diff options
310 files changed, 4119 insertions, 1678 deletions
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index b6e44884e3ad..41937a8091aa 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -117,6 +117,8 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | RNDR | [63-60] | y | + +------------------------------+---------+---------+ | TS | [55-52] | y | +------------------------------+---------+---------+ | FHM | [51-48] | y | @@ -200,6 +202,12 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | I8MM | [55-52] | y | + +------------------------------+---------+---------+ + | DGH | [51-48] | y | + +------------------------------+---------+---------+ + | BF16 | [47-44] | y | + +------------------------------+---------+---------+ | SB | [39-36] | y | +------------------------------+---------+---------+ | FRINTTS | [35-32] | y | @@ -234,10 +242,18 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | F64MM | [59-56] | y | + +------------------------------+---------+---------+ + | F32MM | [55-52] | y | + +------------------------------+---------+---------+ + | I8MM | [47-44] | y | + +------------------------------+---------+---------+ | SM4 | [43-40] | y | +------------------------------+---------+---------+ | SHA3 | [35-32] | y | +------------------------------+---------+---------+ + | BF16 | [23-20] | y | + +------------------------------+---------+---------+ | BitPerm | [19-16] | y | +------------------------------+---------+---------+ | AES | [7-4] | y | diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index 7fa3d215ae6a..7dfb97dfe416 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -204,6 +204,37 @@ HWCAP2_FRINT Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001. +HWCAP2_SVEI8MM + + Functionality implied by ID_AA64ZFR0_EL1.I8MM == 0b0001. + +HWCAP2_SVEF32MM + + Functionality implied by ID_AA64ZFR0_EL1.F32MM == 0b0001. + +HWCAP2_SVEF64MM + + Functionality implied by ID_AA64ZFR0_EL1.F64MM == 0b0001. + +HWCAP2_SVEBF16 + + Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0001. + +HWCAP2_I8MM + + Functionality implied by ID_AA64ISAR1_EL1.I8MM == 0b0001. + +HWCAP2_BF16 + + Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0001. + +HWCAP2_DGH + + Functionality implied by ID_AA64ISAR1_EL1.DGH == 0b0001. + +HWCAP2_RNG + + Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001. 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 99b2545455ff..9120e59578dc 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -88,6 +88,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A55 | #1530923 | ARM64_ERRATUM_1530923 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index fcedc5349ace..640934b6f7b4 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -25,10 +25,6 @@ good performance with large indices. If your index can be larger than ``ULONG_MAX`` then the XArray is not the data type for you. The most important user of the XArray is the page cache. -Each non-``NULL`` entry in the array has three bits associated with -it called marks. Each mark may be set or cleared independently of -the others. You can iterate over entries which are marked. - Normal pointers may be stored in the XArray directly. They must be 4-byte aligned, which is true for any pointer returned from kmalloc() and alloc_page(). It isn't true for arbitrary user-space pointers, @@ -41,12 +37,11 @@ When you retrieve an entry from the XArray, you can check whether it is a value entry by calling xa_is_value(), and convert it back to an integer by calling xa_to_value(). -Some users want to store tagged pointers instead of using the marks -described above. They can call xa_tag_pointer() to create an -entry with a tag, xa_untag_pointer() to turn a tagged entry -back into an untagged pointer and xa_pointer_tag() to retrieve -the tag of an entry. Tagged pointers use the same bits that are used -to distinguish value entries from normal pointers, so each user must +Some users want to tag the pointers they store in the XArray. You can +call xa_tag_pointer() to create an entry with a tag, xa_untag_pointer() +to turn a tagged entry back into an untagged pointer and xa_pointer_tag() +to retrieve the tag of an entry. Tagged pointers use the same bits that +are used to distinguish value entries from normal pointers, so you must decide whether they want to store value entries or tagged pointers in any particular XArray. @@ -56,10 +51,9 @@ conflict with value entries or internal entries. An unusual feature of the XArray is the ability to create entries which occupy a range of indices. Once stored to, looking up any index in the range will return the same entry as looking up any other index in -the range. Setting a mark on one index will set it on all of them. -Storing to any index will store to all of them. Multi-index entries can -be explicitly split into smaller entries, or storing ``NULL`` into any -entry will cause the XArray to forget about the range. +the range. Storing to any index will store to all of them. Multi-index +entries can be explicitly split into smaller entries, or storing ``NULL`` +into any entry will cause the XArray to forget about the range. Normal API ========== @@ -87,17 +81,11 @@ If you want to only store a new entry to an index if the current entry at that index is ``NULL``, you can use xa_insert() which returns ``-EBUSY`` if the entry is not empty. -You can enquire whether a mark is set on an entry by using -xa_get_mark(). If the entry is not ``NULL``, you can set a mark -on it by using xa_set_mark() and remove the mark from an entry by -calling xa_clear_mark(). You can ask whether any entry in the -XArray has a particular mark set by calling xa_marked(). - You can copy entries out of the XArray into a plain array by calling -xa_extract(). Or you can iterate over the present entries in -the XArray by calling xa_for_each(). You may prefer to use -xa_find() or xa_find_after() to move to the next present -entry in the XArray. +xa_extract(). Or you can iterate over the present entries in the XArray +by calling xa_for_each(), xa_for_each_start() or xa_for_each_range(). +You may prefer to use xa_find() or xa_find_after() to move to the next +present entry in the XArray. Calling xa_store_range() stores the same entry in a range of indices. If you do this, some of the other operations will behave @@ -124,6 +112,31 @@ xa_destroy(). If the XArray entries are pointers, you may wish to free the entries first. You can do this by iterating over all present entries in the XArray using the xa_for_each() iterator. +Search Marks +------------ + +Each entry in the array has three bits associated with it called marks. +Each mark may be set or cleared independently of the others. You can +iterate over marked entries by using the xa_for_each_marked() iterator. + +You can enquire whether a mark is set on an entry by using +xa_get_mark(). If the entry is not ``NULL``, you can set a mark on it +by using xa_set_mark() and remove the mark from an entry by calling +xa_clear_mark(). You can ask whether any entry in the XArray has a +particular mark set by calling xa_marked(). Erasing an entry from the +XArray causes all marks associated with that entry to be cleared. + +Setting or clearing a mark on any index of a multi-index entry will +affect all indices covered by that entry. Querying the mark on any +index will return the same result. + +There is no way to iterate over entries which are not marked; the data +structure does not allow this to be implemented efficiently. There are +not currently iterators to search for logical combinations of bits (eg +iterate over all entries which have both ``XA_MARK_1`` and ``XA_MARK_2`` +set, or iterate over all entries which have ``XA_MARK_0`` or ``XA_MARK_2`` +set). It would be possible to add these if a user arises. + Allocating XArrays ------------------ @@ -180,6 +193,8 @@ No lock needed: Takes RCU read lock: * xa_load() * xa_for_each() + * xa_for_each_start() + * xa_for_each_range() * xa_find() * xa_find_after() * xa_extract() @@ -419,10 +434,9 @@ you last processed. If you have interrupts disabled while iterating, then it is good manners to pause the iteration and reenable interrupts every ``XA_CHECK_SCHED`` entries. -The xas_get_mark(), xas_set_mark() and -xas_clear_mark() functions require the xa_state cursor to have -been moved to the appropriate location in the xarray; they will do -nothing if you have called xas_pause() or xas_set() +The xas_get_mark(), xas_set_mark() and xas_clear_mark() functions require +the xa_state cursor to have been moved to the appropriate location in the +XArray; they will do nothing if you have called xas_pause() or xas_set() immediately before. You can call xas_set_update() to have a callback function diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index 299c0dcd67db..250f8d8cdce4 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -403,6 +403,19 @@ PROPERTIES The settings and programming routines for internal/external MDIO are different. Must be included for internal MDIO. +- fsl,erratum-a011043 + Usage: optional + Value type: <boolean> + Definition: Indicates the presence of the A011043 erratum + describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely + set when reading internal PCS registers. MDIO reads to + internal PCS registers may result in having the + MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and + read data (MDIO_DATA[MDIO_DATA]) is correct. + Software may get false read error when reading internal + PCS registers through MDIO. As a workaround, all internal + MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit. + For internal PHY device on internal mdio bus, a PHY node should be created. See the definition of the PHY node in booting-without-of.txt for an example of how to define a PHY (Internal PHY has no interrupt line). diff --git a/MAINTAINERS b/MAINTAINERS index cf6ccca6e61c..56765f542244 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6197,6 +6197,7 @@ ETHERNET PHY LIBRARY M: Andrew Lunn <[email protected]> M: Florian Fainelli <[email protected]> M: Heiner Kallweit <[email protected]> +R: Russell King <[email protected]> S: Maintained F: Documentation/ABI/testing/sysfs-class-net-phydev @@ -8569,7 +8570,7 @@ S: Maintained F: drivers/platform/x86/intel-vbtn.c INTEL WIRELESS 3945ABG/BG, 4965AGN (iwlegacy) -M: Stanislaw Gruszka <[email protected]> +M: Stanislaw Gruszka <[email protected]> S: Supported F: drivers/net/wireless/intel/iwlegacy/ @@ -11499,6 +11500,7 @@ F: drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" <[email protected]> +M: Jakub Kicinski <[email protected]> W: http://www.linuxfoundation.org/en/Net Q: http://patchwork.ozlabs.org/project/netdev/list/ @@ -13820,7 +13822,7 @@ S: Maintained F: arch/mips/ralink RALINK RT2X00 WIRELESS LAN DRIVER -M: Stanislaw Gruszka <[email protected]> +M: Stanislaw Gruszka <[email protected]> M: Helmut Schaa <[email protected]> S: Maintained @@ -16601,7 +16603,7 @@ F: kernel/time/ntp.c F: tools/testing/selftests/timers/ TIPC NETWORK LAYER -M: Jon Maloy <[email protected]> +M: Jon Maloy <[email protected]> M: Ying Xue <[email protected]> L: [email protected] (core kernel code) L: [email protected] (user apps, general discussion) @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi index 7ad079861efd..91f93bc89716 100644 --- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi +++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi @@ -131,6 +131,11 @@ }; / { + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x20000000>; /* 512 MB */ + }; + clk_mcasp0_fixed: clk_mcasp0_fixed { #clock-cells = <0>; compatible = "fixed-clock"; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 078cb473fa7d..a6fbc088daa8 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -848,6 +848,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&spi0_pins_default>; pinctrl-1 = <&spi0_pins_sleep>; + ti,pindir-d0-out-d1-in = <1>; }; &spi1 { @@ -855,6 +856,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&spi1_pins_default>; pinctrl-1 = <&spi1_pins_sleep>; + ti,pindir-d0-out-d1-in = <1>; }; &usb2_phy1 { diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S index ae5020302de4..6607fa817bba 100644 --- a/arch/arm/kernel/hyp-stub.S +++ b/arch/arm/kernel/hyp-stub.S @@ -146,10 +146,9 @@ ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE #if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER) @ make CNTP_* and CNTPCT accessible from PL1 mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1 - lsr r7, #16 - and r7, #0xf - cmp r7, #1 - bne 1f + ubfx r7, r7, #16, #4 + teq r7, #0 + beq 1f mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL orr r7, r7, #3 @ PL1PCEN | PL1PCTEN mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e688dfad0b72..5616cab8dfda 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -162,6 +162,7 @@ config ARM64 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_RCU_TABLE_FREE select HAVE_RSEQ select HAVE_STACKPROTECTOR @@ -302,6 +303,9 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y +config BROKEN_GAS_INST + def_bool !$(as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n) + config KASAN_SHADOW_OFFSET hex depends on KASAN @@ -515,9 +519,13 @@ config ARM64_ERRATUM_1418040 If unsure, say Y. +config ARM64_WORKAROUND_SPECULATIVE_AT_VHE + bool + config ARM64_ERRATUM_1165522 bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" default y + select ARM64_WORKAROUND_SPECULATIVE_AT_VHE help This option adds a workaround for ARM Cortex-A76 erratum 1165522. @@ -527,6 +535,19 @@ config ARM64_ERRATUM_1165522 If unsure, say Y. +config ARM64_ERRATUM_1530923 + bool "Cortex-A55: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" + default y + select ARM64_WORKAROUND_SPECULATIVE_AT_VHE + help + This option adds a workaround for ARM Cortex-A55 erratum 1530923. + + Affected Cortex-A55 cores (r0p0, r0p1, r1p0, r2p0) could end-up with + corrupted TLBs by speculating an AT instruction during a guest + context switch. + + If unsure, say Y. + config ARM64_ERRATUM_1286807 bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" default y @@ -543,9 +564,13 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. +config ARM64_WORKAROUND_SPECULATIVE_AT_NVHE + bool + config ARM64_ERRATUM_1319367 bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" default y + select ARM64_WORKAROUND_SPECULATIVE_AT_NVHE help This option adds work arounds for ARM Cortex-A57 erratum 1319537 and A72 erratum 1319367 @@ -1364,6 +1389,11 @@ config ARM64_PAN instruction if the cpu does not implement the feature. config ARM64_LSE_ATOMICS + bool + default ARM64_USE_LSE_ATOMICS + depends on $(as-instr,.arch_extension lse) + +config ARM64_USE_LSE_ATOMICS bool "Atomic instructions" depends on JUMP_LABEL default y @@ -1485,6 +1515,30 @@ config ARM64_PTR_AUTH endmenu +menu "ARMv8.5 architectural features" + +config ARM64_E0PD + bool "Enable support for E0PD" + default y + help + E0PD (part of the ARMv8.5 extensions) allows us to ensure + that EL0 accesses made via TTBR1 always fault in constant time, + providing similar benefits to KASLR as those provided by KPTI, but + with lower overhead and without disrupting legitimate access to + kernel memory such as SPE. + + This option enables E0PD for TTBR1 where available. + +config ARCH_RANDOM + bool "Enable support for random number generation" + default y + help + Random number generation (part of the ARMv8.5 Extensions) + provides a high bandwidth, cryptographically secure + hardware random number generator. + +endmenu + config ARM64_SVE bool "ARM Scalable Vector Extension support" default y @@ -1545,7 +1599,7 @@ config ARM64_MODULE_PLTS config ARM64_PSEUDO_NMI bool "Support for NMI-like interrupts" - select CONFIG_ARM_GIC_V3 + select ARM_GIC_V3 help Adds support for mimicking Non-Maskable Interrupts through the use of GIC interrupt priority. This support requires version 3 or later of diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 1fbe24d4fdb6..dca1a97751ab 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -30,11 +30,8 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif endif -# Check for binutils support for specific extensions -lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1) - -ifeq ($(CONFIG_ARM64_LSE_ATOMICS), y) - ifeq ($(lseinstr),) +ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y) + ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y) $(warning LSE atomics not supported by binutils) endif endif @@ -45,19 +42,15 @@ cc_has_k_constraint := $(call try-run,echo \ return 0; \ }' | $(CC) -S -x c -o "$$TMP" -,,-DCONFIG_CC_HAS_K_CONSTRAINT=1) -ifeq ($(CONFIG_ARM64), y) -brokengasinst := $(call as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n,,-DCONFIG_BROKEN_GAS_INST=1) - - ifneq ($(brokengasinst),) +ifeq ($(CONFIG_BROKEN_GAS_INST),y) $(warning Detected assembler with broken .inst; disassembly will be unreliable) - endif endif -KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) \ +KBUILD_CFLAGS += -mgeneral-regs-only \ $(compat_vdso) $(cc_has_k_constraint) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += $(call cc-disable-warning, psabi) -KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) $(compat_vdso) +KBUILD_AFLAGS += $(compat_vdso) KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index 1f012c506434..cd3414898d10 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -16,7 +16,7 @@ OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S -targets := Image Image.gz +targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index b9f8d787eea9..324e7d5ab37e 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -35,13 +35,16 @@ void apply_alternatives_module(void *start, size_t length); static inline void apply_alternatives_module(void *start, size_t length) { } #endif -#define ALTINSTR_ENTRY(feature,cb) \ +#define ALTINSTR_ENTRY(feature) \ " .word 661b - .\n" /* label */ \ - " .if " __stringify(cb) " == 0\n" \ " .word 663f - .\n" /* new instruction */ \ - " .else\n" \ + " .hword " __stringify(feature) "\n" /* feature bit */ \ + " .byte 662b-661b\n" /* source len */ \ + " .byte 664f-663f\n" /* replacement len */ + +#define ALTINSTR_ENTRY_CB(feature, cb) \ + " .word 661b - .\n" /* label */ \ " .word " __stringify(cb) "- .\n" /* callback */ \ - " .endif\n" \ " .hword " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ @@ -62,15 +65,14 @@ static inline void apply_alternatives_module(void *start, size_t length) { } * * Alternatives with callbacks do not generate replacement instructions. */ -#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb) \ +#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature,cb) \ + ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - " .if " __stringify(cb) " == 0\n" \ ".pushsection .altinstr_replacement, \"a\"\n" \ "663:\n\t" \ newinstr "\n" \ @@ -78,17 +80,25 @@ static inline void apply_alternatives_module(void *start, size_t length) { } ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n" \ - ".else\n\t" \ + ".endif\n" + +#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ + ".if "__stringify(cfg_enabled)" == 1\n" \ + "661:\n\t" \ + oldinstr "\n" \ + "662:\n" \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY_CB(feature, cb) \ + ".popsection\n" \ "663:\n\t" \ "664:\n\t" \ - ".endif\n" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ - __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0) + __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) #define ALTERNATIVE_CB(oldinstr, cb) \ - __ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb) + __ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb) #else #include <asm/assembler.h> diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h new file mode 100644 index 000000000000..3fe02da70004 --- /dev/null +++ b/arch/arm64/include/asm/archrandom.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARCHRANDOM_H +#define _ASM_ARCHRANDOM_H + +#ifdef CONFIG_ARCH_RANDOM + +#include <linux/random.h> +#include <asm/cpufeature.h> + +static inline bool __arm64_rndr(unsigned long *v) +{ + bool ok; + + /* + * Reads of RNDR set PSTATE.NZCV to 0b0000 on success, + * and set PSTATE.NZCV to 0b0100 otherwise. + */ + asm volatile( + __mrs_s("%0", SYS_RNDR_EL0) "\n" + " cset %w1, ne\n" + : "=r" (*v), "=r" (ok) + : + : "cc"); + + return ok; +} + +static inline bool __must_check arch_get_random_long(unsigned long *v) +{ + return false; +} + +static inline bool __must_check arch_get_random_int(unsigned int *v) +{ + return false; +} + +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) +{ + /* + * Only support the generic interface after we have detected + * the system wide capability, avoiding complexity with the + * cpufeature code and with potential scheduling between CPUs + * with and without the feature. + */ + if (!cpus_have_const_cap(ARM64_HAS_RNG)) + return false; + + return __arm64_rndr(v); +} + + +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) +{ + unsigned long val; + bool ok = arch_get_random_seed_long(&val); + + *v = val; + return ok; +} + +static inline bool __init __early_cpu_has_rndr(void) +{ + /* Open code as we run prior to the first call to cpufeature. */ + unsigned long ftr = read_sysreg_s(SYS_ID_AA64ISAR0_EL1); + return (ftr >> ID_AA64ISAR0_RNDR_SHIFT) & 0xf; +} + +#else + +static inline bool __arm64_rndr(unsigned long *v) { return false; } +static inline bool __init __early_cpu_has_rndr(void) { return false; } + +#endif /* CONFIG_ARCH_RANDOM */ +#endif /* _ASM_ARCHRANDOM_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index b8cf7c85ffa2..524b3eaf200a 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -40,12 +40,6 @@ msr daif, \flags .endm - /* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */ - .macro inherit_daif, pstate:req, tmp:req - and \tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) - msr daif, \tmp - .endm - /* IRQ is the lowest priority flag, unconditionally unmask the rest. */ .macro enable_da_f msr daifclr, #(8 | 4 | 1) @@ -86,13 +80,6 @@ .endm /* - * SMP data memory barrier - */ - .macro smp_dmb, opt - dmb \opt - .endm - -/* * RAS Error Synchronization barrier */ .macro esb @@ -462,17 +449,6 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .endm /* - * Annotate a function as position independent, i.e., safe to be called before - * the kernel virtual mapping is activated. - */ -#define ENDPIPROC(x) \ - .globl __pi_##x; \ - .type __pi_##x, %function; \ - .set __pi_##x, x; \ - .size __pi_##x, . - x; \ - ENDPROC(x) - -/* * Annotate a function as being unsuitable for kprobes. */ #ifdef CONFIG_KPROBES diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 7b012148bfd6..13869b76b58c 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -12,7 +12,7 @@ #include <linux/stringify.h> -#if IS_ENABLED(CONFIG_ARM64_LSE_ATOMICS) && IS_ENABLED(CONFIG_AS_LSE) +#ifdef CONFIG_ARM64_LSE_ATOMICS #define __LL_SC_FALLBACK(asm_ops) \ " b 3f\n" \ " .subsection 1\n" \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 574808b9df4c..da3280f639cd 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -14,6 +14,7 @@ static inline void __lse_atomic_##op(int i, atomic_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " " #asm_op " %w[i], %[v]\n" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v)); \ @@ -30,6 +31,7 @@ ATOMIC_OP(add, stadd) static inline int __lse_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " " #asm_op #mb " %w[i], %w[i], %[v]" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v) \ @@ -58,6 +60,7 @@ static inline int __lse_atomic_add_return##name(int i, atomic_t *v) \ u32 tmp; \ \ asm volatile( \ + __LSE_PREAMBLE \ " ldadd" #mb " %w[i], %w[tmp], %[v]\n" \ " add %w[i], %w[i], %w[tmp]" \ : [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ @@ -77,6 +80,7 @@ ATOMIC_OP_ADD_RETURN( , al, "memory") static inline void __lse_atomic_and(int i, atomic_t *v) { asm volatile( + __LSE_PREAMBLE " mvn %w[i], %w[i]\n" " stclr %w[i], %[v]" : [i] "+&r" (i), [v] "+Q" (v->counter) @@ -87,6 +91,7 @@ static inline void __lse_atomic_and(int i, atomic_t *v) static inline int __lse_atomic_fetch_and##name(int i, atomic_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " mvn %w[i], %w[i]\n" \ " ldclr" #mb " %w[i], %w[i], %[v]" \ : [i] "+&r" (i), [v] "+Q" (v->counter) \ @@ -106,6 +111,7 @@ ATOMIC_FETCH_OP_AND( , al, "memory") static inline void __lse_atomic_sub(int i, atomic_t *v) { asm volatile( + __LSE_PREAMBLE " neg %w[i], %w[i]\n" " stadd %w[i], %[v]" : [i] "+&r" (i), [v] "+Q" (v->counter) @@ -118,6 +124,7 @@ static inline int __lse_atomic_sub_return##name(int i, atomic_t *v) \ u32 tmp; \ \ asm volatile( \ + __LSE_PREAMBLE \ " neg %w[i], %w[i]\n" \ " ldadd" #mb " %w[i], %w[tmp], %[v]\n" \ " add %w[i], %w[i], %w[tmp]" \ @@ -139,6 +146,7 @@ ATOMIC_OP_SUB_RETURN( , al, "memory") static inline int __lse_atomic_fetch_sub##name(int i, atomic_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " neg %w[i], %w[i]\n" \ " ldadd" #mb " %w[i], %w[i], %[v]" \ : [i] "+&r" (i), [v] "+Q" (v->counter) \ @@ -159,6 +167,7 @@ ATOMIC_FETCH_OP_SUB( , al, "memory") static inline void __lse_atomic64_##op(s64 i, atomic64_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " " #asm_op " %[i], %[v]\n" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v)); \ @@ -175,6 +184,7 @@ ATOMIC64_OP(add, stadd) static inline long __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v)\ { \ asm volatile( \ + __LSE_PREAMBLE \ " " #asm_op #mb " %[i], %[i], %[v]" \ : [i] "+r" (i), [v] "+Q" (v->counter) \ : "r" (v) \ @@ -203,6 +213,7 @@ static inline long __lse_atomic64_add_return##name(s64 i, atomic64_t *v)\ unsigned long tmp; \ \ asm volatile( \ + __LSE_PREAMBLE \ " ldadd" #mb " %[i], %x[tmp], %[v]\n" \ " add %[i], %[i], %x[tmp]" \ : [i] "+r" (i), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) \ @@ -222,6 +233,7 @@ ATOMIC64_OP_ADD_RETURN( , al, "memory") static inline void __lse_atomic64_and(s64 i, atomic64_t *v) { asm volatile( + __LSE_PREAMBLE " mvn %[i], %[i]\n" " stclr %[i], %[v]" : [i] "+&r" (i), [v] "+Q" (v->counter) @@ -232,6 +244,7 @@ static inline void __lse_atomic64_and(s64 i, atomic64_t *v) static inline long __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " mvn %[i], %[i]\n" \ " ldclr" #mb " %[i], %[i], %[v]" \ : [i] "+&r" (i), [v] "+Q" (v->counter) \ @@ -251,6 +264,7 @@ ATOMIC64_FETCH_OP_AND( , al, "memory") static inline void __lse_atomic64_sub(s64 i, atomic64_t *v) { asm volatile( + __LSE_PREAMBLE " neg %[i], %[i]\n" " stadd %[i], %[v]" : [i] "+&r" (i), [v] "+Q" (v->counter) @@ -263,6 +277,7 @@ static inline long __lse_atomic64_sub_return##name(s64 i, atomic64_t *v) \ unsigned long tmp; \ \ asm volatile( \ + __LSE_PREAMBLE \ " neg %[i], %[i]\n" \ " ldadd" #mb " %[i], %x[tmp], %[v]\n" \ " add %[i], %[i], %x[tmp]" \ @@ -284,6 +299,7 @@ ATOMIC64_OP_SUB_RETURN( , al, "memory") static inline long __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v) \ { \ asm volatile( \ + __LSE_PREAMBLE \ " neg %[i], %[i]\n" \ " ldadd" #mb " %[i], %[i], %[v]" \ : [i] "+&r" (i), [v] "+Q" (v->counter) \ @@ -305,6 +321,7 @@ static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) unsigned long tmp; asm volatile( + __LSE_PREAMBLE "1: ldr %x[tmp], %[v]\n" " subs %[ret], %x[tmp], #1\n" " b.lt 2f\n" @@ -332,6 +349,7 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ unsigned long tmp; \ \ asm volatile( \ + __LSE_PREAMBLE \ " mov %" #w "[tmp], %" #w "[old]\n" \ " cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n" \ " mov %" #w "[ret], %" #w "[tmp]" \ @@ -379,6 +397,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \ register unsigned long x4 asm ("x4") = (unsigned long)ptr; \ \ asm volatile( \ + __LSE_PREAMBLE \ " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\ " eor %[old1], %[old1], %[oldval1]\n" \ " eor %[old2], %[old2], %[oldval2]\n" \ diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index d064a50deb5f..8d2a7de39744 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -35,6 +35,9 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) } #define ip_fast_csum ip_fast_csum +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index d72d995b7e25..b4a40535a3d8 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -39,6 +39,7 @@ struct cpuinfo_arm64 { u32 reg_id_isar3; u32 reg_id_isar4; u32 reg_id_isar5; + u32 reg_id_isar6; u32 reg_id_mmfr0; u32 reg_id_mmfr1; u32 reg_id_mmfr2; diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index b92683871119..865e0253fc1e 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -44,7 +44,7 @@ #define ARM64_SSBS 34 #define ARM64_WORKAROUND_1418040 35 #define ARM64_HAS_SB 36 -#define ARM64_WORKAROUND_1165522 37 +#define ARM64_WORKAROUND_SPECULATIVE_AT_VHE 37 #define ARM64_HAS_ADDRESS_AUTH_ARCH 38 #define ARM64_HAS_ADDRESS_AUTH_IMP_DEF 39 #define ARM64_HAS_GENERIC_AUTH_ARCH 40 @@ -55,8 +55,10 @@ #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 #define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 #define ARM64_WORKAROUND_1542419 47 -#define ARM64_WORKAROUND_1319367 48 +#define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE 48 +#define ARM64_HAS_E0PD 49 +#define ARM64_HAS_RNG 50 -#define ARM64_NCAPS 49 +#define ARM64_NCAPS 51 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 4261d55e8506..92ef9539874a 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -613,6 +613,11 @@ static inline bool system_has_prio_mask_debugging(void) system_uses_irq_prio_masking(); } +static inline bool system_capabilities_finalized(void) +{ + return static_branch_likely(&arm64_const_caps_ready); +} + #define ARM64_BP_HARDEN_UNKNOWN -1 #define ARM64_BP_HARDEN_WA_NEEDED 0 #define ARM64_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index aca07c2f6e6e..a87a93f67671 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,8 @@ #define QCOM_CPU_PART_FALKOR_V1 0x800 #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 +#define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 #define NVIDIA_CPU_PART_DENVER 0x003 #define NVIDIA_CPU_PART_CARMEL 0x004 @@ -111,6 +113,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) +#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 72acd2db167f..ec213b4a1650 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -38,7 +38,7 @@ static inline void local_daif_mask(void) trace_hardirqs_off(); } -static inline unsigned long local_daif_save(void) +static inline unsigned long local_daif_save_flags(void) { unsigned long flags; @@ -50,6 +50,15 @@ static inline unsigned long local_daif_save(void) flags |= PSR_I_BIT; } + return flags; +} + +static inline unsigned long local_daif_save(void) +{ + unsigned long flags; + + flags = local_daif_save_flags(); + local_daif_mask(); return flags; diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 4d5f3b5f50cd..b87c6e276ab1 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -45,8 +45,8 @@ void do_sysinstr(unsigned int esr, struct pt_regs *regs); void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); void do_cp15instr(unsigned int esr, struct pt_regs *regs); -void el0_svc_handler(struct pt_regs *regs); -void el0_svc_compat_handler(struct pt_regs *regs); +void do_el0_svc(struct pt_regs *regs); +void do_el0_svc_compat(struct pt_regs *regs); void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, struct pt_regs *regs); diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 3d2f2472a36c..0f00265248b5 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -86,6 +86,14 @@ #define KERNEL_HWCAP_SVESM4 __khwcap2_feature(SVESM4) #define KERNEL_HWCAP_FLAGM2 __khwcap2_feature(FLAGM2) #define KERNEL_HWCAP_FRINT __khwcap2_feature(FRINT) +#define KERNEL_HWCAP_SVEI8MM __khwcap2_feature(SVEI8MM) +#define KERNEL_HWCAP_SVEF32MM __khwcap2_feature(SVEF32MM) +#define KERNEL_HWCAP_SVEF64MM __khwcap2_feature(SVEF64MM) +#define KERNEL_HWCAP_SVEBF16 __khwcap2_feature(SVEBF16) +#define KERNEL_HWCAP_I8MM __khwcap2_feature(I8MM) +#define KERNEL_HWCAP_BF16 __khwcap2_feature(BF16) +#define KERNEL_HWCAP_DGH __khwcap2_feature(DGH) +#define KERNEL_HWCAP_RNG __khwcap2_feature(RNG) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 12a561a54128..d24b527e8c00 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -96,6 +96,10 @@ static inline void crash_post_resume(void) {} struct kimage_arch { void *dtb; unsigned long dtb_mem; + /* Core ELF header buffer */ + void *elf_headers; + unsigned long elf_headers_mem; + unsigned long elf_headers_sz; }; extern const struct kexec_file_ops kexec_image_ops; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index c61260cf63c5..f5acdde17f3b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -547,7 +547,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, * wrong, and hyp will crash and burn when it uses any * cpus_have_const_cap() wrapper. */ - BUG_ON(!static_branch_likely(&arm64_const_caps_ready)); + BUG_ON(!system_capabilities_finalized()); __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2); /* @@ -571,7 +571,7 @@ static inline bool kvm_arch_requires_vhe(void) return true; /* Some implementations have defects that confine them to VHE */ - if (cpus_have_cap(ARM64_WORKAROUND_1165522)) + if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) return true; return false; diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 97f21cc66657..a3a6a2ba9a63 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -91,11 +91,11 @@ static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm) write_sysreg(kvm_get_vttbr(kvm), vttbr_el2); /* - * ARM erratum 1165522 requires the actual execution of the above - * before we can switch to the EL1/EL0 translation regime used by + * ARM errata 1165522 and 1530923 require the actual execution of the + * above before we can switch to the EL1/EL0 translation regime used by * the guest. */ - asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522)); + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE)); } #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 1b266292f0be..ebee3113a62f 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -4,4 +4,20 @@ #define __ALIGN .align 2 #define __ALIGN_STR ".align 2" +/* + * Annotate a function as position independent, i.e., safe to be called before + * the kernel virtual mapping is activated. + */ +#define SYM_FUNC_START_PI(x) \ + SYM_FUNC_START_ALIAS(__pi_##x); \ + SYM_FUNC_START(x) + +#define SYM_FUNC_START_WEAK_PI(x) \ + SYM_FUNC_START_ALIAS(__pi_##x); \ + SYM_FUNC_START_WEAK(x) + +#define SYM_FUNC_END_PI(x) \ + SYM_FUNC_END(x); \ + SYM_FUNC_END_ALIAS(__pi_##x) + #endif diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index 80b388278149..d429f7701c36 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -4,7 +4,9 @@ #include <asm/atomic_ll_sc.h> -#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) +#ifdef CONFIG_ARM64_LSE_ATOMICS + +#define __LSE_PREAMBLE ".arch armv8-a+lse\n" #include <linux/compiler_types.h> #include <linux/export.h> @@ -14,8 +16,6 @@ #include <asm/atomic_lse.h> #include <asm/cpucaps.h> -__asm__(".arch_extension lse"); - extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; @@ -34,9 +34,9 @@ static inline bool system_uses_lse_atomics(void) /* In-line patching at runtime */ #define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ - ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS) + ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS) -#else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ +#else /* CONFIG_ARM64_LSE_ATOMICS */ static inline bool system_uses_lse_atomics(void) { return false; } @@ -44,5 +44,5 @@ static inline bool system_uses_lse_atomics(void) { return false; } #define ARM64_LSE_ATOMIC_INSN(llsc, lse) llsc -#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ +#endif /* CONFIG_ARM64_LSE_ATOMICS */ #endif /* __ASM_LSE_H */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index f217e3292919..e4d862420bb4 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -29,52 +29,11 @@ typedef struct { */ #define ASID(mm) ((mm)->context.id.counter & 0xffff) -static inline bool arm64_kernel_unmapped_at_el0(void) -{ - return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && - cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0); -} +extern bool arm64_use_ng_mappings; -static inline bool arm64_kernel_use_ng_mappings(void) +static inline bool arm64_kernel_unmapped_at_el0(void) { - bool tx1_bug; - - /* What's a kpti? Use global mappings if we don't know. */ - if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) - return false; - - /* - * Note: this function is called before the CPU capabilities have - * been configured, so our early mappings will be global. If we - * later determine that kpti is required, then - * kpti_install_ng_mappings() will make them non-global. - */ - if (arm64_kernel_unmapped_at_el0()) - return true; - - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return false; - - /* - * KASLR is enabled so we're going to be enabling kpti on non-broken - * CPUs regardless of their susceptibility to Meltdown. Rather - * than force everybody to go through the G -> nG dance later on, - * just put down non-global mappings from the beginning. - */ - if (!IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { - tx1_bug = false; -#ifndef MODULE - } else if (!static_branch_likely(&arm64_const_caps_ready)) { - extern const struct midr_range cavium_erratum_27456_cpus[]; - - tx1_bug = is_midr_in_range_list(read_cpuid_id(), - cavium_erratum_27456_cpus); -#endif - } else { - tx1_bug = __cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456); - } - - return !tx1_bug && kaslr_offset() > 0; + return arm64_use_ng_mappings; } typedef void (*bp_hardening_cb_t)(void); @@ -128,6 +87,7 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); +extern bool kaslr_requires_kpti(void); #define INIT_MM_CONTEXT(name) \ .pgd = init_pg_dir, diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d9fbd433cc17..6bf5e650da78 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -110,6 +110,7 @@ #define PUD_TABLE_BIT (_AT(pudval_t, 1) << 1) #define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0) #define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0) +#define PUD_SECT_RDONLY (_AT(pudval_t, 1) << 7) /* AP[2] */ /* * Level 2 descriptor (PMD). @@ -292,6 +293,8 @@ #define TCR_HD (UL(1) << 40) #define TCR_NFD0 (UL(1) << 53) #define TCR_NFD1 (UL(1) << 54) +#define TCR_E0PD0 (UL(1) << 55) +#define TCR_E0PD1 (UL(1) << 56) /* * TTBR. diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index baf52baaa2a5..6f87839f0249 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -26,8 +26,8 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PTE_MAYBE_NG (arm64_kernel_use_ng_mappings() ? PTE_NG : 0) -#define PMD_MAYBE_NG (arm64_kernel_use_ng_mappings() ? PMD_SECT_NG : 0) +#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0) +#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0) #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 25a73aab438f..3994169985ef 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -8,7 +8,6 @@ #include <asm-generic/sections.h> extern char __alt_instructions[], __alt_instructions_end[]; -extern char __exception_text_start[], __exception_text_end[]; extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[]; extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; extern char __hyp_text_start[], __hyp_text_end[]; diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 7434844036d3..89cba2622b79 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -26,6 +26,8 @@ DECLARE_PER_CPU(bool, fpsimd_context_busy); static __must_check inline bool may_use_simd(void) { /* + * We must make sure that the SVE has been initialized properly + * before using the SIMD in kernel. * fpsimd_context_busy is only set while preemption is disabled, * and is clear whenever preemption is enabled. Since * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy @@ -33,8 +35,10 @@ static __must_check inline bool may_use_simd(void) * migrated, and if it's clear we cannot be migrated to a CPU * where it is set. */ - return !in_irq() && !irqs_disabled() && !in_nmi() && - !this_cpu_read(fpsimd_context_busy); + return !WARN_ON(!system_capabilities_finalized()) && + system_supports_fpsimd() && + !in_irq() && !irqs_disabled() && !in_nmi() && + !this_cpu_read(fpsimd_context_busy); } #else /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 6e919fafb43d..b91570ff9db1 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -146,6 +146,7 @@ #define SYS_ID_ISAR4_EL1 sys_reg(3, 0, 0, 2, 4) #define SYS_ID_ISAR5_EL1 sys_reg(3, 0, 0, 2, 5) #define SYS_ID_MMFR4_EL1 sys_reg(3, 0, 0, 2, 6) +#define SYS_ID_ISAR6_EL1 sys_reg(3, 0, 0, 2, 7) #define SYS_MVFR0_EL1 sys_reg(3, 0, 0, 3, 0) #define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1) @@ -365,6 +366,9 @@ #define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) #define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7) +#define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0) +#define SYS_RNDRRS_EL0 sys_reg(3, 3, 2, 4, 1) + #define SYS_PMCR_EL0 sys_reg(3, 3, 9, 12, 0) #define SYS_PMCNTENSET_EL0 sys_reg(3, 3, 9, 12, 1) #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) @@ -538,7 +542,20 @@ SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\ ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1) +/* MAIR_ELx memory attributes (used by Linux) */ +#define MAIR_ATTR_DEVICE_nGnRnE UL(0x00) +#define MAIR_ATTR_DEVICE_nGnRE UL(0x04) +#define MAIR_ATTR_DEVICE_GRE UL(0x0c) +#define MAIR_ATTR_NORMAL_NC UL(0x44) +#define MAIR_ATTR_NORMAL_WT UL(0xbb) +#define MAIR_ATTR_NORMAL UL(0xff) +#define MAIR_ATTR_MASK UL(0xff) + +/* Position the attr at the correct index */ +#define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8)) + /* id_aa64isar0 */ +#define ID_AA64ISAR0_RNDR_SHIFT 60 #define ID_AA64ISAR0_TS_SHIFT 52 #define ID_AA64ISAR0_FHM_SHIFT 48 #define ID_AA64ISAR0_DP_SHIFT 44 @@ -553,6 +570,10 @@ #define ID_AA64ISAR0_AES_SHIFT 4 /* id_aa64isar1 */ +#define ID_AA64ISAR1_I8MM_SHIFT 52 +#define ID_AA64ISAR1_DGH_SHIFT 48 +#define ID_AA64ISAR1_BF16_SHIFT 44 +#define ID_AA64ISAR1_SPECRES_SHIFT 40 #define ID_AA64ISAR1_SB_SHIFT 36 #define ID_AA64ISAR1_FRINTTS_SHIFT 32 #define ID_AA64ISAR1_GPI_SHIFT 28 @@ -605,12 +626,20 @@ #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 /* id_aa64zfr0 */ +#define ID_AA64ZFR0_F64MM_SHIFT 56 +#define ID_AA64ZFR0_F32MM_SHIFT 52 +#define ID_AA64ZFR0_I8MM_SHIFT 44 #define ID_AA64ZFR0_SM4_SHIFT 40 #define ID_AA64ZFR0_SHA3_SHIFT 32 +#define ID_AA64ZFR0_BF16_SHIFT 20 #define ID_AA64ZFR0_BITPERM_SHIFT 16 #define ID_AA64ZFR0_AES_SHIFT 4 #define ID_AA64ZFR0_SVEVER_SHIFT 0 +#define ID_AA64ZFR0_F64MM 0x1 +#define ID_AA64ZFR0_F32MM 0x1 +#define ID_AA64ZFR0_I8MM 0x1 +#define ID_AA64ZFR0_BF16 0x1 #define ID_AA64ZFR0_SM4 0x1 #define ID_AA64ZFR0_SHA3 0x1 #define ID_AA64ZFR0_BITPERM 0x1 @@ -655,6 +684,7 @@ #define ID_AA64MMFR1_VMIDBITS_16 2 /* id_aa64mmfr2 */ +#define ID_AA64MMFR2_E0PD_SHIFT 60 #define ID_AA64MMFR2_FWB_SHIFT 40 #define ID_AA64MMFR2_AT_SHIFT 32 #define ID_AA64MMFR2_LVA_SHIFT 16 @@ -679,6 +709,14 @@ #define ID_ISAR5_AES_SHIFT 4 #define ID_ISAR5_SEVL_SHIFT 0 +#define ID_ISAR6_I8MM_SHIFT 24 +#define ID_ISAR6_BF16_SHIFT 20 +#define ID_ISAR6_SPECRES_SHIFT 16 +#define ID_ISAR6_SB_SHIFT 12 +#define ID_ISAR6_FHM_SHIFT 8 +#define ID_ISAR6_DP_SHIFT 4 +#define ID_ISAR6_JSCVT_SHIFT 0 + #define MVFR0_FPROUND_SHIFT 28 #define MVFR0_FPSHVEC_SHIFT 24 #define MVFR0_FPSQRT_SHIFT 20 diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index a1e72886b30c..7752d93bb50f 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -65,5 +65,13 @@ #define HWCAP2_SVESM4 (1 << 6) #define HWCAP2_FLAGM2 (1 << 7) #define HWCAP2_FRINT (1 << 8) +#define HWCAP2_SVEI8MM (1 << 9) +#define HWCAP2_SVEF32MM (1 << 10) +#define HWCAP2_SVEF64MM (1 << 11) +#define HWCAP2_SVEBF16 (1 << 12) +#define HWCAP2_I8MM (1 << 13) +#define HWCAP2_BF16 (1 << 14) +#define HWCAP2_DGH (1 << 15) +#define HWCAP2_RNG (1 << 16) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 3a58e9db5cfe..a100483b47c4 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -274,7 +274,7 @@ int apei_claim_sea(struct pt_regs *regs) if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES)) return err; - current_flags = arch_local_save_flags(); + current_flags = local_daif_save_flags(); /* * SEA can interrupt SError, mask it and describe this as an NMI so diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index ca158be21f83..7832b3216370 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -618,7 +618,8 @@ static struct insn_emulation_ops setend_ops = { }; /* - * Invoked as late_initcall, since not needed before init spawned. + * Invoked as core_initcall, which guarantees that the instruction + * emulation is ready for userspace. */ static int __init armv8_deprecated_init(void) { diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 6ea337d464c4..32c7bf858dd9 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -42,11 +42,11 @@ ENTRY(__cpu_soft_restart) mov x0, #HVC_SOFT_RESTART hvc #0 // no return -1: mov x18, x1 // entry +1: mov x8, x1 // entry mov x0, x2 // arg0 mov x1, x3 // arg1 mov x2, x4 // arg2 - br x18 + br x8 ENDPROC(__cpu_soft_restart) .popsection diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 85f4bec22f6d..703ad0a84f99 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -548,6 +548,8 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; @@ -757,6 +759,20 @@ static const struct arm64_cpu_capabilities erratum_843419_list[] = { }; #endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE +static const struct midr_range erratum_speculative_at_vhe_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_1165522 + /* Cortex A76 r0p0 to r2p0 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), +#endif +#ifdef CONFIG_ARM64_ERRATUM_1530923 + /* Cortex A55 r0p0 to r2p0 */ + MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0), +#endif + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -883,12 +899,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), }, #endif -#ifdef CONFIG_ARM64_ERRATUM_1165522 +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE { - /* Cortex-A76 r0p0 to r2p0 */ - .desc = "ARM erratum 1165522", - .capability = ARM64_WORKAROUND_1165522, - ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), + .desc = "ARM errata 1165522, 1530923", + .capability = ARM64_WORKAROUND_SPECULATIVE_AT_VHE, + ERRATA_MIDR_RANGE_LIST(erratum_speculative_at_vhe_list), }, #endif #ifdef CONFIG_ARM64_ERRATUM_1463225 @@ -925,7 +940,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_ERRATUM_1319367 { .desc = "ARM erratum 1319367", - .capability = ARM64_WORKAROUND_1319367, + .capability = ARM64_WORKAROUND_SPECULATIVE_AT_NVHE, ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 04cf64e9f0c9..0b6715625cf6 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -32,9 +32,7 @@ static unsigned long elf_hwcap __read_mostly; #define COMPAT_ELF_HWCAP_DEFAULT \ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ - COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ - COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\ COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; @@ -47,19 +45,23 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM6 /* Need also bit for ARM64_CB_PATCH */ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); +bool arm64_use_ng_mappings = false; +EXPORT_SYMBOL(arm64_use_ng_mappings); + /* * Flag to indicate if we have computed the system wide * capabilities based on the boot time active CPUs. This * will be used to determine if a new booting CPU should * go through the verification process to make sure that it * supports the system capabilities, without using a hotplug - * notifier. + * notifier. This is also used to decide if we could use + * the fast path for checking constant CPU caps. */ -static bool sys_caps_initialised; - -static inline void set_sys_caps_initialised(void) +DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); +EXPORT_SYMBOL(arm64_const_caps_ready); +static inline void finalize_system_capabilities(void) { - sys_caps_initialised = true; + static_branch_enable(&arm64_const_caps_ready); } static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p) @@ -119,6 +121,7 @@ static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RNDR_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), @@ -135,6 +138,10 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DGH_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SPECRES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), @@ -177,10 +184,18 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F64MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F32MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), @@ -225,6 +240,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0), @@ -313,6 +329,17 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_isar6[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SPECRES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_FHM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_JSCVT_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* State3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), /* State2 */ @@ -396,6 +423,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5), ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4), + ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), @@ -600,6 +628,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3); init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4); init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5); + init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6); init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0); init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1); init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2); @@ -753,6 +782,8 @@ void update_cpu_features(int cpu, info->reg_id_isar4, boot->reg_id_isar4); taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu, info->reg_id_isar5, boot->reg_id_isar5); + taint |= check_update_ftr_reg(SYS_ID_ISAR6_EL1, cpu, + info->reg_id_isar6, boot->reg_id_isar6); /* * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and @@ -785,7 +816,7 @@ void update_cpu_features(int cpu, /* Probe vector lengths, unless we already gave up on SVE */ if (id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) && - !sys_caps_initialised) + !system_capabilities_finalized()) sve_update_vq_map(); } @@ -831,6 +862,7 @@ static u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_ISAR3_EL1); read_sysreg_case(SYS_ID_ISAR4_EL1); read_sysreg_case(SYS_ID_ISAR5_EL1); + read_sysreg_case(SYS_ID_ISAR6_EL1); read_sysreg_case(SYS_MVFR0_EL1); read_sysreg_case(SYS_MVFR1_EL1); read_sysreg_case(SYS_MVFR2_EL1); @@ -965,6 +997,46 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) return has_cpuid_feature(entry, scope); } +/* + * This check is triggered during the early boot before the cpufeature + * is initialised. Checking the status on the local CPU allows the boot + * CPU to detect the need for non-global mappings and thus avoiding a + * pagetable re-write after all the CPUs are booted. This check will be + * anyway run on individual CPUs, allowing us to get the consistent + * state once the SMP CPUs are up and thus make the switch to non-global + * mappings if required. + */ +bool kaslr_requires_kpti(void) +{ + if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + return false; + + /* + * E0PD does a similar job to KPTI so can be used instead + * where available. + */ + if (IS_ENABLED(CONFIG_ARM64_E0PD)) { + u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + if (cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_E0PD_SHIFT)) + return false; + } + + /* + * Systems affected by Cavium erratum 24756 are incompatible + * with KPTI. + */ + if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { + extern const struct midr_range cavium_erratum_27456_cpus[]; + + if (is_midr_in_range_list(read_cpuid_id(), + cavium_erratum_27456_cpus)) + return false; + } + + return kaslr_offset() > 0; +} + static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ @@ -975,6 +1047,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, static const struct midr_range kpti_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), @@ -1008,7 +1081,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } /* Useful for KASLR robustness */ - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) { + if (kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; @@ -1043,7 +1116,6 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) extern kpti_remap_fn idmap_kpti_install_ng_mappings; kpti_remap_fn *remap_fn; - static bool kpti_applied = false; int cpu = smp_processor_id(); /* @@ -1051,7 +1123,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) * it already or we have KASLR enabled and therefore have not * created any global mappings at all. */ - if (kpti_applied || kaslr_offset() > 0) + if (arm64_use_ng_mappings) return; remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); @@ -1061,7 +1133,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) cpu_uninstall_idmap(); if (!cpu) - kpti_applied = true; + arm64_use_ng_mappings = true; return; } @@ -1251,6 +1323,14 @@ static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_PTR_AUTH */ +#ifdef CONFIG_ARM64_E0PD +static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap) +{ + if (this_cpu_has_cap(ARM64_HAS_E0PD)) + sysreg_clear_set(tcr_el1, 0, TCR_E0PD1); +} +#endif /* CONFIG_ARM64_E0PD */ + #ifdef CONFIG_ARM64_PSEUDO_NMI static bool enable_pseudo_nmi; @@ -1291,7 +1371,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_enable_pan, }, #endif /* CONFIG_ARM64_PAN */ -#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) +#ifdef CONFIG_ARM64_LSE_ATOMICS { .desc = "LSE atomic instructions", .capability = ARM64_HAS_LSE_ATOMICS, @@ -1302,7 +1382,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sign = FTR_UNSIGNED, .min_field_value = 2, }, -#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ +#endif /* CONFIG_ARM64_LSE_ATOMICS */ { .desc = "Software prefetching using PRFM", .capability = ARM64_HAS_NO_HW_PREFETCH, @@ -1368,7 +1448,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { /* FP/SIMD is not implemented */ .capability = ARM64_HAS_NO_FPSIMD, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, .min_field_value = 0, .matches = has_no_fpsimd, }, @@ -1567,6 +1647,31 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = 1, }, #endif +#ifdef CONFIG_ARM64_E0PD + { + .desc = "E0PD", + .capability = ARM64_HAS_E0PD, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64MMFR2_E0PD_SHIFT, + .matches = has_cpuid_feature, + .min_field_value = 1, + .cpu_enable = cpu_enable_e0pd, + }, +#endif +#ifdef CONFIG_ARCH_RANDOM + { + .desc = "Random Number Generator", + .capability = ARM64_HAS_RNG, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64ISAR0_EL1, + .field_pos = ID_AA64ISAR0_RNDR_SHIFT, + .sign = FTR_UNSIGNED, + .min_field_value = 1, + }, +#endif {}, }; @@ -1596,6 +1701,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .match_list = list, \ } +#define HWCAP_CAP_MATCH(match, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -1638,6 +1749,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -1651,6 +1763,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM), HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), @@ -1658,8 +1773,12 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BF16_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BF16, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_I8MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_I8MM, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F32MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F32MM, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_PTR_AUTH @@ -1669,8 +1788,35 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { {}, }; +#ifdef CONFIG_COMPAT +static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope) +{ + /* + * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available, + * in line with that of arm32 as in vfp_init(). We make sure that the + * check is future proof, by making sure value is non-zero. + */ + u32 mvfr1; + + WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); + if (scope == SCOPE_SYSTEM) + mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1); + else + mvfr1 = read_sysreg_s(SYS_MVFR1_EL1); + + return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT); +} +#endif + static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { #ifdef CONFIG_COMPAT + HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), + /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), @@ -1974,7 +2120,7 @@ void check_local_cpu_capabilities(void) * Otherwise, this CPU should verify that it has all the system * advertised capabilities. */ - if (!sys_caps_initialised) + if (!system_capabilities_finalized()) update_cpu_capabilities(SCOPE_LOCAL_CPU); else verify_local_cpu_capabilities(); @@ -1988,14 +2134,6 @@ static void __init setup_boot_cpu_capabilities(void) enable_cpu_capabilities(SCOPE_BOOT_CPU); } -DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); -EXPORT_SYMBOL(arm64_const_caps_ready); - -static void __init mark_const_caps_ready(void) -{ - static_branch_enable(&arm64_const_caps_ready); -} - bool this_cpu_has_cap(unsigned int n) { if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { @@ -2054,7 +2192,6 @@ void __init setup_cpu_features(void) u32 cwg; setup_system_capabilities(); - mark_const_caps_ready(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) @@ -2067,7 +2204,7 @@ void __init setup_cpu_features(void) minsigstksz_setup(); /* Advertise that we have computed the system capabilities */ - set_sys_caps_initialised(); + finalize_system_capabilities(); /* * Check for sane CTR_EL0.CWG value. diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 56bba746da1c..86136075ae41 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -84,6 +84,14 @@ static const char *const hwcap_str[] = { "svesm4", "flagm2", "frint", + "svei8mm", + "svef32mm", + "svef64mm", + "svebf16", + "i8mm", + "bf16", + "dgh", + "rng", NULL }; @@ -360,6 +368,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1); info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1); info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1); + info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1); info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1); info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1); info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 5dce5e56995a..fde59981445c 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -36,14 +36,14 @@ static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) } NOKPROBE_SYMBOL(el1_pc); -static void el1_undef(struct pt_regs *regs) +static void notrace el1_undef(struct pt_regs *regs) { local_daif_inherit(regs); do_undefinstr(regs); } NOKPROBE_SYMBOL(el1_undef); -static void el1_inv(struct pt_regs *regs, unsigned long esr) +static void notrace el1_inv(struct pt_regs *regs, unsigned long esr) { local_daif_inherit(regs); bad_mode(regs, 0, esr); @@ -215,7 +215,7 @@ static void notrace el0_svc(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - el0_svc_handler(regs); + do_el0_svc(regs); } NOKPROBE_SYMBOL(el0_svc); @@ -281,7 +281,7 @@ static void notrace el0_svc_compat(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - el0_svc_compat_handler(regs); + do_el0_svc_compat(regs); } NOKPROBE_SYMBOL(el0_svc_compat); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7c6a0a41676f..1b6b7a86625c 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -60,16 +60,16 @@ .macro kernel_ventry, el, label, regsize = 64 .align 7 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -alternative_if ARM64_UNMAP_KERNEL_AT_EL0 .if \el == 0 +alternative_if ARM64_UNMAP_KERNEL_AT_EL0 .if \regsize == 64 mrs x30, tpidrro_el0 msr tpidrro_el0, xzr .else mov x30, xzr .endif - .endif alternative_else_nop_endif + .endif #endif sub sp, sp, #S_FRAME_SIZE @@ -167,9 +167,13 @@ alternative_cb_end .if \el == 0 clear_gp_regs mrs x21, sp_el0 - ldr_this_cpu tsk, __entry_task, x20 // Ensure MDSCR_EL1.SS is clear, - ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug - disable_step_tsk x19, x20 // exceptions when scheduling. + ldr_this_cpu tsk, __entry_task, x20 + msr sp_el0, tsk + + // Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions + // when scheduling. + ldr x19, [tsk, #TSK_TI_FLAGS] + disable_step_tsk x19, x20 apply_ssbd 1, x22, x23 @@ -232,13 +236,6 @@ alternative_else_nop_endif str w21, [sp, #S_SYSCALLNO] .endif - /* - * Set sp_el0 to current thread_info. - */ - .if \el == 0 - msr sp_el0, tsk - .endif - /* Save pmr */ alternative_if ARM64_HAS_IRQ_PRIO_MASKING mrs_s x20, SYS_ICC_PMR_EL1 @@ -653,6 +650,7 @@ el0_sync: mov x0, sp bl el0_sync_handler b ret_to_user +ENDPROC(el0_sync) #ifdef CONFIG_COMPAT .align 6 @@ -661,16 +659,18 @@ el0_sync_compat: mov x0, sp bl el0_sync_compat_handler b ret_to_user -ENDPROC(el0_sync) +ENDPROC(el0_sync_compat) .align 6 el0_irq_compat: kernel_entry 0, 32 b el0_irq_naked +ENDPROC(el0_irq_compat) el0_error_compat: kernel_entry 0, 32 b el0_error_naked +ENDPROC(el0_error_compat) #endif .align 6 diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 3eb338f14386..94289d126993 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -269,6 +269,7 @@ static void sve_free(struct task_struct *task) */ static void task_fpsimd_load(void) { + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); if (system_supports_sve() && test_thread_flag(TIF_SVE)) @@ -289,6 +290,7 @@ static void fpsimd_save(void) this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { @@ -1092,6 +1094,7 @@ void fpsimd_bind_task_to_cpu(void) struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); + WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sve_vl = current->thread.sve_vl; @@ -1114,6 +1117,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); + WARN_ON(!system_supports_fpsimd()); WARN_ON(!in_softirq() && !irqs_disabled()); last->st = st; @@ -1128,8 +1132,19 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, */ void fpsimd_restore_current_state(void) { - if (!system_supports_fpsimd()) + /* + * For the tasks that were created before we detected the absence of + * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(), + * e.g, init. This could be then inherited by the children processes. + * If we later detect that the system doesn't support FP/SIMD, + * we must clear the flag for all the tasks to indicate that the + * FPSTATE is clean (as we can't have one) to avoid looping for ever in + * do_notify_resume(). + */ + if (!system_supports_fpsimd()) { + clear_thread_flag(TIF_FOREIGN_FPSTATE); return; + } get_cpu_fpsimd_context(); @@ -1148,7 +1163,7 @@ void fpsimd_restore_current_state(void) */ void fpsimd_update_current_state(struct user_fpsimd_state const *state) { - if (!system_supports_fpsimd()) + if (WARN_ON(!system_supports_fpsimd())) return; get_cpu_fpsimd_context(); @@ -1179,7 +1194,13 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) void fpsimd_flush_task_state(struct task_struct *t) { t->thread.fpsimd_cpu = NR_CPUS; - + /* + * If we don't support fpsimd, bail out after we have + * reset the fpsimd_cpu for this task and clear the + * FPSTATE. + */ + if (!system_supports_fpsimd()) + return; barrier(); set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE); @@ -1193,6 +1214,7 @@ void fpsimd_flush_task_state(struct task_struct *t) */ static void fpsimd_flush_cpu_state(void) { + WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -1203,6 +1225,8 @@ static void fpsimd_flush_cpu_state(void) */ void fpsimd_save_and_flush_cpu_state(void) { + if (!system_supports_fpsimd()) + return; WARN_ON(preemptible()); __get_cpu_fpsimd_context(); fpsimd_save(); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index a96b2921d22c..590963c9c609 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -182,78 +182,79 @@ int arch_hibernation_header_restore(void *addr) } EXPORT_SYMBOL(arch_hibernation_header_restore); -/* - * Copies length bytes, starting at src_start into an new page, - * perform cache maintentance, then maps it at the specified address low - * address as executable. - * - * This is used by hibernate to copy the code it needs to execute when - * overwriting the kernel text. This function generates a new set of page - * tables, which it loads into ttbr0. - * - * Length is provided as we probably only want 4K of data, even on a 64K - * page system. - */ -static int create_safe_exec_page(void *src_start, size_t length, - unsigned long dst_addr, - phys_addr_t *phys_dst_addr, - void *(*allocator)(gfp_t mask), - gfp_t mask) +static int trans_pgd_map_page(pgd_t *trans_pgd, void *page, + unsigned long dst_addr, + pgprot_t pgprot) { - int rc = 0; - pgd_t *trans_pgd; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; - unsigned long dst = (unsigned long)allocator(mask); - - if (!dst) { - rc = -ENOMEM; - goto out; - } - - memcpy((void *)dst, src_start, length); - __flush_icache_range(dst, dst + length); - - trans_pgd = allocator(mask); - if (!trans_pgd) { - rc = -ENOMEM; - goto out; - } pgdp = pgd_offset_raw(trans_pgd, dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { - pudp = allocator(mask); - if (!pudp) { - rc = -ENOMEM; - goto out; - } + pudp = (void *)get_safe_page(GFP_ATOMIC); + if (!pudp) + return -ENOMEM; pgd_populate(&init_mm, pgdp, pudp); } pudp = pud_offset(pgdp, dst_addr); if (pud_none(READ_ONCE(*pudp))) { - pmdp = allocator(mask); - if (!pmdp) { - rc = -ENOMEM; - goto out; - } + pmdp = (void *)get_safe_page(GFP_ATOMIC); + if (!pmdp) + return -ENOMEM; pud_populate(&init_mm, pudp, pmdp); } pmdp = pmd_offset(pudp, dst_addr); if (pmd_none(READ_ONCE(*pmdp))) { - ptep = allocator(mask); - if (!ptep) { - rc = -ENOMEM; - goto out; - } + ptep = (void *)get_safe_page(GFP_ATOMIC); + if (!ptep) + return -ENOMEM; pmd_populate_kernel(&init_mm, pmdp, ptep); } ptep = pte_offset_kernel(pmdp, dst_addr); - set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC)); + + return 0; +} + +/* + * Copies length bytes, starting at src_start into an new page, + * perform cache maintenance, then maps it at the specified address low + * address as executable. + * + * This is used by hibernate to copy the code it needs to execute when + * overwriting the kernel text. This function generates a new set of page + * tables, which it loads into ttbr0. + * + * Length is provided as we probably only want 4K of data, even on a 64K + * page system. + */ +static int create_safe_exec_page(void *src_start, size_t length, + unsigned long dst_addr, + phys_addr_t *phys_dst_addr) +{ + void *page = (void *)get_safe_page(GFP_ATOMIC); + pgd_t *trans_pgd; + int rc; + + if (!page) + return -ENOMEM; + + memcpy(page, src_start, length); + __flush_icache_range((unsigned long)page, (unsigned long)page + length); + + trans_pgd = (void *)get_safe_page(GFP_ATOMIC); + if (!trans_pgd) + return -ENOMEM; + + rc = trans_pgd_map_page(trans_pgd, page, dst_addr, + PAGE_KERNEL_EXEC); + if (rc) + return rc; /* * Load our new page tables. A strict BBM approach requires that we @@ -269,13 +270,12 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(trans_pgd)), ttbr0_el1); isb(); - *phys_dst_addr = virt_to_phys((void *)dst); + *phys_dst_addr = virt_to_phys(page); -out: - return rc; + return 0; } #define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start)) @@ -450,7 +450,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, return -ENOMEM; } else { set_pud(dst_pudp, - __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); + __pud(pud_val(pud) & ~PUD_SECT_RDONLY)); } } while (dst_pudp++, src_pudp++, addr = next, addr != end); @@ -476,6 +476,24 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, return 0; } +static int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start, + unsigned long end) +{ + int rc; + pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC); + + if (!trans_pgd) { + pr_err("Failed to allocate memory for temporary page tables.\n"); + return -ENOMEM; + } + + rc = copy_page_tables(trans_pgd, start, end); + if (!rc) + *dst_pgdp = trans_pgd; + + return rc; +} + /* * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit(). * @@ -484,7 +502,7 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, */ int swsusp_arch_resume(void) { - int rc = 0; + int rc; void *zero_page; size_t exit_size; pgd_t *tmp_pg_dir; @@ -497,15 +515,9 @@ int swsusp_arch_resume(void) * Create a second copy of just the linear map, and use this when * restoring. */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables.\n"); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END); + rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END); if (rc) - goto out; + return rc; /* * We need a zero page that is zero before & after resume in order to @@ -514,8 +526,7 @@ int swsusp_arch_resume(void) zero_page = (void *)get_safe_page(GFP_ATOMIC); if (!zero_page) { pr_err("Failed to allocate zero page.\n"); - rc = -ENOMEM; - goto out; + return -ENOMEM; } /* @@ -530,11 +541,10 @@ int swsusp_arch_resume(void) */ rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size, (unsigned long)hibernate_exit, - &phys_hibernate_exit, - (void *)get_safe_page, GFP_ATOMIC); + &phys_hibernate_exit); if (rc) { pr_err("Failed to create safe executable page for hibernate_exit code.\n"); - goto out; + return rc; } /* @@ -561,8 +571,7 @@ int swsusp_arch_resume(void) resume_hdr.reenter_kernel, restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); -out: - return rc; + return 0; } int hibernate_resume_nonboot_cpu_disable(void) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 2a11a962e571..53b8a4ee64ff 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -120,6 +120,17 @@ u64 __init kaslr_early_init(u64 dt_phys) return 0; } + /* + * Mix in any entropy obtainable architecturally, open coded + * since this runs extremely early. + */ + if (__early_cpu_has_rndr()) { + unsigned long raw; + + if (__arm64_rndr(&raw)) + seed ^= raw; + } + if (!seed) { kaslr_status = KASLR_DISABLED_NO_SEED; return 0; diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 29a9428486a5..af9987c154ca 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -47,10 +47,6 @@ static void *image_load(struct kimage *image, struct kexec_segment *kernel_segment; int ret; - /* We don't support crash kernels yet. */ - if (image->type == KEXEC_TYPE_CRASH) - return ERR_PTR(-EOPNOTSUPP); - /* * We require a kernel with an unambiguous Image header. Per * Documentation/arm64/booting.rst, this is the case when image_size diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 0df8493624e0..8e9c924423b4 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -160,18 +160,6 @@ void machine_kexec(struct kimage *kimage) kexec_image_info(kimage); - pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, - kimage->control_code_page); - pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, - &reboot_code_buffer_phys); - pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, - reboot_code_buffer); - pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, - arm64_relocate_new_kernel); - pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", - __func__, __LINE__, arm64_relocate_new_kernel_size, - arm64_relocate_new_kernel_size); - /* * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use * after the kernel is shut down. diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 7b08bf9499b6..dd3ae8081b38 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -17,12 +17,15 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/random.h> +#include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> #include <linux/vmalloc.h> #include <asm/byteorder.h> /* relevant device tree properties */ +#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr" +#define FDT_PROP_MEM_RANGE "linux,usable-memory-range" #define FDT_PROP_INITRD_START "linux,initrd-start" #define FDT_PROP_INITRD_END "linux,initrd-end" #define FDT_PROP_BOOTARGS "bootargs" @@ -40,6 +43,10 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) vfree(image->arch.dtb); image->arch.dtb = NULL; + vfree(image->arch.elf_headers); + image->arch.elf_headers = NULL; + image->arch.elf_headers_sz = 0; + return kexec_image_post_load_cleanup_default(image); } @@ -55,6 +62,31 @@ static int setup_dtb(struct kimage *image, off = ret; + ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + /* add linux,elfcorehdr */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_KEXEC_ELFHDR, + image->arch.elf_headers_mem, + image->arch.elf_headers_sz); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + + /* add linux,usable-memory-range */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_MEM_RANGE, + crashk_res.start, + crashk_res.end - crashk_res.start + 1); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + } + /* add bootargs */ if (cmdline) { ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline); @@ -125,8 +157,8 @@ out: } /* - * More space needed so that we can add initrd, bootargs, kaslr-seed, and - * rng-seed. + * More space needed so that we can add initrd, bootargs, kaslr-seed, + * rng-seed, userable-memory-range and elfcorehdr. */ #define DTB_EXTRA_SPACE 0x1000 @@ -174,6 +206,43 @@ static int create_dtb(struct kimage *image, } } +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + u64 i; + phys_addr_t start, end; + + nr_ranges = 1; /* for exclusion of crashkernel region */ + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) + nr_ranges++; + + cmem = kmalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + cmem->ranges[cmem->nr_ranges].start = start; + cmem->ranges[cmem->nr_ranges].end = end - 1; + cmem->nr_ranges++; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + + kfree(cmem); + return ret; +} + int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, @@ -181,14 +250,43 @@ int load_other_segments(struct kimage *image, char *cmdline) { struct kexec_buf kbuf; - void *dtb = NULL; - unsigned long initrd_load_addr = 0, dtb_len; + void *headers, *dtb = NULL; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len; int ret = 0; kbuf.image = image; /* not allocate anything below the kernel */ kbuf.buf_min = kernel_load_addr + kernel_size; + /* load elf core header */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out_err; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = SZ_64K; /* largest supported page size */ + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out_err; + } + image->arch.elf_headers = headers; + image->arch.elf_headers_mem = kbuf.mem; + image->arch.elf_headers_sz = headers_sz; + + pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->arch.elf_headers_mem, headers_sz, headers_sz); + } + /* load initrd */ if (initrd) { kbuf.buffer = initrd; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index d54586d5b031..bbb0f0c145f6 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -646,6 +646,6 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void) * Only allow a task to be preempted once cpufeatures have been * enabled. */ - if (static_branch_likely(&arm64_const_caps_ready)) + if (system_capabilities_finalized()) preempt_schedule_irq(); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6771c399d40c..cd6e5fa48b9c 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -615,6 +615,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, return 0; } +static int fpr_active(struct task_struct *target, const struct user_regset *regset) +{ + if (!system_supports_fpsimd()) + return -ENODEV; + return regset->n; +} + /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ @@ -637,6 +644,9 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + if (!system_supports_fpsimd()) + return -EINVAL; + if (target == current) fpsimd_preserve_current_state(); @@ -676,6 +686,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, { int ret; + if (!system_supports_fpsimd()) + return -EINVAL; + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; @@ -1134,6 +1147,7 @@ static const struct user_regset aarch64_regsets[] = { */ .size = sizeof(u32), .align = sizeof(u32), + .active = fpr_active, .get = fpr_get, .set = fpr_set }, @@ -1348,6 +1362,9 @@ static int compat_vfp_get(struct task_struct *target, compat_ulong_t fpscr; int ret, vregs_end_pos; + if (!system_supports_fpsimd()) + return -EINVAL; + uregs = &target->thread.uw.fpsimd_state; if (target == current) @@ -1381,6 +1398,9 @@ static int compat_vfp_set(struct task_struct *target, compat_ulong_t fpscr; int ret, vregs_end_pos; + if (!system_supports_fpsimd()) + return -EINVAL; + uregs = &target->thread.uw.fpsimd_state; vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t); @@ -1438,6 +1458,7 @@ static const struct user_regset aarch32_regsets[] = { .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), + .active = fpr_active, .get = compat_vfp_get, .set = compat_vfp_set }, diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 56f664561754..b6f9455d7ca3 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -285,6 +285,13 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; + /* + * If know now we are going to need KPTI then use non-global + * mappings from the start, avoiding the cost of rewriting + * everything later. + */ + arm64_use_ng_mappings = kaslr_requires_kpti(); + early_fixmap_init(); early_ioremap_init(); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index dd2cdc0d5be2..339882db5a91 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -371,6 +371,8 @@ static int parse_user_sigframe(struct user_ctxs *user, goto done; case FPSIMD_MAGIC: + if (!system_supports_fpsimd()) + goto invalid; if (user->fpsimd) goto invalid; @@ -506,7 +508,7 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0) err = parse_user_sigframe(&user, sf); - if (err == 0) { + if (err == 0 && system_supports_fpsimd()) { if (!user.fpsimd) return -EINVAL; @@ -623,7 +625,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); - if (err == 0) { + if (err == 0 && system_supports_fpsimd()) { struct fpsimd_context __user *fpsimd_ctx = apply_user_offset(user, user->fpsimd_offset); err |= preserve_fpsimd_context(fpsimd_ctx); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 12a585386c2f..82feca6f7052 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -223,7 +223,7 @@ static int compat_restore_sigframe(struct pt_regs *regs, err |= !valid_user_regs(®s->user_regs, current); aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; - if (err == 0) + if (err == 0 && system_supports_fpsimd()) err |= compat_restore_vfp_context(&aux->vfp); return err; @@ -419,7 +419,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf, aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; - if (err == 0) + if (err == 0 && system_supports_fpsimd()) err |= compat_preserve_vfp_context(&aux->vfp); __put_user_error(0, &aux->end_magic, err); diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c index 52cfc6148355..b26955f56750 100644 --- a/arch/arm64/kernel/ssbd.c +++ b/arch/arm64/kernel/ssbd.c @@ -37,7 +37,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) /* Unsupported */ if (state == ARM64_SSBD_UNKNOWN) - return -EINVAL; + return -ENODEV; /* Treat the unaffected/mitigated state separately */ if (state == ARM64_SSBD_MITIGATED) { @@ -102,7 +102,7 @@ static int ssbd_prctl_get(struct task_struct *task) { switch (arm64_get_ssbd_state()) { case ARM64_SSBD_UNKNOWN: - return -EINVAL; + return -ENODEV; case ARM64_SSBD_FORCE_ENABLE: return PR_SPEC_DISABLE; case ARM64_SSBD_KERNEL: diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a9d98a443fc..a12c0c88d345 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -void el0_svc_handler(struct pt_regs *regs) +void do_el0_svc(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -void el0_svc_compat_handler(struct pt_regs *regs) +void do_el0_svc_compat(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index e5cc8d66bf53..0c6832ec52b1 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -22,7 +22,12 @@ .text .pushsection .hyp.text, "ax" +/* + * We treat x18 as callee-saved as the host may use it as a platform + * register (e.g. for shadow call stack). + */ .macro save_callee_saved_regs ctxt + str x18, [\ctxt, #CPU_XREG_OFFSET(18)] stp x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)] stp x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)] stp x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)] @@ -32,6 +37,8 @@ .endm .macro restore_callee_saved_regs ctxt + // We require \ctxt is not x18-x28 + ldr x18, [\ctxt, #CPU_XREG_OFFSET(18)] ldp x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)] ldp x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)] ldp x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)] @@ -48,7 +55,7 @@ ENTRY(__guest_enter) // x0: vcpu // x1: host context // x2-x17: clobbered by macros - // x18: guest context + // x29: guest context // Store the host regs save_callee_saved_regs x1 @@ -67,31 +74,28 @@ alternative_else_nop_endif ret 1: - add x18, x0, #VCPU_CONTEXT + add x29, x0, #VCPU_CONTEXT // Macro ptrauth_switch_to_guest format: // ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3) // The below macro to restore guest keys is not implemented in C code // as it may cause Pointer Authentication key signing mismatch errors // when this feature is enabled for kernel code. - ptrauth_switch_to_guest x18, x0, x1, x2 + ptrauth_switch_to_guest x29, x0, x1, x2 // Restore guest regs x0-x17 - ldp x0, x1, [x18, #CPU_XREG_OFFSET(0)] - ldp x2, x3, [x18, #CPU_XREG_OFFSET(2)] - ldp x4, x5, [x18, #CPU_XREG_OFFSET(4)] - ldp x6, x7, [x18, #CPU_XREG_OFFSET(6)] - ldp x8, x9, [x18, #CPU_XREG_OFFSET(8)] - ldp x10, x11, [x18, #CPU_XREG_OFFSET(10)] - ldp x12, x13, [x18, #CPU_XREG_OFFSET(12)] - ldp x14, x15, [x18, #CPU_XREG_OFFSET(14)] - ldp x16, x17, [x18, #CPU_XREG_OFFSET(16)] - - // Restore guest regs x19-x29, lr - restore_callee_saved_regs x18 - - // Restore guest reg x18 - ldr x18, [x18, #CPU_XREG_OFFSET(18)] + ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x29, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x29, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x29, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x29, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x29, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x29, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x29, #CPU_XREG_OFFSET(16)] + + // Restore guest regs x18-x29, lr + restore_callee_saved_regs x29 // Do not touch any register after this! eret @@ -114,7 +118,7 @@ ENTRY(__guest_exit) // Retrieve the guest regs x0-x1 from the stack ldp x2, x3, [sp], #16 // x0, x1 - // Store the guest regs x0-x1 and x4-x18 + // Store the guest regs x0-x1 and x4-x17 stp x2, x3, [x1, #CPU_XREG_OFFSET(0)] stp x4, x5, [x1, #CPU_XREG_OFFSET(4)] stp x6, x7, [x1, #CPU_XREG_OFFSET(6)] @@ -123,9 +127,8 @@ ENTRY(__guest_exit) stp x12, x13, [x1, #CPU_XREG_OFFSET(12)] stp x14, x15, [x1, #CPU_XREG_OFFSET(14)] stp x16, x17, [x1, #CPU_XREG_OFFSET(16)] - str x18, [x1, #CPU_XREG_OFFSET(18)] - // Store the guest regs x19-x29, lr + // Store the guest regs x18-x29, lr save_callee_saved_regs x1 get_host_ctxt x2, x3 diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 72fbbd86eb5e..dfe8dd172512 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -28,7 +28,15 @@ /* Check whether the FP regs were dirtied while in the host-side run loop: */ static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu) { - if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + /* + * When the system doesn't support FP/SIMD, we cannot rely on + * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an + * abort on the very first access to FP and thus we should never + * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always + * trap the accesses. + */ + if (!system_supports_fpsimd() || + vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_FP_HOST); @@ -119,7 +127,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) write_sysreg(val, cptr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; isb(); @@ -158,11 +166,11 @@ static void deactivate_traps_vhe(void) write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); /* - * ARM erratum 1165522 requires the actual execution of the above - * before we can switch to the EL2/EL0 translation regime used by + * ARM errata 1165522 and 1530923 require the actual execution of the + * above before we can switch to the EL2/EL0 translation regime used by * the host. */ - asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522)); + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT_VHE)); write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); @@ -173,7 +181,7 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { u64 val; /* diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 22b8128d19f6..7672a978926c 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -118,7 +118,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + if (!cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); } else if (!ctxt->__hyp_running_vcpu) { @@ -149,7 +149,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); - if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) && + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) && ctxt->__hyp_running_vcpu) { /* * Must only be done for host registers, hence the context diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index c2bc17ca6430..92f560e3e1aa 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -23,10 +23,10 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, local_irq_save(cxt->flags); - if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { /* - * For CPUs that are affected by ARM erratum 1165522, we - * cannot trust stage-1 to be in a correct state at that + * For CPUs that are affected by ARM errata 1165522 or 1530923, + * we cannot trust stage-1 to be in a correct state at that * point. Since we do not want to force a full load of the * vcpu state, we prevent the EL1 page-table walker to * allocate new TLBs. This is done by setting the EPD bits @@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { - if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { u64 val; /* @@ -103,7 +103,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); isb(); - if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) { /* Restore the registers to what they were */ write_sysreg_el1(cxt->tcr, SYS_TCR); write_sysreg_el1(cxt->sctlr, SYS_SCTLR); @@ -117,7 +117,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, { write_sysreg(0, vttbr_el2); - if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) { /* Ensure write of the host VMID */ isb(); /* Restore the host's TCR_EL1 */ diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 9f2165937f7d..3e909b117f0c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1424,7 +1424,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_SANITISED(ID_ISAR4_EL1), ID_SANITISED(ID_ISAR5_EL1), ID_SANITISED(ID_MMFR4_EL1), - ID_UNALLOCATED(2,7), + ID_SANITISED(ID_ISAR6_EL1), /* CRm=3 */ ID_SANITISED(MVFR0_EL1), diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index c21b936dc01d..2fc253466dbf 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,9 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 lib-y := clear_user.o delay.o copy_from_user.o \ copy_to_user.o copy_in_user.o copy_page.o \ - clear_page.o memchr.o memcpy.o memmove.o memset.o \ - memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ - strchr.o strrchr.o tishift.o + clear_page.o csum.o memchr.o memcpy.o memmove.o \ + memset.o memcmp.o strcmp.o strncmp.o strlen.o \ + strnlen.o strchr.o strrchr.o tishift.o ifeq ($(CONFIG_KERNEL_MODE_NEON), y) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S index 78a9ef66288a..073acbf02a7c 100644 --- a/arch/arm64/lib/clear_page.S +++ b/arch/arm64/lib/clear_page.S @@ -14,7 +14,7 @@ * Parameters: * x0 - dest */ -ENTRY(clear_page) +SYM_FUNC_START(clear_page) mrs x1, dczid_el0 and w1, w1, #0xf mov x2, #4 @@ -25,5 +25,5 @@ ENTRY(clear_page) tst x0, #(PAGE_SIZE - 1) b.ne 1b ret -ENDPROC(clear_page) +SYM_FUNC_END(clear_page) EXPORT_SYMBOL(clear_page) diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index aeafc03e961a..48a3a26eff66 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -19,7 +19,7 @@ * * Alignment fixed up by hardware. */ -ENTRY(__arch_clear_user) +SYM_FUNC_START(__arch_clear_user) mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -40,7 +40,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 ret -ENDPROC(__arch_clear_user) +SYM_FUNC_END(__arch_clear_user) EXPORT_SYMBOL(__arch_clear_user) .section .fixup,"ax" diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index ebb3c06cbb5d..8e25e89ad01f 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -53,12 +53,12 @@ .endm end .req x5 -ENTRY(__arch_copy_from_user) +SYM_FUNC_START(__arch_copy_from_user) add end, x0, x2 #include "copy_template.S" mov x0, #0 // Nothing to copy ret -ENDPROC(__arch_copy_from_user) +SYM_FUNC_END(__arch_copy_from_user) EXPORT_SYMBOL(__arch_copy_from_user) .section .fixup,"ax" diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 3d8153a1ebce..667139013ed1 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -55,12 +55,12 @@ end .req x5 -ENTRY(__arch_copy_in_user) +SYM_FUNC_START(__arch_copy_in_user) add end, x0, x2 #include "copy_template.S" mov x0, #0 ret -ENDPROC(__arch_copy_in_user) +SYM_FUNC_END(__arch_copy_in_user) EXPORT_SYMBOL(__arch_copy_in_user) .section .fixup,"ax" diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S index bbb8562396af..e7a793961408 100644 --- a/arch/arm64/lib/copy_page.S +++ b/arch/arm64/lib/copy_page.S @@ -17,7 +17,7 @@ * x0 - dest * x1 - src */ -ENTRY(copy_page) +SYM_FUNC_START(copy_page) alternative_if ARM64_HAS_NO_HW_PREFETCH // Prefetch three cache lines ahead. prfm pldl1strm, [x1, #128] @@ -34,46 +34,46 @@ alternative_else_nop_endif ldp x14, x15, [x1, #96] ldp x16, x17, [x1, #112] - mov x18, #(PAGE_SIZE - 128) + add x0, x0, #256 add x1, x1, #128 1: - subs x18, x18, #128 + tst x0, #(PAGE_SIZE - 1) alternative_if ARM64_HAS_NO_HW_PREFETCH prfm pldl1strm, [x1, #384] alternative_else_nop_endif - stnp x2, x3, [x0] + stnp x2, x3, [x0, #-256] ldp x2, x3, [x1] - stnp x4, x5, [x0, #16] + stnp x4, x5, [x0, #16 - 256] ldp x4, x5, [x1, #16] - stnp x6, x7, [x0, #32] + stnp x6, x7, [x0, #32 - 256] ldp x6, x7, [x1, #32] - stnp x8, x9, [x0, #48] + stnp x8, x9, [x0, #48 - 256] ldp x8, x9, [x1, #48] - stnp x10, x11, [x0, #64] + stnp x10, x11, [x0, #64 - 256] ldp x10, x11, [x1, #64] - stnp x12, x13, [x0, #80] + stnp x12, x13, [x0, #80 - 256] ldp x12, x13, [x1, #80] - stnp x14, x15, [x0, #96] + stnp x14, x15, [x0, #96 - 256] ldp x14, x15, [x1, #96] - stnp x16, x17, [x0, #112] + stnp x16, x17, [x0, #112 - 256] ldp x16, x17, [x1, #112] add x0, x0, #128 add x1, x1, #128 - b.gt 1b + b.ne 1b - stnp x2, x3, [x0] - stnp x4, x5, [x0, #16] - stnp x6, x7, [x0, #32] - stnp x8, x9, [x0, #48] - stnp x10, x11, [x0, #64] - stnp x12, x13, [x0, #80] - stnp x14, x15, [x0, #96] - stnp x16, x17, [x0, #112] + stnp x2, x3, [x0, #-256] + stnp x4, x5, [x0, #16 - 256] + stnp x6, x7, [x0, #32 - 256] + stnp x8, x9, [x0, #48 - 256] + stnp x10, x11, [x0, #64 - 256] + stnp x12, x13, [x0, #80 - 256] + stnp x14, x15, [x0, #96 - 256] + stnp x16, x17, [x0, #112 - 256] ret -ENDPROC(copy_page) +SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 357eae2c18eb..1a104d0089f3 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -52,12 +52,12 @@ .endm end .req x5 -ENTRY(__arch_copy_to_user) +SYM_FUNC_START(__arch_copy_to_user) add end, x0, x2 #include "copy_template.S" mov x0, #0 ret -ENDPROC(__arch_copy_to_user) +SYM_FUNC_END(__arch_copy_to_user) EXPORT_SYMBOL(__arch_copy_to_user) .section .fixup,"ax" diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S index e6135f16649b..243e107e9896 100644 --- a/arch/arm64/lib/crc32.S +++ b/arch/arm64/lib/crc32.S @@ -85,17 +85,17 @@ CPU_BE( rev16 w3, w3 ) .endm .align 5 -ENTRY(crc32_le) +SYM_FUNC_START(crc32_le) alternative_if_not ARM64_HAS_CRC32 b crc32_le_base alternative_else_nop_endif __crc32 -ENDPROC(crc32_le) +SYM_FUNC_END(crc32_le) .align 5 -ENTRY(__crc32c_le) +SYM_FUNC_START(__crc32c_le) alternative_if_not ARM64_HAS_CRC32 b __crc32c_le_base alternative_else_nop_endif __crc32 c -ENDPROC(__crc32c_le) +SYM_FUNC_END(__crc32c_le) diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c new file mode 100644 index 000000000000..1f82c66b32ea --- /dev/null +++ b/arch/arm64/lib/csum.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019-2020 Arm Ltd. + +#include <linux/compiler.h> +#include <linux/kasan-checks.h> +#include <linux/kernel.h> + +#include <net/checksum.h> + +/* Looks dumb, but generates nice-ish code */ +static u64 accumulate(u64 sum, u64 data) +{ + __uint128_t tmp = (__uint128_t)sum + data; + return tmp + (tmp >> 64); +} + +unsigned int do_csum(const unsigned char *buff, int len) +{ + unsigned int offset, shift, sum; + const u64 *ptr; + u64 data, sum64 = 0; + + if (unlikely(len == 0)) + return 0; + + offset = (unsigned long)buff & 7; + /* + * This is to all intents and purposes safe, since rounding down cannot + * result in a different page or cache line being accessed, and @buff + * should absolutely not be pointing to anything read-sensitive. We do, + * however, have to be careful not to piss off KASAN, which means using + * unchecked reads to accommodate the head and tail, for which we'll + * compensate with an explicit check up-front. + */ + kasan_check_read(buff, len); + ptr = (u64 *)(buff - offset); + len = len + offset - 8; + + /* + * Head: zero out any excess leading bytes. Shifting back by the same + * amount should be at least as fast as any other way of handling the + * odd/even alignment, and means we can ignore it until the very end. + */ + shift = offset * 8; + data = READ_ONCE_NOCHECK(*ptr++); +#ifdef __LITTLE_ENDIAN + data = (data >> shift) << shift; +#else + data = (data << shift) >> shift; +#endif + + /* + * Body: straightforward aligned loads from here on (the paired loads + * underlying the quadword type still only need dword alignment). The + * main loop strictly excludes the tail, so the second loop will always + * run at least once. + */ + while (unlikely(len > 64)) { + __uint128_t tmp1, tmp2, tmp3, tmp4; + + tmp1 = READ_ONCE_NOCHECK(*(__uint128_t *)ptr); + tmp2 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 2)); + tmp3 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 4)); + tmp4 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 6)); + + len -= 64; + ptr += 8; + + /* This is the "don't dump the carry flag into a GPR" idiom */ + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp2 += (tmp2 >> 64) | (tmp2 << 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp4 += (tmp4 >> 64) | (tmp4 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp1 = ((tmp1 >> 64) << 64) | sum64; + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + sum64 = tmp1 >> 64; + } + while (len > 8) { + __uint128_t tmp; + + sum64 = accumulate(sum64, data); + tmp = READ_ONCE_NOCHECK(*(__uint128_t *)ptr); + + len -= 16; + ptr += 2; + +#ifdef __LITTLE_ENDIAN + data = tmp >> 64; + sum64 = accumulate(sum64, tmp); +#else + data = tmp; + sum64 = accumulate(sum64, tmp >> 64); +#endif + } + if (len > 0) { + sum64 = accumulate(sum64, data); + data = READ_ONCE_NOCHECK(*ptr); + len -= 8; + } + /* + * Tail: zero any over-read bytes similarly to the head, again + * preserving odd/even alignment. + */ + shift = len * -8; +#ifdef __LITTLE_ENDIAN + data = (data << shift) >> shift; +#else + data = (data >> shift) << shift; +#endif + sum64 = accumulate(sum64, data); + + /* Finally, folding */ + sum64 += (sum64 >> 32) | (sum64 << 32); + sum = sum64 >> 32; + sum += (sum >> 16) | (sum << 16); + if (offset & 1) + return (u16)swab32(sum); + + return sum >> 16; +} diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S index 48a3ab636e4f..edf6b970a277 100644 --- a/arch/arm64/lib/memchr.S +++ b/arch/arm64/lib/memchr.S @@ -19,7 +19,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -WEAK(memchr) +SYM_FUNC_START_WEAK_PI(memchr) and w1, w1, #0xff 1: subs x2, x2, #1 b.mi 2f @@ -30,5 +30,5 @@ WEAK(memchr) ret 2: mov x0, #0 ret -ENDPIPROC(memchr) +SYM_FUNC_END_PI(memchr) EXPORT_SYMBOL_NOKASAN(memchr) diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index b297bdaaf549..c0671e793ea9 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -46,7 +46,7 @@ pos .req x11 limit_wd .req x12 mask .req x13 -WEAK(memcmp) +SYM_FUNC_START_WEAK_PI(memcmp) cbz limit, .Lret0 eor tmp1, src1, src2 tst tmp1, #7 @@ -243,5 +243,5 @@ CPU_LE( rev data2, data2 ) .Lret0: mov result, #0 ret -ENDPIPROC(memcmp) +SYM_FUNC_END_PI(memcmp) EXPORT_SYMBOL_NOKASAN(memcmp) diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index d79f48994dbb..9f382adfa88a 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -57,11 +57,11 @@ .endm .weak memcpy -ENTRY(__memcpy) -ENTRY(memcpy) +SYM_FUNC_START_ALIAS(__memcpy) +SYM_FUNC_START_PI(memcpy) #include "copy_template.S" ret -ENDPIPROC(memcpy) +SYM_FUNC_END_PI(memcpy) EXPORT_SYMBOL(memcpy) -ENDPROC(__memcpy) +SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(__memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index 784775136480..02cda2e33bde 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -46,8 +46,8 @@ D_l .req x13 D_h .req x14 .weak memmove -ENTRY(__memmove) -ENTRY(memmove) +SYM_FUNC_START_ALIAS(__memmove) +SYM_FUNC_START_PI(memmove) cmp dstin, src b.lo __memcpy add tmp1, src, count @@ -184,7 +184,7 @@ ENTRY(memmove) tst count, #0x3f b.ne .Ltail63 ret -ENDPIPROC(memmove) +SYM_FUNC_END_PI(memmove) EXPORT_SYMBOL(memmove) -ENDPROC(__memmove) +SYM_FUNC_END_ALIAS(__memmove) EXPORT_SYMBOL(__memmove) diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index 9fb97e6bc560..77c3c7ba0084 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -43,8 +43,8 @@ tmp3w .req w9 tmp3 .req x9 .weak memset -ENTRY(__memset) -ENTRY(memset) +SYM_FUNC_START_ALIAS(__memset) +SYM_FUNC_START_PI(memset) mov dst, dstin /* Preserve return value. */ and A_lw, val, #255 orr A_lw, A_lw, A_lw, lsl #8 @@ -203,7 +203,7 @@ ENTRY(memset) ands count, count, zva_bits_x b.ne .Ltail_maybe_long ret -ENDPIPROC(memset) +SYM_FUNC_END_PI(memset) EXPORT_SYMBOL(memset) -ENDPROC(__memset) +SYM_FUNC_END_ALIAS(__memset) EXPORT_SYMBOL(__memset) diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S index ca3ec18171a4..1f47eae3b0d6 100644 --- a/arch/arm64/lib/strchr.S +++ b/arch/arm64/lib/strchr.S @@ -18,7 +18,7 @@ * Returns: * x0 - address of first occurrence of 'c' or 0 */ -WEAK(strchr) +SYM_FUNC_START_WEAK(strchr) and w1, w1, #0xff 1: ldrb w2, [x0], #1 cmp w2, w1 @@ -28,5 +28,5 @@ WEAK(strchr) cmp w2, w1 csel x0, x0, xzr, eq ret -ENDPROC(strchr) +SYM_FUNC_END(strchr) EXPORT_SYMBOL_NOKASAN(strchr) diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index e9aefbe0b740..4767540d1b94 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -48,7 +48,7 @@ tmp3 .req x9 zeroones .req x10 pos .req x11 -WEAK(strcmp) +SYM_FUNC_START_WEAK_PI(strcmp) eor tmp1, src1, src2 mov zeroones, #REP8_01 tst tmp1, #7 @@ -219,5 +219,5 @@ CPU_BE( orr syndrome, diff, has_nul ) lsr data1, data1, #56 sub result, data1, data2, lsr #56 ret -ENDPIPROC(strcmp) +SYM_FUNC_END_PI(strcmp) EXPORT_SYMBOL_NOKASAN(strcmp) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 87b0cb066915..ee3ed882dd79 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -44,7 +44,7 @@ pos .req x12 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -WEAK(strlen) +SYM_FUNC_START_WEAK_PI(strlen) mov zeroones, #REP8_01 bic src, srcin, #15 ands tmp1, srcin, #15 @@ -111,5 +111,5 @@ CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ csinv data1, data1, xzr, le csel data2, data2, data2a, le b .Lrealigned -ENDPIPROC(strlen) +SYM_FUNC_END_PI(strlen) EXPORT_SYMBOL_NOKASAN(strlen) diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index f571581888fa..2a7ee949ed47 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -52,7 +52,7 @@ limit_wd .req x13 mask .req x14 endloop .req x15 -WEAK(strncmp) +SYM_FUNC_START_WEAK_PI(strncmp) cbz limit, .Lret0 eor tmp1, src1, src2 mov zeroones, #REP8_01 @@ -295,5 +295,5 @@ CPU_BE( orr syndrome, diff, has_nul ) .Lret0: mov result, #0 ret -ENDPIPROC(strncmp) +SYM_FUNC_END_PI(strncmp) EXPORT_SYMBOL_NOKASAN(strncmp) diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index c0bac9493c68..b72913a99038 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -47,7 +47,7 @@ limit_wd .req x14 #define REP8_7f 0x7f7f7f7f7f7f7f7f #define REP8_80 0x8080808080808080 -WEAK(strnlen) +SYM_FUNC_START_WEAK_PI(strnlen) cbz limit, .Lhit_limit mov zeroones, #REP8_01 bic src, srcin, #15 @@ -156,5 +156,5 @@ CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ .Lhit_limit: mov len, limit ret -ENDPIPROC(strnlen) +SYM_FUNC_END_PI(strnlen) EXPORT_SYMBOL_NOKASAN(strnlen) diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S index 794ac49ea433..13132d1ed6d1 100644 --- a/arch/arm64/lib/strrchr.S +++ b/arch/arm64/lib/strrchr.S @@ -18,7 +18,7 @@ * Returns: * x0 - address of last occurrence of 'c' or 0 */ -WEAK(strrchr) +SYM_FUNC_START_WEAK_PI(strrchr) mov x3, #0 and w1, w1, #0xff 1: ldrb w2, [x0], #1 @@ -29,5 +29,5 @@ WEAK(strrchr) b 1b 2: mov x0, x3 ret -ENDPIPROC(strrchr) +SYM_FUNC_END_PI(strrchr) EXPORT_SYMBOL_NOKASAN(strrchr) diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S index 047622536535..a88613834fb0 100644 --- a/arch/arm64/lib/tishift.S +++ b/arch/arm64/lib/tishift.S @@ -7,7 +7,7 @@ #include <asm/assembler.h> -ENTRY(__ashlti3) +SYM_FUNC_START(__ashlti3) cbz x2, 1f mov x3, #64 sub x3, x3, x2 @@ -26,10 +26,10 @@ ENTRY(__ashlti3) lsl x1, x0, x1 mov x0, x2 ret -ENDPROC(__ashlti3) +SYM_FUNC_END(__ashlti3) EXPORT_SYMBOL(__ashlti3) -ENTRY(__ashrti3) +SYM_FUNC_START(__ashrti3) cbz x2, 1f mov x3, #64 sub x3, x3, x2 @@ -48,10 +48,10 @@ ENTRY(__ashrti3) asr x0, x1, x0 mov x1, x2 ret -ENDPROC(__ashrti3) +SYM_FUNC_END(__ashrti3) EXPORT_SYMBOL(__ashrti3) -ENTRY(__lshrti3) +SYM_FUNC_START(__lshrti3) cbz x2, 1f mov x3, #64 sub x3, x3, x2 @@ -70,5 +70,5 @@ ENTRY(__lshrti3) lsr x0, x1, x0 mov x1, x2 ret -ENDPROC(__lshrti3) +SYM_FUNC_END(__lshrti3) EXPORT_SYMBOL(__lshrti3) diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index db767b072601..2d881f34dd9d 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -24,7 +24,7 @@ * - start - virtual start address of region * - end - virtual end address of region */ -ENTRY(__flush_icache_range) +SYM_FUNC_START(__flush_icache_range) /* FALLTHROUGH */ /* @@ -37,7 +37,7 @@ ENTRY(__flush_icache_range) * - start - virtual start address of region * - end - virtual end address of region */ -ENTRY(__flush_cache_user_range) +SYM_FUNC_START(__flush_cache_user_range) uaccess_ttbr0_enable x2, x3, x4 alternative_if ARM64_HAS_CACHE_IDC dsb ishst @@ -66,8 +66,8 @@ alternative_else_nop_endif 9: mov x0, #-EFAULT b 1b -ENDPROC(__flush_icache_range) -ENDPROC(__flush_cache_user_range) +SYM_FUNC_END(__flush_icache_range) +SYM_FUNC_END(__flush_cache_user_range) /* * invalidate_icache_range(start,end) @@ -77,7 +77,7 @@ ENDPROC(__flush_cache_user_range) * - start - virtual start address of region * - end - virtual end address of region */ -ENTRY(invalidate_icache_range) +SYM_FUNC_START(invalidate_icache_range) alternative_if ARM64_HAS_CACHE_DIC mov x0, xzr isb @@ -94,7 +94,7 @@ alternative_else_nop_endif 2: mov x0, #-EFAULT b 1b -ENDPROC(invalidate_icache_range) +SYM_FUNC_END(invalidate_icache_range) /* * __flush_dcache_area(kaddr, size) @@ -105,10 +105,10 @@ ENDPROC(invalidate_icache_range) * - kaddr - kernel address * - size - size in question */ -ENTRY(__flush_dcache_area) +SYM_FUNC_START_PI(__flush_dcache_area) dcache_by_line_op civac, sy, x0, x1, x2, x3 ret -ENDPIPROC(__flush_dcache_area) +SYM_FUNC_END_PI(__flush_dcache_area) /* * __clean_dcache_area_pou(kaddr, size) @@ -119,14 +119,14 @@ ENDPIPROC(__flush_dcache_area) * - kaddr - kernel address * - size - size in question */ -ENTRY(__clean_dcache_area_pou) +SYM_FUNC_START(__clean_dcache_area_pou) alternative_if ARM64_HAS_CACHE_IDC dsb ishst ret alternative_else_nop_endif dcache_by_line_op cvau, ish, x0, x1, x2, x3 ret -ENDPROC(__clean_dcache_area_pou) +SYM_FUNC_END(__clean_dcache_area_pou) /* * __inval_dcache_area(kaddr, size) @@ -138,7 +138,8 @@ ENDPROC(__clean_dcache_area_pou) * - kaddr - kernel address * - size - size in question */ -ENTRY(__inval_dcache_area) +SYM_FUNC_START_LOCAL(__dma_inv_area) +SYM_FUNC_START_PI(__inval_dcache_area) /* FALLTHROUGH */ /* @@ -146,7 +147,6 @@ ENTRY(__inval_dcache_area) * - start - virtual start address of region * - size - size in question */ -__dma_inv_area: add x1, x1, x0 dcache_line_size x2, x3 sub x3, x2, #1 @@ -165,8 +165,8 @@ __dma_inv_area: b.lo 2b dsb sy ret -ENDPIPROC(__inval_dcache_area) -ENDPROC(__dma_inv_area) +SYM_FUNC_END_PI(__inval_dcache_area) +SYM_FUNC_END(__dma_inv_area) /* * __clean_dcache_area_poc(kaddr, size) @@ -177,7 +177,8 @@ ENDPROC(__dma_inv_area) * - kaddr - kernel address * - size - size in question */ -ENTRY(__clean_dcache_area_poc) +SYM_FUNC_START_LOCAL(__dma_clean_area) +SYM_FUNC_START_PI(__clean_dcache_area_poc) /* FALLTHROUGH */ /* @@ -185,11 +186,10 @@ ENTRY(__clean_dcache_area_poc) * - start - virtual start address of region * - size - size in question */ -__dma_clean_area: dcache_by_line_op cvac, sy, x0, x1, x2, x3 ret -ENDPIPROC(__clean_dcache_area_poc) -ENDPROC(__dma_clean_area) +SYM_FUNC_END_PI(__clean_dcache_area_poc) +SYM_FUNC_END(__dma_clean_area) /* * __clean_dcache_area_pop(kaddr, size) @@ -200,13 +200,13 @@ ENDPROC(__dma_clean_area) * - kaddr - kernel address * - size - size in question */ -ENTRY(__clean_dcache_area_pop) +SYM_FUNC_START_PI(__clean_dcache_area_pop) alternative_if_not ARM64_HAS_DCPOP b __clean_dcache_area_poc alternative_else_nop_endif dcache_by_line_op cvap, sy, x0, x1, x2, x3 ret -ENDPIPROC(__clean_dcache_area_pop) +SYM_FUNC_END_PI(__clean_dcache_area_pop) /* * __dma_flush_area(start, size) @@ -216,10 +216,10 @@ ENDPIPROC(__clean_dcache_area_pop) * - start - virtual start address of region * - size - size in question */ -ENTRY(__dma_flush_area) +SYM_FUNC_START_PI(__dma_flush_area) dcache_by_line_op civac, sy, x0, x1, x2, x3 ret -ENDPIPROC(__dma_flush_area) +SYM_FUNC_END_PI(__dma_flush_area) /* * __dma_map_area(start, size, dir) @@ -227,11 +227,11 @@ ENDPIPROC(__dma_flush_area) * - size - size of region * - dir - DMA direction */ -ENTRY(__dma_map_area) +SYM_FUNC_START_PI(__dma_map_area) cmp w2, #DMA_FROM_DEVICE b.eq __dma_inv_area b __dma_clean_area -ENDPIPROC(__dma_map_area) +SYM_FUNC_END_PI(__dma_map_area) /* * __dma_unmap_area(start, size, dir) @@ -239,8 +239,8 @@ ENDPIPROC(__dma_map_area) * - size - size of region * - dir - DMA direction */ -ENTRY(__dma_unmap_area) +SYM_FUNC_START_PI(__dma_unmap_area) cmp w2, #DMA_TO_DEVICE b.ne __dma_inv_area ret -ENDPIPROC(__dma_unmap_area) +SYM_FUNC_END_PI(__dma_unmap_area) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index b5e329fde2dd..8ef73e89d514 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -29,15 +29,9 @@ static cpumask_t tlb_flush_pending; #define ASID_MASK (~GENMASK(asid_bits - 1, 0)) #define ASID_FIRST_VERSION (1UL << asid_bits) -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define NUM_USER_ASIDS (ASID_FIRST_VERSION >> 1) -#define asid2idx(asid) (((asid) & ~ASID_MASK) >> 1) -#define idx2asid(idx) (((idx) << 1) & ~ASID_MASK) -#else -#define NUM_USER_ASIDS (ASID_FIRST_VERSION) +#define NUM_USER_ASIDS ASID_FIRST_VERSION #define asid2idx(asid) ((asid) & ~ASID_MASK) #define idx2asid(idx) asid2idx(idx) -#endif /* Get the ASIDBits supported by the current CPU */ static u32 get_cpu_asid_bits(void) @@ -77,13 +71,33 @@ void verify_cpu_asid_bits(void) } } +static void set_kpti_asid_bits(void) +{ + unsigned int len = BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(unsigned long); + /* + * In case of KPTI kernel/user ASIDs are allocated in + * pairs, the bottom bit distinguishes the two: if it + * is set, then the ASID will map only userspace. Thus + * mark even as reserved for kernel. + */ + memset(asid_map, 0xaa, len); +} + +static void set_reserved_asid_bits(void) +{ + if (arm64_kernel_unmapped_at_el0()) + set_kpti_asid_bits(); + else + bitmap_clear(asid_map, 0, NUM_USER_ASIDS); +} + static void flush_context(void) { int i; u64 asid; /* Update the list of reserved ASIDs and the ASID bitmap. */ - bitmap_clear(asid_map, 0, NUM_USER_ASIDS); + set_reserved_asid_bits(); for_each_possible_cpu(i) { asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0); @@ -261,6 +275,14 @@ static int asids_init(void) panic("Failed to allocate bitmap for %lu ASIDs\n", NUM_USER_ASIDS); + /* + * We cannot call set_reserved_asid_bits() here because CPU + * caps are not finalized yet, so it is safer to assume KPTI + * and reserve kernel ASID's from beginning. + */ + if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) + set_kpti_asid_bits(); + pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); return 0; } diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 9ce7bd9d4d9c..250c49008d73 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -54,7 +54,7 @@ static int change_memory_common(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) { unsigned long start = addr; - unsigned long size = PAGE_SIZE*numpages; + unsigned long size = PAGE_SIZE * numpages; unsigned long end = start + size; struct vm_struct *area; int i; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index a1e0592d1fbc..aafed6902411 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -42,7 +42,14 @@ #define TCR_KASAN_FLAGS 0 #endif -#define MAIR(attr, mt) ((attr) << ((mt) * 8)) +/* Default MAIR_EL1 */ +#define MAIR_EL1_SET \ + (MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) | \ + MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) | \ + MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) | \ + MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) | \ + MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \ + MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT)) #ifdef CONFIG_CPU_PM /** @@ -50,7 +57,7 @@ * * x0: virtual address of context pointer */ -ENTRY(cpu_do_suspend) +SYM_FUNC_START(cpu_do_suspend) mrs x2, tpidr_el0 mrs x3, tpidrro_el0 mrs x4, contextidr_el1 @@ -74,7 +81,7 @@ alternative_endif stp x10, x11, [x0, #64] stp x12, x13, [x0, #80] ret -ENDPROC(cpu_do_suspend) +SYM_FUNC_END(cpu_do_suspend) /** * cpu_do_resume - restore CPU register context @@ -82,7 +89,7 @@ ENDPROC(cpu_do_suspend) * x0: Address of context pointer */ .pushsection ".idmap.text", "awx" -ENTRY(cpu_do_resume) +SYM_FUNC_START(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16] ldp x6, x8, [x0, #32] @@ -131,7 +138,7 @@ alternative_else_nop_endif isb ret -ENDPROC(cpu_do_resume) +SYM_FUNC_END(cpu_do_resume) .popsection #endif @@ -142,7 +149,7 @@ ENDPROC(cpu_do_resume) * * - pgd_phys - physical address of new TTB */ -ENTRY(cpu_do_switch_mm) +SYM_FUNC_START(cpu_do_switch_mm) mrs x2, ttbr1_el1 mmid x1, x1 // get mm->context.id phys_to_ttbr x3, x0 @@ -161,7 +168,7 @@ alternative_else_nop_endif msr ttbr0_el1, x3 // now update TTBR0 isb b post_ttbr_update_workaround // Back to C code... -ENDPROC(cpu_do_switch_mm) +SYM_FUNC_END(cpu_do_switch_mm) .pushsection ".idmap.text", "awx" @@ -182,7 +189,7 @@ ENDPROC(cpu_do_switch_mm) * This is the low-level counterpart to cpu_replace_ttbr1, and should not be * called by anything else. It can only be executed from a TTBR0 mapping. */ -ENTRY(idmap_cpu_replace_ttbr1) +SYM_FUNC_START(idmap_cpu_replace_ttbr1) save_and_disable_daif flags=x2 __idmap_cpu_set_reserved_ttbr1 x1, x3 @@ -194,7 +201,7 @@ ENTRY(idmap_cpu_replace_ttbr1) restore_daif x2 ret -ENDPROC(idmap_cpu_replace_ttbr1) +SYM_FUNC_END(idmap_cpu_replace_ttbr1) .popsection #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 @@ -222,7 +229,7 @@ ENDPROC(idmap_cpu_replace_ttbr1) */ __idmap_kpti_flag: .long 1 -ENTRY(idmap_kpti_install_ng_mappings) +SYM_FUNC_START(idmap_kpti_install_ng_mappings) cpu .req w0 num_cpus .req w1 swapper_pa .req x2 @@ -250,15 +257,15 @@ ENTRY(idmap_kpti_install_ng_mappings) /* We're the boot CPU. Wait for the others to catch up */ sevl 1: wfe - ldaxr w18, [flag_ptr] - eor w18, w18, num_cpus - cbnz w18, 1b + ldaxr w17, [flag_ptr] + eor w17, w17, num_cpus + cbnz w17, 1b /* We need to walk swapper, so turn off the MMU. */ pre_disable_mmu_workaround - mrs x18, sctlr_el1 - bic x18, x18, #SCTLR_ELx_M - msr sctlr_el1, x18 + mrs x17, sctlr_el1 + bic x17, x17, #SCTLR_ELx_M + msr sctlr_el1, x17 isb /* Everybody is enjoying the idmap, so we can rewrite swapper. */ @@ -281,9 +288,9 @@ skip_pgd: isb /* We're done: fire up the MMU again */ - mrs x18, sctlr_el1 - orr x18, x18, #SCTLR_ELx_M - msr sctlr_el1, x18 + mrs x17, sctlr_el1 + orr x17, x17, #SCTLR_ELx_M + msr sctlr_el1, x17 isb /* @@ -353,47 +360,48 @@ skip_pte: b.ne do_pte b next_pmd + .unreq cpu + .unreq num_cpus + .unreq swapper_pa + .unreq cur_pgdp + .unreq end_pgdp + .unreq pgd + .unreq cur_pudp + .unreq end_pudp + .unreq pud + .unreq cur_pmdp + .unreq end_pmdp + .unreq pmd + .unreq cur_ptep + .unreq end_ptep + .unreq pte + /* Secondary CPUs end up here */ __idmap_kpti_secondary: /* Uninstall swapper before surgery begins */ - __idmap_cpu_set_reserved_ttbr1 x18, x17 + __idmap_cpu_set_reserved_ttbr1 x16, x17 /* Increment the flag to let the boot CPU we're ready */ -1: ldxr w18, [flag_ptr] - add w18, w18, #1 - stxr w17, w18, [flag_ptr] +1: ldxr w16, [flag_ptr] + add w16, w16, #1 + stxr w17, w16, [flag_ptr] cbnz w17, 1b /* Wait for the boot CPU to finish messing around with swapper */ sevl 1: wfe - ldxr w18, [flag_ptr] - cbnz w18, 1b + ldxr w16, [flag_ptr] + cbnz w16, 1b /* All done, act like nothing happened */ - offset_ttbr1 swapper_ttb, x18 + offset_ttbr1 swapper_ttb, x16 msr ttbr1_el1, swapper_ttb isb ret - .unreq cpu - .unreq num_cpus - .unreq swapper_pa .unreq swapper_ttb .unreq flag_ptr - .unreq cur_pgdp - .unreq end_pgdp - .unreq pgd - .unreq cur_pudp - .unreq end_pudp - .unreq pud - .unreq cur_pmdp - .unreq end_pmdp - .unreq pmd - .unreq cur_ptep - .unreq end_ptep - .unreq pte -ENDPROC(idmap_kpti_install_ng_mappings) +SYM_FUNC_END(idmap_kpti_install_ng_mappings) .popsection #endif @@ -404,7 +412,7 @@ ENDPROC(idmap_kpti_install_ng_mappings) * value of the SCTLR_EL1 register. */ .pushsection ".idmap.text", "awx" -ENTRY(__cpu_setup) +SYM_FUNC_START(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh @@ -416,23 +424,9 @@ ENTRY(__cpu_setup) enable_dbg // since this is per-cpu reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* - * Memory region attributes for LPAE: - * - * n = AttrIndx[2:0] - * n MAIR - * DEVICE_nGnRnE 000 00000000 - * DEVICE_nGnRE 001 00000100 - * DEVICE_GRE 010 00001100 - * NORMAL_NC 011 01000100 - * NORMAL 100 11111111 - * NORMAL_WT 101 10111011 + * Memory region attributes */ - ldr x5, =MAIR(0x00, MT_DEVICE_nGnRnE) | \ - MAIR(0x04, MT_DEVICE_nGnRE) | \ - MAIR(0x0c, MT_DEVICE_GRE) | \ - MAIR(0x44, MT_NORMAL_NC) | \ - MAIR(0xff, MT_NORMAL) | \ - MAIR(0xbb, MT_NORMAL_WT) + mov_q x5, MAIR_EL1_SET msr mair_el1, x5 /* * Prepare SCTLR @@ -475,4 +469,4 @@ ENTRY(__cpu_setup) #endif /* CONFIG_ARM64_HW_AFDBM */ msr tcr_el1, x10 ret // return to head.S -ENDPROC(__cpu_setup) +SYM_FUNC_END(__cpu_setup) diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S index c5f05c4a4d00..5b09aca55108 100644 --- a/arch/arm64/xen/hypercall.S +++ b/arch/arm64/xen/hypercall.S @@ -56,11 +56,11 @@ #define XEN_IMM 0xEA1 #define HYPERCALL_SIMPLE(hypercall) \ -ENTRY(HYPERVISOR_##hypercall) \ +SYM_FUNC_START(HYPERVISOR_##hypercall) \ mov x16, #__HYPERVISOR_##hypercall; \ hvc XEN_IMM; \ ret; \ -ENDPROC(HYPERVISOR_##hypercall) +SYM_FUNC_END(HYPERVISOR_##hypercall) #define HYPERCALL0 HYPERCALL_SIMPLE #define HYPERCALL1 HYPERCALL_SIMPLE @@ -86,7 +86,7 @@ HYPERCALL2(multicall); HYPERCALL2(vm_assist); HYPERCALL3(dm_op); -ENTRY(privcmd_call) +SYM_FUNC_START(privcmd_call) mov x16, x0 mov x0, x1 mov x1, x2 @@ -109,4 +109,4 @@ ENTRY(privcmd_call) */ uaccess_ttbr0_disable x6, x7 ret -ENDPROC(privcmd_call); +SYM_FUNC_END(privcmd_call); diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 6663f1741798..6ad6cdac74b3 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -14,6 +14,7 @@ config M68K select HAVE_AOUT if MMU select HAVE_ASM_MODVERSIONS select HAVE_DEBUG_BUGVERBOSE + select HAVE_COPY_THREAD_TLS select GENERIC_IRQ_SHOW select GENERIC_ATOMIC64 select HAVE_UID16 diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 619d30d663a2..e1134c3e0b69 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -562,6 +562,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -574,7 +575,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -612,6 +613,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -620,6 +624,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -651,4 +656,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index caa0558abcdb..484cb1643df1 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -518,6 +518,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -530,7 +531,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -568,6 +569,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -576,6 +580,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -607,4 +612,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 2551c7e9ac54..eb6a46b6d135 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -540,6 +540,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -552,7 +553,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -590,6 +591,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -598,6 +602,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -629,4 +634,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 4ffc1e5646d5..bee9263a409c 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -511,6 +511,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -523,7 +524,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -561,6 +562,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -569,6 +573,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -600,4 +605,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 806da3d97ca4..c8847a8bcbd6 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -520,6 +520,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -532,7 +533,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -570,6 +571,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -578,6 +582,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -609,4 +614,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 250da20e291c..303ffafd9cad 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -542,6 +542,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -554,7 +555,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -592,6 +593,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -600,6 +604,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -631,4 +636,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index b764a0368a56..89a704226cd9 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -628,6 +628,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -640,7 +641,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -678,6 +679,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -686,6 +690,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -717,4 +722,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 7800d3a8d46e..f62c1f4d03a0 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -510,6 +510,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -522,7 +523,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -560,6 +561,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -568,6 +572,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -599,4 +604,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index c32dc2d2058d..58dcad26a751 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -511,6 +511,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -523,7 +524,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -561,6 +562,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -569,6 +573,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -600,4 +605,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index bf0a65ce57e0..5d3c28d1d545 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -529,6 +529,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -541,7 +542,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -579,6 +580,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -587,6 +591,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -618,4 +623,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 5f3cfa2926d2..5ef9e17dcd51 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -513,6 +513,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -525,7 +526,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -563,6 +564,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 58354d2018d5..22e1accc60a3 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -512,6 +512,7 @@ CONFIG_CRYPTO_RSA=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CFB=m @@ -524,7 +525,7 @@ CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_XXHASH=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -562,6 +563,9 @@ 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_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m # CONFIG_CRYPTO_HW is not set CONFIG_CRC32_SELFTEST=m CONFIG_CRC64=m @@ -570,6 +574,7 @@ CONFIG_STRING_SELFTEST=m # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_WW_MUTEX_SELFTEST=m +CONFIG_EARLY_PRINTK=y CONFIG_TEST_LIST_SORT=m CONFIG_TEST_SORT=m CONFIG_REED_SOLOMON_TEST=m @@ -601,4 +606,3 @@ CONFIG_TEST_KMOD=m CONFIG_TEST_MEMCAT_P=m CONFIG_TEST_STACKINIT=m CONFIG_TEST_MEMINIT=m -CONFIG_EARLY_PRINTK=y diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 2e0047cf86f8..4ae52414cd9d 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -30,5 +30,6 @@ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK +#define __ARCH_WANT_SYS_CLONE3 #endif /* _ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 97cd3ea5f10b..9dd76fbb7c6b 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -69,6 +69,13 @@ ENTRY(__sys_vfork) lea %sp@(24),%sp rts +ENTRY(__sys_clone3) + SAVE_SWITCH_STACK + pea %sp@(SWITCH_STACK_SIZE) + jbsr m68k_clone3 + lea %sp@(28),%sp + rts + ENTRY(sys_sigreturn) SAVE_SWITCH_STACK movel %sp,%sp@- | switch_stack pointer diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 4e77a06735c1..8f0d9140700f 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -30,8 +30,9 @@ #include <linux/init_task.h> #include <linux/mqueue.h> #include <linux/rcupdate.h> - +#include <linux/syscalls.h> #include <linux/uaccess.h> + #include <asm/traps.h> #include <asm/machdep.h> #include <asm/setup.h> @@ -107,20 +108,43 @@ void flush_thread(void) * on top of pt_regs, which means that sys_clone() arguments would be * buried. We could, of course, copy them, but it's too costly for no * good reason - generic clone() would have to copy them *again* for - * do_fork() anyway. So in this case it's actually better to pass pt_regs * - * and extract arguments for do_fork() from there. Eventually we might - * go for calling do_fork() directly from the wrapper, but only after we - * are finished with do_fork() prototype conversion. + * _do_fork() anyway. So in this case it's actually better to pass pt_regs * + * and extract arguments for _do_fork() from there. Eventually we might + * go for calling _do_fork() directly from the wrapper, but only after we + * are finished with _do_fork() prototype conversion. */ asmlinkage int m68k_clone(struct pt_regs *regs) { /* regs will be equal to current_pt_regs() */ - return do_fork(regs->d1, regs->d2, 0, - (int __user *)regs->d3, (int __user *)regs->d4); + struct kernel_clone_args args = { + .flags = regs->d1 & ~CSIGNAL, + .pidfd = (int __user *)regs->d3, + .child_tid = (int __user *)regs->d4, + .parent_tid = (int __user *)regs->d3, + .exit_signal = regs->d1 & CSIGNAL, + .stack = regs->d2, + .tls = regs->d5, + }; + + if (!legacy_clone_args_valid(&args)) + return -EINVAL; + + return _do_fork(&args); +} + +/* + * Because extra registers are saved on the stack after the sys_clone3() + * arguments, this C wrapper extracts them from pt_regs * and then calls the + * generic sys_clone3() implementation. + */ +asmlinkage int m68k_clone3(struct pt_regs *regs) +{ + return sys_clone3((struct clone_args __user *)regs->d1, regs->d2); } -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long usp, + unsigned long arg, struct task_struct *p, + unsigned long tls) { struct fork_frame { struct switch_stack sw; @@ -155,7 +179,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.usp = usp ?: rdusp(); if (clone_flags & CLONE_SETTLS) - task_thread_info(p)->tp_value = frame->regs.d5; + task_thread_info(p)->tp_value = tls; #ifdef CONFIG_FPU if (!FPU_IS_EMU) { diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index a88a285a0e5f..a00a5d0db602 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -434,4 +434,4 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 common clone3 __sys_clone3 diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1ec34e16ed65..e2a412113359 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -455,11 +455,7 @@ config PPC_TRANSACTIONAL_MEM config PPC_UV bool "Ultravisor support" depends on KVM_BOOK3S_HV_POSSIBLE - select ZONE_DEVICE - select DEV_PAGEMAP_OPS - select DEVICE_PRIVATE - select MEMORY_HOTPLUG - select MEMORY_HOTREMOVE + depends on DEVICE_PRIVATE default n help This option paravirtualizes the kernel to run in POWER platforms that diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi index e1a961f05dcd..baa0c503e741 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi @@ -63,6 +63,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy0: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi index c288f3c6c637..93095600e808 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi @@ -60,6 +60,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy6: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi index 94f3e7175012..ff4bd38f0645 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi @@ -63,6 +63,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy1: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi index 94a76982d214..1fa38ed6f59e 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi @@ -60,6 +60,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy7: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi index b5ff5f71c6b8..a8cc9780c0c4 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy0: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi index ee44182c6348..8b8bd70c9382 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy1: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi index f05f0d775039..619c880b54d8 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe5000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy2: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi index a9114ec51075..d7ebb73a400d 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe7000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy3: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi index 44dd00ac7367..b151d696a069 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe9000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy4: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi index 5b1b84b58602..adc0ae0013a3 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi @@ -59,6 +59,7 @@ fman@400000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xeb000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy5: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi index 0e1daaef9e74..435047e0e250 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi @@ -60,6 +60,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy14: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi index 68c5ef779266..c098657cca0a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi @@ -60,6 +60,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xf3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy15: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi index 605363cc1117..9d06824815f3 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy8: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi index 1955dfa13634..70e947730c4b 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy9: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi index 2c1476454ee0..ad96e6529595 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe5000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy10: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi index b8b541ff5fb0..034bc4b71f7a 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe7000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy11: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi index 4b2cfddd1b15..93ca23d82b39 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xe9000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy12: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi index 0a52ddf7cc17..23b3117a2fd2 100644 --- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi @@ -59,6 +59,7 @@ fman@500000 { #size-cells = <0>; compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; reg = <0xeb000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ pcsphy13: ethernet-phy@0 { reg = <0x0>; diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 15b75005bc34..3fa1b962dc27 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -600,8 +600,11 @@ extern void slb_set_size(u16 size); * */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) + +// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel #define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ - MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT) + MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2) + /* * For platforms that support on 65bit VA we limit the context bits */ diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h index f2dfcd50a2d3..33aee7490cbb 100644 --- a/arch/powerpc/include/asm/xive-regs.h +++ b/arch/powerpc/include/asm/xive-regs.h @@ -39,6 +39,7 @@ #define XIVE_ESB_VAL_P 0x2 #define XIVE_ESB_VAL_Q 0x1 +#define XIVE_ESB_INVALID 0xFF /* * Thread Management (aka "TM") registers diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f5fadbd2533a..9651ca061828 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -972,12 +972,21 @@ static int xive_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state) { struct xive_irq_data *xd = irq_data_get_irq_handler_data(data); + u8 pq; switch (which) { case IRQCHIP_STATE_ACTIVE: - *state = !xd->stale_p && - (xd->saved_p || - !!(xive_esb_read(xd, XIVE_ESB_GET) & XIVE_ESB_VAL_P)); + pq = xive_esb_read(xd, XIVE_ESB_GET); + + /* + * The esb value being all 1's means we couldn't get + * the PQ state of the interrupt through mmio. It may + * happen, for example when querying a PHB interrupt + * while the PHB is in an error state. We consider the + * interrupt to be inactive in that case. + */ + *state = (pq != XIVE_ESB_INVALID) && !xd->stale_p && + (xd->saved_p || !!(pq & XIVE_ESB_VAL_P)); return 0; default: return -EINVAL; diff --git a/block/partition-generic.c b/block/partition-generic.c index 1d20c9cf213f..564fae77711d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -321,6 +321,24 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, const char *dname; int err; + /* + * Partitions are not supported on zoned block devices that are used as + * such. + */ + switch (disk->queue->limits.zoned) { + case BLK_ZONED_HM: + pr_warn("%s: partitions not supported on host managed zoned block device\n", + disk->disk_name); + return ERR_PTR(-ENXIO); + case BLK_ZONED_HA: + pr_info("%s: disabling host aware zoned block device support due to partitions\n", + disk->disk_name); + disk->queue->limits.zoned = BLK_ZONED_NONE; + break; + case BLK_ZONED_NONE: + break; + } + err = disk_expand_part_tbl(disk, partno); if (err) return ERR_PTR(err); @@ -501,7 +519,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); - if (IS_ERR(part)) { + if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %ld\n", disk->disk_name, p, -PTR_ERR(part)); return true; @@ -540,10 +558,10 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) } /* - * Partitions are not supported on zoned block devices. + * Partitions are not supported on host managed zoned block devices. */ - if (bdev_is_zoned(bdev)) { - pr_warn("%s: ignoring partition table on zoned block device\n", + if (disk->queue->limits.zoned == BLK_ZONED_HM) { + pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 33f71983e001..6078064684c6 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -298,6 +298,59 @@ out: return status; } +struct iort_workaround_oem_info { + char oem_id[ACPI_OEM_ID_SIZE + 1]; + char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; + u32 oem_revision; +}; + +static bool apply_id_count_workaround; + +static struct iort_workaround_oem_info wa_info[] __initdata = { + { + .oem_id = "HISI ", + .oem_table_id = "HIP07 ", + .oem_revision = 0, + }, { + .oem_id = "HISI ", + .oem_table_id = "HIP08 ", + .oem_revision = 0, + } +}; + +static void __init +iort_check_id_count_workaround(struct acpi_table_header *tbl) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(wa_info); i++) { + if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) && + !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) && + wa_info[i].oem_revision == tbl->oem_revision) { + apply_id_count_workaround = true; + pr_warn(FW_BUG "ID count for ID mapping entry is wrong, applying workaround\n"); + break; + } + } +} + +static inline u32 iort_get_map_max(struct acpi_iort_id_mapping *map) +{ + u32 map_max = map->input_base + map->id_count; + + /* + * The IORT specification revision D (Section 3, table 4, page 9) says + * Number of IDs = The number of IDs in the range minus one, but the + * IORT code ignored the "minus one", and some firmware did that too, + * so apply a workaround here to keep compatible with both the spec + * compliant and non-spec compliant firmwares. + */ + if (apply_id_count_workaround) + map_max--; + + return map_max; +} + static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in, u32 *rid_out) { @@ -314,8 +367,7 @@ static int iort_id_map(struct acpi_iort_id_mapping *map, u8 type, u32 rid_in, return -ENXIO; } - if (rid_in < map->input_base || - (rid_in >= map->input_base + map->id_count)) + if (rid_in < map->input_base || rid_in > iort_get_map_max(map)) return -ENXIO; *rid_out = map->output_base + (rid_in - map->input_base); @@ -1631,5 +1683,6 @@ void __init acpi_iort_init(void) return; } + iort_check_id_count_workaround(iort_table); iort_init_platform_devices(); } diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index aad00d2b28f5..cc87004d5e2d 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc) } if (!to) { printk ("No more free channels for FS50..\n"); + kfree(vcc); return -EBUSY; } vcc->channo = dev->channo; @@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc) if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) || ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) { printk ("Channel is in use for FS155.\n"); + kfree(vcc); return -EBUSY; } } @@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc) tc, sizeof (struct fs_transmit_config)); if (!tc) { fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n"); + kfree(vcc); return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 01a793a0cbf7..30a1e3ac21d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1004,7 +1004,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ - {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, /* Navi12 */ {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 5a61a5596912..e6afe4faeca6 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1916,73 +1916,90 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, return parent_lct + 1; } -static int drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt) +static bool drm_dp_mst_is_dp_mst_end_device(u8 pdt, bool mcs) +{ + switch (pdt) { + case DP_PEER_DEVICE_DP_LEGACY_CONV: + case DP_PEER_DEVICE_SST_SINK: + return true; + case DP_PEER_DEVICE_MST_BRANCHING: + /* For sst branch device */ + if (!mcs) + return true; + + return false; + } + return true; +} + +static int +drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt, + bool new_mcs) { struct drm_dp_mst_topology_mgr *mgr = port->mgr; struct drm_dp_mst_branch *mstb; u8 rad[8], lct; int ret = 0; - if (port->pdt == new_pdt) + if (port->pdt == new_pdt && port->mcs == new_mcs) return 0; /* Teardown the old pdt, if there is one */ - switch (port->pdt) { - case DP_PEER_DEVICE_DP_LEGACY_CONV: - case DP_PEER_DEVICE_SST_SINK: - /* - * If the new PDT would also have an i2c bus, don't bother - * with reregistering it - */ - if (new_pdt == DP_PEER_DEVICE_DP_LEGACY_CONV || - new_pdt == DP_PEER_DEVICE_SST_SINK) { - port->pdt = new_pdt; - return 0; - } + if (port->pdt != DP_PEER_DEVICE_NONE) { + if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + /* + * If the new PDT would also have an i2c bus, + * don't bother with reregistering it + */ + if (new_pdt != DP_PEER_DEVICE_NONE && + drm_dp_mst_is_dp_mst_end_device(new_pdt, new_mcs)) { + port->pdt = new_pdt; + port->mcs = new_mcs; + return 0; + } - /* remove i2c over sideband */ - drm_dp_mst_unregister_i2c_bus(&port->aux); - break; - case DP_PEER_DEVICE_MST_BRANCHING: - mutex_lock(&mgr->lock); - drm_dp_mst_topology_put_mstb(port->mstb); - port->mstb = NULL; - mutex_unlock(&mgr->lock); - break; + /* remove i2c over sideband */ + drm_dp_mst_unregister_i2c_bus(&port->aux); + } else { + mutex_lock(&mgr->lock); + drm_dp_mst_topology_put_mstb(port->mstb); + port->mstb = NULL; + mutex_unlock(&mgr->lock); + } } port->pdt = new_pdt; - switch (port->pdt) { - case DP_PEER_DEVICE_DP_LEGACY_CONV: - case DP_PEER_DEVICE_SST_SINK: - /* add i2c over sideband */ - ret = drm_dp_mst_register_i2c_bus(&port->aux); - break; + port->mcs = new_mcs; - case DP_PEER_DEVICE_MST_BRANCHING: - lct = drm_dp_calculate_rad(port, rad); - mstb = drm_dp_add_mst_branch_device(lct, rad); - if (!mstb) { - ret = -ENOMEM; - DRM_ERROR("Failed to create MSTB for port %p", port); - goto out; - } + if (port->pdt != DP_PEER_DEVICE_NONE) { + if (drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { + /* add i2c over sideband */ + ret = drm_dp_mst_register_i2c_bus(&port->aux); + } else { + lct = drm_dp_calculate_rad(port, rad); + mstb = drm_dp_add_mst_branch_device(lct, rad); + if (!mstb) { + ret = -ENOMEM; + DRM_ERROR("Failed to create MSTB for port %p", + port); + goto out; + } - mutex_lock(&mgr->lock); - port->mstb = mstb; - mstb->mgr = port->mgr; - mstb->port_parent = port; + mutex_lock(&mgr->lock); + port->mstb = mstb; + mstb->mgr = port->mgr; + mstb->port_parent = port; - /* - * Make sure this port's memory allocation stays - * around until its child MSTB releases it - */ - drm_dp_mst_get_port_malloc(port); - mutex_unlock(&mgr->lock); + /* + * Make sure this port's memory allocation stays + * around until its child MSTB releases it + */ + drm_dp_mst_get_port_malloc(port); + mutex_unlock(&mgr->lock); - /* And make sure we send a link address for this */ - ret = 1; - break; + /* And make sure we send a link address for this */ + ret = 1; + } } out: @@ -2135,9 +2152,8 @@ drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb, goto error; } - if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV || - port->pdt == DP_PEER_DEVICE_SST_SINK) && - port->port_num >= DP_MST_LOGICAL_PORT_0) { + if (port->pdt != DP_PEER_DEVICE_NONE && + drm_dp_mst_is_dp_mst_end_device(port->pdt, port->mcs)) { port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); drm_connector_set_tile_property(port->connector); @@ -2201,6 +2217,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, struct drm_dp_mst_port *port; int old_ddps = 0, ret; u8 new_pdt = DP_PEER_DEVICE_NONE; + bool new_mcs = 0; bool created = false, send_link_addr = false, changed = false; port = drm_dp_get_port(mstb, port_msg->port_number); @@ -2245,7 +2262,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, port->input = port_msg->input_port; if (!port->input) new_pdt = port_msg->peer_device_type; - port->mcs = port_msg->mcs; + new_mcs = port_msg->mcs; port->ddps = port_msg->ddps; port->ldps = port_msg->legacy_device_plug_status; port->dpcd_rev = port_msg->dpcd_revision; @@ -2272,7 +2289,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, } } - ret = drm_dp_port_set_pdt(port, new_pdt); + ret = drm_dp_port_set_pdt(port, new_pdt, new_mcs); if (ret == 1) { send_link_addr = true; } else if (ret < 0) { @@ -2286,7 +2303,8 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb, * we're coming out of suspend. In this case, always resend the link * address if there's an MSTB on this port */ - if (!created && port->pdt == DP_PEER_DEVICE_MST_BRANCHING) + if (!created && port->pdt == DP_PEER_DEVICE_MST_BRANCHING && + port->mcs) send_link_addr = true; if (port->connector) @@ -2323,6 +2341,7 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, struct drm_dp_mst_port *port; int old_ddps, old_input, ret, i; u8 new_pdt; + bool new_mcs; bool dowork = false, create_connector = false; port = drm_dp_get_port(mstb, conn_stat->port_number); @@ -2354,7 +2373,6 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, old_ddps = port->ddps; old_input = port->input; port->input = conn_stat->input_port; - port->mcs = conn_stat->message_capability_status; port->ldps = conn_stat->legacy_device_plug_status; port->ddps = conn_stat->displayport_device_plug_status; @@ -2367,8 +2385,8 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, } new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type; - - ret = drm_dp_port_set_pdt(port, new_pdt); + new_mcs = conn_stat->message_capability_status; + ret = drm_dp_port_set_pdt(port, new_pdt, new_mcs); if (ret == 1) { dowork = true; } else if (ret < 0) { @@ -3929,6 +3947,8 @@ drm_dp_mst_detect_port(struct drm_connector *connector, switch (port->pdt) { case DP_PEER_DEVICE_NONE: case DP_PEER_DEVICE_MST_BRANCHING: + if (!port->mcs) + ret = connector_status_connected; break; case DP_PEER_DEVICE_SST_SINK: @@ -4541,7 +4561,7 @@ drm_dp_delayed_destroy_port(struct drm_dp_mst_port *port) if (port->connector) port->mgr->cbs->destroy_connector(port->mgr, port->connector); - drm_dp_port_set_pdt(port, DP_PEER_DEVICE_NONE); + drm_dp_port_set_pdt(port, DP_PEER_DEVICE_NONE, port->mcs); drm_dp_mst_put_port_malloc(port); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 3d4f5775a4ba..25235ef630c1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -9,16 +9,16 @@ #include "i915_gem_ioctls.h" #include "i915_gem_object.h" -static __always_inline u32 __busy_read_flag(u8 id) +static __always_inline u32 __busy_read_flag(u16 id) { - if (id == (u8)I915_ENGINE_CLASS_INVALID) + if (id == (u16)I915_ENGINE_CLASS_INVALID) return 0xffff0000u; GEM_BUG_ON(id >= 16); return 0x10000u << id; } -static __always_inline u32 __busy_write_id(u8 id) +static __always_inline u32 __busy_write_id(u16 id) { /* * The uABI guarantees an active writer is also amongst the read @@ -29,14 +29,14 @@ static __always_inline u32 __busy_write_id(u8 id) * last_read - hence we always set both read and write busy for * last_write. */ - if (id == (u8)I915_ENGINE_CLASS_INVALID) + if (id == (u16)I915_ENGINE_CLASS_INVALID) return 0xffffffffu; return (id + 1) | __busy_read_flag(id); } static __always_inline unsigned int -__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id)) +__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id)) { const struct i915_request *rq; @@ -57,7 +57,7 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u8 id)) return 0; /* Beware type-expansion follies! */ - BUILD_BUG_ON(!typecheck(u8, rq->engine->uabi_class)); + BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class)); return flag(rq->engine->uabi_class); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 4c72d74d6576..0dbb44d30885 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -402,7 +402,7 @@ struct get_pages_work { static struct sg_table * __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, - struct page **pvec, int num_pages) + struct page **pvec, unsigned long num_pages) { unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; @@ -448,9 +448,10 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work) { struct get_pages_work *work = container_of(_work, typeof(*work), work); struct drm_i915_gem_object *obj = work->obj; - const int npages = obj->base.size >> PAGE_SHIFT; + const unsigned long npages = obj->base.size >> PAGE_SHIFT; + unsigned long pinned; struct page **pvec; - int pinned, ret; + int ret; ret = -ENOMEM; pinned = 0; @@ -553,7 +554,7 @@ __i915_gem_userptr_get_pages_schedule(struct drm_i915_gem_object *obj) static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) { - const int num_pages = obj->base.size >> PAGE_SHIFT; + const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; struct mm_struct *mm = obj->userptr.mm->mm; struct page **pvec; struct sg_table *pages; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 17f1f1441efc..2b446474e010 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -274,8 +274,8 @@ struct intel_engine_cs { u8 class; u8 instance; - u8 uabi_class; - u8 uabi_instance; + u16 uabi_class; + u16 uabi_instance; u32 uabi_capabilities; u32 context_size; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index c083f516fd35..44727806dfd7 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1177,6 +1177,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2)); vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1))); do { + GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE); vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma; iter->dma += I915_GTT_PAGE_SIZE; @@ -1660,6 +1661,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt)); do { + GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE); vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma); iter.dma += I915_GTT_PAGE_SIZE; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index f61364f7c471..88b431a267af 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -78,8 +78,10 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file) { + struct panfrost_file_priv *priv = file->driver_priv; struct panfrost_gem_object *bo; struct drm_panfrost_create_bo *args = data; + struct panfrost_gem_mapping *mapping; if (!args->size || args->pad || (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP))) @@ -95,7 +97,14 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data, if (IS_ERR(bo)) return PTR_ERR(bo); - args->offset = bo->node.start << PAGE_SHIFT; + mapping = panfrost_gem_mapping_get(bo, priv); + if (!mapping) { + drm_gem_object_put_unlocked(&bo->base.base); + return -EINVAL; + } + + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); return 0; } @@ -119,6 +128,11 @@ panfrost_lookup_bos(struct drm_device *dev, struct drm_panfrost_submit *args, struct panfrost_job *job) { + struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_object *bo; + unsigned int i; + int ret; + job->bo_count = args->bo_handle_count; if (!job->bo_count) @@ -130,9 +144,32 @@ panfrost_lookup_bos(struct drm_device *dev, if (!job->implicit_fences) return -ENOMEM; - return drm_gem_objects_lookup(file_priv, - (void __user *)(uintptr_t)args->bo_handles, - job->bo_count, &job->bos); + ret = drm_gem_objects_lookup(file_priv, + (void __user *)(uintptr_t)args->bo_handles, + job->bo_count, &job->bos); + if (ret) + return ret; + + job->mappings = kvmalloc_array(job->bo_count, + sizeof(struct panfrost_gem_mapping *), + GFP_KERNEL | __GFP_ZERO); + if (!job->mappings) + return -ENOMEM; + + for (i = 0; i < job->bo_count; i++) { + struct panfrost_gem_mapping *mapping; + + bo = to_panfrost_bo(job->bos[i]); + mapping = panfrost_gem_mapping_get(bo, priv); + if (!mapping) { + ret = -EINVAL; + break; + } + + job->mappings[i] = mapping; + } + + return ret; } /** @@ -320,7 +357,9 @@ out: static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct panfrost_file_priv *priv = file_priv->driver_priv; struct drm_panfrost_get_bo_offset *args = data; + struct panfrost_gem_mapping *mapping; struct drm_gem_object *gem_obj; struct panfrost_gem_object *bo; @@ -331,18 +370,26 @@ static int panfrost_ioctl_get_bo_offset(struct drm_device *dev, void *data, } bo = to_panfrost_bo(gem_obj); - args->offset = bo->node.start << PAGE_SHIFT; - + mapping = panfrost_gem_mapping_get(bo, priv); drm_gem_object_put_unlocked(gem_obj); + + if (!mapping) + return -EINVAL; + + args->offset = mapping->mmnode.start << PAGE_SHIFT; + panfrost_gem_mapping_put(mapping); return 0; } static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct panfrost_file_priv *priv = file_priv->driver_priv; struct drm_panfrost_madvise *args = data; struct panfrost_device *pfdev = dev->dev_private; struct drm_gem_object *gem_obj; + struct panfrost_gem_object *bo; + int ret = 0; gem_obj = drm_gem_object_lookup(file_priv, args->handle); if (!gem_obj) { @@ -350,22 +397,48 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, return -ENOENT; } + bo = to_panfrost_bo(gem_obj); + mutex_lock(&pfdev->shrinker_lock); + mutex_lock(&bo->mappings.lock); + if (args->madv == PANFROST_MADV_DONTNEED) { + struct panfrost_gem_mapping *first; + + first = list_first_entry(&bo->mappings.list, + struct panfrost_gem_mapping, + node); + + /* + * If we want to mark the BO purgeable, there must be only one + * user: the caller FD. + * We could do something smarter and mark the BO purgeable only + * when all its users have marked it purgeable, but globally + * visible/shared BOs are likely to never be marked purgeable + * anyway, so let's not bother. + */ + if (!list_is_singular(&bo->mappings.list) || + WARN_ON_ONCE(first->mmu != &priv->mmu)) { + ret = -EINVAL; + goto out_unlock_mappings; + } + } + args->retained = drm_gem_shmem_madvise(gem_obj, args->madv); if (args->retained) { - struct panfrost_gem_object *bo = to_panfrost_bo(gem_obj); - if (args->madv == PANFROST_MADV_DONTNEED) list_add_tail(&bo->base.madv_list, &pfdev->shrinker_list); else if (args->madv == PANFROST_MADV_WILLNEED) list_del_init(&bo->base.madv_list); } + +out_unlock_mappings: + mutex_unlock(&bo->mappings.lock); mutex_unlock(&pfdev->shrinker_lock); drm_gem_object_put_unlocked(gem_obj); - return 0; + return ret; } int panfrost_unstable_ioctl_check(void) diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index fd766b1395fb..17b654e1eb94 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -29,6 +29,12 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) list_del_init(&bo->base.madv_list); mutex_unlock(&pfdev->shrinker_lock); + /* + * If we still have mappings attached to the BO, there's a problem in + * our refcounting. + */ + WARN_ON_ONCE(!list_empty(&bo->mappings.list)); + if (bo->sgts) { int i; int n_sgt = bo->base.base.size / SZ_2M; @@ -46,6 +52,69 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj) drm_gem_shmem_free_object(obj); } +struct panfrost_gem_mapping * +panfrost_gem_mapping_get(struct panfrost_gem_object *bo, + struct panfrost_file_priv *priv) +{ + struct panfrost_gem_mapping *iter, *mapping = NULL; + + mutex_lock(&bo->mappings.lock); + list_for_each_entry(iter, &bo->mappings.list, node) { + if (iter->mmu == &priv->mmu) { + kref_get(&iter->refcount); + mapping = iter; + break; + } + } + mutex_unlock(&bo->mappings.lock); + + return mapping; +} + +static void +panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping) +{ + struct panfrost_file_priv *priv; + + if (mapping->active) + panfrost_mmu_unmap(mapping); + + priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu); + spin_lock(&priv->mm_lock); + if (drm_mm_node_allocated(&mapping->mmnode)) + drm_mm_remove_node(&mapping->mmnode); + spin_unlock(&priv->mm_lock); +} + +static void panfrost_gem_mapping_release(struct kref *kref) +{ + struct panfrost_gem_mapping *mapping; + + mapping = container_of(kref, struct panfrost_gem_mapping, refcount); + + panfrost_gem_teardown_mapping(mapping); + drm_gem_object_put_unlocked(&mapping->obj->base.base); + kfree(mapping); +} + +void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping) +{ + if (!mapping) + return; + + kref_put(&mapping->refcount, panfrost_gem_mapping_release); +} + +void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo) +{ + struct panfrost_gem_mapping *mapping; + + mutex_lock(&bo->mappings.lock); + list_for_each_entry(mapping, &bo->mappings.list, node) + panfrost_gem_teardown_mapping(mapping); + mutex_unlock(&bo->mappings.lock); +} + int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) { int ret; @@ -54,6 +123,16 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) struct panfrost_gem_object *bo = to_panfrost_bo(obj); unsigned long color = bo->noexec ? PANFROST_BO_NOEXEC : 0; struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_mapping *mapping; + + mapping = kzalloc(sizeof(*mapping), GFP_KERNEL); + if (!mapping) + return -ENOMEM; + + INIT_LIST_HEAD(&mapping->node); + kref_init(&mapping->refcount); + drm_gem_object_get(obj); + mapping->obj = bo; /* * Executable buffers cannot cross a 16MB boundary as the program @@ -66,37 +145,48 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) else align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0; - bo->mmu = &priv->mmu; + mapping->mmu = &priv->mmu; spin_lock(&priv->mm_lock); - ret = drm_mm_insert_node_generic(&priv->mm, &bo->node, + ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode, size >> PAGE_SHIFT, align, color, 0); spin_unlock(&priv->mm_lock); if (ret) - return ret; + goto err; if (!bo->is_heap) { - ret = panfrost_mmu_map(bo); - if (ret) { - spin_lock(&priv->mm_lock); - drm_mm_remove_node(&bo->node); - spin_unlock(&priv->mm_lock); - } + ret = panfrost_mmu_map(mapping); + if (ret) + goto err; } + + mutex_lock(&bo->mappings.lock); + WARN_ON(bo->base.madv != PANFROST_MADV_WILLNEED); + list_add_tail(&mapping->node, &bo->mappings.list); + mutex_unlock(&bo->mappings.lock); + +err: + if (ret) + panfrost_gem_mapping_put(mapping); return ret; } void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) { - struct panfrost_gem_object *bo = to_panfrost_bo(obj); struct panfrost_file_priv *priv = file_priv->driver_priv; + struct panfrost_gem_object *bo = to_panfrost_bo(obj); + struct panfrost_gem_mapping *mapping = NULL, *iter; - if (bo->is_mapped) - panfrost_mmu_unmap(bo); + mutex_lock(&bo->mappings.lock); + list_for_each_entry(iter, &bo->mappings.list, node) { + if (iter->mmu == &priv->mmu) { + mapping = iter; + list_del(&iter->node); + break; + } + } + mutex_unlock(&bo->mappings.lock); - spin_lock(&priv->mm_lock); - if (drm_mm_node_allocated(&bo->node)) - drm_mm_remove_node(&bo->node); - spin_unlock(&priv->mm_lock); + panfrost_gem_mapping_put(mapping); } static int panfrost_gem_pin(struct drm_gem_object *obj) @@ -136,6 +226,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t if (!obj) return NULL; + INIT_LIST_HEAD(&obj->mappings.list); + mutex_init(&obj->mappings.lock); obj->base.base.funcs = &panfrost_gem_funcs; return &obj->base.base; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index 4b17e7308764..ca1bc9019600 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -13,23 +13,46 @@ struct panfrost_gem_object { struct drm_gem_shmem_object base; struct sg_table *sgts; - struct panfrost_mmu *mmu; - struct drm_mm_node node; - bool is_mapped :1; + /* + * Use a list for now. If searching a mapping ever becomes the + * bottleneck, we should consider using an RB-tree, or even better, + * let the core store drm_gem_object_mapping entries (where we + * could place driver specific data) instead of drm_gem_object ones + * in its drm_file->object_idr table. + * + * struct drm_gem_object_mapping { + * struct drm_gem_object *obj; + * void *driver_priv; + * }; + */ + struct { + struct list_head list; + struct mutex lock; + } mappings; + bool noexec :1; bool is_heap :1; }; +struct panfrost_gem_mapping { + struct list_head node; + struct kref refcount; + struct panfrost_gem_object *obj; + struct drm_mm_node mmnode; + struct panfrost_mmu *mmu; + bool active :1; +}; + static inline struct panfrost_gem_object *to_panfrost_bo(struct drm_gem_object *obj) { return container_of(to_drm_gem_shmem_obj(obj), struct panfrost_gem_object, base); } -static inline -struct panfrost_gem_object *drm_mm_node_to_panfrost_bo(struct drm_mm_node *node) +static inline struct panfrost_gem_mapping * +drm_mm_node_to_panfrost_mapping(struct drm_mm_node *node) { - return container_of(node, struct panfrost_gem_object, node); + return container_of(node, struct panfrost_gem_mapping, mmnode); } struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t size); @@ -49,6 +72,12 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv); void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv); +struct panfrost_gem_mapping * +panfrost_gem_mapping_get(struct panfrost_gem_object *bo, + struct panfrost_file_priv *priv); +void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping); +void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo); + void panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 458f0fa68111..f5dd7b29bc95 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -39,11 +39,12 @@ panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc static bool panfrost_gem_purge(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); + struct panfrost_gem_object *bo = to_panfrost_bo(obj); if (!mutex_trylock(&shmem->pages_lock)) return false; - panfrost_mmu_unmap(to_panfrost_bo(obj)); + panfrost_gem_teardown_mappings(bo); drm_gem_shmem_purge_locked(obj); mutex_unlock(&shmem->pages_lock); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index d411eb6c8eb9..e364ee00f3d0 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -268,9 +268,20 @@ static void panfrost_job_cleanup(struct kref *ref) dma_fence_put(job->done_fence); dma_fence_put(job->render_done_fence); - if (job->bos) { + if (job->mappings) { for (i = 0; i < job->bo_count; i++) + panfrost_gem_mapping_put(job->mappings[i]); + kvfree(job->mappings); + } + + if (job->bos) { + struct panfrost_gem_object *bo; + + for (i = 0; i < job->bo_count; i++) { + bo = to_panfrost_bo(job->bos[i]); drm_gem_object_put_unlocked(job->bos[i]); + } + kvfree(job->bos); } diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h index 62454128a792..bbd3ba97ff67 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.h +++ b/drivers/gpu/drm/panfrost/panfrost_job.h @@ -32,6 +32,7 @@ struct panfrost_job { /* Exclusive fences we have taken from the BOs to wait for */ struct dma_fence **implicit_fences; + struct panfrost_gem_mapping **mappings; struct drm_gem_object **bos; u32 bo_count; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index a3ed64a1f15e..763cfca886a7 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -269,14 +269,15 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, return 0; } -int panfrost_mmu_map(struct panfrost_gem_object *bo) +int panfrost_mmu_map(struct panfrost_gem_mapping *mapping) { + struct panfrost_gem_object *bo = mapping->obj; struct drm_gem_object *obj = &bo->base.base; struct panfrost_device *pfdev = to_panfrost_device(obj->dev); struct sg_table *sgt; int prot = IOMMU_READ | IOMMU_WRITE; - if (WARN_ON(bo->is_mapped)) + if (WARN_ON(mapping->active)) return 0; if (bo->noexec) @@ -286,25 +287,28 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo) if (WARN_ON(IS_ERR(sgt))) return PTR_ERR(sgt); - mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt); - bo->is_mapped = true; + mmu_map_sg(pfdev, mapping->mmu, mapping->mmnode.start << PAGE_SHIFT, + prot, sgt); + mapping->active = true; return 0; } -void panfrost_mmu_unmap(struct panfrost_gem_object *bo) +void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping) { + struct panfrost_gem_object *bo = mapping->obj; struct drm_gem_object *obj = &bo->base.base; struct panfrost_device *pfdev = to_panfrost_device(obj->dev); - struct io_pgtable_ops *ops = bo->mmu->pgtbl_ops; - u64 iova = bo->node.start << PAGE_SHIFT; - size_t len = bo->node.size << PAGE_SHIFT; + struct io_pgtable_ops *ops = mapping->mmu->pgtbl_ops; + u64 iova = mapping->mmnode.start << PAGE_SHIFT; + size_t len = mapping->mmnode.size << PAGE_SHIFT; size_t unmapped_len = 0; - if (WARN_ON(!bo->is_mapped)) + if (WARN_ON(!mapping->active)) return; - dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len); + dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", + mapping->mmu->as, iova, len); while (unmapped_len < len) { size_t unmapped_page; @@ -318,8 +322,9 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo) unmapped_len += pgsize; } - panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len); - bo->is_mapped = false; + panfrost_mmu_flush_range(pfdev, mapping->mmu, + mapping->mmnode.start << PAGE_SHIFT, len); + mapping->active = false; } static void mmu_tlb_inv_context_s1(void *cookie) @@ -394,10 +399,10 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv) free_io_pgtable_ops(mmu->pgtbl_ops); } -static struct panfrost_gem_object * -addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr) +static struct panfrost_gem_mapping * +addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr) { - struct panfrost_gem_object *bo = NULL; + struct panfrost_gem_mapping *mapping = NULL; struct panfrost_file_priv *priv; struct drm_mm_node *node; u64 offset = addr >> PAGE_SHIFT; @@ -418,8 +423,9 @@ found_mmu: drm_mm_for_each_node(node, &priv->mm) { if (offset >= node->start && offset < (node->start + node->size)) { - bo = drm_mm_node_to_panfrost_bo(node); - drm_gem_object_get(&bo->base.base); + mapping = drm_mm_node_to_panfrost_mapping(node); + + kref_get(&mapping->refcount); break; } } @@ -427,7 +433,7 @@ found_mmu: spin_unlock(&priv->mm_lock); out: spin_unlock(&pfdev->as_lock); - return bo; + return mapping; } #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE) @@ -436,28 +442,30 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr) { int ret, i; + struct panfrost_gem_mapping *bomapping; struct panfrost_gem_object *bo; struct address_space *mapping; pgoff_t page_offset; struct sg_table *sgt; struct page **pages; - bo = addr_to_drm_mm_node(pfdev, as, addr); - if (!bo) + bomapping = addr_to_mapping(pfdev, as, addr); + if (!bomapping) return -ENOENT; + bo = bomapping->obj; if (!bo->is_heap) { dev_WARN(pfdev->dev, "matching BO is not heap type (GPU VA = %llx)", - bo->node.start << PAGE_SHIFT); + bomapping->mmnode.start << PAGE_SHIFT); ret = -EINVAL; goto err_bo; } - WARN_ON(bo->mmu->as != as); + WARN_ON(bomapping->mmu->as != as); /* Assume 2MB alignment and size multiple */ addr &= ~((u64)SZ_2M - 1); page_offset = addr >> PAGE_SHIFT; - page_offset -= bo->node.start; + page_offset -= bomapping->mmnode.start; mutex_lock(&bo->base.pages_lock); @@ -509,13 +517,14 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, goto err_map; } - mmu_map_sg(pfdev, bo->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt); + mmu_map_sg(pfdev, bomapping->mmu, addr, + IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt); - bo->is_mapped = true; + bomapping->active = true; dev_dbg(pfdev->dev, "mapped page fault @ AS%d %llx", as, addr); - drm_gem_object_put_unlocked(&bo->base.base); + panfrost_gem_mapping_put(bomapping); return 0; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h index 7c5b6775ae23..44fc2edf63ce 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.h +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h @@ -4,12 +4,12 @@ #ifndef __PANFROST_MMU_H__ #define __PANFROST_MMU_H__ -struct panfrost_gem_object; +struct panfrost_gem_mapping; struct panfrost_file_priv; struct panfrost_mmu; -int panfrost_mmu_map(struct panfrost_gem_object *bo); -void panfrost_mmu_unmap(struct panfrost_gem_object *bo); +int panfrost_mmu_map(struct panfrost_gem_mapping *mapping); +void panfrost_mmu_unmap(struct panfrost_gem_mapping *mapping); int panfrost_mmu_init(struct panfrost_device *pfdev); void panfrost_mmu_fini(struct panfrost_device *pfdev); diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c index 2c04e858c50a..684820448be3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c +++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c @@ -25,7 +25,7 @@ #define V4_SHADERS_PER_COREGROUP 4 struct panfrost_perfcnt { - struct panfrost_gem_object *bo; + struct panfrost_gem_mapping *mapping; size_t bosize; void *buf; struct panfrost_file_priv *user; @@ -49,7 +49,7 @@ static int panfrost_perfcnt_dump_locked(struct panfrost_device *pfdev) int ret; reinit_completion(&pfdev->perfcnt->dump_comp); - gpuva = pfdev->perfcnt->bo->node.start << PAGE_SHIFT; + gpuva = pfdev->perfcnt->mapping->mmnode.start << PAGE_SHIFT; gpu_write(pfdev, GPU_PERFCNT_BASE_LO, gpuva); gpu_write(pfdev, GPU_PERFCNT_BASE_HI, gpuva >> 32); gpu_write(pfdev, GPU_INT_CLEAR, @@ -89,17 +89,22 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, if (IS_ERR(bo)) return PTR_ERR(bo); - perfcnt->bo = to_panfrost_bo(&bo->base); - /* Map the perfcnt buf in the address space attached to file_priv. */ - ret = panfrost_gem_open(&perfcnt->bo->base.base, file_priv); + ret = panfrost_gem_open(&bo->base, file_priv); if (ret) goto err_put_bo; + perfcnt->mapping = panfrost_gem_mapping_get(to_panfrost_bo(&bo->base), + user); + if (!perfcnt->mapping) { + ret = -EINVAL; + goto err_close_bo; + } + perfcnt->buf = drm_gem_shmem_vmap(&bo->base); if (IS_ERR(perfcnt->buf)) { ret = PTR_ERR(perfcnt->buf); - goto err_close_bo; + goto err_put_mapping; } /* @@ -154,12 +159,17 @@ static int panfrost_perfcnt_enable_locked(struct panfrost_device *pfdev, if (panfrost_has_hw_issue(pfdev, HW_ISSUE_8186)) gpu_write(pfdev, GPU_PRFCNT_TILER_EN, 0xffffffff); + /* The BO ref is retained by the mapping. */ + drm_gem_object_put_unlocked(&bo->base); + return 0; err_vunmap: - drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); + drm_gem_shmem_vunmap(&bo->base, perfcnt->buf); +err_put_mapping: + panfrost_gem_mapping_put(perfcnt->mapping); err_close_bo: - panfrost_gem_close(&perfcnt->bo->base.base, file_priv); + panfrost_gem_close(&bo->base, file_priv); err_put_bo: drm_gem_object_put_unlocked(&bo->base); return ret; @@ -182,11 +192,11 @@ static int panfrost_perfcnt_disable_locked(struct panfrost_device *pfdev, GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_OFF)); perfcnt->user = NULL; - drm_gem_shmem_vunmap(&perfcnt->bo->base.base, perfcnt->buf); + drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf); perfcnt->buf = NULL; - panfrost_gem_close(&perfcnt->bo->base.base, file_priv); - drm_gem_object_put_unlocked(&perfcnt->bo->base.base); - perfcnt->bo = NULL; + panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv); + panfrost_gem_mapping_put(perfcnt->mapping); + perfcnt->mapping = NULL; pm_runtime_mark_last_busy(pfdev->dev); pm_runtime_put_autosuspend(pfdev->dev); diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 6c64d50c9aae..01c2eeb02aa9 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -294,9 +294,10 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn) long reg; if (bypass_attn & (1 << channel)) - reg = (volt * 1024) / 2250; + reg = DIV_ROUND_CLOSEST(volt * 1024, 2250); else - reg = (volt * r[1] * 1024) / ((r[0] + r[1]) * 2250); + reg = DIV_ROUND_CLOSEST(volt * r[1] * 1024, + (r[0] + r[1]) * 2250); return clamp_val(reg, 0, 1023) & (0xff << 2); } diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 1f3b30b085b9..d018b20089ec 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -51,6 +51,7 @@ struct hwmon_device_attribute { #define to_hwmon_attr(d) \ container_of(d, struct hwmon_device_attribute, dev_attr) +#define to_dev_attr(a) container_of(a, struct device_attribute, attr) /* * Thermal zone information @@ -58,7 +59,7 @@ struct hwmon_device_attribute { * also provides the sensor index. */ struct hwmon_thermal_data { - struct hwmon_device *hwdev; /* Reference to hwmon device */ + struct device *dev; /* Reference to hwmon device */ int index; /* sensor index */ }; @@ -95,9 +96,27 @@ static const struct attribute_group *hwmon_dev_attr_groups[] = { NULL }; +static void hwmon_free_attrs(struct attribute **attrs) +{ + int i; + + for (i = 0; attrs[i]; i++) { + struct device_attribute *dattr = to_dev_attr(attrs[i]); + struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr); + + kfree(hattr); + } + kfree(attrs); +} + static void hwmon_dev_release(struct device *dev) { - kfree(to_hwmon_device(dev)); + struct hwmon_device *hwdev = to_hwmon_device(dev); + + if (hwdev->group.attrs) + hwmon_free_attrs(hwdev->group.attrs); + kfree(hwdev->groups); + kfree(hwdev); } static struct class hwmon_class = { @@ -119,11 +138,11 @@ static DEFINE_IDA(hwmon_ida); static int hwmon_thermal_get_temp(void *data, int *temp) { struct hwmon_thermal_data *tdata = data; - struct hwmon_device *hwdev = tdata->hwdev; + struct hwmon_device *hwdev = to_hwmon_device(tdata->dev); int ret; long t; - ret = hwdev->chip->ops->read(&hwdev->dev, hwmon_temp, hwmon_temp_input, + ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input, tdata->index, &t); if (ret < 0) return ret; @@ -137,8 +156,7 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = { .get_temp = hwmon_thermal_get_temp, }; -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { struct hwmon_thermal_data *tdata; struct thermal_zone_device *tzd; @@ -147,10 +165,10 @@ static int hwmon_thermal_add_sensor(struct device *dev, if (!tdata) return -ENOMEM; - tdata->hwdev = hwdev; + tdata->dev = dev; tdata->index = index; - tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata, + tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, &hwmon_thermal_ops); /* * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, @@ -162,8 +180,7 @@ static int hwmon_thermal_add_sensor(struct device *dev, return 0; } #else -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { return 0; } @@ -250,8 +267,7 @@ static bool is_string_attr(enum hwmon_sensor_types type, u32 attr) (type == hwmon_fan && attr == hwmon_fan_label); } -static struct attribute *hwmon_genattr(struct device *dev, - const void *drvdata, +static struct attribute *hwmon_genattr(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int index, @@ -279,7 +295,7 @@ static struct attribute *hwmon_genattr(struct device *dev, if ((mode & 0222) && !ops->write) return ERR_PTR(-EINVAL); - hattr = devm_kzalloc(dev, sizeof(*hattr), GFP_KERNEL); + hattr = kzalloc(sizeof(*hattr), GFP_KERNEL); if (!hattr) return ERR_PTR(-ENOMEM); @@ -492,8 +508,7 @@ static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info) return n; } -static int hwmon_genattrs(struct device *dev, - const void *drvdata, +static int hwmon_genattrs(const void *drvdata, struct attribute **attrs, const struct hwmon_ops *ops, const struct hwmon_channel_info *info) @@ -519,7 +534,7 @@ static int hwmon_genattrs(struct device *dev, attr_mask &= ~BIT(attr); if (attr >= template_size) return -EINVAL; - a = hwmon_genattr(dev, drvdata, info->type, attr, i, + a = hwmon_genattr(drvdata, info->type, attr, i, templates[attr], ops); if (IS_ERR(a)) { if (PTR_ERR(a) != -ENOENT) @@ -533,8 +548,7 @@ static int hwmon_genattrs(struct device *dev, } static struct attribute ** -__hwmon_create_attrs(struct device *dev, const void *drvdata, - const struct hwmon_chip_info *chip) +__hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip) { int ret, i, aindex = 0, nattrs = 0; struct attribute **attrs; @@ -545,15 +559,17 @@ __hwmon_create_attrs(struct device *dev, const void *drvdata, if (nattrs == 0) return ERR_PTR(-EINVAL); - attrs = devm_kcalloc(dev, nattrs + 1, sizeof(*attrs), GFP_KERNEL); + attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return ERR_PTR(-ENOMEM); for (i = 0; chip->info[i]; i++) { - ret = hwmon_genattrs(dev, drvdata, &attrs[aindex], chip->ops, + ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops, chip->info[i]); - if (ret < 0) + if (ret < 0) { + hwmon_free_attrs(attrs); return ERR_PTR(ret); + } aindex += ret; } @@ -595,14 +611,13 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, for (i = 0; groups[i]; i++) ngroups++; - hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups), - GFP_KERNEL); + hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL); if (!hwdev->groups) { err = -ENOMEM; goto free_hwmon; } - attrs = __hwmon_create_attrs(dev, drvdata, chip); + attrs = __hwmon_create_attrs(drvdata, chip); if (IS_ERR(attrs)) { err = PTR_ERR(attrs); goto free_hwmon; @@ -647,8 +662,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, hwmon_temp_input, j)) continue; if (info[i]->config[j] & HWMON_T_INPUT) { - err = hwmon_thermal_add_sensor(dev, - hwdev, j); + err = hwmon_thermal_add_sensor(hdev, j); if (err) { device_unregister(hdev); /* @@ -667,7 +681,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; free_hwmon: - kfree(hwdev); + hwmon_dev_release(hdev); ida_remove: ida_simple_remove(&hwmon_ida, id); return ERR_PTR(err); diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c index f3dd2a17bd42..2e97e56c72c7 100644 --- a/drivers/hwmon/nct7802.c +++ b/drivers/hwmon/nct7802.c @@ -23,8 +23,8 @@ static const u8 REG_VOLTAGE[5] = { 0x09, 0x0a, 0x0c, 0x0d, 0x0e }; static const u8 REG_VOLTAGE_LIMIT_LSB[2][5] = { - { 0x40, 0x00, 0x42, 0x44, 0x46 }, - { 0x3f, 0x00, 0x41, 0x43, 0x45 }, + { 0x46, 0x00, 0x40, 0x42, 0x44 }, + { 0x45, 0x00, 0x3f, 0x41, 0x43 }, }; static const u8 REG_VOLTAGE_LIMIT_MSB[5] = { 0x48, 0x00, 0x47, 0x47, 0x48 }; @@ -58,6 +58,8 @@ static const u8 REG_VOLTAGE_LIMIT_MSB_SHIFT[2][5] = { struct nct7802_data { struct regmap *regmap; struct mutex access_lock; /* for multi-byte read and write operations */ + u8 in_status; + struct mutex in_alarm_lock; }; static ssize_t temp_type_show(struct device *dev, @@ -368,6 +370,66 @@ static ssize_t in_store(struct device *dev, struct device_attribute *attr, return err ? : count; } +static ssize_t in_alarm_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); + struct nct7802_data *data = dev_get_drvdata(dev); + int volt, min, max, ret; + unsigned int val; + + mutex_lock(&data->in_alarm_lock); + + /* + * The SMI Voltage status register is the only register giving a status + * for voltages. A bit is set for each input crossing a threshold, in + * both direction, but the "inside" or "outside" limits info is not + * available. Also this register is cleared on read. + * Note: this is not explicitly spelled out in the datasheet, but + * from experiment. + * To deal with this we use a status cache with one validity bit and + * one status bit for each input. Validity is cleared at startup and + * each time the register reports a change, and the status is processed + * by software based on current input value and limits. + */ + ret = regmap_read(data->regmap, 0x1e, &val); /* SMI Voltage status */ + if (ret < 0) + goto abort; + + /* invalidate cached status for all inputs crossing a threshold */ + data->in_status &= ~((val & 0x0f) << 4); + + /* if cached status for requested input is invalid, update it */ + if (!(data->in_status & (0x10 << sattr->index))) { + ret = nct7802_read_voltage(data, sattr->nr, 0); + if (ret < 0) + goto abort; + volt = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 1); + if (ret < 0) + goto abort; + min = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 2); + if (ret < 0) + goto abort; + max = ret; + + if (volt < min || volt > max) + data->in_status |= (1 << sattr->index); + else + data->in_status &= ~(1 << sattr->index); + + data->in_status |= 0x10 << sattr->index; + } + + ret = sprintf(buf, "%u\n", !!(data->in_status & (1 << sattr->index))); +abort: + mutex_unlock(&data->in_alarm_lock); + return ret; +} + static ssize_t temp_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -660,7 +722,7 @@ static const struct attribute_group nct7802_temp_group = { static SENSOR_DEVICE_ATTR_2_RO(in0_input, in, 0, 0); static SENSOR_DEVICE_ATTR_2_RW(in0_min, in, 0, 1); static SENSOR_DEVICE_ATTR_2_RW(in0_max, in, 0, 2); -static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, alarm, 0x1e, 3); +static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, in_alarm, 0, 3); static SENSOR_DEVICE_ATTR_2_RW(in0_beep, beep, 0x5a, 3); static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); @@ -668,19 +730,19 @@ static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); static SENSOR_DEVICE_ATTR_2_RO(in2_input, in, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_min, in, 2, 1); static SENSOR_DEVICE_ATTR_2_RW(in2_max, in, 2, 2); -static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, alarm, 0x1e, 0); +static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, in_alarm, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_beep, beep, 0x5a, 0); static SENSOR_DEVICE_ATTR_2_RO(in3_input, in, 3, 0); static SENSOR_DEVICE_ATTR_2_RW(in3_min, in, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_max, in, 3, 2); -static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, alarm, 0x1e, 1); +static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, in_alarm, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_beep, beep, 0x5a, 1); static SENSOR_DEVICE_ATTR_2_RO(in4_input, in, 4, 0); static SENSOR_DEVICE_ATTR_2_RW(in4_min, in, 4, 1); static SENSOR_DEVICE_ATTR_2_RW(in4_max, in, 4, 2); -static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, alarm, 0x1e, 2); +static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, in_alarm, 4, 2); static SENSOR_DEVICE_ATTR_2_RW(in4_beep, beep, 0x5a, 2); static struct attribute *nct7802_in_attrs[] = { @@ -1011,6 +1073,7 @@ static int nct7802_probe(struct i2c_client *client, return PTR_ERR(data->regmap); mutex_init(&data->access_lock); + mutex_init(&data->in_alarm_lock); ret = nct7802_init_chip(data); if (ret < 0) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index a1a035270cab..b273e421e910 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -2575,17 +2575,6 @@ isert_wait4logout(struct isert_conn *isert_conn) } } -static void -isert_wait4cmds(struct iscsi_conn *conn) -{ - isert_info("iscsi_conn %p\n", conn); - - if (conn->sess) { - target_sess_cmd_list_set_waiting(conn->sess->se_sess); - target_wait_for_sess_cmds(conn->sess->se_sess); - } -} - /** * isert_put_unsol_pending_cmds() - Drop commands waiting for * unsolicitate dataout @@ -2633,7 +2622,6 @@ static void isert_wait_conn(struct iscsi_conn *conn) ib_drain_qp(isert_conn->qp); isert_put_unsol_pending_cmds(conn); - isert_wait4cmds(conn); isert_wait4logout(isert_conn); queue_work(isert_release_wq, &isert_conn->release_work); diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index f918fca9ada3..cb6e3a5f509c 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -484,10 +484,7 @@ static int evdev_open(struct inode *inode, struct file *file) struct evdev_client *client; int error; - client = kzalloc(struct_size(client, buffer, bufsize), - GFP_KERNEL | __GFP_NOWARN); - if (!client) - client = vzalloc(struct_size(client, buffer, bufsize)); + client = kvzalloc(struct_size(client, buffer, bufsize), GFP_KERNEL); if (!client) return -ENOMEM; diff --git a/drivers/input/misc/keyspan_remote.c b/drivers/input/misc/keyspan_remote.c index 83368f1e7c4e..4650f4a94989 100644 --- a/drivers/input/misc/keyspan_remote.c +++ b/drivers/input/misc/keyspan_remote.c @@ -336,7 +336,8 @@ static int keyspan_setup(struct usb_device* dev) int retval = 0; retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x11, 0x40, 0x5601, 0x0, NULL, 0, 0); + 0x11, 0x40, 0x5601, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to set bit rate due to error: %d\n", __func__, retval); @@ -344,7 +345,8 @@ static int keyspan_setup(struct usb_device* dev) } retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x44, 0x40, 0x0, 0x0, NULL, 0, 0); + 0x44, 0x40, 0x0, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to set resume sensitivity due to error: %d\n", __func__, retval); @@ -352,7 +354,8 @@ static int keyspan_setup(struct usb_device* dev) } retval = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), - 0x22, 0x40, 0x0, 0x0, NULL, 0, 0); + 0x22, 0x40, 0x0, 0x0, NULL, 0, + USB_CTRL_SET_TIMEOUT); if (retval) { dev_dbg(&dev->dev, "%s - failed to turn receive on due to error: %d\n", __func__, retval); diff --git a/drivers/input/misc/max77650-onkey.c b/drivers/input/misc/max77650-onkey.c index 4d875f2ac13d..ee55f22dbca5 100644 --- a/drivers/input/misc/max77650-onkey.c +++ b/drivers/input/misc/max77650-onkey.c @@ -108,9 +108,16 @@ static int max77650_onkey_probe(struct platform_device *pdev) return input_register_device(onkey->input); } +static const struct of_device_id max77650_onkey_of_match[] = { + { .compatible = "maxim,max77650-onkey" }, + { } +}; +MODULE_DEVICE_TABLE(of, max77650_onkey_of_match); + static struct platform_driver max77650_onkey_driver = { .driver = { .name = "max77650-onkey", + .of_match_table = max77650_onkey_of_match, }, .probe = max77650_onkey_probe, }; diff --git a/drivers/input/misc/pm8xxx-vibrator.c b/drivers/input/misc/pm8xxx-vibrator.c index ecd762f93732..53ad25eaf1a2 100644 --- a/drivers/input/misc/pm8xxx-vibrator.c +++ b/drivers/input/misc/pm8xxx-vibrator.c @@ -90,7 +90,7 @@ static int pm8xxx_vib_set(struct pm8xxx_vib *vib, bool on) if (regs->enable_mask) rc = regmap_update_bits(vib->regmap, regs->enable_addr, - on ? regs->enable_mask : 0, val); + regs->enable_mask, on ? ~0 : 0); return rc; } diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c index 0bc01cfc2b51..6b23e679606e 100644 --- a/drivers/input/rmi4/rmi_f54.c +++ b/drivers/input/rmi4/rmi_f54.c @@ -24,6 +24,12 @@ #define F54_NUM_TX_OFFSET 1 #define F54_NUM_RX_OFFSET 0 +/* + * The smbus protocol can read only 32 bytes max at a time. + * But this should be fine for i2c/spi as well. + */ +#define F54_REPORT_DATA_SIZE 32 + /* F54 commands */ #define F54_GET_REPORT 1 #define F54_FORCE_CAL 2 @@ -526,6 +532,7 @@ static void rmi_f54_work(struct work_struct *work) int report_size; u8 command; int error; + int i; report_size = rmi_f54_get_report_size(f54); if (report_size == 0) { @@ -558,23 +565,27 @@ static void rmi_f54_work(struct work_struct *work) rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Get report command completed, reading data\n"); - fifo[0] = 0; - fifo[1] = 0; - error = rmi_write_block(fn->rmi_dev, - fn->fd.data_base_addr + F54_FIFO_OFFSET, - fifo, sizeof(fifo)); - if (error) { - dev_err(&fn->dev, "Failed to set fifo start offset\n"); - goto abort; - } + for (i = 0; i < report_size; i += F54_REPORT_DATA_SIZE) { + int size = min(F54_REPORT_DATA_SIZE, report_size - i); + + fifo[0] = i & 0xff; + fifo[1] = i >> 8; + error = rmi_write_block(fn->rmi_dev, + fn->fd.data_base_addr + F54_FIFO_OFFSET, + fifo, sizeof(fifo)); + if (error) { + dev_err(&fn->dev, "Failed to set fifo start offset\n"); + goto abort; + } - error = rmi_read_block(fn->rmi_dev, fn->fd.data_base_addr + - F54_REPORT_DATA_OFFSET, f54->report_data, - report_size); - if (error) { - dev_err(&fn->dev, "%s: read [%d bytes] returned %d\n", - __func__, report_size, error); - goto abort; + error = rmi_read_block(fn->rmi_dev, fn->fd.data_base_addr + + F54_REPORT_DATA_OFFSET, + f54->report_data + i, size); + if (error) { + dev_err(&fn->dev, "%s: read [%d bytes] returned %d\n", + __func__, size, error); + goto abort; + } } abort: diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c index b313c579914f..2407ea43de59 100644 --- a/drivers/input/rmi4/rmi_smbus.c +++ b/drivers/input/rmi4/rmi_smbus.c @@ -163,6 +163,7 @@ static int rmi_smb_write_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to write next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; + rmiaddr += SMB_MAX_COUNT; } exit: mutex_unlock(&rmi_smb->page_mutex); @@ -214,6 +215,7 @@ static int rmi_smb_read_block(struct rmi_transport_dev *xport, u16 rmiaddr, /* prepare to read next block of bytes */ cur_len -= SMB_MAX_COUNT; databuff += SMB_MAX_COUNT; + rmiaddr += SMB_MAX_COUNT; } retval = 0; diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index 2ca586fb914f..e08b0ef078e8 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -1713,7 +1713,7 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) aiptek->inputdev = inputdev; aiptek->intf = intf; - aiptek->ifnum = intf->altsetting[0].desc.bInterfaceNumber; + aiptek->ifnum = intf->cur_altsetting->desc.bInterfaceNumber; aiptek->inDelay = 0; aiptek->endDelay = 0; aiptek->previousJitterable = 0; @@ -1802,14 +1802,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0); /* Verify that a device really has an endpoint */ - if (intf->altsetting[0].desc.bNumEndpoints < 1) { + if (intf->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&intf->dev, "interface has %d endpoints, but must have minimum 1\n", - intf->altsetting[0].desc.bNumEndpoints); + intf->cur_altsetting->desc.bNumEndpoints); err = -EINVAL; goto fail3; } - endpoint = &intf->altsetting[0].endpoint[0].desc; + endpoint = &intf->cur_altsetting->endpoint[0].desc; /* Go set up our URB, which is called when the tablet receives * input. diff --git a/drivers/input/tablet/gtco.c b/drivers/input/tablet/gtco.c index 35031228a6d0..96d65575f75a 100644 --- a/drivers/input/tablet/gtco.c +++ b/drivers/input/tablet/gtco.c @@ -875,18 +875,14 @@ static int gtco_probe(struct usb_interface *usbinterface, } /* Sanity check that a device has an endpoint */ - if (usbinterface->altsetting[0].desc.bNumEndpoints < 1) { + if (usbinterface->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&usbinterface->dev, "Invalid number of endpoints\n"); error = -EINVAL; goto err_free_urb; } - /* - * The endpoint is always altsetting 0, we know this since we know - * this device only has one interrupt endpoint - */ - endpoint = &usbinterface->altsetting[0].endpoint[0].desc; + endpoint = &usbinterface->cur_altsetting->endpoint[0].desc; /* Some debug */ dev_dbg(&usbinterface->dev, "gtco # interfaces: %d\n", usbinterface->num_altsetting); @@ -896,7 +892,8 @@ static int gtco_probe(struct usb_interface *usbinterface, if (usb_endpoint_xfer_int(endpoint)) dev_dbg(&usbinterface->dev, "endpoint: we have interrupt endpoint\n"); - dev_dbg(&usbinterface->dev, "endpoint extra len:%d\n", usbinterface->altsetting[0].extralen); + dev_dbg(&usbinterface->dev, "interface extra len:%d\n", + usbinterface->cur_altsetting->extralen); /* * Find the HID descriptor so we can find out the size of the @@ -973,8 +970,6 @@ static int gtco_probe(struct usb_interface *usbinterface, input_dev->dev.parent = &usbinterface->dev; /* Setup the URB, it will be posted later on open of input device */ - endpoint = &usbinterface->altsetting[0].endpoint[0].desc; - usb_fill_int_urb(gtco->urbinfo, udev, usb_rcvintpipe(udev, diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c index a1f3a0cb197e..38f087404f7a 100644 --- a/drivers/input/tablet/pegasus_notetaker.c +++ b/drivers/input/tablet/pegasus_notetaker.c @@ -275,7 +275,7 @@ static int pegasus_probe(struct usb_interface *intf, return -ENODEV; /* Sanity check that the device has an endpoint */ - if (intf->altsetting[0].desc.bNumEndpoints < 1) { + if (intf->cur_altsetting->desc.bNumEndpoints < 1) { dev_err(&intf->dev, "Invalid number of endpoints\n"); return -EINVAL; } diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c index 0af0fe8c40d7..742a7e96c1b5 100644 --- a/drivers/input/touchscreen/sun4i-ts.c +++ b/drivers/input/touchscreen/sun4i-ts.c @@ -237,6 +237,7 @@ static int sun4i_ts_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; struct device *hwmon; + struct thermal_zone_device *thermal; int error; u32 reg; bool ts_attached; @@ -355,7 +356,10 @@ static int sun4i_ts_probe(struct platform_device *pdev) if (IS_ERR(hwmon)) return PTR_ERR(hwmon); - devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, &sun4i_ts_tz_ops); + thermal = devm_thermal_zone_of_sensor_register(ts->dev, 0, ts, + &sun4i_ts_tz_ops); + if (IS_ERR(thermal)) + return PTR_ERR(thermal); writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC); diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c index 1dd47dda71cd..34d31c7ec8ba 100644 --- a/drivers/input/touchscreen/sur40.c +++ b/drivers/input/touchscreen/sur40.c @@ -661,7 +661,7 @@ static int sur40_probe(struct usb_interface *interface, int error; /* Check if we really have the right interface. */ - iface_desc = &interface->altsetting[0]; + iface_desc = interface->cur_altsetting; if (iface_desc->desc.bInterfaceClass != 0xFF) return -ENODEV; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 568c52317757..483f7bc379fa 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1655,27 +1655,39 @@ static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, static void init_iommu_perf_ctr(struct amd_iommu *iommu) { struct pci_dev *pdev = iommu->dev; - u64 val = 0xabcd, val2 = 0; + u64 val = 0xabcd, val2 = 0, save_reg = 0; if (!iommu_feature(iommu, FEATURE_PC)) return; amd_iommu_pc_present = true; + /* save the value to restore, if writable */ + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, false)) + goto pc_false; + /* Check if the performance counters can be written to */ if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) || (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) || - (val != val2)) { - pci_err(pdev, "Unable to write to IOMMU perf counter.\n"); - amd_iommu_pc_present = false; - return; - } + (val != val2)) + goto pc_false; + + /* restore */ + if (iommu_pc_get_set_reg(iommu, 0, 0, 0, &save_reg, true)) + goto pc_false; pci_info(pdev, "IOMMU performance counters supported\n"); val = readl(iommu->mmio_base + MMIO_CNTR_CONF_OFFSET); iommu->max_banks = (u8) ((val >> 12) & 0x3f); iommu->max_counters = (u8) ((val >> 7) & 0xf); + + return; + +pc_false: + pci_err(pdev, "Unable to read/write to IOMMU perf counter.\n"); + amd_iommu_pc_present = false; + return; } static ssize_t amd_iommu_show_cap(struct device *dev, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 1801f0aaf013..932267f49f9a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5163,7 +5163,8 @@ static void dmar_remove_one_dev_info(struct device *dev) spin_lock_irqsave(&device_domain_lock, flags); info = dev->archdata.iommu; - if (info) + if (info && info != DEFER_DEVICE_DOMAIN_INFO + && info != DUMMY_DEVICE_DOMAIN_INFO) __dmar_remove_one_dev_info(info); spin_unlock_irqrestore(&device_domain_lock, flags); } diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index b7e0ae1af8fa..e8922fa03379 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -493,16 +493,17 @@ static int as3645a_parse_node(struct as3645a *flash, switch (id) { case AS_LED_FLASH: flash->flash_node = child; + fwnode_handle_get(child); break; case AS_LED_INDICATOR: flash->indicator_node = child; + fwnode_handle_get(child); break; default: dev_warn(&flash->client->dev, "unknown LED %u encountered, ignoring\n", id); break; } - fwnode_handle_get(child); } if (!flash->flash_node) { diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index a5c73f3d5f79..2bf74595610f 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -151,9 +151,14 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) struct gpio_led led = {}; const char *state = NULL; + /* + * Acquire gpiod from DT with uninitialized label, which + * will be updated after LED class device is registered, + * Only then the final LED name is known. + */ led.gpiod = devm_fwnode_get_gpiod_from_child(dev, NULL, child, GPIOD_ASIS, - led.name); + NULL); if (IS_ERR(led.gpiod)) { fwnode_handle_put(child); return ERR_CAST(led.gpiod); @@ -186,6 +191,9 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) fwnode_handle_put(child); return ERR_PTR(ret); } + /* Set gpiod label to match the corresponding LED name. */ + gpiod_set_consumer_name(led_dat->gpiod, + led_dat->cdev.dev->kobj.name); priv->num_leds++; } diff --git a/drivers/leds/leds-lm3532.c b/drivers/leds/leds-lm3532.c index 0507c6575c08..491268bb34a7 100644 --- a/drivers/leds/leds-lm3532.c +++ b/drivers/leds/leds-lm3532.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // TI LM3532 LED driver // Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ +// http://www.ti.com/lit/ds/symlink/lm3532.pdf #include <linux/i2c.h> #include <linux/leds.h> @@ -623,7 +624,7 @@ static int lm3532_parse_node(struct lm3532_data *priv) led->num_leds = fwnode_property_count_u32(child, "led-sources"); if (led->num_leds > LM3532_MAX_LED_STRINGS) { - dev_err(&priv->client->dev, "To many LED string defined\n"); + dev_err(&priv->client->dev, "Too many LED string defined\n"); continue; } diff --git a/drivers/leds/leds-max77650.c b/drivers/leds/leds-max77650.c index 4c2d0b3c6dad..a0d4b725c917 100644 --- a/drivers/leds/leds-max77650.c +++ b/drivers/leds/leds-max77650.c @@ -135,9 +135,16 @@ err_node_put: return rv; } +static const struct of_device_id max77650_led_of_match[] = { + { .compatible = "maxim,max77650-led" }, + { } +}; +MODULE_DEVICE_TABLE(of, max77650_led_of_match); + static struct platform_driver max77650_led_driver = { .driver = { .name = "max77650-led", + .of_match_table = max77650_led_of_match, }, .probe = max77650_led_probe, }; diff --git a/drivers/leds/leds-rb532.c b/drivers/leds/leds-rb532.c index db5af83f0cec..b6447c1721b4 100644 --- a/drivers/leds/leds-rb532.c +++ b/drivers/leds/leds-rb532.c @@ -21,7 +21,6 @@ static void rb532_led_set(struct led_classdev *cdev, { if (brightness) set_latch_u5(LO_ULED, 0); - else set_latch_u5(0, LO_ULED); } diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index 718729c89440..3abcafe46278 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -455,7 +455,7 @@ static void __exit pattern_trig_exit(void) module_init(pattern_trig_init); module_exit(pattern_trig_exit); -MODULE_AUTHOR("Raphael Teysseyre <[email protected]"); -MODULE_AUTHOR("Baolin Wang <[email protected]"); +MODULE_AUTHOR("Raphael Teysseyre <[email protected]>"); +MODULE_AUTHOR("Baolin Wang <[email protected]>"); MODULE_DESCRIPTION("LED Pattern trigger"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 7bc950520fd9..403ac44a7378 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -386,7 +386,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50; if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104; - if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50) + if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50) clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE; } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 1b1c26da3fe0..659a9459ace3 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -3913,11 +3913,13 @@ int sdhci_setup_host(struct sdhci_host *host) if (host->ops->get_min_clock) mmc->f_min = host->ops->get_min_clock(host); else if (host->version >= SDHCI_SPEC_300) { - if (host->clk_mul) { - mmc->f_min = (host->max_clk * host->clk_mul) / 1024; + if (host->clk_mul) max_clk = host->max_clk * host->clk_mul; - } else - mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; + /* + * Divided Clock Mode minimum clock rate is always less than + * Programmable Clock Mode minimum clock rate. + */ + mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; } else mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index b8e897e31e2e..b8fe94fd9525 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -240,6 +240,35 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) writeb(val, host->ioaddr + reg); } +static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + struct sdhci_host *host = mmc_priv(mmc); + int err = sdhci_execute_tuning(mmc, opcode); + + if (err) + return err; + /* + * Tuning data remains in the buffer after tuning. + * Do a command and data reset to get rid of it + */ + sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); + + return 0; +} + +static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask) +{ + int cmd_error = 0; + int data_error = 0; + + if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error)) + return intmask; + + cqhci_irq(host->mmc, intmask, cmd_error, data_error); + + return 0; +} + static struct sdhci_ops sdhci_am654_ops = { .get_max_clock = sdhci_pltfm_clk_get_max_clock, .get_timeout_clock = sdhci_pltfm_clk_get_max_clock, @@ -248,13 +277,13 @@ static struct sdhci_ops sdhci_am654_ops = { .set_power = sdhci_am654_set_power, .set_clock = sdhci_am654_set_clock, .write_b = sdhci_am654_write_b, + .irq = sdhci_am654_cqhci_irq, .reset = sdhci_reset, }; static const struct sdhci_pltfm_data sdhci_am654_pdata = { .ops = &sdhci_am654_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -263,19 +292,6 @@ static const struct sdhci_am654_driver_data sdhci_am654_drvdata = { .flags = IOMUX_PRESENT | FREQSEL_2_BIT | STRBSEL_4_BIT | DLL_PRESENT, }; -static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask) -{ - int cmd_error = 0; - int data_error = 0; - - if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error)) - return intmask; - - cqhci_irq(host->mmc, intmask, cmd_error, data_error); - - return 0; -} - static struct sdhci_ops sdhci_j721e_8bit_ops = { .get_max_clock = sdhci_pltfm_clk_get_max_clock, .get_timeout_clock = sdhci_pltfm_clk_get_max_clock, @@ -290,8 +306,7 @@ static struct sdhci_ops sdhci_j721e_8bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { .ops = &sdhci_j721e_8bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -314,8 +329,7 @@ static struct sdhci_ops sdhci_j721e_4bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { .ops = &sdhci_j721e_4bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -549,6 +563,8 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto pm_runtime_put; } + host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; + ret = sdhci_am654_init(host); if (ret) goto pm_runtime_put; diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 2e57122f02fb..2f5c287eac95 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -344,9 +344,16 @@ static void slcan_transmit(struct work_struct *work) */ static void slcan_write_wakeup(struct tty_struct *tty) { - struct slcan *sl = tty->disc_data; + struct slcan *sl; + + rcu_read_lock(); + sl = rcu_dereference(tty->disc_data); + if (!sl) + goto out; schedule_work(&sl->tx_work); +out: + rcu_read_unlock(); } /* Send a can_frame to a TTY queue. */ @@ -644,10 +651,11 @@ static void slcan_close(struct tty_struct *tty) return; spin_lock_bh(&sl->lock); - tty->disc_data = NULL; + rcu_assign_pointer(tty->disc_data, NULL); sl->tty = NULL; spin_unlock_bh(&sl->lock); + synchronize_rcu(); flush_work(&sl->tx_work); /* Flush network side */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 120fa05a39ff..0a8624be44a9 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2164,8 +2164,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv, DMA_END_ADDR); /* Initialize Tx NAPI */ - netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, - NAPI_POLL_WEIGHT); + netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll, + NAPI_POLL_WEIGHT); } /* Initialize a RDMA ring */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 58f89f6a040f..97ff8608f0ab 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (!is_offload(adapter)) return -EOPNOTSUPP; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; if (!(adapter->flags & FULL_INIT_DONE)) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index aca9f7a20a2a..4144c230dc97 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -70,8 +70,7 @@ static void *seq_tab_start(struct seq_file *seq, loff_t *pos) static void *seq_tab_next(struct seq_file *seq, void *v, loff_t *pos) { v = seq_tab_get_idx(seq->private, *pos + 1); - if (v) - ++*pos; + ++(*pos); return v; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index e9e45006632d..1a16449e9deb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -678,8 +678,7 @@ static void *l2t_seq_start(struct seq_file *seq, loff_t *pos) static void *l2t_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = l2t_get_idx(seq, *pos); - if (v) - ++*pos; + ++(*pos); return v; } diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 41c6fa200e74..e1901874c19f 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -110,7 +110,7 @@ do { \ /* Interface Mode Register (IF_MODE) */ #define IF_MODE_MASK 0x00000003 /* 30-31 Mask on i/f mode bits */ -#define IF_MODE_XGMII 0x00000000 /* 30-31 XGMII (10G) interface */ +#define IF_MODE_10G 0x00000000 /* 30-31 10G interface */ #define IF_MODE_GMII 0x00000002 /* 30-31 GMII (1G) interface */ #define IF_MODE_RGMII 0x00000004 #define IF_MODE_RGMII_AUTO 0x00008000 @@ -440,7 +440,7 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg, tmp = 0; switch (phy_if) { case PHY_INTERFACE_MODE_XGMII: - tmp |= IF_MODE_XGMII; + tmp |= IF_MODE_10G; break; default: tmp |= IF_MODE_GMII; diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index e03b30c60dcf..c82c85ef5fb3 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -49,6 +49,7 @@ struct tgec_mdio_controller { struct mdio_fsl_priv { struct tgec_mdio_controller __iomem *mdio_base; bool is_little_endian; + bool has_a011043; }; static u32 xgmac_read32(void __iomem *regs, @@ -226,7 +227,8 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) return ret; /* Return all Fs if nothing was there */ - if (xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) { + if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) && + !priv->has_a011043) { dev_err(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); @@ -274,6 +276,9 @@ static int xgmac_mdio_probe(struct platform_device *pdev) priv->is_little_endian = of_property_read_bool(pdev->dev.of_node, "little-endian"); + priv->has_a011043 = of_property_read_bool(pdev->dev.of_node, + "fsl,erratum-a011043"); + ret = of_mdiobus_register(bus, np); if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index d4055037af89..45b90eb11adb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1113,7 +1113,7 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, */ pba_size--; if (pba_num_size < (((u32)pba_size * 2) + 1)) { - hw_dbg(hw, "Buffer to small for PBA data.\n"); + hw_dbg(hw, "Buffer too small for PBA data.\n"); return I40E_ERR_PARAM; } 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 778dab1af8fc..f260dd96873b 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 @@ -180,7 +180,7 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq, struct tx_sync_info { u64 rcd_sn; - s32 sync_len; + u32 sync_len; int nr_frags; skb_frag_t frags[MAX_SKB_FRAGS]; }; @@ -193,13 +193,14 @@ enum mlx5e_ktls_sync_retval { static enum mlx5e_ktls_sync_retval tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, - u32 tcp_seq, struct tx_sync_info *info) + u32 tcp_seq, int datalen, struct tx_sync_info *info) { struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx; enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE; struct tls_record_info *record; int remaining, i = 0; unsigned long flags; + bool ends_before; spin_lock_irqsave(&tx_ctx->lock, flags); record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn); @@ -209,9 +210,21 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, goto out; } - if (unlikely(tcp_seq < tls_record_start_seq(record))) { - ret = tls_record_is_start_marker(record) ? - MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL; + /* There are the following cases: + * 1. packet ends before start marker: bypass offload. + * 2. packet starts before start marker and ends after it: drop, + * not supported, breaks contract with kernel. + * 3. packet ends before tls record info starts: drop, + * this packet was already acknowledged and its record info + * was released. + */ + ends_before = before(tcp_seq + datalen, tls_record_start_seq(record)); + + if (unlikely(tls_record_is_start_marker(record))) { + ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL; + goto out; + } else if (ends_before) { + ret = MLX5E_KTLS_SYNC_FAIL; goto out; } @@ -337,7 +350,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, u8 num_wqebbs; int i = 0; - ret = tx_sync_info_get(priv_tx, seq, &info); + ret = tx_sync_info_get(priv_tx, seq, datalen, &info); if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) { if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) { stats->tls_skip_no_sync_data++; @@ -351,14 +364,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, goto err_out; } - if (unlikely(info.sync_len < 0)) { - if (likely(datalen <= -info.sync_len)) - return MLX5E_KTLS_SYNC_DONE; - - stats->tls_drop_bypass_req++; - goto err_out; - } - stats->tls_ooo++; tx_post_resync_params(sq, priv_tx, info.rcd_sn); @@ -378,8 +383,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, if (unlikely(contig_wqebbs_room < num_wqebbs)) mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); - tx_post_resync_params(sq, priv_tx, info.rcd_sn); - for (; i < info.nr_frags; i++) { unsigned int orig_fsz, frag_offset = 0, n = 0; skb_frag_t *f = &info.frags[i]; @@ -455,12 +458,18 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, enum mlx5e_ktls_sync_retval ret = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq); - if (likely(ret == MLX5E_KTLS_SYNC_DONE)) + switch (ret) { + case MLX5E_KTLS_SYNC_DONE: *wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi); - else if (ret == MLX5E_KTLS_SYNC_FAIL) + break; + case MLX5E_KTLS_SYNC_SKIP_NO_DATA: + if (likely(!skb->decrypted)) + goto out; + WARN_ON_ONCE(1); + /* fall-through */ + default: /* MLX5E_KTLS_SYNC_FAIL */ goto err_out; - else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */ - goto out; + } } priv_tx->expected_seq = seq + datalen; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 024e1cddfd0e..7e32b9e3667c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4036,6 +4036,13 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, u32 rate_mbps; int err; + vport_num = rpriv->rep->vport; + if (vport_num >= MLX5_VPORT_ECPF) { + NL_SET_ERR_MSG_MOD(extack, + "Ingress rate limit is supported only for Eswitch ports connected to VFs"); + return -EOPNOTSUPP; + } + esw = priv->mdev->priv.eswitch; /* rate is given in bytes/sec. * First convert to bits/sec and then round to the nearest mbit/secs. @@ -4044,8 +4051,6 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate, * 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"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2c965ad0d744..3df3604e8929 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1928,8 +1928,10 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) struct mlx5_vport *vport; int i; - mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { memset(&vport->info, 0, sizeof(vport->info)); + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + } } /* Public E-Switch API */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 243a5440867e..3e6412783078 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -866,7 +866,7 @@ out: */ #define ESW_SIZE (16 * 1024 * 1024) const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024, - 64 * 1024, 4 * 1024 }; + 64 * 1024, 128 }; static int get_sz_from_pool(struct mlx5_eswitch *esw) @@ -1377,7 +1377,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, return -EINVAL; } - mlx5_eswitch_disable(esw, false); + mlx5_eswitch_disable(esw, true); mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS); if (err) { @@ -2220,7 +2220,8 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type int esw_offloads_enable(struct mlx5_eswitch *esw) { - int err; + struct mlx5_vport *vport; + int err, i; if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap)) @@ -2237,6 +2238,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vport_metadata; + /* Representor will control the vport link state */ + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN; + err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); if (err) goto err_vports; @@ -2266,7 +2271,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err, err1; - mlx5_eswitch_disable(esw, false); + mlx5_eswitch_disable(esw, true); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cf7b8da0f010..f554cfddcf4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1563,6 +1563,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */ { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ + { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 51803eef13dd..c7f10d4f8f8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2019 Mellanox Technologies. */ +#include <linux/smp.h> #include "dr_types.h" #define QUEUE_SIZE 128 @@ -729,7 +730,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = smp_processor_id() % mlx5_comp_vectors_count(mdev); + vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev); err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); if (err) { kvfree(in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 3d587d0bdbbe..1e32e2443f73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -352,26 +352,16 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { list_for_each_entry(dst, &fte->node.children, node.list) { enum mlx5_flow_destination_type type = dst->dest_attr.type; - u32 id; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { err = -ENOSPC; goto free_actions; } - switch (type) { - case MLX5_FLOW_DESTINATION_TYPE_COUNTER: - id = dst->dest_attr.counter_id; + if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; - tmp_action = - mlx5dr_action_create_flow_counter(id); - if (!tmp_action) { - err = -ENOMEM; - goto free_actions; - } - fs_dr_actions[fs_dr_num_actions++] = tmp_action; - actions[num_actions++] = tmp_action; - break; + switch (type) { case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: tmp_action = create_ft_action(dev, dst); if (!tmp_action) { @@ -397,6 +387,32 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, } } + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + list_for_each_entry(dst, &fte->node.children, node.list) { + u32 id; + + if (dst->dest_attr.type != + MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -ENOSPC; + goto free_actions; + } + + id = dst->dest_attr.counter_id; + tmp_action = + mlx5dr_action_create_flow_counter(id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + } + params.match_sz = match_sz; params.match_buf = (u64 *)fte->val; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 150b3a144b83..3d3cca596116 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -8,6 +8,7 @@ #include <linux/string.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <linux/mutex.h> #include <net/net_namespace.h> #include <net/tc_act/tc_vlan.h> @@ -25,6 +26,7 @@ struct mlxsw_sp_acl { struct mlxsw_sp_fid *dummy_fid; struct rhashtable ruleset_ht; struct list_head rules; + struct mutex rules_lock; /* Protects rules list */ struct { struct delayed_work dw; unsigned long interval; /* ms */ @@ -701,7 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, goto err_ruleset_block_bind; } + mutex_lock(&mlxsw_sp->acl->rules_lock); list_add_tail(&rule->list, &mlxsw_sp->acl->rules); + mutex_unlock(&mlxsw_sp->acl->rules_lock); block->rule_count++; block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; @@ -723,7 +727,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; ruleset->ht_key.block->rule_count--; + mutex_lock(&mlxsw_sp->acl->rules_lock); list_del(&rule->list); + mutex_unlock(&mlxsw_sp->acl->rules_lock); if (!ruleset->ht_key.chain_index && mlxsw_sp_acl_ruleset_is_singular(ruleset)) mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset, @@ -783,19 +789,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl) struct mlxsw_sp_acl_rule *rule; int err; - /* Protect internal structures from changes */ - rtnl_lock(); + mutex_lock(&acl->rules_lock); list_for_each_entry(rule, &acl->rules, list) { err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp, rule); if (err) goto err_rule_update; } - rtnl_unlock(); + mutex_unlock(&acl->rules_lock); return 0; err_rule_update: - rtnl_unlock(); + mutex_unlock(&acl->rules_lock); return err; } @@ -880,6 +885,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) acl->dummy_fid = fid; INIT_LIST_HEAD(&acl->rules); + mutex_init(&acl->rules_lock); err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam); if (err) goto err_acl_ops_init; @@ -892,6 +898,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp) return 0; err_acl_ops_init: + mutex_destroy(&acl->rules_lock); mlxsw_sp_fid_put(fid); err_fid_get: rhashtable_destroy(&acl->ruleset_ht); @@ -908,6 +915,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw); mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam); + mutex_destroy(&acl->rules_lock); WARN_ON(!list_empty(&acl->rules)); mlxsw_sp_fid_put(acl->dummy_fid); rhashtable_destroy(&acl->ruleset_ht); diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index b339125b2f09..05e760444a92 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -64,6 +64,8 @@ static int sonic_open(struct net_device *dev) netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__); + spin_lock_init(&lp->lock); + for (i = 0; i < SONIC_NUM_RRS; i++) { struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); if (skb == NULL) { @@ -114,6 +116,24 @@ static int sonic_open(struct net_device *dev) return 0; } +/* Wait for the SONIC to become idle. */ +static void sonic_quiesce(struct net_device *dev, u16 mask) +{ + struct sonic_local * __maybe_unused lp = netdev_priv(dev); + int i; + u16 bits; + + for (i = 0; i < 1000; ++i) { + bits = SONIC_READ(SONIC_CMD) & mask; + if (!bits) + return; + if (irqs_disabled() || in_interrupt()) + udelay(20); + else + usleep_range(100, 200); + } + WARN_ONCE(1, "command deadline expired! 0x%04x\n", bits); +} /* * Close the SONIC device @@ -130,6 +150,9 @@ static int sonic_close(struct net_device *dev) /* * stop the SONIC, disable interrupts */ + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + sonic_quiesce(dev, SONIC_CR_ALL); + SONIC_WRITE(SONIC_IMR, 0); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -169,6 +192,9 @@ static void sonic_tx_timeout(struct net_device *dev) * put the Sonic into software-reset mode and * disable all interrupts before releasing DMA buffers */ + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + sonic_quiesce(dev, SONIC_CR_ALL); + SONIC_WRITE(SONIC_IMR, 0); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); @@ -206,8 +232,6 @@ static void sonic_tx_timeout(struct net_device *dev) * wake the tx queue * Concurrently with all of this, the SONIC is potentially writing to * the status flags of the TDs. - * Until some mutual exclusion is added, this code will not work with SMP. However, - * MIPS Jazz machines and m68k Macs were all uni-processor machines. */ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) @@ -215,7 +239,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) struct sonic_local *lp = netdev_priv(dev); dma_addr_t laddr; int length; - int entry = lp->next_tx; + int entry; + unsigned long flags; netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb); @@ -237,6 +262,10 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + spin_lock_irqsave(&lp->lock, flags); + + entry = lp->next_tx; + sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0); /* clear status */ sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1); /* single fragment */ sonic_tda_put(dev, entry, SONIC_TD_PKTSIZE, length); /* length of packet */ @@ -246,10 +275,6 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) sonic_tda_put(dev, entry, SONIC_TD_LINK, sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL); - /* - * Must set tx_skb[entry] only after clearing status, and - * before clearing EOL and before stopping queue - */ wmb(); lp->tx_len[entry] = length; lp->tx_laddr[entry] = laddr; @@ -272,6 +297,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + spin_unlock_irqrestore(&lp->lock, flags); + return NETDEV_TX_OK; } @@ -284,15 +311,28 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) struct net_device *dev = dev_id; struct sonic_local *lp = netdev_priv(dev); int status; + unsigned long flags; + + /* The lock has two purposes. Firstly, it synchronizes sonic_interrupt() + * with sonic_send_packet() so that the two functions can share state. + * Secondly, it makes sonic_interrupt() re-entrant, as that is required + * by macsonic which must use two IRQs with different priority levels. + */ + spin_lock_irqsave(&lp->lock, flags); + + status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT; + if (!status) { + spin_unlock_irqrestore(&lp->lock, flags); - if (!(status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT)) return IRQ_NONE; + } do { + SONIC_WRITE(SONIC_ISR, status); /* clear the interrupt(s) */ + if (status & SONIC_INT_PKTRX) { netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__); sonic_rx(dev); /* got packet(s) */ - SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */ } if (status & SONIC_INT_TXDN) { @@ -300,11 +340,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) int td_status; int freed_some = 0; - /* At this point, cur_tx is the index of a TD that is one of: - * unallocated/freed (status set & tx_skb[entry] clear) - * allocated and sent (status set & tx_skb[entry] set ) - * allocated and not yet sent (status clear & tx_skb[entry] set ) - * still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear) + /* The state of a Transmit Descriptor may be inferred + * from { tx_skb[entry], td_status } as follows. + * { clear, clear } => the TD has never been used + * { set, clear } => the TD was handed to SONIC + * { set, set } => the TD was handed back + * { clear, set } => the TD is available for re-use */ netif_dbg(lp, intr, dev, "%s: tx done\n", __func__); @@ -313,18 +354,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0) break; - if (td_status & 0x0001) { + if (td_status & SONIC_TCR_PTX) { lp->stats.tx_packets++; lp->stats.tx_bytes += sonic_tda_get(dev, entry, SONIC_TD_PKTSIZE); } else { - lp->stats.tx_errors++; - if (td_status & 0x0642) + if (td_status & (SONIC_TCR_EXD | + SONIC_TCR_EXC | SONIC_TCR_BCM)) lp->stats.tx_aborted_errors++; - if (td_status & 0x0180) + if (td_status & + (SONIC_TCR_NCRS | SONIC_TCR_CRLS)) lp->stats.tx_carrier_errors++; - if (td_status & 0x0020) + if (td_status & SONIC_TCR_OWC) lp->stats.tx_window_errors++; - if (td_status & 0x0004) + if (td_status & SONIC_TCR_FU) lp->stats.tx_fifo_errors++; } @@ -346,7 +388,6 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if (freed_some || lp->tx_skb[entry] == NULL) netif_wake_queue(dev); /* The ring is no longer full */ lp->cur_tx = entry; - SONIC_WRITE(SONIC_ISR, SONIC_INT_TXDN); /* clear the interrupt */ } /* @@ -355,42 +396,37 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) if (status & SONIC_INT_RFO) { netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n", __func__); - lp->stats.rx_fifo_errors++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */ } if (status & SONIC_INT_RDE) { netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n", __func__); - lp->stats.rx_dropped++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */ } if (status & SONIC_INT_RBAE) { netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n", __func__); - lp->stats.rx_dropped++; - SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */ } /* counter overruns; all counters are 16bit wide */ - if (status & SONIC_INT_FAE) { + if (status & SONIC_INT_FAE) lp->stats.rx_frame_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_FAE); /* clear the interrupt */ - } - if (status & SONIC_INT_CRC) { + if (status & SONIC_INT_CRC) lp->stats.rx_crc_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_CRC); /* clear the interrupt */ - } - if (status & SONIC_INT_MP) { + if (status & SONIC_INT_MP) lp->stats.rx_missed_errors += 65536; - SONIC_WRITE(SONIC_ISR, SONIC_INT_MP); /* clear the interrupt */ - } /* transmit error */ if (status & SONIC_INT_TXER) { - if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU) - netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n", - __func__); - SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */ + u16 tcr = SONIC_READ(SONIC_TCR); + + netif_dbg(lp, tx_err, dev, "%s: TXER intr, TCR %04x\n", + __func__, tcr); + + if (tcr & (SONIC_TCR_EXD | SONIC_TCR_EXC | + SONIC_TCR_FU | SONIC_TCR_BCM)) { + /* Aborted transmission. Try again. */ + netif_stop_queue(dev); + SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + } } /* bus retry */ @@ -400,107 +436,164 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) /* ... to help debug DMA problems causing endless interrupts. */ /* Bounce the eth interface to turn on the interrupt again. */ SONIC_WRITE(SONIC_IMR, 0); - SONIC_WRITE(SONIC_ISR, SONIC_INT_BR); /* clear the interrupt */ } - /* load CAM done */ - if (status & SONIC_INT_LCD) - SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */ - } while((status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT)); + status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT; + } while (status); + + spin_unlock_irqrestore(&lp->lock, flags); + return IRQ_HANDLED; } +/* Return the array index corresponding to a given Receive Buffer pointer. */ +static int index_from_addr(struct sonic_local *lp, dma_addr_t addr, + unsigned int last) +{ + unsigned int i = last; + + do { + i = (i + 1) & SONIC_RRS_MASK; + if (addr == lp->rx_laddr[i]) + return i; + } while (i != last); + + return -ENOENT; +} + +/* Allocate and map a new skb to be used as a receive buffer. */ +static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp, + struct sk_buff **new_skb, dma_addr_t *new_addr) +{ + *new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); + if (!*new_skb) + return false; + + if (SONIC_BUS_SCALE(lp->dma_bitmode) == 2) + skb_reserve(*new_skb, 2); + + *new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE), + SONIC_RBSIZE, DMA_FROM_DEVICE); + if (!*new_addr) { + dev_kfree_skb(*new_skb); + *new_skb = NULL; + return false; + } + + return true; +} + +/* Place a new receive resource in the Receive Resource Area and update RWP. */ +static void sonic_update_rra(struct net_device *dev, struct sonic_local *lp, + dma_addr_t old_addr, dma_addr_t new_addr) +{ + unsigned int entry = sonic_rr_entry(dev, SONIC_READ(SONIC_RWP)); + unsigned int end = sonic_rr_entry(dev, SONIC_READ(SONIC_RRP)); + u32 buf; + + /* The resources in the range [RRP, RWP) belong to the SONIC. This loop + * scans the other resources in the RRA, those in the range [RWP, RRP). + */ + do { + buf = (sonic_rra_get(dev, entry, SONIC_RR_BUFADR_H) << 16) | + sonic_rra_get(dev, entry, SONIC_RR_BUFADR_L); + + if (buf == old_addr) + break; + + entry = (entry + 1) & SONIC_RRS_MASK; + } while (entry != end); + + WARN_ONCE(buf != old_addr, "failed to find resource!\n"); + + sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, new_addr >> 16); + sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, new_addr & 0xffff); + + entry = (entry + 1) & SONIC_RRS_MASK; + + SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, entry)); +} + /* * We have a good packet(s), pass it/them up the network stack. */ static void sonic_rx(struct net_device *dev) { struct sonic_local *lp = netdev_priv(dev); - int status; int entry = lp->cur_rx; + int prev_entry = lp->eol_rx; + bool rbe = false; while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) { - struct sk_buff *used_skb; - struct sk_buff *new_skb; - dma_addr_t new_laddr; - u16 bufadr_l; - u16 bufadr_h; - int pkt_len; - - status = sonic_rda_get(dev, entry, SONIC_RD_STATUS); - if (status & SONIC_RCR_PRX) { - /* Malloc up new buffer. */ - new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2); - if (new_skb == NULL) { - lp->stats.rx_dropped++; + u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS); + + /* If the RD has LPKT set, the chip has finished with the RB */ + if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) { + struct sk_buff *new_skb; + dma_addr_t new_laddr; + u32 addr = (sonic_rda_get(dev, entry, + SONIC_RD_PKTPTR_H) << 16) | + sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L); + int i = index_from_addr(lp, addr, entry); + + if (i < 0) { + WARN_ONCE(1, "failed to find buffer!\n"); break; } - /* provide 16 byte IP header alignment unless DMA requires otherwise */ - if(SONIC_BUS_SCALE(lp->dma_bitmode) == 2) - skb_reserve(new_skb, 2); - - new_laddr = dma_map_single(lp->device, skb_put(new_skb, SONIC_RBSIZE), - SONIC_RBSIZE, DMA_FROM_DEVICE); - if (!new_laddr) { - dev_kfree_skb(new_skb); - printk(KERN_ERR "%s: Failed to map rx buffer, dropping packet.\n", dev->name); + + if (sonic_alloc_rb(dev, lp, &new_skb, &new_laddr)) { + struct sk_buff *used_skb = lp->rx_skb[i]; + int pkt_len; + + /* Pass the used buffer up the stack */ + dma_unmap_single(lp->device, addr, SONIC_RBSIZE, + DMA_FROM_DEVICE); + + pkt_len = sonic_rda_get(dev, entry, + SONIC_RD_PKTLEN); + skb_trim(used_skb, pkt_len); + used_skb->protocol = eth_type_trans(used_skb, + dev); + netif_rx(used_skb); + lp->stats.rx_packets++; + lp->stats.rx_bytes += pkt_len; + + lp->rx_skb[i] = new_skb; + lp->rx_laddr[i] = new_laddr; + } else { + /* Failed to obtain a new buffer so re-use it */ + new_laddr = addr; lp->stats.rx_dropped++; - break; } - - /* now we have a new skb to replace it, pass the used one up the stack */ - dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE); - used_skb = lp->rx_skb[entry]; - pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN); - skb_trim(used_skb, pkt_len); - used_skb->protocol = eth_type_trans(used_skb, dev); - netif_rx(used_skb); - lp->stats.rx_packets++; - lp->stats.rx_bytes += pkt_len; - - /* and insert the new skb */ - lp->rx_laddr[entry] = new_laddr; - lp->rx_skb[entry] = new_skb; - - bufadr_l = (unsigned long)new_laddr & 0xffff; - bufadr_h = (unsigned long)new_laddr >> 16; - sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, bufadr_l); - sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h); - } else { - /* This should only happen, if we enable accepting broken packets. */ - lp->stats.rx_errors++; - if (status & SONIC_RCR_FAER) - lp->stats.rx_frame_errors++; - if (status & SONIC_RCR_CRCR) - lp->stats.rx_crc_errors++; - } - if (status & SONIC_RCR_LPKT) { - /* - * this was the last packet out of the current receive buffer - * give the buffer back to the SONIC + /* If RBE is already asserted when RWP advances then + * it's safe to clear RBE after processing this packet. */ - lp->cur_rwp += SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode); - if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff; - SONIC_WRITE(SONIC_RWP, lp->cur_rwp); - if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) { - netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n", - __func__); - SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */ - } - } else - printk(KERN_ERR "%s: rx desc without RCR_LPKT. Shouldn't happen !?\n", - dev->name); + rbe = rbe || SONIC_READ(SONIC_ISR) & SONIC_INT_RBE; + sonic_update_rra(dev, lp, addr, new_laddr); + } /* * give back the descriptor */ - sonic_rda_put(dev, entry, SONIC_RD_LINK, - sonic_rda_get(dev, entry, SONIC_RD_LINK) | SONIC_EOL); + sonic_rda_put(dev, entry, SONIC_RD_STATUS, 0); sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1); - sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, - sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK) & ~SONIC_EOL); - lp->eol_rx = entry; - lp->cur_rx = entry = (entry + 1) & SONIC_RDS_MASK; + + prev_entry = entry; + entry = (entry + 1) & SONIC_RDS_MASK; + } + + lp->cur_rx = entry; + + if (prev_entry != lp->eol_rx) { + /* Advance the EOL flag to put descriptors back into service */ + sonic_rda_put(dev, prev_entry, SONIC_RD_LINK, SONIC_EOL | + sonic_rda_get(dev, prev_entry, SONIC_RD_LINK)); + sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, ~SONIC_EOL & + sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK)); + lp->eol_rx = prev_entry; } + + if (rbe) + SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* * If any worth-while packets have been received, netif_rx() * has done a mark_bh(NET_BH) for us and will work on them @@ -550,6 +643,8 @@ static void sonic_multicast_list(struct net_device *dev) (netdev_mc_count(dev) > 15)) { rcr |= SONIC_RCR_AMC; } else { + unsigned long flags; + netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__, netdev_mc_count(dev)); sonic_set_cam_enable(dev, 1); /* always enable our own address */ @@ -563,9 +658,14 @@ static void sonic_multicast_list(struct net_device *dev) i++; } SONIC_WRITE(SONIC_CDC, 16); - /* issue Load CAM command */ SONIC_WRITE(SONIC_CDP, lp->cda_laddr & 0xffff); + + /* LCAM and TXP commands can't be used simultaneously */ + spin_lock_irqsave(&lp->lock, flags); + sonic_quiesce(dev, SONIC_CR_TXP); SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM); + sonic_quiesce(dev, SONIC_CR_LCAM); + spin_unlock_irqrestore(&lp->lock, flags); } } @@ -580,7 +680,6 @@ static void sonic_multicast_list(struct net_device *dev) */ static int sonic_init(struct net_device *dev) { - unsigned int cmd; struct sonic_local *lp = netdev_priv(dev); int i; @@ -592,12 +691,16 @@ static int sonic_init(struct net_device *dev) SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_CMD, SONIC_CR_RST); + /* While in reset mode, clear CAM Enable register */ + SONIC_WRITE(SONIC_CE, 0); + /* * clear software reset flag, disable receiver, clear and * enable interrupts, then completely initialize the SONIC */ SONIC_WRITE(SONIC_CMD, 0); - SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS); + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP); + sonic_quiesce(dev, SONIC_CR_ALL); /* * initialize the receive resource area @@ -615,15 +718,10 @@ static int sonic_init(struct net_device *dev) } /* initialize all RRA registers */ - lp->rra_end = (lp->rra_laddr + SONIC_NUM_RRS * SIZEOF_SONIC_RR * - SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff; - lp->cur_rwp = (lp->rra_laddr + (SONIC_NUM_RRS - 1) * SIZEOF_SONIC_RR * - SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff; - - SONIC_WRITE(SONIC_RSA, lp->rra_laddr & 0xffff); - SONIC_WRITE(SONIC_REA, lp->rra_end); - SONIC_WRITE(SONIC_RRP, lp->rra_laddr & 0xffff); - SONIC_WRITE(SONIC_RWP, lp->cur_rwp); + SONIC_WRITE(SONIC_RSA, sonic_rr_addr(dev, 0)); + SONIC_WRITE(SONIC_REA, sonic_rr_addr(dev, SONIC_NUM_RRS)); + SONIC_WRITE(SONIC_RRP, sonic_rr_addr(dev, 0)); + SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, SONIC_NUM_RRS - 1)); SONIC_WRITE(SONIC_URRA, lp->rra_laddr >> 16); SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1)); @@ -631,14 +729,7 @@ static int sonic_init(struct net_device *dev) netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__); SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA); - i = 0; - while (i++ < 100) { - if (SONIC_READ(SONIC_CMD) & SONIC_CR_RRRA) - break; - } - - netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__, - SONIC_READ(SONIC_CMD), i); + sonic_quiesce(dev, SONIC_CR_RRRA); /* * Initialize the receive descriptors so that they @@ -713,28 +804,17 @@ static int sonic_init(struct net_device *dev) * load the CAM */ SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM); - - i = 0; - while (i++ < 100) { - if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD) - break; - } - netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__, - SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i); + sonic_quiesce(dev, SONIC_CR_LCAM); /* * enable receiver, disable loopback * and enable all interrupts */ - SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN | SONIC_CR_STP); SONIC_WRITE(SONIC_RCR, SONIC_RCR_DEFAULT); SONIC_WRITE(SONIC_TCR, SONIC_TCR_DEFAULT); SONIC_WRITE(SONIC_ISR, 0x7fff); SONIC_WRITE(SONIC_IMR, SONIC_IMR_DEFAULT); - - cmd = SONIC_READ(SONIC_CMD); - if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0) - printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd); + SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN); netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__, SONIC_READ(SONIC_CMD)); diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h index 2b27f7049acb..1df6d2f06cc4 100644 --- a/drivers/net/ethernet/natsemi/sonic.h +++ b/drivers/net/ethernet/natsemi/sonic.h @@ -110,6 +110,9 @@ #define SONIC_CR_TXP 0x0002 #define SONIC_CR_HTX 0x0001 +#define SONIC_CR_ALL (SONIC_CR_LCAM | SONIC_CR_RRRA | \ + SONIC_CR_RXEN | SONIC_CR_TXP) + /* * SONIC data configuration bits */ @@ -175,6 +178,7 @@ #define SONIC_TCR_NCRS 0x0100 #define SONIC_TCR_CRLS 0x0080 #define SONIC_TCR_EXC 0x0040 +#define SONIC_TCR_OWC 0x0020 #define SONIC_TCR_PMB 0x0008 #define SONIC_TCR_FU 0x0004 #define SONIC_TCR_BCM 0x0002 @@ -274,8 +278,9 @@ #define SONIC_NUM_RDS SONIC_NUM_RRS /* number of receive descriptors */ #define SONIC_NUM_TDS 16 /* number of transmit descriptors */ -#define SONIC_RDS_MASK (SONIC_NUM_RDS-1) -#define SONIC_TDS_MASK (SONIC_NUM_TDS-1) +#define SONIC_RRS_MASK (SONIC_NUM_RRS - 1) +#define SONIC_RDS_MASK (SONIC_NUM_RDS - 1) +#define SONIC_TDS_MASK (SONIC_NUM_TDS - 1) #define SONIC_RBSIZE 1520 /* size of one resource buffer */ @@ -312,8 +317,6 @@ struct sonic_local { u32 rda_laddr; /* logical DMA address of RDA */ dma_addr_t rx_laddr[SONIC_NUM_RRS]; /* logical DMA addresses of rx skbuffs */ dma_addr_t tx_laddr[SONIC_NUM_TDS]; /* logical DMA addresses of tx skbuffs */ - unsigned int rra_end; - unsigned int cur_rwp; unsigned int cur_rx; unsigned int cur_tx; /* first unacked transmit packet */ unsigned int eol_rx; @@ -322,6 +325,7 @@ struct sonic_local { int msg_enable; struct device *device; /* generic device */ struct net_device_stats stats; + spinlock_t lock; }; #define TX_TIMEOUT (3 * HZ) @@ -344,30 +348,30 @@ static void sonic_msg_init(struct net_device *dev); as far as we can tell. */ /* OpenBSD calls this "SWO". I'd like to think that sonic_buf_put() is a much better name. */ -static inline void sonic_buf_put(void* base, int bitmode, +static inline void sonic_buf_put(u16 *base, int bitmode, int offset, __u16 val) { if (bitmode) #ifdef __BIG_ENDIAN - ((__u16 *) base + (offset*2))[1] = val; + __raw_writew(val, base + (offset * 2) + 1); #else - ((__u16 *) base + (offset*2))[0] = val; + __raw_writew(val, base + (offset * 2) + 0); #endif else - ((__u16 *) base)[offset] = val; + __raw_writew(val, base + (offset * 1) + 0); } -static inline __u16 sonic_buf_get(void* base, int bitmode, +static inline __u16 sonic_buf_get(u16 *base, int bitmode, int offset) { if (bitmode) #ifdef __BIG_ENDIAN - return ((volatile __u16 *) base + (offset*2))[1]; + return __raw_readw(base + (offset * 2) + 1); #else - return ((volatile __u16 *) base + (offset*2))[0]; + return __raw_readw(base + (offset * 2) + 0); #endif else - return ((volatile __u16 *) base)[offset]; + return __raw_readw(base + (offset * 1) + 0); } /* Inlines that you should actually use for reading/writing DMA buffers */ @@ -447,6 +451,22 @@ static inline __u16 sonic_rra_get(struct net_device* dev, int entry, (entry * SIZEOF_SONIC_RR) + offset); } +static inline u16 sonic_rr_addr(struct net_device *dev, int entry) +{ + struct sonic_local *lp = netdev_priv(dev); + + return lp->rra_laddr + + entry * SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode); +} + +static inline u16 sonic_rr_entry(struct net_device *dev, u16 addr) +{ + struct sonic_local *lp = netdev_priv(dev); + + return (addr - (u16)lp->rra_laddr) / (SIZEOF_SONIC_RR * + SONIC_BUS_SCALE(lp->dma_bitmode)); +} + static const char version[] = "sonic.c:v0.92 20.9.98 [email protected]\n"; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index a496390b8632..07f9067affc6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -2043,6 +2043,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev, break; } entry += p_hdr->size; + cond_resched(); } p_dev->ahw->reset.seq_index = index; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index afa10a163da1..f34ae8c75bc5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -703,6 +703,7 @@ static u32 qlcnic_read_memory_test_agent(struct qlcnic_adapter *adapter, addr += 16; reg_read -= 16; ret += 16; + cond_resched(); } out: mutex_unlock(&adapter->ahw->mem_lock); @@ -1383,6 +1384,7 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter) buf_offset += entry->hdr.cap_size; entry_offset += entry->hdr.offset; buffer = fw_dump->data + buf_offset; + cond_resched(); } fw_dump->clr = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 4775f49d7f3b..d10ac54bf385 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -412,9 +412,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) *mac = NULL; } - rc = of_get_phy_mode(np, &plat->phy_interface); - if (rc) - return ERR_PTR(rc); + plat->phy_interface = device_get_phy_mode(&pdev->dev); + if (plat->phy_interface < 0) + return ERR_PTR(plat->phy_interface); plat->interface = stmmac_of_get_mac_mode(np); if (plat->interface < 0) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index f6222ada6818..9b3ba98726d7 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type, return NULL; } - if (sock->sk->sk_protocol != IPPROTO_UDP) { + sk = sock->sk; + if (sk->sk_protocol != IPPROTO_UDP || + sk->sk_type != SOCK_DGRAM || + (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { pr_debug("socket fd=%d not UDP\n", fd); sk = ERR_PTR(-EINVAL); goto out_sock; } - lock_sock(sock->sk); - if (sock->sk->sk_user_data) { + lock_sock(sk); + if (sk->sk_user_data) { sk = ERR_PTR(-EBUSY); goto out_rel_sock; } - sk = sock->sk; sock_hold(sk); tuncfg.sk_user_data = gtp; diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 2a91c192659f..61d7e0d1d77d 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work) */ static void slip_write_wakeup(struct tty_struct *tty) { - struct slip *sl = tty->disc_data; + struct slip *sl; + + rcu_read_lock(); + sl = rcu_dereference(tty->disc_data); + if (!sl) + goto out; schedule_work(&sl->tx_work); +out: + rcu_read_unlock(); } static void sl_tx_timeout(struct net_device *dev) @@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty) return; spin_lock_bh(&sl->lock); - tty->disc_data = NULL; + rcu_assign_pointer(tty->disc_data, NULL); sl->tty = NULL; spin_unlock_bh(&sl->lock); + synchronize_rcu(); flush_work(&sl->tx_work); /* VSV = very important to remove timers */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 683d371e6e82..35e884a8242d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1936,6 +1936,10 @@ drop: if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } return total_len; } } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 75bdfae5f3e2..c2a58f05b9a1 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -20,6 +20,7 @@ #include <linux/mdio.h> #include <linux/phy.h> #include <net/ip6_checksum.h> +#include <net/vxlan.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/irq.h> @@ -3668,6 +3669,19 @@ static void lan78xx_tx_timeout(struct net_device *net) tasklet_schedule(&dev->bh); } +static netdev_features_t lan78xx_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE) + features &= ~NETIF_F_GSO_MASK; + + features = vlan_features_check(skb, features); + features = vxlan_features_check(skb, features); + + return features; +} + static const struct net_device_ops lan78xx_netdev_ops = { .ndo_open = lan78xx_open, .ndo_stop = lan78xx_stop, @@ -3681,6 +3695,7 @@ static const struct net_device_ops lan78xx_netdev_ops = { .ndo_set_features = lan78xx_set_features, .ndo_vlan_rx_add_vid = lan78xx_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid, + .ndo_features_check = lan78xx_features_check, }; static void lan78xx_stat_monitor(struct timer_list *t) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 031cb8fff909..3f425f974d03 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -31,7 +31,7 @@ #define NETNEXT_VERSION "11" /* Information for net */ -#define NET_VERSION "10" +#define NET_VERSION "11" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers <[email protected]>" @@ -68,6 +68,7 @@ #define PLA_LED_FEATURE 0xdd92 #define PLA_PHYAR 0xde00 #define PLA_BOOT_CTRL 0xe004 +#define PLA_LWAKE_CTRL_REG 0xe007 #define PLA_GPHY_INTR_IMR 0xe022 #define PLA_EEE_CR 0xe040 #define PLA_EEEP_CR 0xe080 @@ -95,6 +96,7 @@ #define PLA_TALLYCNT 0xe890 #define PLA_SFF_STS_7 0xe8de #define PLA_PHYSTATUS 0xe908 +#define PLA_CONFIG6 0xe90a /* CONFIG6 */ #define PLA_BP_BA 0xfc26 #define PLA_BP_0 0xfc28 #define PLA_BP_1 0xfc2a @@ -107,6 +109,7 @@ #define PLA_BP_EN 0xfc38 #define USB_USB2PHY 0xb41e +#define USB_SSPHYLINK1 0xb426 #define USB_SSPHYLINK2 0xb428 #define USB_U2P3_CTRL 0xb460 #define USB_CSR_DUMMY1 0xb464 @@ -300,6 +303,9 @@ #define LINK_ON_WAKE_EN 0x0010 #define LINK_OFF_WAKE_EN 0x0008 +/* PLA_CONFIG6 */ +#define LANWAKE_CLR_EN BIT(0) + /* PLA_CONFIG5 */ #define BWF_EN 0x0040 #define MWF_EN 0x0020 @@ -312,6 +318,7 @@ /* PLA_PHY_PWR */ #define TX_10M_IDLE_EN 0x0080 #define PFM_PWM_SWITCH 0x0040 +#define TEST_IO_OFF BIT(4) /* PLA_MAC_PWR_CTRL */ #define D3_CLK_GATED_EN 0x00004000 @@ -324,6 +331,7 @@ #define MAC_CLK_SPDWN_EN BIT(15) /* PLA_MAC_PWR_CTRL3 */ +#define PLA_MCU_SPDWN_EN BIT(14) #define PKT_AVAIL_SPDWN_EN 0x0100 #define SUSPEND_SPDWN_EN 0x0004 #define U1U2_SPDWN_EN 0x0002 @@ -354,6 +362,9 @@ /* PLA_BOOT_CTRL */ #define AUTOLOAD_DONE 0x0002 +/* PLA_LWAKE_CTRL_REG */ +#define LANWAKE_PIN BIT(7) + /* PLA_SUSPEND_FLAG */ #define LINK_CHG_EVENT BIT(0) @@ -365,13 +376,18 @@ #define DEBUG_LTSSM 0x0082 /* PLA_EXTRA_STATUS */ +#define CUR_LINK_OK BIT(15) #define U3P3_CHECK_EN BIT(7) /* RTL_VER_05 only */ #define LINK_CHANGE_FLAG BIT(8) +#define POLL_LINK_CHG BIT(0) /* USB_USB2PHY */ #define USB2PHY_SUSPEND 0x0001 #define USB2PHY_L1 0x0002 +/* USB_SSPHYLINK1 */ +#define DELAY_PHY_PWR_CHG BIT(1) + /* USB_SSPHYLINK2 */ #define pwd_dn_scale_mask 0x3ffe #define pwd_dn_scale(x) ((x) << 1) @@ -2863,6 +2879,17 @@ static int rtl8153_enable(struct r8152 *tp) r8153_set_rx_early_timeout(tp); r8153_set_rx_early_size(tp); + if (tp->version == RTL_VER_09) { + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_FW_TASK); + ocp_data &= ~FC_PATCH_TASK; + ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data); + usleep_range(1000, 2000); + ocp_data |= FC_PATCH_TASK; + ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data); + } + return rtl_enable(tp); } @@ -3376,8 +3403,8 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable) r8153b_ups_en(tp, false); r8153_queue_wake(tp, false); rtl_runtime_suspend_enable(tp, false); - r8153_u2p3en(tp, true); - r8153b_u1u2en(tp, true); + if (tp->udev->speed != USB_SPEED_HIGH) + r8153b_u1u2en(tp, true); } } @@ -4675,7 +4702,6 @@ static void r8153b_hw_phy_cfg(struct r8152 *tp) r8153_aldps_en(tp, true); r8152b_enable_fc(tp); - r8153_u2p3en(tp, true); set_bit(PHY_RESET, &tp->flags); } @@ -4954,6 +4980,8 @@ static void rtl8152_down(struct r8152 *tp) static void rtl8153_up(struct r8152 *tp) { + u32 ocp_data; + if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; @@ -4961,6 +4989,19 @@ static void rtl8153_up(struct r8152 *tp) r8153_u2p3en(tp, false); r8153_aldps_en(tp, false); r8153_first_init(tp); + + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6); + ocp_data |= LANWAKE_CLR_EN; + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data); + + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG); + ocp_data &= ~LANWAKE_PIN; + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data); + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1); + ocp_data &= ~DELAY_PHY_PWR_CHG; + ocp_write_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1, ocp_data); + r8153_aldps_en(tp, true); switch (tp->version) { @@ -4979,11 +5020,17 @@ static void rtl8153_up(struct r8152 *tp) static void rtl8153_down(struct r8152 *tp) { + u32 ocp_data; + if (test_bit(RTL8152_UNPLUG, &tp->flags)) { rtl_drop_queued_tx(tp); return; } + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6); + ocp_data &= ~LANWAKE_CLR_EN; + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data); + r8153_u1u2en(tp, false); r8153_u2p3en(tp, false); r8153_power_cut_en(tp, false); @@ -4994,6 +5041,8 @@ static void rtl8153_down(struct r8152 *tp) static void rtl8153b_up(struct r8152 *tp) { + u32 ocp_data; + if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; @@ -5004,18 +5053,29 @@ static void rtl8153b_up(struct r8152 *tp) r8153_first_init(tp); ocp_write_dword(tp, MCU_TYPE_USB, USB_RX_BUF_TH, RX_THR_B); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3); + ocp_data &= ~PLA_MCU_SPDWN_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data); + r8153_aldps_en(tp, true); - r8153_u2p3en(tp, true); - r8153b_u1u2en(tp, true); + + if (tp->udev->speed != USB_SPEED_HIGH) + r8153b_u1u2en(tp, true); } static void rtl8153b_down(struct r8152 *tp) { + u32 ocp_data; + if (test_bit(RTL8152_UNPLUG, &tp->flags)) { rtl_drop_queued_tx(tp); return; } + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3); + ocp_data |= PLA_MCU_SPDWN_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data); + r8153b_u1u2en(tp, false); r8153_u2p3en(tp, false); r8153b_power_cut_en(tp, false); @@ -5387,6 +5447,16 @@ static void r8153_init(struct r8152 *tp) else ocp_data |= DYNAMIC_BURST; ocp_write_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1, ocp_data); + + r8153_queue_wake(tp, false); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS); + if (rtl8152_get_speed(tp) & LINK_STATUS) + ocp_data |= CUR_LINK_OK; + else + ocp_data &= ~CUR_LINK_OK; + ocp_data |= POLL_LINK_CHG; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data); } ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY2); @@ -5416,10 +5486,19 @@ static void r8153_init(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001); r8153_power_cut_en(tp, false); + rtl_runtime_suspend_enable(tp, false); r8153_u1u2en(tp, true); r8153_mac_clk_spd(tp, false); usb_enable_lpm(tp->udev); + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6); + ocp_data |= LANWAKE_CLR_EN; + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data); + + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG); + ocp_data &= ~LANWAKE_PIN; + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data); + /* rx aggregation */ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL); ocp_data &= ~(RX_AGG_DISABLE | RX_ZERO_EN); @@ -5484,7 +5563,17 @@ static void r8153b_init(struct r8152 *tp) r8153b_ups_en(tp, false); r8153_queue_wake(tp, false); rtl_runtime_suspend_enable(tp, false); - r8153b_u1u2en(tp, true); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS); + if (rtl8152_get_speed(tp) & LINK_STATUS) + ocp_data |= CUR_LINK_OK; + else + ocp_data &= ~CUR_LINK_OK; + ocp_data |= POLL_LINK_CHG; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data); + + if (tp->udev->speed != USB_SPEED_HIGH) + r8153b_u1u2en(tp, true); usb_enable_lpm(tp->udev); /* MAC clock speed down */ @@ -5492,6 +5581,19 @@ static void r8153b_init(struct r8152 *tp) ocp_data |= MAC_CLK_SPDWN_EN; ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, ocp_data); + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3); + ocp_data &= ~PLA_MCU_SPDWN_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data); + + if (tp->version == RTL_VER_09) { + /* Disable Test IO for 32QFN */ + if (ocp_read_byte(tp, MCU_TYPE_PLA, 0xdc00) & BIT(5)) { + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR); + ocp_data |= TEST_IO_OFF; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR, ocp_data); + } + } + set_bit(GREEN_ETHERNET, &tp->flags); /* rx aggregation */ @@ -6707,6 +6809,11 @@ static int rtl8152_probe(struct usb_interface *intf, intf->needs_remote_wakeup = 1; + if (!rtl_can_wakeup(tp)) + __rtl_set_wol(tp, 0); + else + tp->saved_wolopts = __rtl_get_wol(tp); + tp->rtl_ops.init(tp); #if IS_BUILTIN(CONFIG_USB_RTL8152) /* Retry in case request_firmware() is not ready yet. */ @@ -6724,10 +6831,6 @@ static int rtl8152_probe(struct usb_interface *intf, goto out1; } - if (!rtl_can_wakeup(tp)) - __rtl_set_wol(tp, 0); - - tp->saved_wolopts = __rtl_get_wol(tp); if (tp->saved_wolopts) device_set_wakeup_enable(&udev->dev, true); else diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index f43c06569ea1..c4c8f1b62e1e 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -7790,16 +7790,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) { case AIROGVLIST: ridcode = RID_APLIST; break; case AIROGDRVNAM: ridcode = RID_DRVNAME; break; case AIROGEHTENC: ridcode = RID_ETHERENCAP; break; - case AIROGWEPKTMP: ridcode = RID_WEP_TEMP; - /* Only super-user can read WEP keys */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - break; - case AIROGWEPKNV: ridcode = RID_WEP_PERM; - /* Only super-user can read WEP keys */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - break; + case AIROGWEPKTMP: ridcode = RID_WEP_TEMP; break; + case AIROGWEPKNV: ridcode = RID_WEP_PERM; break; case AIROGSTAT: ridcode = RID_STATUS; break; case AIROGSTATSD32: ridcode = RID_STATSDELTA; break; case AIROGSTATSC32: ridcode = RID_STATS; break; @@ -7813,7 +7805,13 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) { return -EINVAL; } - if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL) + if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) { + /* Only super-user can read WEP keys */ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + } + + if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL) return -ENOMEM; PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c index cd73fc5cfcbb..fd454836adbe 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c @@ -267,7 +267,7 @@ int iwlagn_tx_skb(struct iwl_priv *priv, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct iwl_station_priv *sta_priv = NULL; struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS]; - struct iwl_device_cmd *dev_cmd; + struct iwl_device_tx_cmd *dev_cmd; struct iwl_tx_cmd *tx_cmd; __le16 fc; u8 hdr_len; @@ -348,7 +348,6 @@ int iwlagn_tx_skb(struct iwl_priv *priv, if (unlikely(!dev_cmd)) goto drop_unlock_priv; - memset(dev_cmd, 0, sizeof(*dev_cmd)); dev_cmd->hdr.cmd = REPLY_TX; tx_cmd = (struct iwl_tx_cmd *) dev_cmd->payload; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 40fe2d667622..48d375a86d86 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -357,8 +357,8 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) { union acpi_object *wifi_pkg, *data; bool enabled; - int i, n_profiles, tbl_rev; - int ret = 0; + int i, n_profiles, tbl_rev, pos; + int ret = 0; data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD); if (IS_ERR(data)) @@ -390,10 +390,10 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) goto out_free; } - for (i = 0; i < n_profiles; i++) { - /* the tables start at element 3 */ - int pos = 3; + /* the tables start at element 3 */ + pos = 3; + for (i = 0; i < n_profiles; i++) { /* The EWRD profiles officially go from 2 to 4, but we * save them in sar_profiles[1-3] (because we don't * have profile 0). So in the array we start from 1. diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index ed90dd104366..4c60f9959f7b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -2669,12 +2669,7 @@ int iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt, { int ret = 0; - /* if the FW crashed or not debug monitor cfg was given, there is - * no point in changing the recording state - */ - if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status) || - (!fwrt->trans->dbg.dest_tlv && - fwrt->trans->dbg.ini_dest == IWL_FW_INI_LOCATION_INVALID)) + if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) return 0; if (fw_has_capa(&fwrt->fw->ucode_capa, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index 92d9898ab7c2..c2f7252ae4e7 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -379,7 +379,7 @@ enum { /* CSR GIO */ -#define CSR_GIO_REG_VAL_L0S_ENABLED (0x00000002) +#define CSR_GIO_REG_VAL_L0S_DISABLED (0x00000002) /* * UCODE-DRIVER GP (general purpose) mailbox register 1 diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index f266647dc08c..ce8f248c33ea 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -480,7 +480,14 @@ static int iwl_dbg_tlv_alloc_fragment(struct iwl_fw_runtime *fwrt, if (!frag || frag->size || !pages) return -EIO; - while (pages) { + /* + * We try to allocate as many pages as we can, starting with + * the requested amount and going down until we can allocate + * something. Because of DIV_ROUND_UP(), pages will never go + * down to 0 and stop the loop, so stop when pages reaches 1, + * which is too small anyway. + */ + while (pages > 1) { block = dma_alloc_coherent(fwrt->dev, pages * PAGE_SIZE, &physical, GFP_KERNEL | __GFP_NOWARN); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 4096ccf58b07..bc8c959588ca 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1817,9 +1817,6 @@ MODULE_PARM_DESC(antenna_coupling, module_param_named(nvm_file, iwlwifi_mod_params.nvm_file, charp, 0444); MODULE_PARM_DESC(nvm_file, "NVM file name"); -module_param_named(lar_disable, iwlwifi_mod_params.lar_disable, bool, 0444); -MODULE_PARM_DESC(lar_disable, "disable LAR functionality (default: N)"); - module_param_named(uapsd_disable, iwlwifi_mod_params.uapsd_disable, uint, 0644); MODULE_PARM_DESC(uapsd_disable, "disable U-APSD functionality bitmap 1: BSS 2: P2P Client (default: 3)"); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h index ebea3f308b5d..82e5cac23d8d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h @@ -115,7 +115,6 @@ enum iwl_uapsd_disable { * @nvm_file: specifies a external NVM file * @uapsd_disable: disable U-APSD, see &enum iwl_uapsd_disable, default = * IWL_DISABLE_UAPSD_BSS | IWL_DISABLE_UAPSD_P2P_CLIENT - * @lar_disable: disable LAR (regulatory), default = 0 * @fw_monitor: allow to use firmware monitor * @disable_11ac: disable VHT capabilities, default = false. * @remove_when_gone: remove an inaccessible device from the PCIe bus. @@ -136,7 +135,6 @@ struct iwl_mod_params { int antenna_coupling; char *nvm_file; u32 uapsd_disable; - bool lar_disable; bool fw_monitor; bool disable_11ac; /** diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 1e240a2a8329..d4f834b52f50 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -224,6 +224,34 @@ enum iwl_nvm_channel_flags { NVM_CHANNEL_DC_HIGH = BIT(12), }; +/** + * enum iwl_reg_capa_flags - global flags applied for the whole regulatory + * domain. + * @REG_CAPA_BF_CCD_LOW_BAND: Beam-forming or Cyclic Delay Diversity in the + * 2.4Ghz band is allowed. + * @REG_CAPA_BF_CCD_HIGH_BAND: Beam-forming or Cyclic Delay Diversity in the + * 5Ghz band is allowed. + * @REG_CAPA_160MHZ_ALLOWED: 11ac channel with a width of 160Mhz is allowed + * for this regulatory domain (valid only in 5Ghz). + * @REG_CAPA_80MHZ_ALLOWED: 11ac channel with a width of 80Mhz is allowed + * for this regulatory domain (valid only in 5Ghz). + * @REG_CAPA_MCS_8_ALLOWED: 11ac with MCS 8 is allowed. + * @REG_CAPA_MCS_9_ALLOWED: 11ac with MCS 9 is allowed. + * @REG_CAPA_40MHZ_FORBIDDEN: 11n channel with a width of 40Mhz is forbidden + * for this regulatory domain (valid only in 5Ghz). + * @REG_CAPA_DC_HIGH_ENABLED: DC HIGH allowed. + */ +enum iwl_reg_capa_flags { + REG_CAPA_BF_CCD_LOW_BAND = BIT(0), + REG_CAPA_BF_CCD_HIGH_BAND = BIT(1), + REG_CAPA_160MHZ_ALLOWED = BIT(2), + REG_CAPA_80MHZ_ALLOWED = BIT(3), + REG_CAPA_MCS_8_ALLOWED = BIT(4), + REG_CAPA_MCS_9_ALLOWED = BIT(5), + REG_CAPA_40MHZ_FORBIDDEN = BIT(7), + REG_CAPA_DC_HIGH_ENABLED = BIT(9), +}; + static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level, int chan, u32 flags) { @@ -939,10 +967,11 @@ iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg, struct iwl_nvm_data * iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, + const struct iwl_fw *fw, const __be16 *nvm_hw, const __le16 *nvm_sw, const __le16 *nvm_calib, const __le16 *regulatory, const __le16 *mac_override, const __le16 *phy_sku, - u8 tx_chains, u8 rx_chains, bool lar_fw_supported) + u8 tx_chains, u8 rx_chains) { struct iwl_nvm_data *data; bool lar_enabled; @@ -1022,7 +1051,8 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, return NULL; } - if (lar_fw_supported && lar_enabled) + if (lar_enabled && + fw_has_capa(&fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT)) sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR; if (iwl_nvm_no_wide_in_5ghz(trans, cfg, nvm_hw)) @@ -1038,6 +1068,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data); static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan, int ch_idx, u16 nvm_flags, + u16 cap_flags, const struct iwl_cfg *cfg) { u32 flags = NL80211_RRF_NO_HT40; @@ -1076,13 +1107,27 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan, (flags & NL80211_RRF_NO_IR)) flags |= NL80211_RRF_GO_CONCURRENT; + /* + * cap_flags is per regulatory domain so apply it for every channel + */ + if (ch_idx >= NUM_2GHZ_CHANNELS) { + if (cap_flags & REG_CAPA_40MHZ_FORBIDDEN) + flags |= NL80211_RRF_NO_HT40; + + if (!(cap_flags & REG_CAPA_80MHZ_ALLOWED)) + flags |= NL80211_RRF_NO_80MHZ; + + if (!(cap_flags & REG_CAPA_160MHZ_ALLOWED)) + flags |= NL80211_RRF_NO_160MHZ; + } + return flags; } struct ieee80211_regdomain * iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int num_of_ch, __le32 *channels, u16 fw_mcc, - u16 geo_info) + u16 geo_info, u16 cap) { int ch_idx; u16 ch_flags; @@ -1140,7 +1185,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, } reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx, - ch_flags, cfg); + ch_flags, cap, + cfg); /* we can't continue the same rule */ if (ch_idx == 0 || prev_reg_rule_flags != reg_rule_flags || @@ -1405,9 +1451,6 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, .id = WIDE_ID(REGULATORY_AND_NVM_GROUP, NVM_GET_INFO) }; int ret; - bool lar_fw_supported = !iwlwifi_mod_params.lar_disable && - fw_has_capa(&fw->ucode_capa, - IWL_UCODE_TLV_CAPA_LAR_SUPPORT); bool empty_otp; u32 mac_flags; u32 sbands_flags = 0; @@ -1485,7 +1528,9 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, nvm->valid_tx_ant = (u8)le32_to_cpu(rsp->phy_sku.tx_chains); nvm->valid_rx_ant = (u8)le32_to_cpu(rsp->phy_sku.rx_chains); - if (le32_to_cpu(rsp->regulatory.lar_enabled) && lar_fw_supported) { + if (le32_to_cpu(rsp->regulatory.lar_enabled) && + fw_has_capa(&fw->ucode_capa, + IWL_UCODE_TLV_CAPA_LAR_SUPPORT)) { nvm->lar_enabled = true; sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h index b7e1ddf8f177..fb0b385d10fd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h @@ -7,7 +7,7 @@ * * Copyright(c) 2008 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -29,7 +29,7 @@ * * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -85,10 +85,11 @@ enum iwl_nvm_sbands_flags { */ struct iwl_nvm_data * iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, + const struct iwl_fw *fw, const __be16 *nvm_hw, const __le16 *nvm_sw, const __le16 *nvm_calib, const __le16 *regulatory, const __le16 *mac_override, const __le16 *phy_sku, - u8 tx_chains, u8 rx_chains, bool lar_fw_supported); + u8 tx_chains, u8 rx_chains); /** * iwl_parse_mcc_info - parse MCC (mobile country code) info coming from FW @@ -103,7 +104,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, struct ieee80211_regdomain * iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int num_of_ch, __le32 *channels, u16 fw_mcc, - u16 geo_info); + u16 geo_info, u16 cap); /** * struct iwl_nvm_section - describes an NVM section in memory. diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c index 28bdc9a9617e..f91197e4ae40 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c @@ -66,7 +66,9 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, struct device *dev, - const struct iwl_trans_ops *ops) + const struct iwl_trans_ops *ops, + unsigned int cmd_pool_size, + unsigned int cmd_pool_align) { struct iwl_trans *trans; #ifdef CONFIG_LOCKDEP @@ -90,10 +92,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, "iwl_cmd_pool:%s", dev_name(trans->dev)); trans->dev_cmd_pool = kmem_cache_create(trans->dev_cmd_pool_name, - sizeof(struct iwl_device_cmd), - sizeof(void *), - SLAB_HWCACHE_ALIGN, - NULL); + cmd_pool_size, cmd_pool_align, + SLAB_HWCACHE_ALIGN, NULL); if (!trans->dev_cmd_pool) return NULL; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index 8cadad7364ac..e33df5ad00e0 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -193,6 +193,18 @@ struct iwl_device_cmd { }; } __packed; +/** + * struct iwl_device_tx_cmd - buffer for TX command + * @hdr: the header + * @payload: the payload placeholder + * + * The actual structure is sized dynamically according to need. + */ +struct iwl_device_tx_cmd { + struct iwl_cmd_header hdr; + u8 payload[]; +} __packed; + #define TFD_MAX_PAYLOAD_SIZE (sizeof(struct iwl_device_cmd)) /* @@ -544,7 +556,7 @@ struct iwl_trans_ops { int (*send_cmd)(struct iwl_trans *trans, struct iwl_host_cmd *cmd); int (*tx)(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int queue); + struct iwl_device_tx_cmd *dev_cmd, int queue); void (*reclaim)(struct iwl_trans *trans, int queue, int ssn, struct sk_buff_head *skbs); @@ -948,22 +960,22 @@ iwl_trans_dump_data(struct iwl_trans *trans, u32 dump_mask) return trans->ops->dump_data(trans, dump_mask); } -static inline struct iwl_device_cmd * +static inline struct iwl_device_tx_cmd * iwl_trans_alloc_tx_cmd(struct iwl_trans *trans) { - return kmem_cache_alloc(trans->dev_cmd_pool, GFP_ATOMIC); + return kmem_cache_zalloc(trans->dev_cmd_pool, GFP_ATOMIC); } int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); static inline void iwl_trans_free_tx_cmd(struct iwl_trans *trans, - struct iwl_device_cmd *dev_cmd) + struct iwl_device_tx_cmd *dev_cmd) { kmem_cache_free(trans->dev_cmd_pool, dev_cmd); } static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int queue) + struct iwl_device_tx_cmd *dev_cmd, int queue) { if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status))) return -EIO; @@ -1271,7 +1283,9 @@ static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans) *****************************************************/ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size, struct device *dev, - const struct iwl_trans_ops *ops); + const struct iwl_trans_ops *ops, + unsigned int cmd_pool_size, + unsigned int cmd_pool_align); void iwl_trans_free(struct iwl_trans *trans); /***************************************************** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h index 60aff2ecec12..58df25e2fb32 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h @@ -154,5 +154,6 @@ #define IWL_MVM_D3_DEBUG false #define IWL_MVM_USE_TWT false #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA 10 +#define IWL_MVM_USE_NSSN_SYNC 0 #endif /* __MVM_CONSTANTS_H */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index dd685f7eb410..c09624d8d7ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -841,9 +841,13 @@ int iwl_mvm_ppag_send_cmd(struct iwl_mvm *mvm) return 0; } + if (!mvm->fwrt.ppag_table.enabled) { + IWL_DEBUG_RADIO(mvm, + "PPAG not enabled, command not sent.\n"); + return 0; + } + IWL_DEBUG_RADIO(mvm, "Sending PER_PLATFORM_ANT_GAIN_CMD\n"); - IWL_DEBUG_RADIO(mvm, "PPAG is %s\n", - mvm->fwrt.ppag_table.enabled ? "enabled" : "disabled"); for (i = 0; i < ACPI_PPAG_NUM_CHAINS; i++) { for (j = 0; j < ACPI_PPAG_NUM_SUB_BANDS; j++) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 32dc9d6f0fb6..6717f25c46b1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -256,7 +256,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy, __le32_to_cpu(resp->n_channels), resp->channels, __le16_to_cpu(resp->mcc), - __le16_to_cpu(resp->geo_info)); + __le16_to_cpu(resp->geo_info), + __le16_to_cpu(resp->cap)); /* Store the return source id */ src_id = resp->source_id; kfree(resp); @@ -754,6 +755,20 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) return ret; } +static void iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta) +{ + if (likely(sta)) { + if (likely(iwl_mvm_tx_skb_sta(mvm, skb, sta) == 0)) + return; + } else { + if (likely(iwl_mvm_tx_skb_non_sta(mvm, skb) == 0)) + return; + } + + ieee80211_free_txskb(mvm->hw, skb); +} + static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) @@ -797,14 +812,7 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, } } - if (sta) { - if (iwl_mvm_tx_skb(mvm, skb, sta)) - goto drop; - return; - } - - if (iwl_mvm_tx_skb_non_sta(mvm, skb)) - goto drop; + iwl_mvm_tx_skb(mvm, skb, sta); return; drop: ieee80211_free_txskb(hw, skb); @@ -854,10 +862,7 @@ void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) break; } - if (!txq->sta) - iwl_mvm_tx_skb_non_sta(mvm, skb); - else - iwl_mvm_tx_skb(mvm, skb, txq->sta); + iwl_mvm_tx_skb(mvm, skb, txq->sta); } } while (atomic_dec_return(&mvmtxq->tx_request)); rcu_read_unlock(); @@ -4771,6 +4776,125 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx, return ret; } +static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo) +{ + switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) { + case RATE_MCS_CHAN_WIDTH_20: + rinfo->bw = RATE_INFO_BW_20; + break; + case RATE_MCS_CHAN_WIDTH_40: + rinfo->bw = RATE_INFO_BW_40; + break; + case RATE_MCS_CHAN_WIDTH_80: + rinfo->bw = RATE_INFO_BW_80; + break; + case RATE_MCS_CHAN_WIDTH_160: + rinfo->bw = RATE_INFO_BW_160; + break; + } + + if (rate_n_flags & RATE_MCS_HT_MSK) { + rinfo->flags |= RATE_INFO_FLAGS_MCS; + rinfo->mcs = u32_get_bits(rate_n_flags, RATE_HT_MCS_INDEX_MSK); + rinfo->nss = u32_get_bits(rate_n_flags, + RATE_HT_MCS_NSS_MSK) + 1; + if (rate_n_flags & RATE_MCS_SGI_MSK) + rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; + } else if (rate_n_flags & RATE_MCS_VHT_MSK) { + rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; + rinfo->mcs = u32_get_bits(rate_n_flags, + RATE_VHT_MCS_RATE_CODE_MSK); + rinfo->nss = u32_get_bits(rate_n_flags, + RATE_VHT_MCS_NSS_MSK) + 1; + if (rate_n_flags & RATE_MCS_SGI_MSK) + rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; + } else if (rate_n_flags & RATE_MCS_HE_MSK) { + u32 gi_ltf = u32_get_bits(rate_n_flags, + RATE_MCS_HE_GI_LTF_MSK); + + rinfo->flags |= RATE_INFO_FLAGS_HE_MCS; + rinfo->mcs = u32_get_bits(rate_n_flags, + RATE_VHT_MCS_RATE_CODE_MSK); + rinfo->nss = u32_get_bits(rate_n_flags, + RATE_VHT_MCS_NSS_MSK) + 1; + + if (rate_n_flags & RATE_MCS_HE_106T_MSK) { + rinfo->bw = RATE_INFO_BW_HE_RU; + rinfo->he_ru_alloc = NL80211_RATE_INFO_HE_RU_ALLOC_106; + } + + switch (rate_n_flags & RATE_MCS_HE_TYPE_MSK) { + case RATE_MCS_HE_TYPE_SU: + case RATE_MCS_HE_TYPE_EXT_SU: + if (gi_ltf == 0 || gi_ltf == 1) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8; + else if (gi_ltf == 2) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6; + else if (rate_n_flags & RATE_MCS_SGI_MSK) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8; + else + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2; + break; + case RATE_MCS_HE_TYPE_MU: + if (gi_ltf == 0 || gi_ltf == 1) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8; + else if (gi_ltf == 2) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6; + else + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2; + break; + case RATE_MCS_HE_TYPE_TRIG: + if (gi_ltf == 0 || gi_ltf == 1) + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6; + else + rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2; + break; + } + + if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK) + rinfo->he_dcm = 1; + } else { + switch (u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK)) { + case IWL_RATE_1M_PLCP: + rinfo->legacy = 10; + break; + case IWL_RATE_2M_PLCP: + rinfo->legacy = 20; + break; + case IWL_RATE_5M_PLCP: + rinfo->legacy = 55; + break; + case IWL_RATE_11M_PLCP: + rinfo->legacy = 110; + break; + case IWL_RATE_6M_PLCP: + rinfo->legacy = 60; + break; + case IWL_RATE_9M_PLCP: + rinfo->legacy = 90; + break; + case IWL_RATE_12M_PLCP: + rinfo->legacy = 120; + break; + case IWL_RATE_18M_PLCP: + rinfo->legacy = 180; + break; + case IWL_RATE_24M_PLCP: + rinfo->legacy = 240; + break; + case IWL_RATE_36M_PLCP: + rinfo->legacy = 360; + break; + case IWL_RATE_48M_PLCP: + rinfo->legacy = 480; + break; + case IWL_RATE_54M_PLCP: + rinfo->legacy = 540; + break; + } + } +} + static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -4785,6 +4909,13 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG); } + if (iwl_mvm_has_tlc_offload(mvm)) { + struct iwl_lq_sta_rs_fw *lq_sta = &mvmsta->lq_sta.rs_fw; + + iwl_mvm_set_sta_rate(lq_sta->last_rate_n_flags, &sinfo->txrate); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE); + } + /* if beacon filtering isn't on mac80211 does it anyway */ if (!(vif->driver_flags & IEEE80211_VIF_BEACON_FILTER)) return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 3ec8de00f3aa..67ab7e7e9c9d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1298,9 +1298,6 @@ static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm) bool tlv_lar = fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT); - if (iwlwifi_mod_params.lar_disable) - return false; - /* * Enable LAR only if it is supported by the FW (TLV) && * enabled in the NVM @@ -1508,8 +1505,8 @@ int __must_check iwl_mvm_send_cmd_status(struct iwl_mvm *mvm, int __must_check iwl_mvm_send_cmd_pdu_status(struct iwl_mvm *mvm, u32 id, u16 len, const void *data, u32 *status); -int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, - struct ieee80211_sta *sta); +int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta); int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb); void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb, struct iwl_tx_cmd *tx_cmd, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 945c1ea5cda8..46128a2a9c6e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -277,11 +277,10 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) struct iwl_nvm_section *sections = mvm->nvm_sections; const __be16 *hw; const __le16 *sw, *calib, *regulatory, *mac_override, *phy_sku; - bool lar_enabled; int regulatory_type; /* Checking for required sections */ - if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) { + if (mvm->trans->cfg->nvm_type == IWL_NVM) { if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data || !mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) { IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n"); @@ -327,14 +326,9 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm) (const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY_SDP].data : (const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY].data; - lar_enabled = !iwlwifi_mod_params.lar_disable && - fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_LAR_SUPPORT); - - return iwl_parse_nvm_data(mvm->trans, mvm->cfg, hw, sw, calib, + return iwl_parse_nvm_data(mvm->trans, mvm->cfg, mvm->fw, hw, sw, calib, regulatory, mac_override, phy_sku, - mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant, - lar_enabled); + mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant); } /* Loads the NVM data stored in mvm->nvm_sections into the NIC */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index ef99c49247b7..c15f7dbc9516 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -514,14 +514,17 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 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)); + if (IWL_MVM_USE_NSSN_SYNC) { + 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) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index a046ac9fa852..a5af8f4128b1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1213,7 +1213,7 @@ static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm) cmd_size = sizeof(struct iwl_scan_config_v2); else cmd_size = sizeof(struct iwl_scan_config_v1); - cmd_size += num_channels; + cmd_size += mvm->fw->ucode_capa.n_scan_channels; cfg = kzalloc(cmd_size, GFP_KERNEL); if (!cfg) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index dc5c02fbc65a..ddfc9a668036 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -490,13 +490,13 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm, /* * Allocates and sets the Tx cmd the driver data pointers in the skb */ -static struct iwl_device_cmd * +static struct iwl_device_tx_cmd * iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_tx_info *info, int hdrlen, struct ieee80211_sta *sta, u8 sta_id) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct iwl_device_cmd *dev_cmd; + struct iwl_device_tx_cmd *dev_cmd; struct iwl_tx_cmd *tx_cmd; dev_cmd = iwl_trans_alloc_tx_cmd(mvm->trans); @@ -504,11 +504,6 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, if (unlikely(!dev_cmd)) return NULL; - /* Make sure we zero enough of dev_cmd */ - BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) > sizeof(*tx_cmd)); - BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) > sizeof(*tx_cmd)); - - memset(dev_cmd, 0, sizeof(dev_cmd->hdr) + sizeof(*tx_cmd)); dev_cmd->hdr.cmd = TX_CMD; if (iwl_mvm_has_new_tx_api(mvm)) { @@ -597,7 +592,7 @@ out: } static void iwl_mvm_skb_prepare_status(struct sk_buff *skb, - struct iwl_device_cmd *cmd) + struct iwl_device_tx_cmd *cmd) { struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb); @@ -716,7 +711,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_tx_info info; - struct iwl_device_cmd *dev_cmd; + struct iwl_device_tx_cmd *dev_cmd; u8 sta_id; int hdrlen = ieee80211_hdrlen(hdr->frame_control); __le16 fc = hdr->frame_control; @@ -1078,7 +1073,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct iwl_mvm_sta *mvmsta; - struct iwl_device_cmd *dev_cmd; + struct iwl_device_tx_cmd *dev_cmd; __le16 fc; u16 seq_number = 0; u8 tid = IWL_MAX_TID_COUNT; @@ -1154,7 +1149,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, if (WARN_ONCE(txq_id == IWL_MVM_INVALID_QUEUE, "Invalid TXQ id")) { iwl_trans_free_tx_cmd(mvm->trans, dev_cmd); spin_unlock(&mvmsta->lock); - return 0; + return -1; } if (!iwl_mvm_has_new_tx_api(mvm)) { @@ -1206,8 +1201,8 @@ drop: return -1; } -int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb, - struct ieee80211_sta *sta) +int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_sta *sta) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_tx_info info; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c index d38cefbb779e..e249e3fd14c6 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c @@ -57,6 +57,42 @@ #include "internal.h" #include "iwl-prph.h" +static void *_iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans, + size_t size, + dma_addr_t *phys, + int depth) +{ + void *result; + + if (WARN(depth > 2, + "failed to allocate DMA memory not crossing 2^32 boundary")) + return NULL; + + result = dma_alloc_coherent(trans->dev, size, phys, GFP_KERNEL); + + if (!result) + return NULL; + + if (unlikely(iwl_pcie_crosses_4g_boundary(*phys, size))) { + void *old = result; + dma_addr_t oldphys = *phys; + + result = _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size, + phys, + depth + 1); + dma_free_coherent(trans->dev, size, old, oldphys); + } + + return result; +} + +static void *iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans, + size_t size, + dma_addr_t *phys) +{ + return _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size, phys, 0); +} + void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans) { struct iwl_self_init_dram *dram = &trans->init_dram; @@ -161,14 +197,17 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, struct iwl_context_info *ctxt_info; struct iwl_context_info_rbd_cfg *rx_cfg; u32 control_flags = 0, rb_size; + dma_addr_t phys; int ret; - ctxt_info = dma_alloc_coherent(trans->dev, sizeof(*ctxt_info), - &trans_pcie->ctxt_info_dma_addr, - GFP_KERNEL); + ctxt_info = iwl_pcie_ctxt_info_dma_alloc_coherent(trans, + sizeof(*ctxt_info), + &phys); if (!ctxt_info) return -ENOMEM; + trans_pcie->ctxt_info_dma_addr = phys; + ctxt_info->version.version = 0; ctxt_info->version.mac_id = cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV)); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index a091690f6c79..f14bcef3495e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -305,7 +305,7 @@ struct iwl_cmd_meta { #define IWL_FIRST_TB_SIZE_ALIGN ALIGN(IWL_FIRST_TB_SIZE, 64) struct iwl_pcie_txq_entry { - struct iwl_device_cmd *cmd; + void *cmd; struct sk_buff *skb; /* buffer to free after command completes */ const void *free_buf; @@ -672,6 +672,16 @@ void iwl_pcie_disable_ict(struct iwl_trans *trans); /***************************************************** * TX / HCMD ******************************************************/ +/* + * We need this inline in case dma_addr_t is only 32-bits - since the + * hardware is always 64-bit, the issue can still occur in that case, + * so use u64 for 'phys' here to force the addition in 64-bit. + */ +static inline bool iwl_pcie_crosses_4g_boundary(u64 phys, u16 len) +{ + return upper_32_bits(phys) != upper_32_bits(phys + len); +} + int iwl_pcie_tx_init(struct iwl_trans *trans); int iwl_pcie_gen2_tx_init(struct iwl_trans *trans, int txq_id, int queue_size); @@ -688,7 +698,7 @@ void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id, void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq); int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int txq_id); + struct iwl_device_tx_cmd *dev_cmd, int txq_id); void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans); int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx); @@ -1082,7 +1092,8 @@ void iwl_pcie_apply_destination(struct iwl_trans *trans); void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie, struct sk_buff *skb); #ifdef CONFIG_INET -struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len); +struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len, + struct sk_buff *skb); #endif /* common functions that are used by gen3 transport */ @@ -1106,7 +1117,7 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans, unsigned int timeout); void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue); int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int txq_id); + struct iwl_device_tx_cmd *dev_cmd, int txq_id); int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd); void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 452da44a21e0..f0b8ff67a1bc 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1529,13 +1529,13 @@ out: napi = &rxq->napi; if (napi->poll) { + napi_gro_flush(napi, false); + if (napi->rx_count) { netif_receive_skb_list(&napi->rx_list); INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; } - - napi_gro_flush(napi, false); } iwl_pcie_rxq_restock(trans, rxq); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index a0677131634d..f60d66f1e55b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -79,6 +79,7 @@ #include "iwl-agn-hw.h" #include "fw/error-dump.h" #include "fw/dbg.h" +#include "fw/api/tx.h" #include "internal.h" #include "iwl-fh.h" @@ -301,18 +302,13 @@ void iwl_pcie_apm_config(struct iwl_trans *trans) u16 cap; /* - * HW bug W/A for instability in PCIe bus L0S->L1 transition. - * Check if BIOS (or OS) enabled L1-ASPM on this device. - * If so (likely), disable L0S, so device moves directly L0->L1; - * costs negligible amount of power savings. - * If not (unlikely), enable L0S, so there is at least some - * power savings, even without L1. + * L0S states have been found to be unstable with our devices + * and in newer hardware they are not officially supported at + * all, so we must always set the L0S_DISABLED bit. */ + iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED); + pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl); - if (lctl & PCI_EXP_LNKCTL_ASPM_L1) - iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); - else - iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED); trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S); pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap); @@ -3460,19 +3456,34 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, { struct iwl_trans_pcie *trans_pcie; struct iwl_trans *trans; - int ret, addr_size; + int ret, addr_size, txcmd_size, txcmd_align; + const struct iwl_trans_ops *ops = &trans_ops_pcie_gen2; + + if (!cfg_trans->gen2) { + ops = &trans_ops_pcie; + txcmd_size = sizeof(struct iwl_tx_cmd); + txcmd_align = sizeof(void *); + } else if (cfg_trans->device_family < IWL_DEVICE_FAMILY_AX210) { + txcmd_size = sizeof(struct iwl_tx_cmd_gen2); + txcmd_align = 64; + } else { + txcmd_size = sizeof(struct iwl_tx_cmd_gen3); + txcmd_align = 128; + } + + txcmd_size += sizeof(struct iwl_cmd_header); + txcmd_size += 36; /* biggest possible 802.11 header */ + + /* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */ + if (WARN_ON(cfg_trans->gen2 && txcmd_size >= txcmd_align)) + return ERR_PTR(-EINVAL); ret = pcim_enable_device(pdev); if (ret) return ERR_PTR(ret); - if (cfg_trans->gen2) - trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), - &pdev->dev, &trans_ops_pcie_gen2); - else - trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), - &pdev->dev, &trans_ops_pcie); - + trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), &pdev->dev, ops, + txcmd_size, txcmd_align); if (!trans) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 8ca0250de99e..bfb984b2e00c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -221,6 +221,17 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans, int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd); struct iwl_tfh_tb *tb; + /* + * Only WARN here so we know about the issue, but we mess up our + * unmap path because not every place currently checks for errors + * returned from this function - it can only return an error if + * there's no more space, and so when we know there is enough we + * don't always check ... + */ + WARN(iwl_pcie_crosses_4g_boundary(addr, len), + "possible DMA problem with iova:0x%llx, len:%d\n", + (unsigned long long)addr, len); + if (WARN_ON(idx >= IWL_TFH_NUM_TBS)) return -EINVAL; tb = &tfd->tbs[idx]; @@ -240,13 +251,114 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans, return idx; } +static struct page *get_workaround_page(struct iwl_trans *trans, + struct sk_buff *skb) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + struct page **page_ptr; + struct page *ret; + + page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); + + ret = alloc_page(GFP_ATOMIC); + if (!ret) + return NULL; + + /* set the chaining pointer to the previous page if there */ + *(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr; + *page_ptr = ret; + + return ret; +} + +/* + * Add a TB and if needed apply the FH HW bug workaround; + * meta != NULL indicates that it's a page mapping and we + * need to dma_unmap_page() and set the meta->tbs bit in + * this case. + */ +static int iwl_pcie_gen2_set_tb_with_wa(struct iwl_trans *trans, + struct sk_buff *skb, + struct iwl_tfh_tfd *tfd, + dma_addr_t phys, void *virt, + u16 len, struct iwl_cmd_meta *meta) +{ + dma_addr_t oldphys = phys; + struct page *page; + int ret; + + if (unlikely(dma_mapping_error(trans->dev, phys))) + return -ENOMEM; + + if (likely(!iwl_pcie_crosses_4g_boundary(phys, len))) { + ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len); + + if (ret < 0) + goto unmap; + + if (meta) + meta->tbs |= BIT(ret); + + ret = 0; + goto trace; + } + + /* + * Work around a hardware bug. If (as expressed in the + * condition above) the TB ends on a 32-bit boundary, + * then the next TB may be accessed with the wrong + * address. + * To work around it, copy the data elsewhere and make + * a new mapping for it so the device will not fail. + */ + + if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) { + ret = -ENOBUFS; + goto unmap; + } + + page = get_workaround_page(trans, skb); + if (!page) { + ret = -ENOMEM; + goto unmap; + } + + memcpy(page_address(page), virt, len); + + phys = dma_map_single(trans->dev, page_address(page), len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(trans->dev, phys))) + return -ENOMEM; + ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len); + if (ret < 0) { + /* unmap the new allocation as single */ + oldphys = phys; + meta = NULL; + goto unmap; + } + IWL_WARN(trans, + "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n", + len, (unsigned long long)oldphys, (unsigned long long)phys); + + ret = 0; +unmap: + if (meta) + dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE); + else + dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE); +trace: + trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len); + + return ret; +} + static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_tfh_tfd *tfd, int start_len, - u8 hdr_len, struct iwl_device_cmd *dev_cmd) + u8 hdr_len, + struct iwl_device_tx_cmd *dev_cmd) { #ifdef CONFIG_INET - struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload; struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; @@ -254,7 +366,6 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, u16 length, amsdu_pad; u8 *start_hdr; struct iwl_tso_hdr_page *hdr_page; - struct page **page_ptr; struct tso_t tso; trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), @@ -270,14 +381,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)); /* Our device supports 9 segments at most, it will fit in 1 page */ - hdr_page = get_page_hdr(trans, hdr_room); + hdr_page = get_page_hdr(trans, hdr_room, skb); if (!hdr_page) return -ENOMEM; - get_page(hdr_page->page); start_hdr = hdr_page->pos; - page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); - *page_ptr = hdr_page->page; /* * Pull the ieee80211 header to be able to use TSO core, @@ -332,6 +440,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, dev_kfree_skb(csum_skb); goto out_err; } + /* + * No need for _with_wa, this is from the TSO page and + * we leave some space at the end of it so can't hit + * the buggy scenario. + */ iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len); trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr, tb_phys, tb_len); @@ -343,16 +456,18 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans, /* put the payload */ while (data_left) { + int ret; + tb_len = min_t(unsigned int, tso.size, data_left); tb_phys = dma_map_single(trans->dev, tso.data, tb_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(trans->dev, tb_phys))) { + ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, + tb_phys, tso.data, + tb_len, NULL); + if (ret) { dev_kfree_skb(csum_skb); goto out_err; } - iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len); - trace_iwlwifi_dev_tx_tb(trans->dev, skb, tso.data, - tb_phys, tb_len); data_left -= tb_len; tso_build_data(skb, &tso, tb_len); @@ -372,7 +487,7 @@ out_err: static struct iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans, struct iwl_txq *txq, - struct iwl_device_cmd *dev_cmd, + struct iwl_device_tx_cmd *dev_cmd, struct sk_buff *skb, struct iwl_cmd_meta *out_meta, int hdr_len, @@ -386,6 +501,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans, tb_phys = iwl_pcie_get_first_tb_dma(txq, idx); + /* + * No need for _with_wa, the first TB allocation is aligned up + * to a 64-byte boundary and thus can't be at the end or cross + * a page boundary (much less a 2^32 boundary). + */ iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE); /* @@ -404,6 +524,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans, tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(trans->dev, tb_phys))) goto out_err; + /* + * No need for _with_wa(), we ensure (via alignment) that the data + * here can never cross or end at a page boundary. + */ iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len); if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd, @@ -430,24 +554,19 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t tb_phys; - int tb_idx; + unsigned int fragsz = skb_frag_size(frag); + int ret; - if (!skb_frag_size(frag)) + if (!fragsz) continue; tb_phys = skb_frag_dma_map(trans->dev, frag, 0, - skb_frag_size(frag), DMA_TO_DEVICE); - - if (unlikely(dma_mapping_error(trans->dev, tb_phys))) - return -ENOMEM; - tb_idx = iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, - skb_frag_size(frag)); - trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb_frag_address(frag), - tb_phys, skb_frag_size(frag)); - if (tb_idx < 0) - return tb_idx; - - out_meta->tbs |= BIT(tb_idx); + fragsz, DMA_TO_DEVICE); + ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys, + skb_frag_address(frag), + fragsz, out_meta); + if (ret) + return ret; } return 0; @@ -456,7 +575,7 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans, static struct iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, struct iwl_txq *txq, - struct iwl_device_cmd *dev_cmd, + struct iwl_device_tx_cmd *dev_cmd, struct sk_buff *skb, struct iwl_cmd_meta *out_meta, int hdr_len, @@ -475,6 +594,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, /* The first TB points to bi-directional DMA data */ memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE); + /* + * No need for _with_wa, the first TB allocation is aligned up + * to a 64-byte boundary and thus can't be at the end or cross + * a page boundary (much less a 2^32 boundary). + */ iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE); /* @@ -496,6 +620,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(trans->dev, tb_phys))) goto out_err; + /* + * No need for _with_wa(), we ensure (via alignment) that the data + * here can never cross or end at a page boundary. + */ iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len); trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr, IWL_FIRST_TB_SIZE + tb1_len, hdr_len); @@ -504,26 +632,30 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, tb2_len = skb_headlen(skb) - hdr_len; if (tb2_len > 0) { + int ret; + tb_phys = dma_map_single(trans->dev, skb->data + hdr_len, tb2_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(trans->dev, tb_phys))) + ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys, + skb->data + hdr_len, tb2_len, + NULL); + if (ret) goto out_err; - iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb2_len); - trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb->data + hdr_len, - tb_phys, tb2_len); } if (iwl_pcie_gen2_tx_add_frags(trans, skb, tfd, out_meta)) goto out_err; skb_walk_frags(skb, frag) { + int ret; + tb_phys = dma_map_single(trans->dev, frag->data, skb_headlen(frag), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(trans->dev, tb_phys))) + ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys, + frag->data, + skb_headlen(frag), NULL); + if (ret) goto out_err; - iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, skb_headlen(frag)); - trace_iwlwifi_dev_tx_tb(trans->dev, skb, frag->data, - tb_phys, skb_headlen(frag)); if (iwl_pcie_gen2_tx_add_frags(trans, frag, tfd, out_meta)) goto out_err; } @@ -538,7 +670,7 @@ out_err: static struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq, - struct iwl_device_cmd *dev_cmd, + struct iwl_device_tx_cmd *dev_cmd, struct sk_buff *skb, struct iwl_cmd_meta *out_meta) { @@ -578,7 +710,7 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans, } int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int txq_id) + struct iwl_device_tx_cmd *dev_cmd, int txq_id) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct iwl_cmd_meta *out_meta; @@ -603,7 +735,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb, /* don't put the packet on the ring, if there is no room */ if (unlikely(iwl_queue_space(trans, txq) < 3)) { - struct iwl_device_cmd **dev_cmd_ptr; + struct iwl_device_tx_cmd **dev_cmd_ptr; dev_cmd_ptr = (void *)((u8 *)skb->cb + trans_pcie->dev_cmd_offs); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index f21f16ab2a97..b0eb52b4951b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -213,8 +213,8 @@ static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans, u8 sec_ctl = 0; u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE; __le16 bc_ent; - struct iwl_tx_cmd *tx_cmd = - (void *)txq->entries[txq->write_ptr].cmd->payload; + struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd; + struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload; u8 sta_id = tx_cmd->sta_id; scd_bc_tbl = trans_pcie->scd_bc_tbls.addr; @@ -257,8 +257,8 @@ static void iwl_pcie_txq_inval_byte_cnt_tbl(struct iwl_trans *trans, int read_ptr = txq->read_ptr; u8 sta_id = 0; __le16 bc_ent; - struct iwl_tx_cmd *tx_cmd = - (void *)txq->entries[read_ptr].cmd->payload; + struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd; + struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload; WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX); @@ -624,12 +624,18 @@ void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie, struct sk_buff *skb) { struct page **page_ptr; + struct page *next; page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); + next = *page_ptr; + *page_ptr = NULL; - if (*page_ptr) { - __free_page(*page_ptr); - *page_ptr = NULL; + while (next) { + struct page *tmp = next; + + next = *(void **)(page_address(next) + PAGE_SIZE - + sizeof(void *)); + __free_page(tmp); } } @@ -1196,7 +1202,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn, while (!skb_queue_empty(&overflow_skbs)) { struct sk_buff *skb = __skb_dequeue(&overflow_skbs); - struct iwl_device_cmd *dev_cmd_ptr; + struct iwl_device_tx_cmd *dev_cmd_ptr; dev_cmd_ptr = *(void **)((u8 *)skb->cb + trans_pcie->dev_cmd_offs); @@ -2052,17 +2058,34 @@ static int iwl_fill_data_tbs(struct iwl_trans *trans, struct sk_buff *skb, } #ifdef CONFIG_INET -struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len) +struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len, + struct sk_buff *skb) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct iwl_tso_hdr_page *p = this_cpu_ptr(trans_pcie->tso_hdr_page); + struct page **page_ptr; + + page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); + + if (WARN_ON(*page_ptr)) + return NULL; if (!p->page) goto alloc; - /* enough room on this page */ - if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE) - return p; + /* + * Check if there's enough room on this page + * + * Note that we put a page chaining pointer *last* in the + * page - we need it somewhere, and if it's there then we + * avoid DMA mapping the last bits of the page which may + * trigger the 32-bit boundary hardware bug. + * + * (see also get_workaround_page() in tx-gen2.c) + */ + if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE - + sizeof(void *)) + goto out; /* We don't have enough room on this page, get a new one. */ __free_page(p->page); @@ -2072,6 +2095,11 @@ alloc: if (!p->page) return NULL; p->pos = page_address(p->page); + /* set the chaining pointer to NULL */ + *(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL; +out: + *page_ptr = p->page; + get_page(p->page); return p; } @@ -2097,7 +2125,8 @@ static void iwl_compute_pseudo_hdr_csum(void *iph, struct tcphdr *tcph, static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_txq *txq, u8 hdr_len, struct iwl_cmd_meta *out_meta, - struct iwl_device_cmd *dev_cmd, u16 tb1_len) + struct iwl_device_tx_cmd *dev_cmd, + u16 tb1_len) { struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload; struct iwl_trans_pcie *trans_pcie = txq->trans_pcie; @@ -2107,7 +2136,6 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, u16 length, iv_len, amsdu_pad; u8 *start_hdr; struct iwl_tso_hdr_page *hdr_page; - struct page **page_ptr; struct tso_t tso; /* if the packet is protected, then it must be CCMP or GCMP */ @@ -2130,14 +2158,11 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, (3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len; /* Our device supports 9 segments at most, it will fit in 1 page */ - hdr_page = get_page_hdr(trans, hdr_room); + hdr_page = get_page_hdr(trans, hdr_room, skb); if (!hdr_page) return -ENOMEM; - get_page(hdr_page->page); start_hdr = hdr_page->pos; - page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs); - *page_ptr = hdr_page->page; memcpy(hdr_page->pos, skb->data + hdr_len, iv_len); hdr_page->pos += iv_len; @@ -2279,7 +2304,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_txq *txq, u8 hdr_len, struct iwl_cmd_meta *out_meta, - struct iwl_device_cmd *dev_cmd, u16 tb1_len) + struct iwl_device_tx_cmd *dev_cmd, + u16 tb1_len) { /* No A-MSDU without CONFIG_INET */ WARN_ON(1); @@ -2289,7 +2315,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, #endif /* CONFIG_INET */ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, - struct iwl_device_cmd *dev_cmd, int txq_id) + struct iwl_device_tx_cmd *dev_cmd, int txq_id) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct ieee80211_hdr *hdr; @@ -2346,7 +2372,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, /* don't put the packet on the ring, if there is no room */ if (unlikely(iwl_queue_space(trans, txq) < 3)) { - struct iwl_device_cmd **dev_cmd_ptr; + struct iwl_device_tx_cmd **dev_cmd_ptr; dev_cmd_ptr = (void *)((u8 *)skb->cb + trans_pcie->dev_cmd_offs); diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c index 57edfada0665..c9401c121a14 100644 --- a/drivers/net/wireless/marvell/libertas/cfg.c +++ b/drivers/net/wireless/marvell/libertas/cfg.c @@ -273,6 +273,10 @@ add_ie_rates(u8 *tlv, const u8 *ie, int *nrates) int hw, ap, ap_max = ie[1]; u8 hw_rate; + if (ap_max > MAX_RATES) { + lbs_deb_assoc("invalid rates\n"); + return tlv; + } /* Advance past IE header */ ie += 2; @@ -1717,6 +1721,9 @@ static int lbs_ibss_join_existing(struct lbs_private *priv, struct cmd_ds_802_11_ad_hoc_join cmd; u8 preamble = RADIO_PREAMBLE_SHORT; int ret = 0; + int hw, i; + u8 rates_max; + u8 *rates; /* TODO: set preamble based on scan result */ ret = lbs_set_radio(priv, preamble, 1); @@ -1775,9 +1782,12 @@ static int lbs_ibss_join_existing(struct lbs_private *priv, if (!rates_eid) { lbs_add_rates(cmd.bss.rates); } else { - int hw, i; - u8 rates_max = rates_eid[1]; - u8 *rates = cmd.bss.rates; + rates_max = rates_eid[1]; + if (rates_max > MAX_RATES) { + lbs_deb_join("invalid rates"); + goto out; + } + rates = cmd.bss.rates; for (hw = 0; hw < ARRAY_SIZE(lbs_rates); hw++) { u8 hw_rate = lbs_rates[hw].bitrate / 5; for (i = 0; i < rates_max; i++) { diff --git a/drivers/net/wireless/mediatek/mt76/airtime.c b/drivers/net/wireless/mediatek/mt76/airtime.c index 55116f395f9a..a4a785467748 100644 --- a/drivers/net/wireless/mediatek/mt76/airtime.c +++ b/drivers/net/wireless/mediatek/mt76/airtime.c @@ -242,7 +242,7 @@ u32 mt76_calc_rx_airtime(struct mt76_dev *dev, struct mt76_rx_status *status, return 0; sband = dev->hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx > sband->n_bitrates) + if (!sband || status->rate_idx >= sband->n_bitrates) return 0; rate = &sband->bitrates[status->rate_idx]; diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index b9f2a401041a..96018fd65779 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -378,7 +378,8 @@ void mt76_unregister_device(struct mt76_dev *dev) { struct ieee80211_hw *hw = dev->hw; - mt76_led_cleanup(dev); + if (IS_ENABLED(CONFIG_MT76_LEDS)) + mt76_led_cleanup(dev); mt76_tx_status_check(dev, NULL, true); ieee80211_unregister_hw(hw); } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 4937a088d7d8..fbeb9f73ef28 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5074,18 +5074,25 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); #ifdef CONFIG_PCI_ATS /* - * Some devices have a broken ATS implementation causing IOMMU stalls. - * Don't use ATS for those devices. + * Some devices require additional driver setup to enable ATS. Don't use + * ATS for those devices as ATS will be enabled before the driver has had a + * chance to load and configure the device. */ -static void quirk_no_ats(struct pci_dev *pdev) +static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - pci_info(pdev, "disabling ATS (broken on this device)\n"); + if (pdev->device == 0x7340 && pdev->revision != 0xc5) + return; + + pci_info(pdev, "disabling ATS\n"); pdev->ats_cap = 0; } /* AMD Stoney platform GPU */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); +/* AMD Iceland dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); +/* AMD Navi14 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ /* Freescale PCIe doesn't support MSI in RC mode */ diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 55083c67b2bb..95dca2cb5265 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -633,13 +633,17 @@ static int ddr_perf_probe(struct platform_device *pdev) if (ret < 0) { dev_err(&pdev->dev, "cpuhp_setup_state_multi failed\n"); - goto ddr_perf_err; + goto cpuhp_state_err; } pmu->cpuhp_state = ret; /* Register the pmu instance for cpu hotplug */ - cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node); + ret = cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node); + if (ret) { + dev_err(&pdev->dev, "Error %d registering hotplug\n", ret); + goto cpuhp_instance_err; + } /* Request irq */ irq = of_irq_get(np, 0); @@ -673,9 +677,10 @@ static int ddr_perf_probe(struct platform_device *pdev) return 0; ddr_perf_err: - if (pmu->cpuhp_state) - cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); - + cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); +cpuhp_instance_err: + cpuhp_remove_multi_state(pmu->cpuhp_state); +cpuhp_state_err: ida_simple_remove(&ddr_ida, pmu->id); dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret); return ret; @@ -686,6 +691,7 @@ static int ddr_perf_remove(struct platform_device *pdev) struct ddr_pmu *pmu = platform_get_drvdata(pdev); cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); + cpuhp_remove_multi_state(pmu->cpuhp_state); irq_set_affinity_hint(pmu->irq, NULL); perf_pmu_unregister(&pmu->pmu); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index 96183e31b96a..584de8f807cc 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -337,38 +337,44 @@ void hisi_uncore_pmu_disable(struct pmu *pmu) hisi_pmu->ops->stop_counters(hisi_pmu); } + /* - * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1. - * If multi-threading is supported, On Huawei Kunpeng 920 SoC whose cpu - * core is tsv110, CCL_ID is the low 3-bits in MPIDR[Aff2] and SCCL_ID - * is the upper 5-bits of Aff2 field; while for other cpu types, SCCL_ID - * is in MPIDR[Aff3] and CCL_ID is in MPIDR[Aff2], if not, SCCL_ID - * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1]. + * The Super CPU Cluster (SCCL) and CPU Cluster (CCL) IDs can be + * determined from the MPIDR_EL1, but the encoding varies by CPU: + * + * - For MT variants of TSV110: + * SCCL is Aff2[7:3], CCL is Aff2[2:0] + * + * - For other MT parts: + * SCCL is Aff3[7:0], CCL is Aff2[7:0] + * + * - For non-MT parts: + * SCCL is Aff2[7:0], CCL is Aff1[7:0] */ -static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id) +static void hisi_read_sccl_and_ccl_id(int *scclp, int *cclp) { u64 mpidr = read_cpuid_mpidr(); - - if (mpidr & MPIDR_MT_BITMASK) { - if (read_cpuid_part_number() == HISI_CPU_PART_TSV110) { - int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); - - if (sccl_id) - *sccl_id = aff2 >> 3; - if (ccl_id) - *ccl_id = aff2 & 0x7; - } else { - if (sccl_id) - *sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3); - if (ccl_id) - *ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); - } + int aff3 = MPIDR_AFFINITY_LEVEL(mpidr, 3); + int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); + int aff1 = MPIDR_AFFINITY_LEVEL(mpidr, 1); + bool mt = mpidr & MPIDR_MT_BITMASK; + int sccl, ccl; + + if (mt && read_cpuid_part_number() == HISI_CPU_PART_TSV110) { + sccl = aff2 >> 3; + ccl = aff2 & 0x7; + } else if (mt) { + sccl = aff3; + ccl = aff2; } else { - if (sccl_id) - *sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); - if (ccl_id) - *ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); + sccl = aff2; + ccl = aff1; } + + if (scclp) + *scclp = sccl; + if (cclp) + *cclp = ccl; } /* diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 44d7f50bbc82..d936e7aa74c4 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -49,6 +49,7 @@ .padown_offset = SPT_PAD_OWN, \ .padcfglock_offset = SPT_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ + .is_offset = SPT_GPI_IS, \ .ie_offset = SPT_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 8ef150dfb6f7..b60795893994 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -439,6 +439,9 @@ static int fnic_queuecommand_lck(struct scsi_cmnd *sc, void (*done)(struct scsi_ if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) return SCSI_MLQUEUE_HOST_BUSY; + if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) + return SCSI_MLQUEUE_HOST_BUSY; + rport = starget_to_rport(scsi_target(sc->device)); if (!rport) { FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 65ce10c7989c..902b649fc8ef 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2958,15 +2958,16 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) q->limits.zoned = BLK_ZONED_HM; } else { sdkp->zoned = (buffer[8] >> 4) & 3; - if (sdkp->zoned == 1) + if (sdkp->zoned == 1 && !disk_has_partitions(sdkp->disk)) { /* Host-aware */ q->limits.zoned = BLK_ZONED_HA; - else + } else { /* - * Treat drive-managed devices as - * regular block devices. + * Treat drive-managed devices and host-aware devices + * with partitions as regular block devices. */ q->limits.zoned = BLK_ZONED_NONE; + } } if (blk_queue_is_zoned(q) && sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 7251a87bb576..b94ed4e30770 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4149,9 +4149,6 @@ int iscsit_close_connection( iscsit_stop_nopin_response_timer(conn); iscsit_stop_nopin_timer(conn); - if (conn->conn_transport->iscsit_wait_conn) - conn->conn_transport->iscsit_wait_conn(conn); - /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4237,6 +4234,9 @@ int iscsit_close_connection( target_sess_cmd_list_set_waiting(sess->se_sess); target_wait_for_sess_cmds(sess->se_sess); + if (conn->conn_transport->iscsit_wait_conn) + conn->conn_transport->iscsit_wait_conn(conn); + ahash_request_free(conn->conn_tx_hash); if (conn->conn_rx_hash) { struct crypto_ahash *tfm; diff --git a/drivers/tee/optee/Kconfig b/drivers/tee/optee/Kconfig index d1ad512e1708..3ca71e3812ed 100644 --- a/drivers/tee/optee/Kconfig +++ b/drivers/tee/optee/Kconfig @@ -3,6 +3,7 @@ config OPTEE tristate "OP-TEE" depends on HAVE_ARM_SMCCC + depends on MMU help This implements the OP-TEE Trusted Execution Environment (TEE) driver. diff --git a/fs/afs/cell.c b/fs/afs/cell.c index fd5133e26a38..78ba5f932287 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -134,8 +134,17 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, _leave(" = -ENAMETOOLONG"); return ERR_PTR(-ENAMETOOLONG); } - if (namelen == 5 && memcmp(name, "@cell", 5) == 0) + + /* Prohibit cell names that contain unprintable chars, '/' and '@' or + * that begin with a dot. This also precludes "@cell". + */ + if (name[0] == '.') return ERR_PTR(-EINVAL); + for (i = 0; i < namelen; i++) { + char ch = name[i]; + if (!isprint(ch) || ch == '/' || ch == '@') + return ERR_PTR(-EINVAL); + } _enter("%*.*s,%s", namelen, namelen, name, addresses); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f639dde2a679..ba4d8f375b3c 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -500,11 +500,8 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, &dev_replace->scrub_progress, 0, 1); ret = btrfs_dev_replace_finishing(fs_info, ret); - if (ret == -EINPROGRESS) { + if (ret == -EINPROGRESS) ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS; - } else if (ret != -ECANCELED) { - WARN_ON(ret); - } return ret; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 21de630b0730..fd266a2d15ec 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3577,17 +3577,27 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * This can easily boost the amount of SYSTEM chunks if cleaner * thread can't be triggered fast enough, and use up all space * of btrfs_super_block::sys_chunk_array + * + * While for dev replace, we need to try our best to mark block + * group RO, to prevent race between: + * - Write duplication + * Contains latest data + * - Scrub copy + * Contains data from commit tree + * + * If target block group is not marked RO, nocow writes can + * be overwritten by scrub copy, causing data corruption. + * So for dev-replace, it's not allowed to continue if a block + * group is not RO. */ - ret = btrfs_inc_block_group_ro(cache, false); - scrub_pause_off(fs_info); - + ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); if (ret == 0) { ro_set = 1; - } else if (ret == -ENOSPC) { + } else if (ret == -ENOSPC && !sctx->is_dev_replace) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. - * It is not a problem for scrub/replace, because + * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. */ @@ -3596,9 +3606,22 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, btrfs_warn(fs_info, "failed setting block group ro: %d", ret); btrfs_put_block_group(cache); + scrub_pause_off(fs_info); break; } + /* + * Now the target block is marked RO, wait for nocow writes to + * finish before dev-replace. + * COW is fine, as COW never overwrites extents in commit tree. + */ + if (sctx->is_dev_replace) { + btrfs_wait_nocow_writers(cache); + btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start, + cache->length); + } + + scrub_pause_off(fs_info); down_write(&dev_replace->rwsem); dev_replace->cursor_right = found_key.offset + length; dev_replace->cursor_left = found_key.offset; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 374db1bd57d1..145d46ba25ae 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -708,8 +708,10 @@ void ceph_mdsc_release_request(struct kref *kref) /* avoid calling iput_final() in mds dispatch threads */ ceph_async_iput(req->r_inode); } - if (req->r_parent) + if (req->r_parent) { ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ceph_async_iput(req->r_parent); + } ceph_async_iput(req->r_target_inode); if (req->r_dentry) dput(req->r_dentry); @@ -2676,8 +2678,10 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); - if (req->r_parent) + if (req->r_parent) { ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ihold(req->r_parent); + } if (req->r_old_dentry_dir) ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); diff --git a/fs/io_uring.c b/fs/io_uring.c index 187dd94fd6b1..e54556b0fcc6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4463,13 +4463,15 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; + if (up.resv) + return -EINVAL; if (check_add_overflow(up.offset, nr_args, &done)) return -EOVERFLOW; if (done > ctx->nr_user_files) return -EINVAL; done = 0; - fds = (__s32 __user *) up.fds; + fds = u64_to_user_ptr(up.fds); while (nr_args) { struct fixed_file_table *table; unsigned index; @@ -5042,10 +5044,6 @@ static int io_uring_flush(struct file *file, void *data) struct io_ring_ctx *ctx = file->private_data; io_uring_cancel_files(ctx, data); - if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) { - io_cqring_overflow_flush(ctx, true); - io_wq_cancel_all(ctx->io_wq); - } return 0; } @@ -5159,12 +5157,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } else if (to_submit) { struct mm_struct *cur_mm; - if (current->mm != ctx->sqo_mm || - current_cred() != ctx->creds) { - ret = -EPERM; - goto out; - } - to_submit = min(to_submit, ctx->sq_entries); mutex_lock(&ctx->uring_lock); /* already have mm, so io_submit_sqes() won't try to grab it */ diff --git a/fs/namei.c b/fs/namei.c index d2720dc71d0e..4fb61e0754ed 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1001,7 +1001,8 @@ static int may_linkat(struct path *link) * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. - * @dir: the sticky parent directory + * @dir_mode: mode bits of directory + * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: @@ -1017,18 +1018,18 @@ static int may_linkat(struct path *link) * * Returns 0 if the open is allowed, -ve on error. */ -static int may_create_in_sticky(struct dentry * const dir, +static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || - likely(!(dir->d_inode->i_mode & S_ISVTX)) || - uid_eq(inode->i_uid, dir->d_inode->i_uid) || + likely(!(dir_mode & S_ISVTX)) || + uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; - if (likely(dir->d_inode->i_mode & 0002) || - (dir->d_inode->i_mode & 0020 && + if (likely(dir_mode & 0002) || + (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { const char *operation = S_ISFIFO(inode->i_mode) ? @@ -3201,6 +3202,8 @@ static int do_last(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; + kuid_t dir_uid = dir->d_inode->i_uid; + umode_t dir_mode = dir->d_inode->i_mode; int open_flag = op->open_flag; bool will_truncate = (open_flag & O_TRUNC) != 0; bool got_write = false; @@ -3331,7 +3334,7 @@ finish_open: error = -EISDIR; if (d_is_dir(nd->path.dentry)) goto out; - error = may_create_in_sticky(dir, + error = may_create_in_sticky(dir_mode, dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) goto out; diff --git a/fs/readdir.c b/fs/readdir.c index d26d5ea4de7b..de2eceffdee8 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -102,10 +102,14 @@ EXPORT_SYMBOL(iterate_dir); * filename length, and the above "soft error" worry means * that it's probably better left alone until we have that * issue clarified. + * + * Note the PATH_MAX check - it's arbitrary but the real + * kernel limit on a possible path component, not NAME_MAX, + * which is the technical standard limit. */ static int verify_dirent_name(const char *name, int len) { - if (!len) + if (len <= 0 || len >= PATH_MAX) return -EIO; if (memchr(name, '/', len)) return -EIO; @@ -206,7 +210,7 @@ struct linux_dirent { struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; - struct linux_dirent __user * previous; + int prev_reclen; int count; int error; }; @@ -214,12 +218,13 @@ struct getdents_callback { static int filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent __user * dirent; + struct linux_dirent __user *dirent, *prev; struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -232,28 +237,24 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, buf->error = -EOVERFLOW; return -EOVERFLOW; } - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *) dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->current_dir = (void __user *)dirent + reclen; + buf->prev_reclen = reclen; buf->count -= reclen; return 0; efault_end: @@ -267,7 +268,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct linux_dirent __user *, dirent, unsigned int, count) { struct fd f; - struct linux_dirent __user * lastdirent; struct getdents_callback buf = { .ctx.actor = filldir, .count = count, @@ -285,8 +285,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent __user * lastdirent; + lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else @@ -299,7 +301,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; - struct linux_dirent64 __user * previous; + int prev_reclen; int count; int error; }; @@ -307,11 +309,12 @@ struct getdents_callback64 { static int filldir64(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent64 __user *dirent; + struct linux_dirent64 __user *dirent, *prev; struct getdents_callback64 *buf = container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -319,30 +322,27 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *)dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, &dirent->d_type, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->prev_reclen = reclen; + buf->current_dir = (void __user *)dirent + reclen; buf->count -= reclen; return 0; + efault_end: user_access_end(); efault: @@ -354,7 +354,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count) { struct fd f; - struct linux_dirent64 __user * lastdirent; struct getdents_callback64 buf = { .ctx.actor = filldir64, .count = count, @@ -372,9 +371,11 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent64 __user * lastdirent; typeof(lastdirent->d_off) d_off = buf.ctx.pos; + + lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; if (__put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8bb63027e4d6..ea4c133b4139 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,6 +245,18 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) !(disk->flags & GENHD_FL_NO_PART_SCAN); } +static inline bool disk_has_partitions(struct gendisk *disk) +{ + bool ret = false; + + rcu_read_lock(); + if (rcu_dereference(disk->part_tbl)->len > 1) + ret = true; + rcu_read_unlock(); + + return ret; +} + static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ae5e260911e2..cac56fb59af8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3698,6 +3698,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_validate_mtu(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu_ext(struct net_device *dev, int mtu, struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 4d8b1eaf7708..908d38dbcb91 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -426,13 +426,6 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr) sizeof(*addr)); } -/* Calculate the bytes required to store the inclusive range of a-b */ -static inline int -bitmap_bytes(u32 a, u32 b) -{ - return 4 * ((((b - a + 8) / 8) + 3) / 4); -} - /* How often should the gc be run by default */ #define IPSET_GC_TIME (3 * 60) diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index cf09ab37b45b..851425c3178f 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -31,7 +31,7 @@ struct nfnetlink_subsystem { const struct nfnl_callback *cb; /* callback for individual types */ struct module *owner; int (*commit)(struct net *net, struct sk_buff *skb); - int (*abort)(struct net *net, struct sk_buff *skb); + int (*abort)(struct net *net, struct sk_buff *skb, bool autoload); void (*cleanup)(struct net *net); bool (*valid_genid)(struct net *net, u32 genid); }; diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 86eecbd98e84..f73e1775ded0 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -417,6 +417,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) } /** + * xa_for_each_range() - Iterate over a portion of an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * @last: Last index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_range() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_range(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_range(xa, index, entry, start, last) \ + for (index = start, \ + entry = xa_find(xa, &index, last, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, last, XA_PRESENT)) + +/** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. @@ -439,11 +469,8 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each_start(xa, index, entry, start) \ - for (index = start, \ - entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ - entry; \ - entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) +#define xa_for_each_start(xa, index, entry, start) \ + xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. @@ -508,6 +535,14 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +#define xa_lock_nested(xa, subclass) \ + spin_lock_nested(&(xa)->xa_lock, subclass) +#define xa_lock_bh_nested(xa, subclass) \ + spin_lock_bh_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irq_nested(xa, subclass) \ + spin_lock_irq_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irqsave_nested(xa, flags, subclass) \ + spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 286fd960896f..a1a8d45adb42 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -7,6 +7,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; + struct list_head module_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 9a0e8af21310..a5ccfa67bc5c 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -66,7 +66,11 @@ TRACE_EVENT(xen_mc_callback, TP_PROTO(xen_mc_callback_fn_t fn, void *data), TP_ARGS(fn, data), TP_STRUCT__entry( - __field(xen_mc_callback_fn_t, fn) + /* + * Use field_struct to avoid is_signed_type() + * comparison of a function pointer. + */ + __field_struct(xen_mc_callback_fn_t, fn) __field(void *, data) ), TP_fast_assign( diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index c160a5354eb6..f94f65d429be 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -11,6 +11,8 @@ #define PROT_WRITE 0x2 /* page can be written */ #define PROT_EXEC 0x4 /* page can be executed */ #define PROT_SEM 0x8 /* page may be used for atomic ops */ +/* 0x10 reserved for arch-specific use */ +/* 0x20 reserved for arch-specific use */ #define PROT_NONE 0x0 /* page can not be accessed */ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a3300e1b9a01..55cfcb71606d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -178,7 +178,8 @@ struct io_uring_params { struct io_uring_files_update { __u32 offset; - __s32 *fds; + __u32 resv; + __aligned_u64 /* __s32 * */ fds; }; #endif diff --git a/kernel/kexec.c b/kernel/kexec.c index bc933c0db9bf..f977786fe498 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* Install the new kernel and uninstall the old */ image = xchg(dest_image, image); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 15d70a90b50d..c19c0dad1ebe 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -589,6 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image) kimage_free_page_list(&image->unusable_pages); } + +int __weak machine_kexec_post_load(struct kimage *image) +{ + return 0; +} + void kimage_terminate(struct kimage *image) { if (*image->entry != 0) @@ -1171,7 +1177,7 @@ int kernel_kexec(void) * CPU hotplug again; so re-enable it here. */ cpu_hotplug_enable(); - pr_emerg("Starting new kernel\n"); + pr_notice("Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index a2df93948665..faa74d5f6941 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -441,6 +441,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* * Free up any temporary buffers allocated which are not needed * after image has been loaded diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 48aaf2ac0d0d..39d30ccf8d87 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); +int machine_kexec_post_load(struct kimage *image); + extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 26b9168321e7..d65f2d5ab694 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void) void clear_free_pages(void) { -#ifdef CONFIG_PAGE_POISONING_ZERO struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; - memory_bm_position_reset(bm); - pfn = memory_bm_next_pfn(bm); - while (pfn != BM_END_OF_MAP) { - if (pfn_valid(pfn)) - clear_highpage(pfn_to_page(pfn)); - + if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) { + memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (pfn_valid(pfn)) + clear_highpage(pfn_to_page(pfn)); + + pfn = memory_bm_next_pfn(bm); + } + memory_bm_position_reset(bm); + pr_info("free pages cleared after restore\n"); } - memory_bm_position_reset(bm); - pr_info("free pages cleared after restore\n"); -#endif /* PAGE_POISONING_ZERO */ } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ddb7e7f5fe8d..5b6ee4aadc26 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9420,6 +9420,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f62de5f43e79..6ac35b9e195d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -116,6 +116,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1766,11 +1767,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data, struct event_trigger_data *test; struct hist_field *hist_field; + lockdep_assert_held(&event_mutex); + hist_field = find_var_field(hist_data, var_name); if (hist_field) return hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1820,7 +1823,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file, struct event_trigger_data *test; struct hist_field *hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -2423,8 +2428,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -2466,6 +2479,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2661,6 +2676,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { @@ -3115,7 +3141,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, { struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (test->private_data == hist_data) return test->filter_str; @@ -3166,9 +3194,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data, struct event_trigger_data *test; unsigned int n_keys; + lockdep_assert_held(&event_mutex); + n_keys = target_hist_data->n_fields - target_hist_data->n_vals; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; @@ -5528,7 +5558,7 @@ static int hist_show(struct seq_file *m, void *v) goto out_unlock; } - list_for_each_entry_rcu(data, &event_file->triggers, list) { + list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } @@ -5921,7 +5951,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->attrs->name && !named_data) goto new; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6005,10 +6037,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data, struct event_trigger_data *test, *named_data = NULL; bool match = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (hist_trigger_match(data, test, named_data, false)) { match = true; @@ -6026,10 +6060,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, struct hist_trigger_data *hist_data = data->private_data; struct event_trigger_data *test, *named_data = NULL; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6051,10 +6087,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, *named_data = NULL; bool unregistered = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6080,7 +6118,9 @@ static bool hist_file_check_refs(struct trace_event_file *file) struct hist_trigger_data *hist_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; if (check_var_refs(hist_data)) @@ -6323,7 +6363,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, struct enable_trigger_data *enable_data = data->private_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &enable_data->file->triggers, list) { + list_for_each_entry_rcu(test, &enable_data->file->triggers, list, + lockdep_is_held(&event_mutex)) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (enable_data->enable) test->paused = false; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2cd53ca21b51..40106fff06a4 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file) struct event_trigger_data *data; bool set_cond = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->filter || event_command_post_trigger(data->cmd_ops) || event_command_needs_rec(data->cmd_ops)) { set_cond = true; @@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { ret = -EEXIST; goto out; @@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { unregistered = true; list_del_rcu(&data->list); @@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { test_enable_data = test->private_data; if (test_enable_data && (test->cmd_ops->trigger_type == @@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { enable_data = data->private_data; if (enable_data && (data->cmd_ops->trigger_type == diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7f890262c8a3..3f54dc2f6e1c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, false); if (ret < 0) goto error; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 905b10af5d5c..9ae87be422f2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -984,15 +984,19 @@ void trace_probe_cleanup(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, bool alloc_filter) { struct trace_event_call *call; + size_t size = sizeof(struct trace_probe_event); int ret = 0; if (!event || !group) return -EINVAL; - tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL); + if (alloc_filter) + size += sizeof(struct trace_uprobe_filter); + + tp->event = kzalloc(size, GFP_KERNEL); if (!tp->event) return -ENOMEM; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4ee703728aec..a0ff9e200ef6 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -223,6 +223,12 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* Event call and class holder */ struct trace_probe_event { unsigned int flags; /* For TP_FLAG_* */ @@ -230,6 +236,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + struct trace_uprobe_filter filter[0]; }; struct trace_probe { @@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, bool alloc_filter); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 352073d36585..2619bc5ed520 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -34,12 +34,6 @@ struct uprobe_trace_entry_head { #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) -struct trace_uprobe_filter { - rwlock_t rwlock; - int nr_systemwide; - struct list_head perf_events; -}; - static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); @@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; @@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: @@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp) struct trace_probe *pos; struct trace_uprobe *tu; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } @@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call, } tu = container_of(tp, struct trace_uprobe, tp); - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; @@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - err = 0; - if (!done) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); - } - return err; + return done; } -static int uprobe_perf_multi_call(struct trace_event_call *call, - struct perf_event *event, - int (*op)(struct trace_uprobe *tu, struct perf_event *event)) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; @@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call, if (WARN_ON_ONCE(!tp)) return -ENODEV; + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); - ret = op(tu, event); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; +} + static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_multi_call(event, data, uprobe_perf_open); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_multi_call(event, data, uprobe_perf_close); + return uprobe_perf_close(event, data); #endif default: diff --git a/lib/Makefile b/lib/Makefile index 93217d44237f..c20b1debe9b4 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -223,7 +223,7 @@ KASAN_SANITIZE_stackdepot.o := n KCOV_INSTRUMENT_stackdepot.o := n libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \ - fdt_empty_tree.o + fdt_empty_tree.o fdt_addresses.o $(foreach file, $(libfdt_files), \ $(eval CFLAGS_$(file) = -I $(srctree)/scripts/dtc/libfdt)) lib-$(CONFIG_LIBFDT) += $(libfdt_files) diff --git a/lib/fdt_addresses.c b/lib/fdt_addresses.c new file mode 100644 index 000000000000..23610bcf390b --- /dev/null +++ b/lib/fdt_addresses.c @@ -0,0 +1,2 @@ +#include <linux/libfdt_env.h> +#include "../scripts/dtc/libfdt/fdt_addresses.c" diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index dccb95af6003..706020b06617 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -30,13 +30,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; - /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; @@ -114,6 +107,13 @@ long strncpy_from_user(char *dst, const char __user *src, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_access_begin(src, max)) { diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 6c0005d5dd5c..41670d4a5816 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -27,13 +27,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long c; /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - - /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ @@ -109,6 +102,13 @@ long strnlen_user(const char __user *str, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + if (user_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_access_end(); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 7df4f7f395bf..55c14e8c8859 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -2,6 +2,7 @@ /* * test_xarray.c: Test the XArray API * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2019-2020 Oracle * Author: Matthew Wilcox <[email protected]> */ @@ -902,28 +903,34 @@ static noinline void check_store_iter(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_find(struct xarray *xa) +static noinline void check_multi_find_1(struct xarray *xa, unsigned order) { #ifdef CONFIG_XARRAY_MULTI + unsigned long multi = 3 << order; + unsigned long next = 4 << order; unsigned long index; - xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL); - XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL); + xa_store_order(xa, multi, order, xa_mk_value(multi), GFP_KERNEL); + XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store_index(xa, next + 1, GFP_KERNEL) != NULL); index = 0; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, index != 12); - index = 13; + xa_mk_value(multi)); + XA_BUG_ON(xa, index != multi); + index = multi + 1; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, (index < 12) || (index >= 16)); + xa_mk_value(multi)); + XA_BUG_ON(xa, (index < multi) || (index >= next)); XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(16)); - XA_BUG_ON(xa, index != 16); - - xa_erase_index(xa, 12); - xa_erase_index(xa, 16); + xa_mk_value(next)); + XA_BUG_ON(xa, index != next); + XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL); + XA_BUG_ON(xa, index != next); + + xa_erase_index(xa, multi); + xa_erase_index(xa, next); + xa_erase_index(xa, next + 1); XA_BUG_ON(xa, !xa_empty(xa)); #endif } @@ -1046,12 +1053,33 @@ static noinline void check_find_3(struct xarray *xa) xa_destroy(xa); } +static noinline void check_find_4(struct xarray *xa) +{ + unsigned long index = 0; + void *entry; + + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry != xa_mk_index(ULONG_MAX)); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry); + + xa_erase_index(xa, ULONG_MAX); +} + static noinline void check_find(struct xarray *xa) { + unsigned i; + check_find_1(xa); check_find_2(xa); check_find_3(xa); - check_multi_find(xa); + check_find_4(xa); + + for (i = 2; i < 10; i++) + check_multi_find_1(xa, i); check_multi_find_2(xa); } @@ -1132,6 +1160,27 @@ static noinline void check_move_tiny(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_move_max(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + rcu_read_lock(); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX)); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL); + rcu_read_unlock(); + + xas_set(&xas, 0); + rcu_read_lock(); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX)); + xas_pause(&xas); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL); + rcu_read_unlock(); + + xa_erase_index(xa, ULONG_MAX); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_move_small(struct xarray *xa, unsigned long idx) { XA_STATE(xas, xa, 0); @@ -1240,6 +1289,7 @@ static noinline void check_move(struct xarray *xa) xa_destroy(xa); check_move_tiny(xa); + check_move_max(xa); for (i = 0; i < 16; i++) check_move_small(xa, 1UL << i); diff --git a/lib/xarray.c b/lib/xarray.c index 1237c213f52b..1d9fab7db8da 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation - * Copyright (c) 2017 Microsoft Corporation + * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <[email protected]> */ @@ -967,6 +968,7 @@ void xas_pause(struct xa_state *xas) if (xas_invalid(xas)) return; + xas->xa_node = XAS_RESTART; if (node) { unsigned int offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { @@ -974,10 +976,11 @@ void xas_pause(struct xa_state *xas) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; + if (xas->xa_index == 0) + xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } - xas->xa_node = XAS_RESTART; } EXPORT_SYMBOL_GPL(xas_pause); @@ -1079,13 +1082,15 @@ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; - if (xas_error(xas)) + if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; + if (xas->xa_index > max) + return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); - } else if (xas_top(xas->xa_node)) { + } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; @@ -1150,6 +1155,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) if (xas_error(xas)) return NULL; + if (xas->xa_index > max) + goto max; if (!xas->xa_node) { xas->xa_index = 1; @@ -1824,6 +1831,17 @@ void *xa_find(struct xarray *xa, unsigned long *indexp, } EXPORT_SYMBOL(xa_find); +static bool xas_sibling(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + unsigned long mask; + + if (!node) + return false; + mask = (XA_CHUNK_SIZE << node->shift) - 1; + return (xas->xa_index & mask) > (xas->xa_offset << node->shift); +} + /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. @@ -1847,21 +1865,20 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp, XA_STATE(xas, xa, *indexp + 1); void *entry; + if (xas.xa_index == 0) + return NULL; + rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); - if (xas.xa_node == XAS_BOUNDS) + + if (xas_invalid(&xas)) break; - if (xas.xa_shift) { - if (xas.xa_index & ((1UL << xas.xa_shift) - 1)) - continue; - } else { - if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK)) - continue; - } + if (xas_sibling(&xas)) + continue; if (!xas_retry(&xas, entry)) break; } diff --git a/net/atm/proc.c b/net/atm/proc.c index d79221fd4dae..c31896707313 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v) static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = vcc_walk(seq, 1); - if (v) - (*pos)++; + (*pos)++; return v; } diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 76bd67891fb3..a0116b9503d9 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -62,7 +62,7 @@ static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt) hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1); if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) { - pr_warn("Headroom to small\n"); + pr_warn("Headroom too small\n"); kfree_skb(skb); return -EIO; } diff --git a/net/core/dev.c b/net/core/dev.c index 7e885d069707..81befd0c2510 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5491,9 +5491,29 @@ static void flush_all_backlogs(void) put_online_cpus(); } +/* 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); +} + INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); -static int napi_gro_complete(struct sk_buff *skb) +static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; __be16 type = skb->protocol; @@ -5526,7 +5546,8 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb_internal(skb); + gro_normal_one(napi, skb); + return NET_RX_SUCCESS; } static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, @@ -5539,7 +5560,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; skb_list_del_init(skb); - napi_gro_complete(skb); + napi_gro_complete(napi, skb); napi->gro_hash[index].count--; } @@ -5641,7 +5662,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } -static void gro_flush_oldest(struct list_head *head) +static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) { struct sk_buff *oldest; @@ -5657,7 +5678,7 @@ static void gro_flush_oldest(struct list_head *head) * SKB to the chain. */ skb_list_del_init(oldest); - napi_gro_complete(oldest); + napi_gro_complete(napi, oldest); } INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, @@ -5733,7 +5754,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (pp) { skb_list_del_init(pp); - napi_gro_complete(pp); + napi_gro_complete(napi, pp); napi->gro_hash[hash].count--; } @@ -5744,7 +5765,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff goto normal; if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { - gro_flush_oldest(gro_head); + gro_flush_oldest(napi, gro_head); } else { napi->gro_hash[hash].count++; } @@ -5802,26 +5823,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); -/* 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 void napi_skb_free_stolen_head(struct sk_buff *skb) { skb_dst_drop(skb); @@ -6200,8 +6201,6 @@ 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; @@ -6217,6 +6216,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } + + gro_normal_list(n); + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); @@ -6548,8 +6550,6 @@ 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. @@ -6557,6 +6557,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) napi_gro_flush(n, HZ >= 1000); } + gro_normal_list(n); + /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ @@ -8194,6 +8196,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) } EXPORT_SYMBOL(__dev_set_mtu); +int dev_validate_mtu(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) +{ + /* MTU must be positive, and in range */ + if (new_mtu < 0 || new_mtu < dev->min_mtu) { + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); + return -EINVAL; + } + + if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); + return -EINVAL; + } + return 0; +} + /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device @@ -8210,16 +8228,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, if (new_mtu == dev->mtu) return 0; - /* MTU must be positive, and in range */ - if (new_mtu < 0 || new_mtu < dev->min_mtu) { - NL_SET_ERR_MSG(extack, "mtu less than device minimum"); - return -EINVAL; - } - - if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); - return -EINVAL; - } + err = dev_validate_mtu(dev, new_mtu, extack); + if (err) + return err; if (!netif_device_present(dev)) return -ENODEV; @@ -9302,8 +9313,10 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) + if (ret) { + dev->reg_state = NETREG_UNREGISTERED; goto err_uninit; + } dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 920784a9b7ff..789a73aa7bd8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } + (*pos)++; return NULL; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 02916f43bf63..d9001b5c48eb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3048,8 +3048,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - if (tb[IFLA_MTU]) - dev->mtu = nla_get_u32(tb[IFLA_MTU]); + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + int err; + + err = dev_validate_mtu(dev, mtu, extack); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + dev->mtu = mtu; + } if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 3866d7e20c07..ded2d5227678 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -594,8 +594,6 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sock_owned_by_me(sk); - sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); diff --git a/net/core/utils.c b/net/core/utils.c index 6b6e51db9f3b..1f31a39236d5 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, } EXPORT_SYMBOL(inet_proto_csum_replace4); +/** + * inet_proto_csum_replace16 - update layer 4 header checksum field + * @sum: Layer 4 header checksum field + * @skb: sk_buff for the packet + * @from: old IPv6 address + * @to: new IPv6 address + * @pseudohdr: True if layer 4 header checksum includes pseudoheader + * + * Update layer 4 header as per the update in IPv6 src/dst address. + * + * There is no need to update skb->csum in this function, because update in two + * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other + * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to + * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, + * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as + * L4 Header checksum for skb->csum calculation. + */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) @@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); - if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) - skb->csum = ~csum_partial(diff, sizeof(diff), - ~skb->csum); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index d40de84a637f..754d84b217f0 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -191,7 +191,7 @@ void hsr_debugfs_term(struct hsr_priv *priv); void hsr_debugfs_create_root(void); void hsr_debugfs_remove_root(void); #else -static inline void void hsr_debugfs_rename(struct net_device *dev) +static inline void hsr_debugfs_rename(struct net_device *dev) { } static inline void hsr_debugfs_init(struct hsr_priv *priv, diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 0e4a7cf6bc87..e2e219c7854a 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 30fa771d382a..dcc79ff54b41 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, - [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), }, [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0fe2a5d3e258..74e1d964a615 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e90b600c7a25..37cddd18f282 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -187,8 +187,17 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); } dst_hold(dst); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 87e979f2b74a..e356ea779227 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d885ba868822..a7d766e6390e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2524,6 +2524,7 @@ static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); @@ -2614,7 +2615,6 @@ int tcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; - tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index a6545ef0d27b..6c4d79baff26 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5347ab2c9c58..2a976f57f7e7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3164,6 +3164,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 58c92a7d671c..b62b59b18db9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3232,6 +3232,7 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 93a355b6b092..030d43c7c957 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2)) + if (size < (sk->sk_rcvbuf >> 2) && + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index e31626ffccd1..fd535053245b 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -79,6 +79,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7bae6a91b487..cfae0a1529a1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2495,14 +2495,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; + ++(*pos); if (!v) goto iter_table; n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); - if (n) { - ++*pos; + if (n) return n; - } iter_table: ipv6_route_check_sernum(iter); @@ -2510,8 +2509,6 @@ iter_table: r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { - if (v) - ++*pos; return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index ee968d980746..55bfc5149d0c 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) dev->mtu -= 8; if (tunnel->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; netif_keep_dst(dev); } ip6gre_tnl_init_features(dev); @@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); @@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2f376dbc37d5..b5dd20c4599b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev) if (err) return err; ip6_tnl_link_config(t); - if (t->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (t->parms.collect_md) netif_keep_dst(dev); - } return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 6f08b760c2a7..524006aa0d78 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -449,8 +449,17 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; + if (!dst) { + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + goto tx_err_link_failure; + } + skb_dst_set(skb, dst); + } dst_hold(dst); dst = xfrm_lookup(t->net, dst, fl, NULL, 0); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 85a5447a3e8d..7cbc19731997 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -23,6 +23,7 @@ #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/dst_cache.h> +#include <net/ip_tunnels.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif @@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->encapsulation = 0; + if (iptunnel_pull_offloads(skb)) + return false; return true; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 077a2cb65fcb..26ab0e9612d8 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -75,7 +75,7 @@ mtype_flush(struct ip_set *set) if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); - memset(map->members, 0, map->memsize); + bitmap_zero(map->members, map->elements); set->elements = 0; set->ext_size = 0; } diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index abe8f77d7d23..0a2196f59106 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, u32 first_ip, u32 last_ip, u32 elements, u32 hosts, u8 netmask) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -322,7 +322,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index b618713297da..739e343efaf6 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -42,7 +42,7 @@ enum { /* Type structure */ struct bitmap_ipmac { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -299,7 +299,7 @@ static bool init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, u32 first_ip, u32 last_ip, u32 elements) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -360,7 +360,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { kfree(map); diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 23d6095cb196..b49978dd810d 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -30,7 +30,7 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -231,7 +231,7 @@ static bool init_map_port(struct ip_set *set, struct bitmap_port *map, u16 first_port, u16 last_port) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_port = first_port; @@ -271,7 +271,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -ENOMEM; map->elements = elements; - map->memsize = bitmap_bytes(0, map->elements); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { kfree(map); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8dc892a9dc91..605e0f68f8bd 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1239,7 +1239,7 @@ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, p = msg_end; if (p + sizeof(s->v4) > buffer+buflen) { - IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n"); + IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n"); return; } s = (union ip_vs_sync_conn *)p; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 0399ae8f1188..4f897b14b606 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, @@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* REPLY */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ /* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, /* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, @@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag; } - ct->proto.sctp.state = new_state; + ct->proto.sctp.state = SCTP_CONNTRACK_NONE; } return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 65f51a2e9c2a..7e63b481cc86 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -553,47 +553,70 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nft_chain_type * +__nft_chain_type_get(u8 family, enum nft_chain_types type) +{ + if (family >= NFPROTO_NUMPROTO || + type >= NFT_CHAIN_T_MAX) + return NULL; + + return chain_type[family][type]; +} + +static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { + const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { - if (chain_type[family][i] != NULL && - !nla_strcmp(nla, chain_type[family][i]->name)) - return chain_type[family][i]; + type = __nft_chain_type_get(family, i); + if (!type) + continue; + if (!nla_strcmp(nla, type->name)) + return type; } return NULL; } -/* - * Loading a module requires dropping mutex that guards the transaction. - * A different client might race to start a new transaction meanwhile. Zap the - * list of pending transaction and then restore it once the mutex is grabbed - * again. Users of this function return EAGAIN which implicitly triggers the - * transaction abort path to clean up the list of pending transactions. - */ +struct nft_module_request { + struct list_head list; + char module[MODULE_NAME_LEN]; + bool done; +}; + #ifdef CONFIG_MODULES -static void nft_request_module(struct net *net, const char *fmt, ...) +static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; - LIST_HEAD(commit_list); + struct nft_module_request *req; va_list args; int ret; - list_splice_init(&net->nft.commit_list, &commit_list); - va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) - return; + return 0; - mutex_unlock(&net->nft.commit_mutex); - request_module("%s", module_name); - mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(req, &net->nft.module_list, list) { + if (!strcmp(req->module, module_name)) { + if (req->done) + return 0; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_splice(&commit_list, &net->nft.commit_list); + /* A request to load this module already exists. */ + return -EAGAIN; + } + } + + req = kmalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->done = false; + strlcpy(req->module, module_name, MODULE_NAME_LEN); + list_add_tail(&req->list, &net->nft.module_list); + + return -EAGAIN; } #endif @@ -617,10 +640,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { - nft_request_module(net, "nft-chain-%u-%.*s", family, - nla_len(nla), (const char *)nla_data(nla)); - type = __nf_tables_chain_type_lookup(nla, family); - if (type != NULL) + if (nft_request_module(net, "nft-chain-%u-%.*s", family, + nla_len(nla), + (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -1162,11 +1184,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) void nft_register_chain_type(const struct nft_chain_type *ctype) { - if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) - return; - nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) { + if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } @@ -1768,7 +1787,10 @@ static int nft_chain_parse_hook(struct net *net, hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - type = chain_type[family][NFT_CHAIN_T_DEFAULT]; + type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); + if (!type) + return -EOPNOTSUPP; + if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); @@ -2328,9 +2350,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, static int nft_expr_type_request_module(struct net *net, u8 family, struct nlattr *nla) { - nft_request_module(net, "nft-expr-%u-%.*s", family, - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) return -EAGAIN; return 0; @@ -2356,9 +2377,9 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); - nft_request_module(net, "nft-expr-%.*s", - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%.*s", + nla_len(nla), + (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -2449,9 +2470,10 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); #ifdef CONFIG_MODULES if (err == -EAGAIN) - nft_expr_type_request_module(ctx->net, - ctx->family, - tb[NFTA_EXPR_NAME]); + if (nft_expr_type_request_module(ctx->net, + ctx->family, + tb[NFTA_EXPR_NAME]) != -EAGAIN) + err = -ENOENT; #endif goto err1; } @@ -3288,8 +3310,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { - nft_request_module(ctx->net, "nft-set"); - if (!list_empty(&nf_tables_set_types)) + if (nft_request_module(ctx->net, "nft-set") == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5415,8 +5436,7 @@ nft_obj_type_get(struct net *net, u32 objtype) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nft-obj-%u", objtype); - if (__nft_obj_type_get(objtype)) + if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5989,8 +6009,7 @@ nft_flowtable_type_get(struct net *net, u8 family) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nf-flowtable-%u", family); - if (__nft_flowtable_type_get(family)) + if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -6992,6 +7011,18 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nf_tables_module_autoload_cleanup(struct net *net) +{ + struct nft_module_request *req, *next; + + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); + list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!req->done); + list_del(&req->list); + kfree(req); + } +} + static void nf_tables_commit_release(struct net *net) { struct nft_trans *trans; @@ -7004,6 +7035,7 @@ static void nf_tables_commit_release(struct net *net) * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&net->nft.commit_list)) { + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); return; } @@ -7018,6 +7050,7 @@ static void nf_tables_commit_release(struct net *net) list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); schedule_work(&trans_destroy_work); @@ -7209,6 +7242,26 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } +static void nf_tables_module_autoload(struct net *net) +{ + struct nft_module_request *req, *next; + LIST_HEAD(module_list); + + list_splice_init(&net->nft.module_list, &module_list); + mutex_unlock(&net->nft.commit_mutex); + list_for_each_entry_safe(req, next, &module_list, list) { + if (req->done) { + list_del(&req->list); + kfree(req); + } else { + request_module("%s", req->module); + req->done = true; + } + } + mutex_lock(&net->nft.commit_mutex); + list_splice(&module_list, &net->nft.module_list); +} + static void nf_tables_abort_release(struct nft_trans *trans) { switch (trans->msg_type) { @@ -7238,7 +7291,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net) +static int __nf_tables_abort(struct net *net, bool autoload) { struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -7360,6 +7413,11 @@ static int __nf_tables_abort(struct net *net) nf_tables_abort_release(trans); } + if (autoload) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + return 0; } @@ -7368,9 +7426,9 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) { - int ret = __nf_tables_abort(net); + int ret = __nf_tables_abort(net, autoload); mutex_unlock(&net->nft.commit_mutex); @@ -7965,6 +8023,7 @@ static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); + INIT_LIST_HEAD(&net->nft.module_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -7976,7 +8035,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net); + __nf_tables_abort(net, false); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index a9ea29afb09f..2bb28483af22 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -564,7 +564,7 @@ static void nft_indr_block_cb(struct net_device *dev, mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); - if (chain) { + if (chain && chain->flags & NFT_CHAIN_HW_OFFLOAD) { struct nft_base_chain *basechain; basechain = nft_base_chain(chain); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abbb452cf6c..99127e2d95a8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -476,7 +476,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb); + ss->abort(net, oskb, true); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -487,11 +487,11 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb); + ss->abort(net, oskb, false); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb); + ss->abort(net, oskb, false); } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index f54d6ae15bb1..b42247aa48a9 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; + if (!tb[NFTA_OSF_DREG]) + return -EINVAL; + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 46b8ff24020d..1e8eeb044b07 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1475,7 +1475,7 @@ static int __init rose_proto_init(void) int rc; if (rose_ndevs > 0x7FFFFFFF/sizeof(struct net_device *)) { - printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter to large\n"); + printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter too large\n"); rc = -EINVAL; goto out; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 76e0d122616a..c2cdd0fc2e70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2055,9 +2055,8 @@ replay: &chain_info)); mutex_unlock(&chain->filter_chain_lock); - tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, rtnl_held, - extack); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); if (IS_ERR(tp_new)) { err = PTR_ERR(tp_new); goto errout_tp; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 8f2ad706784d..d0140a92694a 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -263,12 +263,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 7ac1542feaf8..dc651a628dcf 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -268,9 +268,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; - dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { @@ -297,7 +294,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) @@ -343,6 +340,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -352,10 +350,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_IPV6): xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + if (!dst) { + fl.u.ip6.flowi6_oif = dev->ifindex; + fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); + if (dst->error) { + dst_release(dst); + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, dst); + } break; case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + if (!dst) { + struct rtable *rt; + + fl.u.ip4.flowi4_oif = dev->ifindex; + fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); + if (IS_ERR(rt)) { + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, &rt->dst); + } break; default: goto tx_err; @@ -563,12 +584,9 @@ static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->type = ARPHRD_NONE; - dev->hard_header_len = ETH_HLEN; - dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = ETH_DATA_LEN; - dev->addr_len = ETH_ALEN; + dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index d4adfbe42690..9d07e59cbdf7 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -31,6 +31,10 @@ cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /de # Return y if the linker supports <flag>, n otherwise ld-option = $(success,$(LD) -v $(1)) +# $(as-instr,<instr>) +# Return y if the assembler supports <instr>, n otherwise +as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler -o /dev/null -) + # check if $(CC) and $(LD) exist $(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found) $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 612268eabef4..7225107a9aaf 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -38,6 +38,10 @@ #define R_AARCH64_ABS64 257 #endif +#define R_ARM_PC24 1 +#define R_ARM_THM_CALL 10 +#define R_ARM_CALL 28 + static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ @@ -418,6 +422,18 @@ static char const *already_has_rel_mcount = "success"; /* our work here is done! #define RECORD_MCOUNT_64 #include "recordmcount.h" +static int arm_is_fake_mcount(Elf32_Rel const *rp) +{ + switch (ELF32_R_TYPE(w(rp->r_info))) { + case R_ARM_THM_CALL: + case R_ARM_CALL: + case R_ARM_PC24: + return 0; + } + + return 1; +} + /* 64-bit EM_MIPS has weird ELF64_Rela.r_info. * http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf * We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40] @@ -523,6 +539,7 @@ static int do_file(char const *const fname) altmcount = "__gnu_mcount_nc"; make_nop = make_nop_arm; rel_type_nop = R_ARM_NONE; + is_fake_mcount32 = arm_is_fake_mcount; gpfx = 0; break; case EM_AARCH64: |