,35 @@ static int run_test(int server_fd, int results_fd) goto err; } - if (value != 1) { - log_err("Didn't match syncookie: %llu", value); + if (value == 0) { + log_err("Didn't match syncookie: %u", value); + goto err; + } + + if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (xdp && value_gen == 0) { + // SYN packets do not get passed through generic XDP, skip the + // rest of the test. + printf("Skipping XDP cookie check\n"); + goto out; + } + + if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) { + log_err("Can't lookup result"); + goto err; + } + + if (value != value_gen) { + log_err("BPF generated cookie does not match kernel one"); + goto err; + } + + if (value_mss < 536 || value_mss > USHRT_MAX) { + log_err("Unexpected MSS retrieved"); goto err; } @@ -163,13 +207,14 @@ int main(int argc, char **argv) int server_v6 = -1; int results = -1; int err = 0; + bool xdp; if (argc < 2) { fprintf(stderr, "Usage: %s prog_id\n", argv[0]); exit(1); } - results = get_map_fd_by_prog_id(atoi(argv[1])); + results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp); if (results < 0) { log_err("Can't get map"); goto err; @@ -194,10 +239,10 @@ int main(int argc, char **argv) if (server_v6 == -1) goto err; - if (run_test(server, results)) + if (run_test(server, results, xdp)) goto err; - if (run_test(server_v6, results)) + if (run_test(server_v6, results, xdp)) goto err; printf("ok\n"); diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 86152d9ae95b..f9765ddf0761 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -17,6 +17,7 @@ #include <linux/rtnetlink.h> #include <signal.h> #include <linux/perf_event.h> +#include <linux/err.h> #include "bpf_rlimit.h" #include "bpf_util.h" @@ -30,28 +31,34 @@ pthread_t tid; int rx_callbacks; -static int dummyfn(void *data, int size) +static void dummyfn(void *ctx, int cpu, void *data, __u32 size) { struct tcp_notifier *t = data; if (t->type != 0xde || t->subtype != 0xad || t->source != 0xbe || t->hash != 0xef) - return 1; + return; rx_callbacks++; - return 0; } -void tcp_notifier_poller(int fd) +void tcp_notifier_poller(struct perf_buffer *pb) { - while (1) - perf_event_poller(fd, dummyfn); + int err; + + while (1) { + err = perf_buffer__poll(pb, 100); + if (err < 0 && err != -EINTR) { + printf("failed perf_buffer__poll: %d\n", err); + return; + } + } } static void *poller_thread(void *arg) { - int fd = *(int *)arg; + struct perf_buffer *pb = arg; - tcp_notifier_poller(fd); + tcp_notifier_poller(pb); return arg; } @@ -60,52 +67,20 @@ int verify_result(const struct tcpnotify_globals *result) return (result->ncalls > 0 && result->ncalls == rx_callbacks ? 0 : 1); } -static int bpf_find_map(const char *test, struct bpf_object *obj, - const char *name) -{ - struct bpf_map *map; - - map = bpf_object__find_map_by_name(obj, name); - if (!map) { - printf("%s:FAIL:map '%s' not found\n", test, name); - return -1; - } - return bpf_map__fd(map); -} - -static int setup_bpf_perf_event(int mapfd) -{ - struct perf_event_attr attr = { - .sample_type = PERF_SAMPLE_RAW, - .type = PERF_TYPE_SOFTWARE, - .config = PERF_COUNT_SW_BPF_OUTPUT, - }; - int key = 0; - int pmu_fd; - - pmu_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, 0); - if (pmu_fd < 0) - return pmu_fd; - bpf_map_update_elem(mapfd, &key, &pmu_fd, BPF_ANY); - - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - return pmu_fd; -} - int main(int argc, char **argv) { const char *file = "test_tcpnotify_kern.o"; - int prog_fd, map_fd, perf_event_fd; + struct bpf_map *perf_map, *global_map; + struct perf_buffer_opts pb_opts = {}; struct tcpnotify_globals g = {0}; + struct perf_buffer *pb = NULL; const char *cg_path = "/foo"; + int prog_fd, rv, cg_fd = -1; int error = EXIT_FAILURE; struct bpf_object *obj; - int cg_fd = -1; - __u32 key = 0; - int rv; char test_script[80]; - int pmu_fd; cpu_set_t cpuset; + __u32 key = 0; CPU_ZERO(&cpuset); CPU_SET(0, &cpuset); @@ -133,19 +108,24 @@ int main(int argc, char **argv) goto err; } - perf_event_fd = bpf_find_map(__func__, obj, "perf_event_map"); - if (perf_event_fd < 0) + perf_map = bpf_object__find_map_by_name(obj, "perf_event_map"); + if (!perf_map) { + printf("FAIL:map '%s' not found\n", "perf_event_map"); goto err; + } - map_fd = bpf_find_map(__func__, obj, "global_map"); - if (map_fd < 0) - goto err; + global_map = bpf_object__find_map_by_name(obj, "global_map"); + if (!global_map) { + printf("FAIL:map '%s' not found\n", "global_map"); + return -1; + } - pmu_fd = setup_bpf_perf_event(perf_event_fd); - if (pmu_fd < 0 || perf_event_mmap(pmu_fd) < 0) + pb_opts.sample_cb = dummyfn; + pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts); + if (IS_ERR(pb)) goto err; - pthread_create(&tid, NULL, poller_thread, (void *)&pmu_fd); + pthread_create(&tid, NULL, poller_thread, pb); sprintf(test_script, "iptables -A INPUT -p tcp --dport %d -j DROP", @@ -162,7 +142,7 @@ int main(int argc, char **argv) TESTPORT); system(test_script); - rv = bpf_map_lookup_elem(map_fd, &key, &g); + rv = bpf_map_lookup_elem(bpf_map__fd(global_map), &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); goto err; @@ -182,5 +162,7 @@ err: bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); close(cg_fd); cleanup_cgroup_environment(); + if (!IS_ERR_OR_NULL(pb)) + perf_buffer__free(pb); return error; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 84135d5f4b35..44e2d640b088 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -50,7 +50,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 18 +#define MAX_NR_MAPS 19 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -84,6 +84,7 @@ struct bpf_test { int fixup_map_array_wo[MAX_FIXUPS]; int fixup_map_array_small[MAX_FIXUPS]; int fixup_sk_storage_map[MAX_FIXUPS]; + int fixup_map_event_output[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t insn_processed; @@ -632,6 +633,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_wo = test->fixup_map_array_wo; int *fixup_map_array_small = test->fixup_map_array_small; int *fixup_sk_storage_map = test->fixup_sk_storage_map; + int *fixup_map_event_output = test->fixup_map_event_output; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -793,6 +795,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_sk_storage_map++; } while (*fixup_sk_storage_map); } + if (*fixup_map_event_output) { + map_fds[18] = __create_map(BPF_MAP_TYPE_PERF_EVENT_ARRAY, + sizeof(int), sizeof(int), 1, 0); + do { + prog[*fixup_map_event_output].imm = map_fds[18]; + fixup_map_event_output++; + } while (*fixup_map_event_output); + } } static int set_admin(bool admin) diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 51a3a31d1aac..bb8b0da91686 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -1,6 +1,14 @@ #!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Author: Jesper Dangaard Brouer <[email protected]> -TESTNAME=xdp_vlan +# Allow wrapper scripts to name test +if [ -z "$TESTNAME" ]; then + TESTNAME=xdp_vlan +fi + +# Default XDP mode +XDP_MODE=xdpgeneric usage() { echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME" @@ -9,9 +17,23 @@ usage() { echo " -v | --verbose : Verbose" echo " --flush : Flush before starting (e.g. after --interactive)" echo " --interactive : Keep netns setup running after test-run" + echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)" echo "" } +valid_xdp_mode() +{ + local mode=$1 + + case "$mode" in + xdpgeneric | xdpdrv | xdp) + return 0 + ;; + *) + return 1 + esac +} + cleanup() { local status=$? @@ -37,7 +59,7 @@ cleanup() # Using external program "getopt" to get --long-options OPTIONS=$(getopt -o hvfi: \ - --long verbose,flush,help,interactive,debug -- "$@") + --long verbose,flush,help,interactive,debug,mode: -- "$@") if (( $? != 0 )); then usage echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?" @@ -60,6 +82,11 @@ while true; do cleanup shift ;; + --mode ) + shift + XDP_MODE=$1 + shift + ;; -- ) shift break @@ -81,8 +108,14 @@ if [ "$EUID" -ne 0 ]; then exit 1 fi -ip link set dev lo xdp off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then +valid_xdp_mode $XDP_MODE +if [ $? -ne 0 ]; then + echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)" + exit 1 +fi + +ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null +if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" exit 0 fi @@ -155,7 +188,7 @@ ip netns exec ns2 ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"' +ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -166,7 +199,7 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) @@ -177,8 +210,8 @@ ip netns exec ns1 tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -187,9 +220,9 @@ ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 xdp off -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh new file mode 100755 index 000000000000..c515326d6d59 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test generic-XDP +export TESTNAME=xdp_vlan_mode_generic +./test_xdp_vlan.sh --mode=xdpgeneric diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh new file mode 100755 index 000000000000..5cf7ce1f16c1 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test native-XDP +export TESTNAME=xdp_vlan_mode_native +./test_xdp_vlan.sh --mode=xdpdrv diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index b47f205f0310..7f989b3e4e22 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -86,128 +86,3 @@ long ksym_get_addr(const char *name) return 0; } - -static int page_size; -static int page_cnt = 8; -static struct perf_event_mmap_page *header; - -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header) -{ - void *base; - int mmap_size; - - page_size = getpagesize(); - mmap_size = page_size * (page_cnt + 1); - - base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (base == MAP_FAILED) { - printf("mmap err\n"); - return -1; - } - - *header = base; - return 0; -} - -int perf_event_mmap(int fd) -{ - return perf_event_mmap_header(fd, &header); -} - -static int perf_event_poll(int fd) -{ - struct pollfd pfd = { .fd = fd, .events = POLLIN }; - - return poll(&pfd, 1, 1000); -} - -struct perf_event_sample { - struct perf_event_header header; - __u32 size; - char data[]; -}; - -static enum bpf_perf_event_ret -bpf_perf_event_print(struct perf_event_header *hdr, void *private_data) -{ - struct perf_event_sample *e = (struct perf_event_sample *)hdr; - perf_event_print_fn fn = private_data; - int ret; - - if (e->header.type == PERF_RECORD_SAMPLE) { - ret = fn(e->data, e->size); - if (ret != LIBBPF_PERF_EVENT_CONT) - return ret; - } else if (e->header.type == PERF_RECORD_LOST) { - struct { - struct perf_event_header header; - __u64 id; - __u64 lost; - } *lost = (void *) e; - printf("lost %lld events\n", lost->lost); - } else { - printf("unknown event type=%d size=%d\n", - e->header.type, e->header.size); - } - - return LIBBPF_PERF_EVENT_CONT; -} - -int perf_event_poller(int fd, perf_event_print_fn output_fn) -{ - enum bpf_perf_event_ret ret; - void *buf = NULL; - size_t len = 0; - - for (;;) { - perf_event_poll(fd); - ret = bpf_perf_event_read_simple(header, page_cnt * page_size, - page_size, &buf, &len, - bpf_perf_event_print, - output_fn); - if (ret != LIBBPF_PERF_EVENT_CONT) - break; - } - free(buf); - - return ret; -} - -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn) -{ - enum bpf_perf_event_ret ret; - struct pollfd *pfds; - void *buf = NULL; - size_t len = 0; - int i; - - pfds = calloc(num_fds, sizeof(*pfds)); - if (!pfds) - return LIBBPF_PERF_EVENT_ERROR; - - for (i = 0; i < num_fds; i++) { - pfds[i].fd = fds[i]; - pfds[i].events = POLLIN; - } - - for (;;) { - poll(pfds, num_fds, 1000); - for (i = 0; i < num_fds; i++) { - if (!pfds[i].revents) - continue; - - ret = bpf_perf_event_read_simple(headers[i], - page_cnt * page_size, - page_size, &buf, &len, - bpf_perf_event_print, - output_fn); - if (ret != LIBBPF_PERF_EVENT_CONT) - break; - } - } - free(buf); - free(pfds); - - return ret; -} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 18924f23db1b..aa4dcfe18050 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -3,7 +3,6 @@ #define __TRACE_HELPER_H #include <libbpf.h> -#include <linux/perf_event.h> struct ksym { long addr; @@ -14,12 +13,4 @@ int load_kallsyms(void); struct ksym *ksym_search(long key); long ksym_get_addr(const char *name); -typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size); - -int perf_event_mmap(int fd); -int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header); -/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */ -int perf_event_poller(int fd, perf_event_print_fn output_fn); -int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers, - int num_fds, perf_event_print_fn output_fn); #endif diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index b0fda2877119..d438193804b2 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -975,6 +975,17 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, { + "read gso_segs from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ "write gso_segs from CGROUP_SKB", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c new file mode 100644 index 000000000000..130553e19eca --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -0,0 +1,94 @@ +/* instructions used to output a skb based software event, produced + * from code snippet: + * struct TMP { + * uint64_t tmp; + * } tt; + * tt.tmp = 5; + * bpf_perf_event_output(skb, &connection_tracking_event_map, 0, + * &tt, sizeof(tt)); + * return 1; + * + * the bpf assembly from llvm is: + * 0: b7 02 00 00 05 00 00 00 r2 = 5 + * 1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2 + * 2: bf a4 00 00 00 00 00 00 r4 = r10 + * 3: 07 04 00 00 f8 ff ff ff r4 += -8 + * 4: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0ll + * 6: b7 03 00 00 00 00 00 00 r3 = 0 + * 7: b7 05 00 00 08 00 00 00 r5 = 8 + * 8: 85 00 00 00 19 00 00 00 call 25 + * 9: b7 00 00 00 01 00 00 00 r0 = 1 + * 10: 95 00 00 00 00 00 00 00 exit + * + * The reason I put the code here instead of fill_helpers is that map fixup + * is against the insns, instead of filled prog. + */ + +#define __PERF_EVENT_INSNS__ \ + BPF_MOV64_IMM(BPF_REG_2, 5), \ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), \ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), \ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), \ + BPF_LD_MAP_FD(BPF_REG_2, 0), \ + BPF_MOV64_IMM(BPF_REG_3, 0), \ + BPF_MOV64_IMM(BPF_REG_5, 8), \ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, \ + BPF_FUNC_perf_event_output), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), +{ + "perfevent for sockops", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCK_OPS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for tc", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for lwt out", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_LWT_OUT, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for xdp", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_XDP, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for socket filter", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for sk_skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "perfevent for cgroup skb", + .insns = { __PERF_EVENT_INSNS__ }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .fixup_map_event_output = { 4 }, + .result = ACCEPT, + .retval = 1, +}, diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 4c223266299a..bdb69599c4bd 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -191,8 +191,7 @@ int cg_find_unified_root(char *root, size_t len) strtok(NULL, delim); strtok(NULL, delim); - if (strcmp(fs, "cgroup") == 0 && - strcmp(type, "cgroup2") == 0) { + if (strcmp(type, "cgroup2") == 0) { strncpy(root, mount, len); return 0; } diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 0a76314b4414..8b944cf042f6 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -28,7 +28,7 @@ # override by exporting to your environment prior running this script. # For instance this script assumes you do not have xfs loaded upon boot. # If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this -# script if the filesyste module you don't have loaded upon bootup +# script if the filesystem module you don't have loaded upon bootup # is ext4 instead. Refer to allow_user_defaults() for a list of user # override variables possible. # @@ -263,7 +263,7 @@ config_get_test_result() config_reset() { if ! echo -n "1" >"$DIR"/reset; then - echo "$0: reset shuld have worked" >&2 + echo "$0: reset should have worked" >&2 exit 1 fi } @@ -488,7 +488,7 @@ usage() echo Example uses: echo echo "${TEST_NAME}.sh -- executes all tests" - echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recomended" + echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recommended" echo "${TEST_NAME}.sh -w 0008 -- Watch test ID 0008 run until an error occurs" echo "${TEST_NAME}.sh -s 0008 -- Run test ID 0008 once" echo "${TEST_NAME}.sh -c 0008 3 -- Run test ID 0008 three times" diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index ec15c4f6af55..0ac49d91a260 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -10,6 +10,7 @@ #ifndef __KSELFTEST_H #define __KSELFTEST_H +#include <errno.h> #include <stdlib.h> #include <unistd.h> #include <stdarg.h> @@ -81,58 +82,68 @@ static inline void ksft_print_cnts(void) static inline void ksft_print_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("# "); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_pass(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_pass++; va_start(args, msg); printf("ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_fail(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_fail++; va_start(args, msg); printf("not ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_skip(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_xskip++; va_start(args, msg); printf("not ok %d # SKIP ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_error(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_error++; va_start(args, msg); printf("not ok %d # error ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } @@ -152,10 +163,12 @@ static inline int ksft_exit_fail(void) static inline int ksft_exit_fail_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("Bail out! "); + errno = saved_errno; vprintf(msg, args); va_end(args); @@ -178,10 +191,12 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { if (msg) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("not ok %d # SKIP ", 1 + ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } else { diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index 30195449c63c..79b0affd21fb 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -13,6 +13,14 @@ function log() { echo "$1" > /dev/kmsg } +# skip(msg) - testing can't proceed +# msg - explanation +function skip() { + log "SKIP: $1" + echo "SKIP: $1" >&2 + exit 4 +} + # die(msg) - game over, man # msg - dying words function die() { @@ -21,13 +29,27 @@ function die() { exit 1 } -# set_dynamic_debug() - setup kernel dynamic debug -# TODO - push and pop this config? +function push_dynamic_debug() { + DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \ + awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') +} + +function pop_dynamic_debug() { + if [[ -n "$DYNAMIC_DEBUG" ]]; then + echo -n "$DYNAMIC_DEBUG" > /sys/kernel/debug/dynamic_debug/control + fi +} + +# set_dynamic_debug() - save the current dynamic debug config and tweak +# it for the self-tests. Set a script exit trap +# that restores the original config. function set_dynamic_debug() { - cat << EOF > /sys/kernel/debug/dynamic_debug/control -file kernel/livepatch/* +p -func klp_try_switch_task -p -EOF + push_dynamic_debug + trap pop_dynamic_debug EXIT INT TERM HUP + cat <<-EOF > /sys/kernel/debug/dynamic_debug/control + file kernel/livepatch/* +p + func klp_try_switch_task -p + EOF } # loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES, @@ -43,6 +65,12 @@ function loop_until() { done } +function assert_mod() { + local mod="$1" + + modprobe --dry-run "$mod" &>/dev/null +} + function is_livepatch_mod() { local mod="$1" @@ -75,6 +103,9 @@ function __load_mod() { function load_mod() { local mod="$1"; shift + assert_mod "$mod" || + skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" + is_livepatch_mod "$mod" && die "use load_lp() to load the livepatch module $mod" @@ -88,6 +119,9 @@ function load_mod() { function load_lp_nowait() { local mod="$1"; shift + assert_mod "$mod" || + skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" + is_livepatch_mod "$mod" || die "module $mod is not a livepatch" diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 4ce0bc1612f5..c7cced739c34 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -17,7 +17,7 @@ tcp_inq tls txring_overwrite ip_defrag +ipv6_flowlabel +ipv6_flowlabel_mgr so_txtime -flowlabel -flowlabel_mgr tcp_fastopen_backup_key diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1b24e36b4047..0bd6b23c97ef 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -10,9 +10,9 @@ TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh -TEST_PROGS += tcp_fastopen_backup_key.sh +TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh TEST_PROGS_EXTENDED := in_netns.sh -TEST_GEN_FILES = socket +TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh new file mode 100755 index 000000000000..9fd3a0b97f0d --- /dev/null +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -0,0 +1,3432 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2019 David Ahern <[email protected]>. All rights reserved. +# +# IPv4 and IPv6 functional tests focusing on VRF and routing lookups +# for various permutations: +# 1. icmp, tcp, udp and netfilter +# 2. client, server, no-server +# 3. global address on interface +# 4. global address on 'lo' +# 5. remote and local traffic +# 6. VRF and non-VRF permutations +# +# Setup: +# ns-A | ns-B +# No VRF case: +# [ lo ] [ eth1 ]---|---[ eth1 ] [ lo ] +# remote address +# VRF case: +# [ red ]---[ eth1 ]---|---[ eth1 ] [ lo ] +# +# ns-A: +# eth1: 172.16.1.1/24, 2001:db8:1::1/64 +# lo: 127.0.0.1/8, ::1/128 +# 172.16.2.1/32, 2001:db8:2::1/128 +# red: 127.0.0.1/8, ::1/128 +# 172.16.3.1/32, 2001:db8:3::1/128 +# +# ns-B: +# eth1: 172.16.1.2/24, 2001:db8:1::2/64 +# lo2: 127.0.0.1/8, ::1/128 +# 172.16.2.2/32, 2001:db8:2::2/128 +# +# server / client nomenclature relative to ns-A + +VERBOSE=0 + +NSA_DEV=eth1 +NSB_DEV=eth1 +VRF=red +VRF_TABLE=1101 + +# IPv4 config +NSA_IP=172.16.1.1 +NSB_IP=172.16.1.2 +VRF_IP=172.16.3.1 + +# IPv6 config +NSA_IP6=2001:db8:1::1 +NSB_IP6=2001:db8:1::2 +VRF_IP6=2001:db8:3::1 + +NSA_LO_IP=172.16.2.1 +NSB_LO_IP=172.16.2.2 +NSA_LO_IP6=2001:db8:2::1 +NSB_LO_IP6=2001:db8:2::2 + +MCAST=ff02::1 +# set after namespace create +NSA_LINKIP6= +NSB_LINKIP6= + +NSA=ns-A +NSB=ns-B + +NSA_CMD="ip netns exec ${NSA}" +NSB_CMD="ip netns exec ${NSB}" + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# utilities + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + [ "${VERBOSE}" = "1" ] && echo + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "TEST: %-70s [ OK ]\n" "${msg}" + else + nfail=$((nfail+1)) + printf "TEST: %-70s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + + kill_procs +} + +log_test_addr() +{ + local addr=$1 + local rc=$2 + local expected=$3 + local msg="$4" + local astr + + astr=$(addr2str ${addr}) + log_test $rc $expected "$msg - ${astr}" +} + +log_section() +{ + echo + echo "###########################################################################" + echo "$*" + echo "###########################################################################" + echo +} + +log_subsection() +{ + echo + echo "#################################################################" + echo "$*" + echo +} + +log_start() +{ + # make sure we have no test instances running + kill_procs + + if [ "${VERBOSE}" = "1" ]; then + echo + echo "#######################################################" + fi +} + +log_debug() +{ + if [ "${VERBOSE}" = "1" ]; then + echo + echo "$*" + echo + fi +} + +show_hint() +{ + if [ "${VERBOSE}" = "1" ]; then + echo "HINT: $*" + echo + fi +} + +kill_procs() +{ + killall nettest ping ping6 >/dev/null 2>&1 + sleep 1 +} + +do_run_cmd() +{ + local cmd="$*" + local out + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: ${cmd}" + fi + + out=$($cmd 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo "$out" + fi + + return $rc +} + +run_cmd() +{ + do_run_cmd ${NSA_CMD} $* +} + +run_cmd_nsb() +{ + do_run_cmd ${NSB_CMD} $* +} + +setup_cmd() +{ + local cmd="$*" + local rc + + run_cmd ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +setup_cmd_nsb() +{ + local cmd="$*" + local rc + + run_cmd_nsb ${cmd} + rc=$? + if [ $rc -ne 0 ]; then + # show user the command if not done so already + if [ "$VERBOSE" = "0" ]; then + echo "setup command: $cmd" + fi + echo "failed. stopping tests" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue" + read a + fi + exit $rc + fi +} + +# set sysctl values in NS-A +set_sysctl() +{ + echo "SYSCTL: $*" + echo + run_cmd sysctl -q -w $* +} + +################################################################################ +# Setup for tests + +addr2str() +{ + case "$1" in + 127.0.0.1) echo "loopback";; + ::1) echo "IPv6 loopback";; + + ${NSA_IP}) echo "ns-A IP";; + ${NSA_IP6}) echo "ns-A IPv6";; + ${NSA_LO_IP}) echo "ns-A loopback IP";; + ${NSA_LO_IP6}) echo "ns-A loopback IPv6";; + ${NSA_LINKIP6}|${NSA_LINKIP6}%*) echo "ns-A IPv6 LLA";; + + ${NSB_IP}) echo "ns-B IP";; + ${NSB_IP6}) echo "ns-B IPv6";; + ${NSB_LO_IP}) echo "ns-B loopback IP";; + ${NSB_LO_IP6}) echo "ns-B loopback IPv6";; + ${NSB_LINKIP6}|${NSB_LINKIP6}%*) echo "ns-B IPv6 LLA";; + + ${VRF_IP}) echo "VRF IP";; + ${VRF_IP6}) echo "VRF IPv6";; + + ${MCAST}%*) echo "multicast IP";; + + *) echo "unknown";; + esac +} + +get_linklocal() +{ + local ns=$1 + local dev=$2 + local addr + + addr=$(ip -netns ${ns} -6 -br addr show dev ${dev} | \ + awk '{ + for (i = 3; i <= NF; ++i) { + if ($i ~ /^fe80/) + print $i + } + }' + ) + addr=${addr/\/*} + + [ -z "$addr" ] && return 1 + + echo $addr + + return 0 +} + +################################################################################ +# create namespaces and vrf + +create_vrf() +{ + local ns=$1 + local vrf=$2 + local table=$3 + local addr=$4 + local addr6=$5 + + ip -netns ${ns} link add ${vrf} type vrf table ${table} + ip -netns ${ns} link set ${vrf} up + ip -netns ${ns} route add vrf ${vrf} unreachable default metric 8192 + ip -netns ${ns} -6 route add vrf ${vrf} unreachable default metric 8192 + + ip -netns ${ns} addr add 127.0.0.1/8 dev ${vrf} + ip -netns ${ns} -6 addr add ::1 dev ${vrf} nodad + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev ${vrf} ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev ${vrf} ${addr6} + fi + + ip -netns ${ns} ru del pref 0 + ip -netns ${ns} ru add pref 32765 from all lookup local + ip -netns ${ns} -6 ru del pref 0 + ip -netns ${ns} -6 ru add pref 32765 from all lookup local +} + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +cleanup() +{ + # explicit cleanups to check those code paths + ip netns | grep -q ${NSA} + if [ $? -eq 0 ]; then + ip -netns ${NSA} link delete ${VRF} + ip -netns ${NSA} ro flush table ${VRF_TABLE} + + ip -netns ${NSA} addr flush dev ${NSA_DEV} + ip -netns ${NSA} -6 addr flush dev ${NSA_DEV} + ip -netns ${NSA} link set dev ${NSA_DEV} down + ip -netns ${NSA} link del dev ${NSA_DEV} + + ip netns del ${NSA} + fi + + ip netns del ${NSB} +} + +setup() +{ + local with_vrf=${1} + + # make sure we are starting with a clean slate + kill_procs + cleanup 2>/dev/null + + log_debug "Configuring network namespaces" + set -e + + create_ns ${NSA} ${NSA_LO_IP}/32 ${NSA_LO_IP6}/128 + create_ns ${NSB} ${NSB_LO_IP}/32 ${NSB_LO_IP6}/128 + connect_ns ${NSA} ${NSA_DEV} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSB} ${NSB_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 + + NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV}) + NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV}) + + # tell ns-A how to get to remote addresses of ns-B + if [ "${with_vrf}" = "yes" ]; then + create_vrf ${NSA} ${VRF} ${VRF_TABLE} ${VRF_IP} ${VRF_IP6} + + ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF} + ip -netns ${NSA} ro add vrf ${VRF} ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} -6 ro add vrf ${VRF} ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + + ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + else + ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} + ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} + fi + + + # tell ns-B how to get to remote addresses of ns-A + ip -netns ${NSB} ro add ${NSA_LO_IP}/32 via ${NSA_IP} dev ${NSB_DEV} + ip -netns ${NSB} ro add ${NSA_LO_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + set +e + + sleep 1 +} + +################################################################################ +# IPv4 + +ipv4_ping_novrf() +{ + local a + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_LO_IP} ${a} + log_test_addr ${a} $? 0 "ping out, address bind" + done + + # + # in + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # loopback addresses not reachable from device bind + # fails in a really weird way though because ipv4 special cases + # route lookups with oif set. + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on loopback device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks reachability to remote address + # + log_start + setup_cmd ip rule add pref 32765 from all lookup local + setup_cmd ip rule del pref 0 from all lookup local + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite the rule + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response generates ICMP (or arp request is ignored) due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 32765 from all lookup local + setup_cmd ip rule add pref 0 from all lookup local + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip route replace unreachable ${NSB_LO_IP} + setup_cmd ip route replace unreachable ${NSB_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + + a=${NSA_LO_IP} + log_start + show_hint "Response is dropped (or arp request is ignored) due to ip route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable default route" + + # NOTE: ipv4 actually allows the lookup to fail and yet still create + # a viable rtable if the oif (e.g., bind to device) is set, so this + # case succeeds despite not having a route for the address + # run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} +} + +ipv4_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${NSA_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + dev address bind" + + log_start + run_cmd ip vrf exec ${VRF} ping -c1 -w1 -I ${VRF_IP} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device + vrf address bind" + done + + # + # in + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + # + # local traffic, socket bound to device + # + # address on device + a=${NSA_IP} + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + + # vrf device is out of scope + for a in ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Fails since address on vrf device is out of device scope" + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 1 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip rule add pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule add pref 51 from ${NSB_IP} prohibit + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, blocked by rule" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + [ "$VERBOSE" = "1" ] && echo + setup_cmd ip rule del pref 50 to ${NSB_LO_IP} prohibit + setup_cmd ip rule del pref 51 from ${NSB_IP} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip ro del vrf ${VRF} ${NSB_LO_IP} + + a=${NSB_LO_IP} + run_cmd ping -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 2 "ping out, vrf bind, unreachable route" + + log_start + run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + a=${NSA_LO_IP} + log_start + show_hint "Response lost by unreachable route" + run_cmd_nsb ping -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, unreachable route" +} + +ipv4_ping() +{ + log_section "IPv4 ping" + + log_subsection "No VRF" + setup + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + ipv4_ping_novrf + setup + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + ipv4_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_ping_vrf +} + +################################################################################ +# IPv4 TCP + +ipv4_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset sent and received + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -0 ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" +} + +ipv4_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + # (${VRF_IP} and 127.0.0.1 both timeout) + a=${NSA_IP} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "client socket should be bound to VRF" + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + # verify TCP reset received + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + show_hint "client socket should be bound to device" + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # local address tests + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Should fail 'No route to host' since client is not bound to VRF" + run_cmd nettest -s -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + + log_start + run_cmd_nsb nettest -s & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since client is out of VRF scope" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd nettest -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" +} + +ipv4_tcp() +{ + log_section "IPv4/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv4_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv4_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_tcp_vrf +} + +################################################################################ +# IPv4 UDP + +ipv4_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + + # + # client + # + for a in ${NSB_IP} ${NSB_LO_IP} + do + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP} + log_test_addr ${a} $? 0 "Client, device bind via IP_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP} ${NSA_LO_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -s -D & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IP_UNICAST_IF, local connection" + + # IPv4 with device bind has really weird behavior - it overrides the + # fib lookup, generates an rtable and tries to send the packet. This + # causes failures for local traffic at different places + for a in ${NSA_LO_IP} 127.0.0.1 + do + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 2 "Global server, device client, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail since addresses on loopback are out of device scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 2 "No server, device client, local conn" +} + +ipv4_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + show_hint "Fails because ingress is in a VRF and global server is disabled" + run_cmd nettest -D -s & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + + log_start + show_hint "Should fail 'Connection refused' since global server is out of scope" + run_cmd nettest -D -s & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local connection" + done + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, enslaved device client, local connection" + + a=${NSA_IP} + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # enable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + log_start + run_cmd nettest -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${VRF} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "VRF client" + + log_start + run_cmd_nsb nettest -D -s & + sleep 1 + run_cmd nettest -d ${NSA_DEV} -D -r ${NSB_IP} -1 ${NSA_IP} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${NSB_IP} + log_test $? 1 "No server, VRF client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${NSA_DEV} -r ${NSB_IP} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP} + log_start + run_cmd nettest -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + done + + for a in ${VRF_IP} 127.0.0.1 + do + log_start + run_cmd nettest -s -D -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + # negative test - should fail + # verifies ECONNREFUSED + for a in ${NSA_IP} ${VRF_IP} 127.0.0.1 + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done +} + +ipv4_udp() +{ + log_section "IPv4/UDP" + log_subsection "No VRF" + + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv4_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv4_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_udp_vrf +} + +################################################################################ +# IPv4 address bind +# +# verifies ability or inability to bind to an address / device + +ipv4_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${NSA_LO_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP} + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -l ${a} -r ${NSB_IP} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not + #a=${NSA_LO_IP} + #log_start + #show_hint "Should fail with 'Cannot assign requested address'" + #run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + #log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv4_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -R -P icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + log_start + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after VRF bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -s -R -P icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind" + + # + # tcp sockets + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + done + + a=${NSA_LO_IP} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" +} + +ipv4_addr_bind() +{ + log_section "IPv4 address binds" + + log_subsection "No VRF" + setup + ipv4_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv4_addr_bind_vrf +} + +################################################################################ +# IPv4 runtime tests + +ipv4_rt() +{ + local desc="$1" + local varg="$2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s -d ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + # + # local address tests + # + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client, local" + + setup ${with_vrf} + done + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client, local" + + setup ${with_vrf} + done + + a=${NSA_IP} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, enslaved device client, local" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server and client, local" +} + +ipv4_ping_rt() +{ + local with_vrf="yes" + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd_nsb ping -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + done + + a=${NSB_IP} + log_start + run_cmd ping -f -I ${VRF} ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv4_runtime() +{ + log_section "Run time tests - ipv4" + + setup "yes" + ipv4_ping_rt + + setup "yes" + ipv4_rt "TCP active socket" "-n -1" + + setup "yes" + ipv4_rt "TCP passive socket" "-i" +} + +################################################################################ +# IPv6 + +ipv6_ping_novrf() +{ + local a + + # should not have an impact, but make a known state + set_sysctl net.ipv4.raw_l3mdev_accept=0 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping out" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_LO_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, loopback address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping local, no bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Fails since address on loopback is out of device scope" + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping local, device bind" + done + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 0 from all lookup local + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + setup_cmd ip -6 rule add pref 0 from all lookup local + setup_cmd ip -6 rule del pref 32765 from all lookup local + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # route blocks reachability to remote address + # + log_start + setup_cmd ip -6 route del ${NSB_LO_IP6} + setup_cmd ip -6 route add unreachable ${NSB_LO_IP6} metric 10 + setup_cmd ip -6 route add unreachable ${NSB_IP6} metric 10 + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by route" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip route" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by route" + + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del unreachable ${NSB_LO_IP6} + setup_cmd ip -6 ro del unreachable ${NSB_IP6} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" +} + +ipv6_ping_vrf() +{ + local a + + # should default on; does not exist on older kernels + set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null + + # + # out + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping out, VRF bind" + done + + for a in ${NSB_LINKIP6}%${VRF} ${MCAST}%${VRF} + do + log_start + show_hint "Fails since VRF device does not support linklocal or multicast" + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, VRF bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping out, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd ip vrf exec ${VRF} ${ping6} -c1 -w1 -I ${VRF_IP6} ${a} + log_test_addr ${a} $? 0 "ping out, vrf device+address bind" + done + + # + # in + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} ${MCAST}%${NSB_DEV} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 0 "ping in" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Fails since loopback address is out of VRF scope" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in" + + # + # local traffic, local address + # + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + show_hint "Source address should be ${a}" + run_cmd ${ping6} -c1 -w1 -I ${VRF} ${a} + log_test_addr ${a} $? 0 "ping local, VRF bind" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} + do + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 0 "ping local, device bind" + done + + # LLA to GUA - remove ipv6 global addresses from ns-B + setup_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr del ${NSB_LO_IP6}/128 dev lo + setup_cmd_nsb ip -6 ro add ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test_addr ${a} $? 0 "ping in, LLA to GUA" + done + + setup_cmd_nsb ip -6 ro del ${NSA_IP6}/128 via ${NSA_LINKIP6} dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} + setup_cmd_nsb ip -6 addr add ${NSB_LO_IP6}/128 dev lo + + # + # ip rule blocks address + # + log_start + setup_cmd ip -6 rule add pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule add pref 51 from ${NSB_IP6} prohibit + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, blocked by rule" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, blocked by rule" + + a=${NSA_LO_IP6} + log_start + show_hint "Response lost due to ip rule" + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 1 "ping in, blocked by rule" + + log_start + setup_cmd ip -6 rule del pref 50 to ${NSB_LO_IP6} prohibit + setup_cmd ip -6 rule del pref 51 from ${NSB_IP6} prohibit + + # + # remove 'remote' routes; fallback to default + # + log_start + setup_cmd ip -6 ro del ${NSB_LO_IP6} vrf ${VRF} + + a=${NSB_LO_IP6} + run_cmd ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping out, unreachable route" + + log_start + run_cmd ${ping6} -c1 -w1 -I ${NSA_DEV} ${a} + log_test_addr ${a} $? 2 "ping out, device bind, unreachable route" + + ip -netns ${NSB} -6 ro del ${NSA_LO_IP6} + a=${NSA_LO_IP6} + log_start + run_cmd_nsb ${ping6} -c1 -w1 ${a} + log_test_addr ${a} $? 2 "ping in, unreachable route" +} + +ipv6_ping() +{ + log_section "IPv6 ping" + + log_subsection "No VRF" + setup + ipv6_ping_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_ping_vrf +} + +################################################################################ +# IPv6 TCP + +ipv6_tcp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Device server, unbound client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since addresses on loopback are out of device scope" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + done + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + done +} + +ipv6_tcp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # link local is always bound to ingress device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server with VRF is disabled" + run_cmd nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, local connection" + + # + # enable VRF global server + # + log_subsection "VRF Global server enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + # For LLA, child socket is bound to device + a=${NSA_LINKIP6}%${NSB_DEV} + log_start + run_cmd nettest -6 -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "VRF server" + + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + # verify TCP reset received + for a in ${NSA_IP6} ${VRF_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # local address tests + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Fails 'No route to host' since client is not in VRF" + run_cmd nettest -6 -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, local connection" + done + + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 0 "Client, VRF bind" + done + + a=${NSB_LINKIP6} + log_start + show_hint "Fails since VRF device does not allow linklocal addresses" + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "Client, VRF bind" + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + run_cmd_nsb nettest -6 -s & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 0 "Client, device bind" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${VRF} + log_test_addr ${a} $? 1 "No server, VRF client" + done + + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6} + do + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + for a in ${NSA_IP6} ${VRF_IP6} ::1 + do + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -d ${VRF} -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local connection" + + a=${NSA_IP6} + log_start + show_hint "Should fail since unbound client is out of VRF scope" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd nettest -6 -r ${a} + log_test_addr ${a} $? 1 "VRF server, unbound client, local connection" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${VRF} -0 ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local connection" + + for a in ${NSA_IP6} ${NSA_LINKIP6} + do + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -r ${a} -d ${NSA_DEV} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local connection" + done +} + +ipv6_tcp() +{ + log_section "IPv6/TCP" + log_subsection "No VRF" + setup + + # tcp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "tcp_l3mdev_accept disabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=0 + ipv6_tcp_novrf + log_subsection "tcp_l3mdev_accept enabled" + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + ipv6_tcp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_tcp_vrf +} + +################################################################################ +# IPv6 UDP + +ipv6_udp_novrf() +{ + local a + + # + # server tests + # + for a in ${NSA_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server" + done + + a=${NSA_LO_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + + # should fail since loopback address is out of scope for a device + # bound server, but it does not - hence this is more documenting + # behavior. + #log_start + #show_hint "Should fail since loopback address is out of scope" + #run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + #sleep 1 + #run_cmd_nsb nettest -6 -D -r ${a} + #log_test_addr ${a} $? 1 "Device server" + + # negative test - should fail + for a in ${NSA_IP6} ${NSA_LO_IP6} ${NSA_LINKIP6}%${NSB_DEV} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client + # + for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} + do + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device send via cmsg" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S -0 ${NSA_IP6} + log_test_addr ${a} $? 0 "Client, device bind via IPV6_UNICAST_IF" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server, unbound client" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "No server, device client" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${NSA_LO_IP6} ::1 + do + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -0 ${a} -1 ${a} + log_test_addr ${a} $? 0 "Global server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Device server, unbound client, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'Connection refused' since address is out of device scope" + run_cmd nettest -6 -s -D -d ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Device server, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -C -r ${a} + log_test_addr ${a} $? 0 "Global server, device send via cmsg, local connection" + + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -S -r ${a} + log_test_addr ${a} $? 0 "Global server, device client via IPV6_UNICAST_IF, local connection" + + for a in ${NSA_LO_IP6} ::1 + do + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} + log_test_addr ${a} $? 1 "Global server, device client, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -C + log_test_addr ${a} $? 1 "Global server, device send via cmsg, local connection" + + log_start + show_hint "Should fail 'No route to host' since addresses on loopback are out of device scope" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -r ${a} -d ${NSA_DEV} -S + log_test_addr ${a} $? 1 "Global server, device client via IP_UNICAST_IF, local connection" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -d ${NSA_DEV} -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} -0 ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + show_hint "Should fail 'Connection refused'" + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp_vrf() +{ + local a + + # disable global server + log_subsection "Global server disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since there is no server" + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "Global server, VRF client, local conn" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + done + + a=${NSA_IP6} + log_start + show_hint "Should fail 'Connection refused' since global server is disabled" + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server, device client, local conn" + + # disable global server + log_subsection "Global server enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Global server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "VRF server" + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 0 "Enslaved device server" + done + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd_nsb nettest -6 -D -r ${a} + log_test_addr ${a} $? 1 "No server" + done + + # + # client tests + # + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 0 "VRF client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${NSB_IP6} + log_test $? 1 "No server, VRF client" + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 0 "Enslaved device client" + + # negative test - should fail + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_IP6} + log_test $? 1 "No server, enslaved device client" + + # + # local address tests + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + #log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Global server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${VRF} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "VRF server, VRF client, local conn" + + # negative test - should fail + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 1 "No server, VRF client, local conn" + done + + # device to global IP + a=${NSA_IP6} + log_start + run_cmd nettest -6 -D -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Global server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${VRF} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "VRF server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${VRF} -r ${a} + log_test_addr ${a} $? 0 "Device server, VRF client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -s -2 ${NSA_DEV} & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 0 "Device server, device client, local conn" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${a} + log_test_addr ${a} $? 1 "No server, device client, local conn" + + + # link local addresses + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Global server, linklocal IP" + + log_start + run_cmd_nsb nettest -6 -D -d ${NSB_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, linklocal IP" + + + log_start + run_cmd_nsb nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 0 "Enslaved device client, linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSB_LINKIP6} + log_test $? 1 "No server, device client, peer linklocal IP" + + + log_start + run_cmd nettest -6 -D -s & + sleep 1 + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 0 "Enslaved device client, local conn - linklocal IP" + + log_start + run_cmd nettest -6 -D -d ${NSA_DEV} -r ${NSA_LINKIP6} + log_test $? 1 "No server, device client, local conn - linklocal IP" + + # LLA to GUA + run_cmd_nsb ip -6 addr del ${NSB_IP6}/64 dev ${NSB_DEV} + run_cmd_nsb ip -6 ro add ${NSA_IP6}/128 dev ${NSB_DEV} + log_start + run_cmd nettest -6 -s -D & + sleep 1 + run_cmd_nsb nettest -6 -D -r ${NSA_IP6} + log_test $? 0 "UDP in - LLA to GUA" + + run_cmd_nsb ip -6 ro del ${NSA_IP6}/128 dev ${NSB_DEV} + run_cmd_nsb ip -6 addr add ${NSB_IP6}/64 dev ${NSB_DEV} nodad +} + +ipv6_udp() +{ + # should not matter, but set to known state + set_sysctl net.ipv4.udp_early_demux=1 + + log_section "IPv6/UDP" + log_subsection "No VRF" + setup + + # udp_l3mdev_accept should have no affect without VRF; + # run tests with it enabled and disabled to verify + log_subsection "udp_l3mdev_accept disabled" + set_sysctl net.ipv4.udp_l3mdev_accept=0 + ipv6_udp_novrf + log_subsection "udp_l3mdev_accept enabled" + set_sysctl net.ipv4.udp_l3mdev_accept=1 + ipv6_udp_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_udp_vrf +} + +################################################################################ +# IPv6 address bind + +ipv6_addr_bind_novrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${NSA_LO_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + # + # tcp sockets + # + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address" + + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Should fail with 'Cannot assign requested address'" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" +} + +ipv6_addr_bind_vrf() +{ + # + # raw socket + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after vrf bind" + + log_start + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to local address after device bind" + done + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback is out of VRF scope" + run_cmd nettest -6 -s -R -P ipv6-icmp -l ${a} -d ${VRF} -b + log_test_addr ${a} $? 1 "Raw socket bind to invalid local address after vrf bind" + + # + # tcp sockets + # + # address on enslaved device is valid for the VRF or device in a VRF + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with VRF bind" + done + + a=${NSA_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + + a=${VRF_IP6} + log_start + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + + a=${NSA_LO_IP6} + log_start + show_hint "Address on loopback out of scope for VRF" + run_cmd nettest -6 -s -l ${a} -d ${VRF} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for VRF" + + log_start + show_hint "Address on loopback out of scope for device in VRF" + run_cmd nettest -6 -s -l ${a} -d ${NSA_DEV} -t1 -b + log_test_addr ${a} $? 1 "TCP socket bind to invalid local address for device bind" + +} + +ipv6_addr_bind() +{ + log_section "IPv6 address binds" + + log_subsection "No VRF" + setup + ipv6_addr_bind_novrf + + log_subsection "With VRF" + setup "yes" + ipv6_addr_bind_vrf +} + +################################################################################ +# IPv6 runtime tests + +ipv6_rt() +{ + local desc="$1" + local varg="-6 $2" + local with_vrf="yes" + local a + + # + # server tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd_nsb nettest ${varg} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, enslaved device server" + + setup ${with_vrf} + done + + # + # client test + # + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, VRF client" + + setup ${with_vrf} + + log_start + run_cmd_nsb nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${NSB_IP6} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test 0 0 "${desc}, enslaved device client" + + setup ${with_vrf} + + + # + # local address tests + # + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, VRF client" + + setup ${with_vrf} + done + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${VRF} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server and client" + + setup ${with_vrf} + done + + a=${NSA_IP6} + log_start + run_cmd nettest ${varg} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, global server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${VRF} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, VRF server, device client" + + setup ${with_vrf} + + log_start + run_cmd nettest ${varg} -d ${NSA_DEV} -s & + sleep 1 + run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "${desc}, device server, device client" +} + +ipv6_ping_rt() +{ + local with_vrf="yes" + local a + + a=${NSA_IP6} + log_start + run_cmd_nsb ${ping6} -f ${a} & + sleep 3 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping in" + + setup ${with_vrf} + + log_start + run_cmd ${ping6} -f ${NSB_IP6} -I ${VRF} & + sleep 1 + run_cmd ip link del ${VRF} + sleep 1 + log_test_addr ${a} 0 0 "Device delete with active traffic - ping out" +} + +ipv6_runtime() +{ + log_section "Run time tests - ipv6" + + setup "yes" + ipv6_ping_rt + + setup "yes" + ipv6_rt "TCP active socket" "-n -1" + + setup "yes" + ipv6_rt "TCP passive socket" "-i" + + setup "yes" + ipv6_rt "UDP active socket" "-D -n -1" +} + +################################################################################ +# netfilter blocking connections + +netfilter_tcp_reset() +{ + local a + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="-D" + + for a in ${NSA_IP} ${VRF_IP} + do + log_start + run_cmd nettest ${arg} -s & + sleep 1 + run_cmd_nsb nettest ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv4_netfilter() +{ + log_section "IPv4 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp_reset + + log_start + log_subsection "ICMP unreachable" + + log_start + run_cmd iptables -F + run_cmd iptables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + run_cmd iptables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp-port-unreachable + + netfilter_icmp "TCP" + netfilter_icmp "UDP" + + log_start + iptables -F +} + +netfilter_tcp6_reset() +{ + local a + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${a} + log_test_addr ${a} $? 1 "Global server, reject with TCP-reset on Rx" + done +} + +netfilter_icmp6() +{ + local stype="$1" + local arg + local a + + [ "${stype}" = "UDP" ] && arg="$arg -D" + + for a in ${NSA_IP6} ${VRF_IP6} + do + log_start + run_cmd nettest -6 -s ${arg} & + sleep 1 + run_cmd_nsb nettest -6 ${arg} -r ${a} + log_test_addr ${a} $? 1 "Global ${stype} server, Rx reject icmp-port-unreach" + done +} + +ipv6_netfilter() +{ + log_section "IPv6 Netfilter" + log_subsection "TCP reset" + + setup "yes" + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset + + netfilter_tcp6_reset + + log_subsection "ICMP unreachable" + + log_start + run_cmd ip6tables -F + run_cmd ip6tables -A INPUT -p tcp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + run_cmd ip6tables -A INPUT -p udp --dport 12345 -j REJECT --reject-with icmp6-port-unreachable + + netfilter_icmp6 "TCP" + netfilter_icmp6 "UDP" + + log_start + ip6tables -F +} + +################################################################################ +# specific use cases + +# VRF only. +# ns-A device enslaved to bridge. Verify traffic with and without +# br_netfilter module loaded. Repeat with SVI on bridge. +use_case_br() +{ + setup "yes" + + setup_cmd ip link set ${NSA_DEV} down + setup_cmd ip addr del dev ${NSA_DEV} ${NSA_IP}/24 + setup_cmd ip -6 addr del dev ${NSA_DEV} ${NSA_IP6}/64 + + setup_cmd ip link add br0 type bridge + setup_cmd ip addr add dev br0 ${NSA_IP}/24 + setup_cmd ip -6 addr add dev br0 ${NSA_IP6}/64 nodad + + setup_cmd ip li set ${NSA_DEV} master br0 + setup_cmd ip li set ${NSA_DEV} up + setup_cmd ip li set br0 up + setup_cmd ip li set br0 vrf ${VRF} + + rmmod br_netfilter 2>/dev/null + sleep 5 # DAD + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0 ${NSB_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0 ${NSB_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 ${NSA_IP} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 ${NSA_IP6} + log_test $? 0 "Bridge into VRF with br_netfilter - IPv6 ping in" + fi + + setup_cmd ip li set br0 nomaster + setup_cmd ip li add br0.100 link br0 type vlan id 100 + setup_cmd ip li set br0.100 vrf ${VRF} up + setup_cmd ip addr add dev br0.100 172.16.101.1/24 + setup_cmd ip -6 addr add dev br0.100 2001:db8:101::1/64 nodad + + setup_cmd_nsb ip li add vlan100 link ${NSB_DEV} type vlan id 100 + setup_cmd_nsb ip addr add dev vlan100 172.16.101.2/24 + setup_cmd_nsb ip -6 addr add dev vlan100 2001:db8:101::2/64 nodad + setup_cmd_nsb ip li set vlan100 up + sleep 1 + + rmmod br_netfilter 2>/dev/null + + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + + modprobe br_netfilter + if [ $? -eq 0 ]; then + run_cmd ip neigh flush all + run_cmd ping -c1 -w1 -I br0.100 172.16.101.2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv4 ping out" + + run_cmd ip neigh flush all + run_cmd ${ping6} -c1 -w1 -I br0.100 2001:db8:101::2 + log_test $? 0 "Bridge vlan into VRF with br_netfilter - IPv6 ping out" + + run_cmd ip neigh flush all + run_cmd_nsb ping -c1 -w1 172.16.101.1 + log_test $? 0 "Bridge vlan into VRF - IPv4 ping in" + + run_cmd ip neigh flush all + run_cmd_nsb ${ping6} -c1 -w1 2001:db8:101::1 + log_test $? 0 "Bridge vlan into VRF - IPv6 ping in" + fi + + setup_cmd ip li del br0 2>/dev/null + setup_cmd_nsb ip li del vlan100 2>/dev/null +} + +use_cases() +{ + log_section "Use cases" + use_case_br +} + +################################################################################ +# usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -4 IPv4 tests only + -6 IPv6 tests only + -t <test> Test name/set to run + -p Pause on fail + -P Pause after each test + -v Be verbose +EOF +} + +################################################################################ +# main + +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_OTHER="use_cases" + +PAUSE_ON_FAIL=no +PAUSE=no + +while getopts :46t:pPvh o +do + case $o in + 4) TESTS=ipv4;; + 6) TESTS=ipv6;; + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=1;; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +# +# show user test config +# +if [ -z "$TESTS" ]; then + TESTS="$TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER" +elif [ "$TESTS" = "ipv4" ]; then + TESTS="$TESTS_IPV4" +elif [ "$TESTS" = "ipv6" ]; then + TESTS="$TESTS_IPV6" +fi + +which nettest >/dev/null +if [ $? -ne 0 ]; then + echo "'nettest' command not found; skipping tests" + exit 0 +fi + +declare -i nfail=0 +declare -i nsuccess=0 + +for t in $TESTS +do + case $t in + ipv4_ping|ping) ipv4_ping;; + ipv4_tcp|tcp) ipv4_tcp;; + ipv4_udp|udp) ipv4_udp;; + ipv4_bind|bind) ipv4_addr_bind;; + ipv4_runtime) ipv4_runtime;; + ipv4_netfilter) ipv4_netfilter;; + + ipv6_ping|ping6) ipv6_ping;; + ipv6_tcp|tcp6) ipv6_tcp;; + ipv6_udp|udp6) ipv6_udp;; + ipv6_bind|bind6) ipv6_addr_bind;; + ipv6_runtime) ipv6_runtime;; + ipv6_netfilter) ipv6_netfilter;; + + use_cases) use_cases;; + + # setup namespaces and config, but do not run any tests + setup) setup; exit 0;; + vrf_setup) setup "yes"; exit 0;; + + help) echo "Test names: $TESTS"; exit 0;; + esac +done + +cleanup 2>/dev/null + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index cca2baa03fb8..a8d8e8b3dc81 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -93,18 +93,10 @@ sw1_create() ip route add vrf v$ol1 192.0.2.16/28 \ nexthop dev g1a \ nexthop dev g1b - - tc qdisc add dev $ul1 clsact - tc filter add dev $ul1 egress pref 111 prot ipv4 \ - flower dst_ip 192.0.2.66 action pass - tc filter add dev $ul1 egress pref 222 prot ipv4 \ - flower dst_ip 192.0.2.82 action pass } sw1_destroy() { - tc qdisc del dev $ul1 clsact - ip route del vrf v$ol1 192.0.2.16/28 ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 @@ -139,10 +131,18 @@ sw2_create() ip route add vrf v$ol2 192.0.2.0/28 \ nexthop dev g2a \ nexthop dev g2b + + tc qdisc add dev $ul2 clsact + tc filter add dev $ul2 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul2 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass } sw2_destroy() { + tc qdisc del dev $ul2 clsact + ip route del vrf v$ol2 192.0.2.0/28 ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 @@ -187,12 +187,16 @@ setup_prepare() sw1_create sw2_create h2_create + + forwarding_enable } cleanup() { pre_cleanup + forwarding_restore + h2_destroy sw2_destroy sw1_destroy @@ -211,15 +215,15 @@ multipath4_test() nexthop dev g1a weight $weight1 \ nexthop dev g1b weight $weight2 - local t0_111=$(tc_rule_stats_get $ul1 111 egress) - local t0_222=$(tc_rule_stats_get $ul1 222 egress) + local t0_111=$(tc_rule_stats_get $ul2 111 ingress) + local t0_222=$(tc_rule_stats_get $ul2 222 ingress) ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ -d 1msec -t udp "sp=1024,dp=0-32768" - local t1_111=$(tc_rule_stats_get $ul1 111 egress) - local t1_222=$(tc_rule_stats_get $ul1 222 egress) + local t1_111=$(tc_rule_stats_get $ul2 111 ingress) + local t1_222=$(tc_rule_stats_get $ul2 222 ingress) local d111=$((t1_111 - t0_111)) local d222=$((t1_222 - t0_222)) diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh new file mode 100644 index 000000000000..5782433886fc --- /dev/null +++ b/tools/testing/selftests/net/l2tp.sh @@ -0,0 +1,382 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# L2TPv3 tunnel between 2 hosts +# +# host-1 | router | host-2 +# | | +# lo l2tp | | l2tp lo +# 172.16.101.1 172.16.1.1 | | 172.16.1.2 172.16.101.2 +# fc00:101::1 fc00:1::1 | | fc00:1::2 fc00:101::2 +# | | +# eth0 | | eth0 +# 10.1.1.1 | | 10.1.2.1 +# 2001:db8:1::1 | | 2001:db8:2::1 + +VERBOSE=0 +PAUSE_ON_FAIL=no + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +################################################################################ +# +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf "TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf "TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +run_cmd() +{ + local ns + local cmd + local out + local rc + + ns="$1" + shift + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: $cmd\n" + fi + + out=$(eval ip netns exec ${ns} ${cmd} 2>&1) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + [ "$VERBOSE" = "1" ] && echo + + return $rc +} + +################################################################################ +# create namespaces and interconnects + +create_ns() +{ + local ns=$1 + local addr=$2 + local addr6=$3 + + [ -z "${addr}" ] && addr="-" + [ -z "${addr6}" ] && addr6="-" + + ip netns add ${ns} + + ip -netns ${ns} link set lo up + if [ "${addr}" != "-" ]; then + ip -netns ${ns} addr add dev lo ${addr} + fi + if [ "${addr6}" != "-" ]; then + ip -netns ${ns} -6 addr add dev lo ${addr6} + fi + + ip -netns ${ns} ro add unreachable default metric 8192 + ip -netns ${ns} -6 ro add unreachable default metric 8192 + + ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 + ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.accept_dad=0 +} + +# create veth pair to connect namespaces and apply addresses. +connect_ns() +{ + local ns1=$1 + local ns1_dev=$2 + local ns1_addr=$3 + local ns1_addr6=$4 + local ns2=$5 + local ns2_dev=$6 + local ns2_addr=$7 + local ns2_addr6=$8 + + ip -netns ${ns1} li add ${ns1_dev} type veth peer name tmp + ip -netns ${ns1} li set ${ns1_dev} up + ip -netns ${ns1} li set tmp netns ${ns2} name ${ns2_dev} + ip -netns ${ns2} li set ${ns2_dev} up + + if [ "${ns1_addr}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr} + fi + + if [ "${ns1_addr6}" != "-" ]; then + ip -netns ${ns1} addr add dev ${ns1_dev} ${ns1_addr6} + ip -netns ${ns2} addr add dev ${ns2_dev} ${ns2_addr6} + fi +} + +################################################################################ +# test setup + +cleanup() +{ + local ns + + for ns in host-1 host-2 router + do + ip netns del ${ns} 2>/dev/null + done +} + +setup_l2tp_ipv4() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1041 peer_tunnel_id 1042 \ + encap ip local 10.1.1.1 remote 10.1.2.1 + ip -netns host-1 l2tp add session name l2tp4 tunnel_id 1041 \ + session_id 1041 peer_session_id 1042 + ip -netns host-1 link set dev l2tp4 up + ip -netns host-1 addr add dev l2tp4 172.16.1.1 peer 172.16.1.2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1042 peer_tunnel_id 1041 \ + encap ip local 10.1.2.1 remote 10.1.1.1 + ip -netns host-2 l2tp add session name l2tp4 tunnel_id 1042 \ + session_id 1042 peer_session_id 1041 + ip -netns host-2 link set dev l2tp4 up + ip -netns host-2 addr add dev l2tp4 172.16.1.2 peer 172.16.1.1 + + # + # add routes to loopback addresses + # + ip -netns host-1 ro add 172.16.101.2/32 via 172.16.1.2 + ip -netns host-2 ro add 172.16.101.1/32 via 172.16.1.1 +} + +setup_l2tp_ipv6() +{ + # + # configure l2tpv3 tunnel on host-1 + # + ip -netns host-1 l2tp add tunnel tunnel_id 1061 peer_tunnel_id 1062 \ + encap ip local 2001:db8:1::1 remote 2001:db8:2::1 + ip -netns host-1 l2tp add session name l2tp6 tunnel_id 1061 \ + session_id 1061 peer_session_id 1062 + ip -netns host-1 link set dev l2tp6 up + ip -netns host-1 addr add dev l2tp6 fc00:1::1 peer fc00:1::2 + + # + # configure l2tpv3 tunnel on host-2 + # + ip -netns host-2 l2tp add tunnel tunnel_id 1062 peer_tunnel_id 1061 \ + encap ip local 2001:db8:2::1 remote 2001:db8:1::1 + ip -netns host-2 l2tp add session name l2tp6 tunnel_id 1062 \ + session_id 1062 peer_session_id 1061 + ip -netns host-2 link set dev l2tp6 up + ip -netns host-2 addr add dev l2tp6 fc00:1::2 peer fc00:1::1 + + # + # add routes to loopback addresses + # + ip -netns host-1 -6 ro add fc00:101::2/128 via fc00:1::2 + ip -netns host-2 -6 ro add fc00:101::1/128 via fc00:1::1 +} + +setup() +{ + # start clean + cleanup + + set -e + create_ns host-1 172.16.101.1/32 fc00:101::1/128 + create_ns host-2 172.16.101.2/32 fc00:101::2/128 + create_ns router + + connect_ns host-1 eth0 10.1.1.1/24 2001:db8:1::1/64 \ + router eth1 10.1.1.2/24 2001:db8:1::2/64 + + connect_ns host-2 eth0 10.1.2.1/24 2001:db8:2::1/64 \ + router eth2 10.1.2.2/24 2001:db8:2::2/64 + + ip -netns host-1 ro add 10.1.2.0/24 via 10.1.1.2 + ip -netns host-1 -6 ro add 2001:db8:2::/64 via 2001:db8:1::2 + + ip -netns host-2 ro add 10.1.1.0/24 via 10.1.2.2 + ip -netns host-2 -6 ro add 2001:db8:1::/64 via 2001:db8:2::2 + + setup_l2tp_ipv4 + setup_l2tp_ipv6 + set +e +} + +setup_ipsec() +{ + # + # IPv4 + # + run_cmd host-1 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.1.1 dst 10.1.2.1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip xfrm policy add \ + src 10.1.2.1 dst 10.1.1.1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.1.1 dst 10.1.2.1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 xfrm state add \ + src 10.1.2.1 dst 10.1.1.1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + # + # IPV6 + # + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir out \ + tmpl proto esp mode transport + + run_cmd host-1 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:1::1 dst 2001:db8:2::1 dir in \ + tmpl proto esp mode transport + + run_cmd host-2 ip -6 xfrm policy add \ + src 2001:db8:2::1 dst 2001:db8:1::1 dir out \ + tmpl proto esp mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-1 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:1::1 dst 2001:db8:2::1 \ + spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport + + ip -netns host-2 -6 xfrm state add \ + src 2001:db8:2::1 dst 2001:db8:1::1 \ + spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' \ + 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode transport +} + +teardown_ipsec() +{ + run_cmd host-1 ip xfrm state flush + run_cmd host-1 ip xfrm policy flush + run_cmd host-2 ip xfrm state flush + run_cmd host-2 ip xfrm policy flush +} + +################################################################################ +# generate traffic through tunnel for various cases + +run_ping() +{ + local desc="$1" + + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel ${desc}" +} + +run_tests() +{ + local desc + + setup + run_ping + + setup_ipsec + run_ping "- with IPsec" + run_cmd host-1 ping -c1 -w1 172.16.1.2 + log_test $? 0 "IPv4 basic L2TP tunnel ${desc}" + + run_cmd host-1 ping -c1 -w1 -I 172.16.101.1 172.16.101.2 + log_test $? 0 "IPv4 route through L2TP tunnel ${desc}" + + run_cmd host-1 ${ping6} -c1 -w1 fc00:1::2 + log_test $? 0 "IPv6 basic L2TP tunnel - with IPsec" + + run_cmd host-1 ${ping6} -c1 -w1 -I fc00:101::1 fc00:101::2 + log_test $? 0 "IPv6 route through L2TP tunnel - with IPsec" + + teardown_ipsec + run_ping "- after IPsec teardown" +} + +################################################################################ +# main + +declare -i nfail=0 +declare -i nsuccess=0 + +while getopts :pv o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + *) exit 1;; + esac +done + +run_tests +cleanup + +printf "\nTests passed: %3d\n" ${nsuccess} +printf "Tests failed: %3d\n" ${nfail} diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c new file mode 100644 index 000000000000..83515e5ea4dc --- /dev/null +++ b/tools/testing/selftests/net/nettest.c @@ -0,0 +1,1756 @@ +// SPDX-License-Identifier: GPL-2.0 +/* nettest - used for functional tests of networking APIs + * + * Copyright (c) 2013-2019 David Ahern <[email protected]>. All rights reserved. + */ + +#define _GNU_SOURCE +#include <features.h> +#include <sys/types.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <linux/tcp.h> +#include <arpa/inet.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netdb.h> +#include <fcntl.h> +#include <libgen.h> +#include <limits.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <time.h> +#include <errno.h> + +#ifndef IPV6_UNICAST_IF +#define IPV6_UNICAST_IF 76 +#endif +#ifndef IPV6_MULTICAST_IF +#define IPV6_MULTICAST_IF 17 +#endif + +#define DEFAULT_PORT 12345 + +#ifndef MAX +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +#endif +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + +struct sock_args { + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } local_addr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } remote_addr; + int scope_id; /* remote scope; v6 send only */ + + struct in_addr grp; /* multicast group */ + + unsigned int has_local_ip:1, + has_remote_ip:1, + has_grp:1, + has_expected_laddr:1, + has_expected_raddr:1, + bind_test_only:1; + + unsigned short port; + + int type; /* DGRAM, STREAM, RAW */ + int protocol; + int version; /* AF_INET/AF_INET6 */ + + int use_setsockopt; + int use_cmsg; + const char *dev; + int ifindex; + const char *password; + + /* expected addresses and device index for connection */ + int expected_ifindex; + + /* local address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_laddr; + + /* remote address */ + union { + struct in_addr in; + struct in6_addr in6; + } expected_raddr; +}; + +static int server_mode; +static unsigned int prog_timeout = 5; +static unsigned int interactive; +static int iter = 1; +static char *msg = "Hello world!"; +static int msglen; +static int quiet; +static int try_broadcast = 1; + +static char *timestamp(char *timebuf, int buflen) +{ + time_t now; + + now = time(NULL); + if (strftime(timebuf, buflen, "%T", localtime(&now)) == 0) { + memset(timebuf, 0, buflen); + strncpy(timebuf, "00:00:00", buflen-1); + } + + return timebuf; +} + +static void log_msg(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stdout, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stdout, format, args); + va_end(args); + + fflush(stdout); +} + +static void log_error(const char *format, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s:", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, format); + vfprintf(stderr, format, args); + va_end(args); + + fflush(stderr); +} + +static void log_err_errno(const char *fmt, ...) +{ + char timebuf[64]; + va_list args; + + if (quiet) + return; + + fprintf(stderr, "%s %s: ", + timestamp(timebuf, sizeof(timebuf)), + server_mode ? "server" : "client"); + va_start(args, fmt); + vfprintf(stderr, fmt, args); + va_end(args); + + fprintf(stderr, ": %d: %s\n", errno, strerror(errno)); + fflush(stderr); +} + +static void log_address(const char *desc, struct sockaddr *sa) +{ + char addrstr[64]; + + if (quiet) + return; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + + log_msg("%s %s:%d", + desc, + inet_ntop(AF_INET, &s->sin_addr, addrstr, + sizeof(addrstr)), + ntohs(s->sin_port)); + + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + log_msg("%s [%s]:%d", + desc, + inet_ntop(AF_INET6, &s6->sin6_addr, addrstr, + sizeof(addrstr)), + ntohs(s6->sin6_port)); + } + + printf("\n"); + + fflush(stdout); +} + +static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +{ + struct tcp_md5sig md5sig; + int keylen = password ? strlen(password) : 0; + int rc; + + memset(&md5sig, 0, sizeof(md5sig)); + memcpy(&md5sig.tcpm_addr, addr, alen); + md5sig.tcpm_keylen = keylen; + + if (keylen) + memcpy(md5sig.tcpm_key, password, keylen); + + rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + if (rc < 0) { + /* ENOENT is harmless. Returned when a password is cleared */ + if (errno == ENOENT) + rc = 0; + else + log_err_errno("setsockopt(TCP_MD5SIG)"); + } + + return rc; +} + +static int tcp_md5_remote(int sd, struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + addr = &sin6; + alen = sizeof(sin6); + break; + default: + log_error("unknown address family\n"); + exit(1); + } + + if (tcp_md5sig(sd, addr, alen, args->password)) + return -1; + + return 0; +} + +static int get_ifidx(const char *ifname) +{ + struct ifreq ifdata; + int sd, rc; + + if (!ifname || *ifname == '\0') + return 0; + + memset(&ifdata, 0, sizeof(ifdata)); + + strcpy(ifdata.ifr_name, ifname); + + sd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); + if (sd < 0) { + log_err_errno("socket failed"); + return 0; + } + + rc = ioctl(sd, SIOCGIFINDEX, (char *)&ifdata); + close(sd); + if (rc != 0) { + log_err_errno("ioctl(SIOCGIFINDEX) failed"); + return 0; + } + + return ifdata.ifr_ifindex; +} + +static int bind_to_device(int sd, const char *name) +{ + int rc; + + rc = setsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, strlen(name)+1); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int get_bind_to_device(int sd, char *name, size_t len) +{ + int rc; + socklen_t optlen = len; + + name[0] = '\0'; + rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); + if (rc < 0) + log_err_errno("setsockopt(SO_BINDTODEVICE)"); + + return rc; +} + +static int check_device(int sd, struct sock_args *args) +{ + int ifindex = 0; + char name[32]; + + if (get_bind_to_device(sd, name, sizeof(name))) + *name = '\0'; + else + ifindex = get_ifidx(name); + + log_msg(" bound to device %s/%d\n", + *name ? name : "<none>", ifindex); + + if (!args->expected_ifindex) + return 0; + + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return 1; + } + + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + + return 0; +} + +static int set_pktinfo_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_PKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_PKTINFO)"); + + return rc; +} + +static int set_recvpktinfo_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVPKTINFO, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVPKTINFO)"); + + return rc; +} + +static int set_recverr_v4(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IP_RECVERR)"); + + return rc; +} + +static int set_recverr_v6(int sd) +{ + int one = 1; + int rc; + + rc = setsockopt(sd, SOL_IPV6, IPV6_RECVERR, &one, sizeof(one)); + if (rc < 0 && rc != -ENOTSUP) + log_err_errno("setsockopt(IPV6_RECVERR)"); + + return rc; +} + +static int set_unicast_if(int sd, int ifindex, int version) +{ + int opt = IP_UNICAST_IF; + int level = SOL_IP; + int rc; + + ifindex = htonl(ifindex); + + if (version == AF_INET6) { + opt = IPV6_UNICAST_IF; + level = SOL_IPV6; + } + rc = setsockopt(sd, level, opt, &ifindex, sizeof(ifindex)); + if (rc < 0) + log_err_errno("setsockopt(IP_UNICAST_IF)"); + + return rc; +} + +static int set_multicast_if(int sd, int ifindex) +{ + struct ip_mreqn mreq = { .imr_ifindex = ifindex }; + int rc; + + rc = setsockopt(sd, SOL_IP, IP_MULTICAST_IF, &mreq, sizeof(mreq)); + if (rc < 0) + log_err_errno("setsockopt(IP_MULTICAST_IF)"); + + return rc; +} + +static int set_membership(int sd, uint32_t grp, uint32_t addr, const char *dev) +{ + uint32_t if_addr = addr; + struct ip_mreqn mreq; + int rc; + + if (addr == htonl(INADDR_ANY) && !dev) { + log_error("Either local address or device needs to be given for multicast membership\n"); + return -1; + } + + mreq.imr_multiaddr.s_addr = grp; + mreq.imr_address.s_addr = if_addr; + mreq.imr_ifindex = dev ? get_ifidx(dev) : 0; + + rc = setsockopt(sd, IPPROTO_IP, IP_ADD_MEMBERSHIP, &mreq, sizeof(mreq)); + if (rc < 0) { + log_err_errno("setsockopt(IP_ADD_MEMBERSHIP)"); + return -1; + } + + return 0; +} + +static int set_broadcast(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_BROADCAST)"); + rc = -1; + } + + return rc; +} + +static int set_reuseport(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEPORT)"); + rc = -1; + } + + return rc; +} + +static int set_reuseaddr(int sd) +{ + unsigned int one = 1; + int rc = 0; + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)) != 0) { + log_err_errno("setsockopt(SO_REUSEADDR)"); + rc = -1; + } + + return rc; +} + +static int str_to_uint(const char *str, int min, int max, unsigned int *value) +{ + int number; + char *end; + + errno = 0; + number = (unsigned int) strtoul(str, &end, 0); + + /* entire string should be consumed by conversion + * and value should be between min and max + */ + if (((*end == '\0') || (*end == '\n')) && (end != str) && + (errno != ERANGE) && (min <= number) && (number <= max)) { + *value = number; + return 0; + } + + return -1; +} + +static int expected_addr_match(struct sockaddr *sa, void *expected, + const char *desc) +{ + char addrstr[64]; + int rc = 0; + + if (sa->sa_family == AF_INET) { + struct sockaddr_in *s = (struct sockaddr_in *) sa; + struct in_addr *exp_in = (struct in_addr *) expected; + + if (s->sin_addr.s_addr != exp_in->s_addr) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *exp_in = (struct in6_addr *) expected; + + if (memcmp(&s6->sin6_addr, exp_in, sizeof(*exp_in))) { + log_error("%s address does not match expected %s", + desc, + inet_ntop(AF_INET6, exp_in, + addrstr, sizeof(addrstr))); + rc = 1; + } + } else { + log_error("%s address does not match expected - unknown family", + desc); + rc = 1; + } + + if (!rc) + log_msg("%s address matches expected\n", desc); + + return rc; +} + +static int show_sockstat(int sd, struct sock_args *args) +{ + struct sockaddr_in6 local_addr, remote_addr; + socklen_t alen = sizeof(local_addr); + struct sockaddr *sa; + const char *desc; + int rc = 0; + + desc = server_mode ? "server local:" : "client local:"; + sa = (struct sockaddr *) &local_addr; + if (getsockname(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_laddr) { + rc = expected_addr_match(sa, &args->expected_laddr, + "local"); + } + } else { + log_err_errno("getsockname failed"); + } + + sa = (struct sockaddr *) &remote_addr; + desc = server_mode ? "server peer:" : "client peer:"; + if (getpeername(sd, sa, &alen) == 0) { + log_address(desc, sa); + + if (args->has_expected_raddr) { + rc |= expected_addr_match(sa, &args->expected_raddr, + "remote"); + } + } else { + log_err_errno("getpeername failed"); + } + + return rc; +} + +static int get_index_from_cmsg(struct msghdr *m) +{ + struct cmsghdr *cm; + int ifindex = 0; + char buf[64]; + + for (cm = (struct cmsghdr *)CMSG_FIRSTHDR(m); + m->msg_controllen != 0 && cm; + cm = (struct cmsghdr *)CMSG_NXTHDR(m, cm)) { + + if (cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_PKTINFO) { + struct in_pktinfo *pi; + + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET, &pi->ipi_addr, buf, sizeof(buf)); + ifindex = pi->ipi_ifindex; + } else if (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *pi6; + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + inet_ntop(AF_INET6, &pi6->ipi6_addr, buf, sizeof(buf)); + ifindex = pi6->ipi6_ifindex; + } + } + + if (ifindex) { + log_msg(" pktinfo: ifindex %d dest addr %s\n", + ifindex, buf); + } + return ifindex; +} + +static int send_msg_no_cmsg(int sd, void *addr, socklen_t alen) +{ + int err; + +again: + err = sendto(sd, msg, msglen, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendto failed"); + return 1; + } + + return 0; +} + +static int send_msg_cmsg(int sd, void *addr, socklen_t alen, + int ifindex, int version) +{ + unsigned char cmsgbuf[64]; + struct iovec iov[2]; + struct cmsghdr *cm; + struct msghdr m; + int err; + + iov[0].iov_base = msg; + iov[0].iov_len = msglen; + m.msg_iov = iov; + m.msg_iovlen = 1; + m.msg_name = (caddr_t)addr; + m.msg_namelen = alen; + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + cm = (struct cmsghdr *)cmsgbuf; + m.msg_control = (caddr_t)cm; + + if (version == AF_INET) { + struct in_pktinfo *pi; + + cm->cmsg_level = SOL_IP; + cm->cmsg_type = IP_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pi = (struct in_pktinfo *)(CMSG_DATA(cm)); + pi->ipi_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + + } else if (version == AF_INET6) { + struct in6_pktinfo *pi6; + + cm->cmsg_level = SOL_IPV6; + cm->cmsg_type = IPV6_PKTINFO; + cm->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + + pi6 = (struct in6_pktinfo *)(CMSG_DATA(cm)); + pi6->ipi6_ifindex = ifindex; + + m.msg_controllen = cm->cmsg_len; + } + +again: + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + + log_err_errno("sendmsg failed"); + return 1; + } + + return 0; +} + + +static int send_msg(int sd, void *addr, socklen_t alen, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) { + if (write(sd, msg, msglen) < 0) { + log_err_errno("write failed sending msg to peer"); + return 1; + } + } else if (args->ifindex && args->use_cmsg) { + if (send_msg_cmsg(sd, addr, alen, args->ifindex, args->version)) + return 1; + } else { + if (send_msg_no_cmsg(sd, addr, alen)) + return 1; + } + + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", msg, msglen > 24 ? " ..." : ""); + + return 0; +} + +static int socket_read_dgram(int sd, struct sock_args *args) +{ + unsigned char addr[sizeof(struct sockaddr_in6)]; + struct sockaddr *sa = (struct sockaddr *) addr; + socklen_t alen = sizeof(addr); + struct iovec iov[2]; + struct msghdr m = { + .msg_name = (caddr_t)addr, + .msg_namelen = alen, + .msg_iov = iov, + .msg_iovlen = 1, + }; + unsigned char cmsgbuf[256]; + struct cmsghdr *cm = (struct cmsghdr *)cmsgbuf; + char buf[16*1024]; + int ifindex; + int len; + + iov[0].iov_base = (caddr_t)buf; + iov[0].iov_len = sizeof(buf); + + memset(cmsgbuf, 0, sizeof(cmsgbuf)); + m.msg_control = (caddr_t)cm; + m.msg_controllen = sizeof(cmsgbuf); + + len = recvmsg(sd, &m, 0); + if (len == 0) { + log_msg("peer closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message: %d: %s\n", + errno, strerror(errno)); + return -1; + } + + buf[len] = '\0'; + + log_address("Message from:", sa); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + ifindex = get_index_from_cmsg(&m); + if (args->expected_ifindex) { + if (args->expected_ifindex != ifindex) { + log_error("Device index mismatch: expected %d have %d\n", + args->expected_ifindex, ifindex); + return -1; + } + log_msg("Device index matches: expected %d have %d\n", + args->expected_ifindex, ifindex); + } + + if (!interactive && server_mode) { + if (sa->sa_family == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + struct in6_addr *in6 = &s6->sin6_addr; + + if (IN6_IS_ADDR_V4MAPPED(in6)) { + const uint32_t *pa = (uint32_t *) &in6->s6_addr; + struct in_addr in4; + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *) addr; + pa += 3; + in4.s_addr = *pa; + sin->sin_addr = in4; + sin->sin_family = AF_INET; + if (send_msg_cmsg(sd, addr, alen, + ifindex, AF_INET) < 0) + goto out_err; + } + } +again: + iov[0].iov_len = len; + + if (args->version == AF_INET6) { + struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) sa; + + if (args->dev) { + /* avoid PKTINFO conflicts with bindtodev */ + if (sendto(sd, buf, len, 0, + (void *) addr, alen) < 0) + goto out_err; + } else { + /* kernel is allowing scope_id to be set to VRF + * index for LLA. for sends to global address + * reset scope id + */ + s6->sin6_scope_id = ifindex; + if (sendmsg(sd, &m, 0) < 0) + goto out_err; + } + } else { + int err; + + err = sendmsg(sd, &m, 0); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + goto out_err; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +out_err: + log_err_errno("failed to send msg to peer"); + return -1; +} + +static int socket_read_stream(int sd) +{ + char buf[1024]; + int len; + + len = read(sd, buf, sizeof(buf)-1); + if (len == 0) { + log_msg("client closed connection.\n"); + return 0; + } else if (len < 0) { + log_msg("failed to read message\n"); + return -1; + } + + buf[len] = '\0'; + log_msg("Incoming message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + if (!interactive && server_mode) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + } + + return 1; +} + +static int socket_read(int sd, struct sock_args *args) +{ + if (args->type == SOCK_STREAM) + return socket_read_stream(sd); + + return socket_read_dgram(sd, args); +} + +static int stdin_to_socket(int sd, int type, void *addr, socklen_t alen) +{ + char buf[1024]; + int len; + + if (fgets(buf, sizeof(buf), stdin) == NULL) + return 0; + + len = strlen(buf); + if (type == SOCK_STREAM) { + if (write(sd, buf, len) < 0) { + log_err_errno("failed to send buf"); + return -1; + } + } else { + int err; + +again: + err = sendto(sd, buf, len, 0, addr, alen); + if (err < 0) { + if (errno == EACCES && try_broadcast) { + try_broadcast = 0; + if (!set_broadcast(sd)) + goto again; + errno = EACCES; + } + log_err_errno("failed to send msg to peer"); + return -1; + } + } + log_msg("Sent message:\n"); + log_msg(" %.24s%s\n", buf, len > 24 ? " ..." : ""); + + return 1; +} + +static void set_recv_attr(int sd, int version) +{ + if (version == AF_INET6) { + set_recvpktinfo_v6(sd); + set_recverr_v6(sd); + } else { + set_pktinfo_v4(sd); + set_recverr_v4(sd); + } +} + +static int msg_loop(int client, int sd, void *addr, socklen_t alen, + struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + fd_set rfds; + int nfds; + int rc; + + if (args->type != SOCK_STREAM) + set_recv_attr(sd, args->version); + + if (msg) { + msglen = strlen(msg); + + /* client sends first message */ + if (client) { + if (send_msg(sd, addr, alen, args)) + return 1; + } + if (!interactive) { + ptval = &timeout; + if (!prog_timeout) + timeout.tv_sec = 5; + } + } + + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + while (1) { + FD_ZERO(&rfds); + FD_SET(sd, &rfds); + if (interactive) + FD_SET(fileno(stdin), &rfds); + + rc = select(nfds, &rfds, NULL, NULL, ptval); + if (rc < 0) { + if (errno == EINTR) + continue; + + rc = 1; + log_err_errno("select failed"); + break; + } else if (rc == 0) { + log_error("Timed out waiting for response\n"); + rc = 2; + break; + } + + if (FD_ISSET(sd, &rfds)) { + rc = socket_read(sd, args); + if (rc < 0) { + rc = 1; + break; + } + if (rc == 0) + break; + } + + rc = 0; + + if (FD_ISSET(fileno(stdin), &rfds)) { + if (stdin_to_socket(sd, args->type, addr, alen) <= 0) + break; + } + + if (interactive) + continue; + + if (iter != -1) { + --iter; + if (iter == 0) + break; + } + + log_msg("Going into quiet mode\n"); + quiet = 1; + + if (client) { + if (send_msg(sd, addr, alen, args)) { + rc = 1; + break; + } + } + } + + return rc; +} + +static int msock_init(struct sock_args *args, int server) +{ + uint32_t if_addr = htonl(INADDR_ANY); + struct sockaddr_in laddr = { + .sin_family = AF_INET, + .sin_port = htons(args->port), + }; + int one = 1; + int sd; + + if (!server && args->has_local_ip) + if_addr = args->local_addr.in.s_addr; + + sd = socket(PF_INET, SOCK_DGRAM, 0); + if (sd < 0) { + log_err_errno("socket"); + return -1; + } + + if (setsockopt(sd, SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)) < 0) { + log_err_errno("Setting SO_REUSEADDR error"); + goto out_err; + } + + if (setsockopt(sd, SOL_SOCKET, SO_BROADCAST, + (char *)&one, sizeof(one)) < 0) + log_err_errno("Setting SO_BROADCAST error"); + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto out_err; + else if (args->use_setsockopt && + set_multicast_if(sd, args->ifindex)) + goto out_err; + + laddr.sin_addr.s_addr = if_addr; + + if (bind(sd, (struct sockaddr *) &laddr, sizeof(laddr)) < 0) { + log_err_errno("bind failed"); + goto out_err; + } + + if (server && + set_membership(sd, args->grp.s_addr, + args->local_addr.in.s_addr, args->dev)) + goto out_err; + + return sd; +out_err: + close(sd); + return -1; +} + +static int msock_server(struct sock_args *args) +{ + return msock_init(args, 1); +} + +static int msock_client(struct sock_args *args) +{ + return msock_init(args, 0); +} + +static int bind_socket(int sd, struct sock_args *args) +{ + struct sockaddr_in serv_addr = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 serv6_addr = { + .sin6_family = AF_INET6, + }; + void *addr; + socklen_t alen; + + if (!args->has_local_ip && args->type == SOCK_RAW) + return 0; + + switch (args->version) { + case AF_INET: + serv_addr.sin_port = htons(args->port); + serv_addr.sin_addr = args->local_addr.in; + addr = &serv_addr; + alen = sizeof(serv_addr); + break; + + case AF_INET6: + serv6_addr.sin6_port = htons(args->port); + serv6_addr.sin6_addr = args->local_addr.in6; + addr = &serv6_addr; + alen = sizeof(serv6_addr); + break; + + default: + log_error("Invalid address family\n"); + return -1; + } + + if (bind(sd, addr, alen) < 0) { + log_err_errno("error binding socket"); + return -1; + } + + return 0; +} + +static int lsock_init(struct sock_args *args) +{ + long flags; + int sd; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Error opening socket"); + return -1; + } + + if (set_reuseaddr(sd) != 0) + goto err; + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (bind_socket(sd, args)) + goto err; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM && listen(sd, 1) < 0) { + log_err_errno("listen failed"); + goto err; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0) + log_err_errno("Failed to set close-on-exec flag"); + +out: + return sd; + +err: + close(sd); + return -1; +} + +static int do_server(struct sock_args *args) +{ + struct timeval timeout = { .tv_sec = prog_timeout }, *ptval = NULL; + unsigned char addr[sizeof(struct sockaddr_in6)] = {}; + socklen_t alen = sizeof(addr); + int lsd, csd = -1; + + fd_set rfds; + int rc; + + if (prog_timeout) + ptval = &timeout; + + if (args->has_grp) + lsd = msock_server(args); + else + lsd = lsock_init(args); + + if (lsd < 0) + return 1; + + if (args->bind_test_only) { + close(lsd); + return 0; + } + + if (args->type != SOCK_STREAM) { + rc = msg_loop(0, lsd, (void *) addr, alen, args); + close(lsd); + return rc; + } + + if (args->password && tcp_md5_remote(lsd, args)) { + close(lsd); + return -1; + } + + while (1) { + log_msg("\n"); + log_msg("waiting for client connection.\n"); + FD_ZERO(&rfds); + FD_SET(lsd, &rfds); + + rc = select(lsd+1, &rfds, NULL, NULL, ptval); + if (rc == 0) { + rc = 2; + break; + } + + if (rc < 0) { + if (errno == EINTR) + continue; + + log_err_errno("select failed"); + break; + } + + if (FD_ISSET(lsd, &rfds)) { + + csd = accept(lsd, (void *) addr, &alen); + if (csd < 0) { + log_err_errno("accept failed"); + break; + } + + rc = show_sockstat(csd, args); + if (rc) + break; + + rc = check_device(csd, args); + if (rc) + break; + } + + rc = msg_loop(0, csd, (void *) addr, alen, args); + close(csd); + + if (!interactive) + break; + } + + close(lsd); + + return rc; +} + +static int wait_for_connect(int sd) +{ + struct timeval _tv = { .tv_sec = prog_timeout }, *tv = NULL; + fd_set wfd; + int val = 0, sz = sizeof(val); + int rc; + + FD_ZERO(&wfd); + FD_SET(sd, &wfd); + + if (prog_timeout) + tv = &_tv; + + rc = select(FD_SETSIZE, NULL, &wfd, NULL, tv); + if (rc == 0) { + log_error("connect timed out\n"); + return -2; + } else if (rc < 0) { + log_err_errno("select failed"); + return -3; + } + + if (getsockopt(sd, SOL_SOCKET, SO_ERROR, &val, (socklen_t *)&sz) < 0) { + log_err_errno("getsockopt(SO_ERROR) failed"); + return -4; + } + + if (val != 0) { + log_error("connect failed: %d: %s\n", val, strerror(val)); + return -1; + } + + return 0; +} + +static int connectsock(void *addr, socklen_t alen, struct sock_args *args) +{ + int sd, rc = -1; + long flags; + + sd = socket(args->version, args->type, args->protocol); + if (sd < 0) { + log_err_errno("Failed to create socket"); + return -1; + } + + flags = fcntl(sd, F_GETFL); + if ((flags < 0) || (fcntl(sd, F_SETFL, flags|O_NONBLOCK) < 0)) { + log_err_errno("Failed to set non-blocking option"); + goto err; + } + + if (set_reuseport(sd) != 0) + goto err; + + if (args->dev && bind_to_device(sd, args->dev) != 0) + goto err; + else if (args->use_setsockopt && + set_unicast_if(sd, args->ifindex, args->version)) + goto err; + + if (args->has_local_ip && bind_socket(sd, args)) + goto err; + + if (args->type != SOCK_STREAM) + goto out; + + if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + goto err; + + if (args->bind_test_only) + goto out; + + if (connect(sd, addr, alen) < 0) { + if (errno != EINPROGRESS) { + log_err_errno("Failed to connect to remote host"); + rc = -1; + goto err; + } + rc = wait_for_connect(sd); + if (rc < 0) + goto err; + } +out: + return sd; + +err: + close(sd); + return rc; +} + +static int do_client(struct sock_args *args) +{ + struct sockaddr_in sin = { + .sin_family = AF_INET, + }; + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + }; + void *addr; + int alen; + int rc = 0; + int sd; + + if (!args->has_remote_ip && !args->has_grp) { + fprintf(stderr, "remote IP or multicast group not given\n"); + return 1; + } + + switch (args->version) { + case AF_INET: + sin.sin_port = htons(args->port); + if (args->has_grp) + sin.sin_addr = args->grp; + else + sin.sin_addr = args->remote_addr.in; + addr = &sin; + alen = sizeof(sin); + break; + case AF_INET6: + sin6.sin6_port = htons(args->port); + sin6.sin6_addr = args->remote_addr.in6; + sin6.sin6_scope_id = args->scope_id; + addr = &sin6; + alen = sizeof(sin6); + break; + } + + if (args->has_grp) + sd = msock_client(args); + else + sd = connectsock(addr, alen, args); + + if (sd < 0) + return -sd; + + if (args->bind_test_only) + goto out; + + if (args->type == SOCK_STREAM) { + rc = show_sockstat(sd, args); + if (rc != 0) + goto out; + } + + rc = msg_loop(1, sd, addr, alen, args); + +out: + close(sd); + + return rc; +} + +enum addr_type { + ADDR_TYPE_LOCAL, + ADDR_TYPE_REMOTE, + ADDR_TYPE_MCAST, + ADDR_TYPE_EXPECTED_LOCAL, + ADDR_TYPE_EXPECTED_REMOTE, +}; + +static int convert_addr(struct sock_args *args, const char *_str, + enum addr_type atype) +{ + int family = args->version; + struct in6_addr *in6; + struct in_addr *in; + const char *desc; + char *str, *dev; + void *addr; + int rc = 0; + + str = strdup(_str); + if (!str) + return -ENOMEM; + + switch (atype) { + case ADDR_TYPE_LOCAL: + desc = "local"; + addr = &args->local_addr; + break; + case ADDR_TYPE_REMOTE: + desc = "remote"; + addr = &args->remote_addr; + break; + case ADDR_TYPE_MCAST: + desc = "mcast grp"; + addr = &args->grp; + break; + case ADDR_TYPE_EXPECTED_LOCAL: + desc = "expected local"; + addr = &args->expected_laddr; + break; + case ADDR_TYPE_EXPECTED_REMOTE: + desc = "expected remote"; + addr = &args->expected_raddr; + break; + default: + log_error("unknown address type"); + exit(1); + } + + switch (family) { + case AF_INET: + in = (struct in_addr *) addr; + if (str) { + if (inet_pton(AF_INET, str, in) == 0) { + log_error("Invalid %s IP address\n", desc); + rc = -1; + goto out; + } + } else { + in->s_addr = htonl(INADDR_ANY); + } + break; + + case AF_INET6: + dev = strchr(str, '%'); + if (dev) { + *dev = '\0'; + dev++; + } + + in6 = (struct in6_addr *) addr; + if (str) { + if (inet_pton(AF_INET6, str, in6) == 0) { + log_error("Invalid %s IPv6 address\n", desc); + rc = -1; + goto out; + } + } else { + *in6 = in6addr_any; + } + if (dev) { + args->scope_id = get_ifidx(dev); + if (args->scope_id < 0) { + log_error("Invalid scope on %s IPv6 address\n", + desc); + rc = -1; + goto out; + } + } + break; + + default: + log_error("Invalid address family\n"); + } + +out: + free(str); + return rc; +} + +static char *random_msg(int len) +{ + int i, n = 0, olen = len + 1; + char *m; + + if (len <= 0) + return NULL; + + m = malloc(olen); + if (!m) + return NULL; + + while (len > 26) { + i = snprintf(m + n, olen - n, "%.26s", + "abcdefghijklmnopqrstuvwxyz"); + n += i; + len -= i; + } + i = snprintf(m + n, olen - n, "%.*s", len, + "abcdefghijklmnopqrstuvwxyz"); + return m; +} + +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" + +static void print_usage(char *prog) +{ + printf( + "usage: %s OPTS\n" + "Required:\n" + " -r addr remote address to connect to (client mode only)\n" + " -p port port to connect to (client mode)/listen on (server mode)\n" + " (default: %d)\n" + " -s server mode (default: client mode)\n" + " -t timeout seconds (default: none)\n" + "\n" + "Optional:\n" + " -F Restart server loop\n" + " -6 IPv6 (default is IPv4)\n" + " -P proto protocol for socket: icmp, ospf (default: none)\n" + " -D|R datagram (D) / raw (R) socket (default stream)\n" + " -l addr local address to bind to\n" + "\n" + " -d dev bind socket to given device name\n" + " -S use setsockopt (IP_UNICAST_IF or IP_MULTICAST_IF)\n" + " to set device binding\n" + " -C use cmsg and IP_PKTINFO to specify device binding\n" + "\n" + " -L len send random message of given length\n" + " -n num number of times to send message\n" + "\n" + " -M password use MD5 sum protection\n" + " -g grp multicast group (e.g., 239.1.1.1)\n" + " -i interactive mode (default is echo and terminate)\n" + "\n" + " -0 addr Expected local address\n" + " -1 addr Expected remote address\n" + " -2 dev Expected device name (or index) to receive packet\n" + "\n" + " -b Bind test only.\n" + " -q Be quiet. Run test without printing anything.\n" + , prog, DEFAULT_PORT); +} + +int main(int argc, char *argv[]) +{ + struct sock_args args = { + .version = AF_INET, + .type = SOCK_STREAM, + .port = DEFAULT_PORT, + }; + struct protoent *pe; + unsigned int tmp; + int forever = 0; + + /* process inputs */ + extern char *optarg; + int rc = 0; + + /* + * process input args + */ + + while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + switch (rc) { + case 's': + server_mode = 1; + break; + case 'F': + forever = 1; + break; + case 'l': + args.has_local_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_LOCAL) < 0) + return 1; + break; + case 'r': + args.has_remote_ip = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_REMOTE) < 0) + return 1; + break; + case 'p': + if (str_to_uint(optarg, 1, 65535, &tmp) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + args.port = (unsigned short) tmp; + break; + case 't': + if (str_to_uint(optarg, 0, INT_MAX, + &prog_timeout) != 0) { + fprintf(stderr, "Invalid timeout\n"); + return 1; + } + break; + case 'D': + args.type = SOCK_DGRAM; + break; + case 'R': + args.type = SOCK_RAW; + args.port = 0; + break; + case 'P': + pe = getprotobyname(optarg); + if (pe) { + args.protocol = pe->p_proto; + } else { + if (str_to_uint(optarg, 0, 0xffff, &tmp) != 0) { + fprintf(stderr, "Invalid protocol\n"); + return 1; + } + args.protocol = tmp; + } + break; + case 'n': + iter = atoi(optarg); + break; + case 'L': + msg = random_msg(atoi(optarg)); + break; + case 'M': + args.password = optarg; + break; + case 'S': + args.use_setsockopt = 1; + break; + case 'C': + args.use_cmsg = 1; + break; + case 'd': + args.dev = optarg; + args.ifindex = get_ifidx(optarg); + if (args.ifindex < 0) { + fprintf(stderr, "Invalid device name\n"); + return 1; + } + break; + case 'i': + interactive = 1; + break; + case 'g': + args.has_grp = 1; + if (convert_addr(&args, optarg, ADDR_TYPE_MCAST) < 0) + return 1; + args.type = SOCK_DGRAM; + break; + case '6': + args.version = AF_INET6; + break; + case 'b': + args.bind_test_only = 1; + break; + case '0': + args.has_expected_laddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_LOCAL)) + return 1; + break; + case '1': + args.has_expected_raddr = 1; + if (convert_addr(&args, optarg, + ADDR_TYPE_EXPECTED_REMOTE)) + return 1; + + break; + case '2': + if (str_to_uint(optarg, 0, 0x7ffffff, &tmp) != 0) { + tmp = get_ifidx(optarg); + if (tmp < 0) { + fprintf(stderr, + "Invalid device index\n"); + return 1; + } + } + args.expected_ifindex = (int)tmp; + break; + case 'q': + quiet = 1; + break; + default: + print_usage(argv[0]); + return 1; + } + } + + if (args.password && + (!args.has_remote_ip || args.type != SOCK_STREAM)) { + log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); + return 1; + } + + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { + fprintf(stderr, "Device binding not specified\n"); + return 1; + } + if (args.use_setsockopt || args.use_cmsg) + args.dev = NULL; + + if (iter == 0) { + fprintf(stderr, "Invalid number of messages to send\n"); + return 1; + } + + if (args.type == SOCK_STREAM && !args.protocol) + args.protocol = IPPROTO_TCP; + if (args.type == SOCK_DGRAM && !args.protocol) + args.protocol = IPPROTO_UDP; + + if ((args.type == SOCK_STREAM || args.type == SOCK_DGRAM) && + args.port == 0) { + fprintf(stderr, "Invalid port number\n"); + return 1; + } + + if (!server_mode && !args.has_grp && + !args.has_remote_ip && !args.has_local_ip) { + fprintf(stderr, + "Local (server mode) or remote IP (client IP) required\n"); + return 1; + } + + if (interactive) { + prog_timeout = 0; + msg = NULL; + } + + if (server_mode) { + do { + rc = do_server(&args); + } while (forever); + + return rc; + } + return do_client(&args); +} diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 090fff9dbc48..4c285b6e1db8 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,80 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + self->notls = false; + len = sizeof(addr); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + self->fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(self->fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + self->cfd = accept(sfd, &addr, &len); + ASSERT_GE(self->cfd, 0); + + close(sfd); + + ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + ASSERT_EQ(errno, ENOENT); + self->notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + return; + } + + ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_basic) +{ + close(self->fd); + close(self->cfd); +} + +/* Send some data through with ULP but no keys */ +TEST_F(tls_basic, base_base) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + FIXTURE(tls) { int fd, cfd; @@ -165,6 +239,16 @@ TEST_F(tls, msg_more) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, msg_more_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); +} + TEST_F(tls, sendmsg_single) { struct msghdr msg; @@ -610,6 +694,42 @@ TEST_F(tls, recv_lowat) EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0); } +TEST_F(tls, bidir) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + int ret; + + if (!self->notls) { + struct tls12_crypto_info_aes_gcm_128 tls12; + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_3_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + memset(buf, 0, sizeof(buf)); + + EXPECT_EQ(send(self->cfd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->fd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + TEST_F(tls, pollin) { char const *test_str = "test_poll"; @@ -837,6 +957,109 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, shutdown) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + +TEST_F(tls, shutdown_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + +TEST_F(tls, shutdown_reuse) +{ + struct sockaddr_in addr; + int ret; + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); + close(self->cfd); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + ret = bind(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, 0); + ret = listen(self->fd, 10); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EINVAL); + + ret = connect(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EISCONN); +} + +TEST(non_established) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd; + socklen_t len; + + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + /* TLS ULP not supported */ + if (errno == ENOENT) + return; + EXPECT_EQ(errno, ENOTSUPP); + + ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, ENOTSUPP); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EEXIST); + + close(fd); + close(sfd); +} + TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 7eaa8a3de262..b632965e60eb 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -339,13 +339,9 @@ static int test_pidfd_send_signal_syscall_support(void) ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); if (ret < 0) { - /* - * pidfd_send_signal() will currently return ENOSYS when - * CONFIG_PROC_FS is not set. - */ if (errno == ENOSYS) ksft_exit_skip( - "%s test: pidfd_send_signal() syscall not supported (Ensure that CONFIG_PROC_FS=y is set)\n", + "%s test: pidfd_send_signal() syscall not supported\n", test_name); ksft_exit_fail_msg("%s test: Failed to send signal\n", diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index cc7c7d758008..6503b1ce091f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -713,5 +713,99 @@ "teardown": [ "$TC actions flush action vlan" ] + }, + { + "id": "294e", + "name": "Add batch of 32 vlan push actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "56f7", + "name": "Delete batch of 32 vlan push actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "759f", + "name": "Add batch of 32 vlan pop actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop continue index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "c84a", + "name": "Delete batch of 32 vlan pop actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json new file mode 100644 index 000000000000..5f24c0598624 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/matchall.json @@ -0,0 +1,391 @@ +[ + { + "id": "f62b", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7f09", + "name": "Add egress matchall filter for protocol ipv4 and action PASS", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol ip matchall action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 1 protocol ip matchall", + "matchPattern": "^filter parent 1: protocol ip pref 1 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "0596", + "name": "Add ingress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "41df", + "name": "Add egress matchall filter for protocol ipv6 and action DROP", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol ipv6 matchall action drop", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent 1: protocol ipv6 pref 1 matchall.*handle 0x1.*gact action drop.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "e1da", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "3de5", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority at 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 65535 protocol ipv4 matchall action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 65535 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 65535 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "72d7", + "name": "Add ingress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent ffff: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "41d3", + "name": "Add egress matchall filter for protocol ipv4 and action PASS with priority exceeding 16-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 655355 protocol ipv4 matchall action pass", + "expExitCode": "255", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 1 prio 655355 protocol ipv4 matchall", + "matchPattern": "^filter parent 1: protocol ip pref 655355 matchall.*handle 0x1.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "f755", + "name": "Add ingress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "2c33", + "name": "Add egress matchall filter for all protocols and action CONTINUE with handle at 32-bit maximum", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0xffffffff prio 1 protocol all matchall action continue", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 0xffffffff prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0xffffffff.*gact action continue.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "0e4a", + "name": "Add ingress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent ffff: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "7f60", + "name": "Add egress matchall filter for all protocols and action RECLASSIFY with skip_hw flag", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 root handle 1: prio" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: handle 0x1 prio 1 protocol all matchall skip_hw action reclassify", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent 1: handle 0x1 prio 1 protocol all matchall", + "matchPattern": "^filter parent 1: protocol all pref 1 matchall.*handle 0x1.*skip_hw.*not_in_hw.*gact action reclassify.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 root handle 1: prio", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "8bd2", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:1 action pass", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter parent ffff: protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:1.*gact action pass.*ref 1 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "2a4a", + "name": "Add ingress matchall filter for protocol ipv6 and action PASS with invalid classid", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 6789defg action pass", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 6789defg.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "eaf8", + "name": "Delete single ingress matchall filter", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall classid 1:2 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv6 matchall", + "matchPattern": "^filter protocol ipv6 pref 1 matchall.*handle 0x1.*flowid 1:2.*gact action pass.*ref 1 bind 1", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "76ad", + "name": "Delete all ingress matchall filters", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff:", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref.*matchall.*handle.*flowid.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "1eb9", + "name": "Delete single ingress matchall filter out of multiple", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all matchall classid 1:2 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x2 prio 2 protocol all matchall classid 1:3 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x3 prio 3 protocol all matchall classid 1:4 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x4 prio 4 protocol all matchall classid 1:5 action pass" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol all handle 0x2 prio 2 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref 2 matchall.*handle 0x2 flowid 1:2.*gact action pass", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + }, + { + "id": "6d63", + "name": "Delete ingress matchall filter by chain ID", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$IP link add dev $DEV1 type dummy || /bin/true", + "$TC qdisc add dev $DEV1 ingress", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol all chain 1 matchall classid 1:1 action pass", + "$TC filter add dev $DEV1 parent ffff: handle 0x1 prio 1 protocol ipv4 chain 2 matchall classid 1:3 action continue" + ], + "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: chain 2", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", + "matchPattern": "^filter protocol all pref 1 matchall chain 1 handle 0x1 flowid 1:1.*gact action pass", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + "$IP link del dev $DEV1 type dummy" + ] + } +] diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index 4602326b8f5b..a4f4d4cf22c3 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -451,7 +451,7 @@ static int test_vsys_x(void) printf("[OK]\tExecuting the vsyscall page failed: #PF(0x%lx)\n", segv_err); } else { - printf("[FAILT]\tExecution failed with the wrong error: #PF(0x%lx)\n", + printf("[FAIL]\tExecution failed with the wrong error: #PF(0x%lx)\n", segv_err); return 1; } diff --git a/usr/include/Makefile b/usr/include/Makefile index aa316d99e035..1fb6abe29b2f 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -101,10 +101,6 @@ ifeq ($(SRCARCH),riscv) header-test- += linux/bpf_perf_event.h endif -ifeq ($(SRCARCH),s390) -header-test- += asm/zcrypt.h -endif - ifeq ($(SRCARCH),sparc) header-test- += asm/stat.h header-test- += asm/uctx.h diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index f645c0fbf7ec..acc43242a310 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -727,7 +727,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virtual/kvm/vcpu-requests.rst + * Documentation/virt/kvm/vcpu-requests.rst */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 936962abc38d..c45e2d7e942f 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -250,7 +250,7 @@ static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, * pending state of interrupt is latched in pending_latch variable. * Userspace will save and restore pending state and line_level * separately. - * Refer to Documentation/virtual/kvm/devices/arm-vgic-v3.txt + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt * for handling of ISPENDR and ICPENDR. */ for (i = 0; i < len * 8; i++) { diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 57205beaa981..3b7525deec80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -42,7 +42,7 @@ VGIC_AFFINITY_LEVEL(val, 3)) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-v3.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt, * below macros are defined for CPUREG encoding. */ #define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 @@ -63,7 +63,7 @@ KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) /* - * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt, + * As per Documentation/virt/kvm/devices/arm-vgic-its.txt, * below macros are defined for ITS table entry encoding. */ #define KVM_ITS_CTE_VALID_SHIFT 63 |