diff options
233 files changed, 5740 insertions, 2613 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 7bcfb38498c6..dc254a3cb956 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -976,6 +976,29 @@ All cgroup core files are prefixed with "cgroup." killing cgroups is a process directed operation, i.e. it affects the whole thread-group. + cgroup.pressure + A read-write single value file that allowed values are "0" and "1". + The default is "1". + + Writing "0" to the file will disable the cgroup PSI accounting. + Writing "1" to the file will re-enable the cgroup PSI accounting. + + This control attribute is not hierarchical, so disable or enable PSI + accounting in a cgroup does not affect PSI accounting in descendants + and doesn't need pass enablement via ancestors from root. + + The reason this control attribute exists is that PSI accounts stalls for + each cgroup separately and aggregates it at each level of the hierarchy. + This may cause non-negligible overhead for some workloads when under + deep level of the hierarchy, in which case this control attribute can + be used to disable PSI accounting in the non-leaf cgroups. + + irq.pressure + A read-write nested-keyed file. + + Shows pressure stall information for IRQ/SOFTIRQ. See + :ref:`Documentation/accounting/psi.rst <psi>` for details. + Controllers =========== diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 17d9fc5d14fb..808ade4cc008 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -76,6 +76,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A55 | #1530923 | ARM64_ERRATUM_1530923 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A55 | #2441007 | ARM64_ERRATUM_2441007 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #852523 | N/A | diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index 92e0f8c3eff2..99e01f4d0a69 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -66,6 +66,11 @@ properties: - enum: - allwinner,sun20i-d1-plic - const: thead,c900-plic + - items: + - const: sifive,plic-1.0.0 + - const: riscv,plic0 + deprecated: true + description: For the QEMU virt machine only reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index 328952d7acbb..3c14a98430e1 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -79,24 +79,27 @@ properties: the LED. $ref: /schemas/types.yaml#/definitions/string - enum: - # LED will act as a back-light, controlled by the framebuffer system - - backlight - # LED will turn on (but for leds-gpio see "default-state" property in - # Documentation/devicetree/bindings/leds/leds-gpio.yaml) - - default-on - # LED "double" flashes at a load average based rate - - heartbeat - # LED indicates disk activity - - disk-activity - # LED indicates IDE disk activity (deprecated), in new implementations - # use "disk-activity" - - ide-disk - # LED flashes at a fixed, configurable rate - - timer - # LED alters the brightness for the specified duration with one software - # timer (requires "led-pattern" property) - - pattern + oneOf: + - enum: + # LED will act as a back-light, controlled by the framebuffer system + - backlight + # LED will turn on (but for leds-gpio see "default-state" property in + # Documentation/devicetree/bindings/leds/leds-gpio.yaml) + - default-on + # LED "double" flashes at a load average based rate + - heartbeat + # LED indicates disk activity + - disk-activity + # LED indicates IDE disk activity (deprecated), in new implementations + # use "disk-activity" + - ide-disk + # LED flashes at a fixed, configurable rate + - timer + # LED alters the brightness for the specified duration with one software + # timer (requires "led-pattern" property) + - pattern + # LED is triggered by SD/MMC activity + - pattern: "^mmc[0-9]+$" led-pattern: description: | diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 873dd12f6e89..90a7cabf58fe 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -9,6 +9,7 @@ title: RISC-V bindings for 'cpus' DT nodes maintainers: - Paul Walmsley <paul.walmsley@sifive.com> - Palmer Dabbelt <palmer@sifive.com> + - Conor Dooley <conor@kernel.org> description: | This document uses some terminology common to the RISC-V community @@ -79,9 +80,7 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. $ref: "/schemas/types.yaml#/definitions/string" - enum: - - rv64imac - - rv64imafdc + pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$ # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 37f97ee4fe46..714d0fcab399 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip PolarFire SoC-based boards maintainers: - - Cyril Jean <Cyril.Jean@microchip.com> - - Lewis Hanly <lewis.hanly@microchip.com> + - Conor Dooley <conor.dooley@microchip.com> + - Daire McNamara <daire.mcnamara@microchip.com> description: Microchip PolarFire SoC-based boards @@ -17,12 +17,20 @@ properties: $nodename: const: '/' compatible: - items: - - enum: - - microchip,mpfs-icicle-kit - - microchip,mpfs-icicle-reference-rtlv2203 - - sundance,polarberry - - const: microchip,mpfs + oneOf: + - items: + - enum: + - microchip,mpfs-icicle-reference-rtlv2203 + - microchip,mpfs-icicle-reference-rtlv2210 + - const: microchip,mpfs-icicle-kit + - const: microchip,mpfs + + - items: + - enum: + - aries,m100pfsevp + - microchip,mpfs-sev-kit + - sundance,polarberry + - const: microchip,mpfs additionalProperties: true diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml index ca3b9be58058..bf3f07421f7e 100644 --- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml +++ b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml @@ -2,18 +2,18 @@ # Copyright (C) 2020 SiFive, Inc. %YAML 1.2 --- -$id: http://devicetree.org/schemas/riscv/sifive-l2-cache.yaml# +$id: http://devicetree.org/schemas/riscv/sifive,ccache0.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: SiFive L2 Cache Controller +title: SiFive Composable Cache Controller maintainers: - Sagar Kadam <sagar.kadam@sifive.com> - Paul Walmsley <paul.walmsley@sifive.com> description: - The SiFive Level 2 Cache Controller is used to provide access to fast copies - of memory for masters in a Core Complex. The Level 2 Cache Controller also + The SiFive Composable Cache Controller is used to provide access to fast copies + of memory for masters in a Core Complex. The Composable Cache Controller also acts as directory-based coherency manager. All the properties in ePAPR/DeviceTree specification applies for this platform. @@ -22,6 +22,7 @@ select: compatible: contains: enum: + - sifive,ccache0 - sifive,fu540-c000-ccache - sifive,fu740-c000-ccache @@ -33,6 +34,7 @@ properties: oneOf: - items: - enum: + - sifive,ccache0 - sifive,fu540-c000-ccache - sifive,fu740-c000-ccache - const: cache @@ -45,7 +47,7 @@ properties: const: 64 cache-level: - const: 2 + enum: [2, 3] cache-sets: enum: [1024, 2048] @@ -115,6 +117,22 @@ allOf: cache-sets: const: 1024 + - if: + properties: + compatible: + contains: + const: sifive,ccache0 + + then: + properties: + cache-level: + enum: [2, 3] + + else: + properties: + cache-level: + const: 2 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml index e64f46339079..bbad24165837 100644 --- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -22,12 +22,18 @@ description: properties: compatible: - items: - - enum: - - sifive,fu540-c000-clint - - starfive,jh7100-clint - - canaan,k210-clint - - const: sifive,clint0 + oneOf: + - items: + - enum: + - sifive,fu540-c000-clint + - starfive,jh7100-clint + - canaan,k210-clint + - const: sifive,clint0 + - items: + - const: sifive,clint0 + - const: riscv,clint0 + deprecated: true + description: For the QEMU virt machine only description: Should be "<vendor>,<chip>-clint" and "sifive,clint<version>". diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index e23b876ad6eb..2e5b18fbb145 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -8,6 +8,7 @@ RISC-V architecture boot-image-header vm-layout patch-acceptance + uabi features diff --git a/Documentation/riscv/uabi.rst b/Documentation/riscv/uabi.rst new file mode 100644 index 000000000000..21a82cfb6c4d --- /dev/null +++ b/Documentation/riscv/uabi.rst @@ -0,0 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +RISC-V Linux User ABI +===================== + +Misaligned accesses are supported in userspace, but they may perform poorly. diff --git a/MAINTAINERS b/MAINTAINERS index 7483853880b6..cf0f18502372 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -752,7 +752,7 @@ ALIBABA PMU DRIVER M: Shuai Xue <xueshuai@linux.alibaba.com> S: Supported F: Documentation/admin-guide/perf/alibaba_pmu.rst -F: drivers/perf/alibaba_uncore_dwr_pmu.c +F: drivers/perf/alibaba_uncore_drw_pmu.c ALIENWARE WMI DRIVER L: Dell.Client.Kernel@dell.com @@ -15411,7 +15411,7 @@ M: Stafford Horne <shorne@gmail.com> L: openrisc@lists.librecores.org S: Maintained W: http://openrisc.io -T: git git://github.com/openrisc/linux.git +T: git https://github.com/openrisc/linux.git F: Documentation/devicetree/bindings/openrisc/ F: Documentation/openrisc/ F: arch/openrisc/ @@ -17702,6 +17702,7 @@ M: Palmer Dabbelt <palmer@dabbelt.com> M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org S: Supported +Q: https://patchwork.kernel.org/project/linux-riscv/list/ P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ @@ -17713,12 +17714,13 @@ M: Conor Dooley <conor.dooley@microchip.com> M: Daire McNamara <daire.mcnamara@microchip.com> L: linux-riscv@lists.infradead.org S: Supported -F: Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +F: Documentation/devicetree/bindings/clock/microchip,mpfs*.yaml F: Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml F: Documentation/devicetree/bindings/i2c/microchip,corei2c.yaml F: Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml F: Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml F: Documentation/devicetree/bindings/pwm/microchip,corepwm.yaml +F: Documentation/devicetree/bindings/riscv/microchip.yaml F: Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml F: Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml F: Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml @@ -1979,6 +1979,8 @@ endif single-goals := $(addprefix $(build-dir)/, $(single-no-ko)) +KBUILD_MODULES := 1 + endif # Preset locale variables to speed up the build process. Limit locale diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 6d0b3baf97ff..e9348aec4649 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -803,7 +803,7 @@ void __iomem *marvel_ioportmap (unsigned long addr) return (void __iomem *)addr; } -unsigned u8 +u8 marvel_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 79f4a2aa5475..9968239d8041 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -238,7 +238,7 @@ void pxa_usb_phy_deinit(void __iomem *phy_reg) static u64 __maybe_unused usb_dma_mask = ~(u32)0; #if IS_ENABLED(CONFIG_PHY_PXA_USB) -struct resource pxa168_usb_phy_resources[] = { +static struct resource pxa168_usb_phy_resources[] = { [0] = { .start = PXA168_U2O_PHYBASE, .end = PXA168_U2O_PHYBASE + USB_PHY_RANGE, @@ -259,7 +259,7 @@ struct platform_device pxa168_device_usb_phy = { #endif /* CONFIG_PHY_PXA_USB */ #if IS_ENABLED(CONFIG_USB_MV_UDC) -struct resource pxa168_u2o_resources[] = { +static struct resource pxa168_u2o_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, @@ -294,7 +294,7 @@ struct platform_device pxa168_device_u2o = { #endif /* CONFIG_USB_MV_UDC */ #if IS_ENABLED(CONFIG_USB_EHCI_MV_U2O) -struct resource pxa168_u2oehci_resources[] = { +static struct resource pxa168_u2oehci_resources[] = { [0] = { .start = PXA168_U2O_REGBASE, .end = PXA168_U2O_REGBASE + USB_REG_RANGE, @@ -321,7 +321,7 @@ struct platform_device pxa168_device_u2oehci = { #endif #if IS_ENABLED(CONFIG_USB_MV_OTG) -struct resource pxa168_u2ootg_resources[] = { +static struct resource pxa168_u2ootg_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h index 43b7996ab754..9e36920d4cfd 100644 --- a/arch/arm/mach-spear/generic.h +++ b/arch/arm/mach-spear/generic.h @@ -25,11 +25,8 @@ extern struct pl022_ssp_controller pl022_plat_data; extern struct pl08x_platform_data pl080_plat_data; void __init spear_setup_of_timer(void); -void __init spear3xx_clk_init(void __iomem *misc_base, - void __iomem *soc_config_base); void __init spear3xx_map_io(void); void __init spear3xx_dt_init_irq(void); -void __init spear6xx_clk_init(void __iomem *misc_base); void __init spear13xx_map_io(void); void __init spear13xx_l2x0_init(void); diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c index 2ba406e92c41..7ef9670d3029 100644 --- a/arch/arm/mach-spear/spear3xx.c +++ b/arch/arm/mach-spear/spear3xx.c @@ -13,6 +13,7 @@ #include <linux/amba/pl022.h> #include <linux/amba/pl080.h> #include <linux/clk.h> +#include <linux/clk/spear.h> #include <linux/io.h> #include <asm/mach/map.h> #include "pl080.h" diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c index 58183493e06d..f0a1e704cceb 100644 --- a/arch/arm/mach-spear/spear6xx.c +++ b/arch/arm/mach-spear/spear6xx.c @@ -12,6 +12,7 @@ #include <linux/amba/pl08x.h> #include <linux/clk.h> +#include <linux/clk/spear.h> #include <linux/err.h> #include <linux/of.h> #include <linux/of_address.h> @@ -339,7 +340,7 @@ static struct pl08x_platform_data spear6xx_pl080_plat_data = { * 0xD0000000 0xFD000000 * 0xFC000000 0xFC000000 */ -struct map_desc spear6xx_io_desc[] __initdata = { +static struct map_desc spear6xx_io_desc[] __initdata = { { .virtual = (unsigned long)VA_SPEAR6XX_ML_CPU_BASE, .pfn = __phys_to_pfn(SPEAR_ICM3_ML1_2_BASE), @@ -359,12 +360,12 @@ struct map_desc spear6xx_io_desc[] __initdata = { }; /* This will create static memory mapping for selected devices */ -void __init spear6xx_map_io(void) +static void __init spear6xx_map_io(void) { iotable_init(spear6xx_io_desc, ARRAY_SIZE(spear6xx_io_desc)); } -void __init spear6xx_timer_init(void) +static void __init spear6xx_timer_init(void) { char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; @@ -394,7 +395,7 @@ void __init spear6xx_timer_init(void) } /* Add auxdata to pass platform data */ -struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { +static struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("arm,pl080", SPEAR_ICM3_DMA_BASE, NULL, &spear6xx_pl080_plat_data), {} diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f6737d2f37b2..505c8a1ccbe0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -632,6 +632,23 @@ config ARM64_ERRATUM_1530923 config ARM64_WORKAROUND_REPEAT_TLBI bool +config ARM64_ERRATUM_2441007 + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" + default y + select ARM64_WORKAROUND_REPEAT_TLBI + help + This option adds a workaround for ARM Cortex-A55 erratum #2441007. + + Under very rare circumstances, affected Cortex-A55 CPUs + may not handle a race between a break-before-make sequence on one + CPU, and another CPU accessing the same page. This could allow a + store to a page that has been unmapped. + + Work around this by adding the affected CPUs to the list that needs + TLB sequences to be done twice. + + 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 diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 8aa0d276a636..abc418650fec 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -172,6 +175,7 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 58ca4f6b25d6..89ac00084f38 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -230,6 +230,11 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2441007 + { + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2441009 { /* Cortex-A510 r0p0 -> r1p1. Fixed in r1p2 */ diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index aca88470fb69..7467217c1eaf 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -48,7 +48,12 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte, if (!pte_is_tagged) return; - mte_clear_page_tags(page_address(page)); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_clear_page_tags(page_address(page)); } void mte_sync_tags(pte_t old_pte, pte_t pte) @@ -64,7 +69,7 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) /* if PG_mte_tagged is set, tags have already been initialised */ for (i = 0; i < nr_pages; i++, page++) { - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (!test_bit(PG_mte_tagged, &page->flags)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index a8ea1637b137..bfce41c2a53b 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -868,6 +868,10 @@ u8 spectre_bhb_loop_affected(int scope) MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), {}, }; + static const struct midr_range spectre_bhb_k11_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + {}, + }; static const struct midr_range spectre_bhb_k8_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), @@ -878,6 +882,8 @@ u8 spectre_bhb_loop_affected(int scope) k = 32; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list)) + k = 11; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) k = 8; diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index 4334dec93bd4..bed803d8e158 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -53,7 +53,12 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page) if (!tags) return false; - mte_restore_page_tags(page_address(page), tags); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_restore_page_tags(page_address(page), tags); return true; } diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7f1fb36f208c..384757a7eda9 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -732,7 +732,7 @@ EndSysreg Sysreg SCTLR_EL1 3 0 1 0 0 Field 63 TIDCP -Field 62 SPINMASK +Field 62 SPINTMASK Field 61 NMI Field 60 EnTP2 Res0 59:58 diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 8ea57e2f0e04..946704bee599 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -412,6 +412,9 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, __update_tlb(vma, address, ptep); } +#define __HAVE_ARCH_UPDATE_MMU_TLB +#define update_mmu_tlb update_mmu_cache + static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index a82b2caaa560..b3edbb33b621 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,10 +74,10 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ - mmap_read_lock(&init_mm); - error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, - NULL); - mmap_read_unlock(&init_mm); + mmap_write_lock(&init_mm); + error = walk_page_range_novma(&init_mm, va, va + size, + &set_nocache_walk_ops, NULL, NULL); + mmap_write_unlock(&init_mm); if (error) return ERR_PTR(error); @@ -88,11 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; - mmap_read_lock(&init_mm); + mmap_write_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ - WARN_ON(walk_page_range(&init_mm, va, va + size, - &clear_nocache_walk_ops, NULL)); - mmap_read_unlock(&init_mm); + WARN_ON(walk_page_range_novma(&init_mm, va, va + size, + &clear_nocache_walk_ops, NULL, NULL)); + mmap_write_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h index 0ec54f43d6d2..1ed45fd085d3 100644 --- a/arch/parisc/include/asm/alternative.h +++ b/arch/parisc/include/asm/alternative.h @@ -22,10 +22,10 @@ struct alt_instr { s32 orig_offset; /* offset to original instructions */ - s32 len; /* end of original instructions */ - u32 cond; /* see ALT_COND_XXX */ + s16 len; /* end of original instructions */ + u16 cond; /* see ALT_COND_XXX */ u32 replacement; /* replacement instruction or code */ -}; +} __packed; void set_kernel_text_rw(int enable_read_write); void apply_alternatives_all(void); @@ -35,8 +35,9 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* Alternative SMP implementation. */ #define ALTERNATIVE(cond, replacement) "!0:" \ ".section .altinstructions, \"aw\" !" \ - ".word (0b-4-.), 1, " __stringify(cond) "," \ - __stringify(replacement) " !" \ + ".word (0b-4-.) !" \ + ".hword 1, " __stringify(cond) " !" \ + ".word " __stringify(replacement) " !" \ ".previous" #else @@ -44,15 +45,17 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace one single instructions by a new instruction */ #define ALTERNATIVE(from, to, cond, replacement)\ .section .altinstructions, "aw" ! \ - .word (from - .), (to - from)/4 ! \ - .word cond, replacement ! \ + .word (from - .) ! \ + .hword (to - from)/4, cond ! \ + .word replacement ! \ .previous /* to replace multiple instructions by new code */ #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\ .section .altinstructions, "aw" ! \ - .word (from - .), -num_instructions ! \ - .word cond, (new_instr_ptr - .) ! \ + .word (from - .) ! \ + .hword -num_instructions, cond ! \ + .word (new_instr_ptr - .) ! \ .previous #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index b643092d4b98..fcbcf9a96c11 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -19,9 +19,6 @@ extern unsigned long parisc_pat_pdc_cap; /* PDC capabilities (PAT) */ #define PDC_TYPE_SYSTEM_MAP 1 /* 32-bit, but supports PDC_SYSTEM_MAP */ #define PDC_TYPE_SNAKE 2 /* Doesn't support SYSTEM_MAP */ -void pdc_console_init(void); /* in pdc_console.c */ -void pdc_console_restart(void); - void setup_pdc(void); /* in inventory.c */ /* wrapper-functions from pdc.c */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index df7b931865d2..ecd028854469 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -192,6 +192,11 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ #define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ +#ifdef CONFIG_HUGETLB_PAGE +#define _PAGE_SPECIAL_BIT _PAGE_DMB_BIT /* DMB feature is currently unused */ +#else +#define _PAGE_SPECIAL_BIT _PAGE_HPAGE_BIT /* use unused HUGE PAGE bit */ +#endif /* N.B. The bits are defined in terms of a 32 bit word above, so the */ /* following macro is ok for both 32 and 64 bit. */ @@ -219,7 +224,7 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) #define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) -#define _PAGE_SPECIAL (_PAGE_DMB) +#define _PAGE_SPECIAL (1 << xlate_pabit(_PAGE_SPECIAL_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) diff --git a/arch/parisc/kernel/alternative.c b/arch/parisc/kernel/alternative.c index daa1e9047275..66f5672c70bd 100644 --- a/arch/parisc/kernel/alternative.c +++ b/arch/parisc/kernel/alternative.c @@ -26,7 +26,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *entry; int index = 0, applied = 0; int num_cpus = num_online_cpus(); - u32 cond_check; + u16 cond_check; cond_check = ALT_COND_ALWAYS | ((num_cpus == 1) ? ALT_COND_NO_SMP : 0) | @@ -45,8 +45,9 @@ void __init_or_module apply_alternatives(struct alt_instr *start, for (entry = start; entry < end; entry++, index++) { - u32 *from, cond, replacement; - s32 len; + u32 *from, replacement; + u16 cond; + s16 len; from = (u32 *)((ulong)&entry->orig_offset + entry->orig_offset); len = entry->len; diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index df8102fb435f..0e5ebfe8d9d2 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -499,6 +499,10 @@ * Finally, _PAGE_READ goes in the top bit of PL1 (so we * trigger an access rights trap in user space if the user * tries to read an unreadable page */ +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif depd \pte,8,7,\prot /* PAGE_USER indicates the page can be read with user privileges, @@ -529,6 +533,10 @@ * makes the tlb entry for the differently formatted pa11 * insertion instructions */ .macro make_insert_tlb_11 spc,pte,prot +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif zdep \spc,30,15,\prot dep \pte,8,7,\prot extru,= \pte,_PAGE_NO_CACHE_BIT,1,%r0 diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c index 2661cdd256ae..7d0989f523d0 100644 --- a/arch/parisc/kernel/pdc_cons.c +++ b/arch/parisc/kernel/pdc_cons.c @@ -1,46 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * PDC Console support - ie use firmware to dump text via boot console + * PDC early console support - use PDC firmware to dump text via boot console * - * Copyright (C) 1999-2003 Matthew Wilcox <willy at parisc-linux.org> - * Copyright (C) 2000 Martin K Petersen <mkp at mkp.net> - * Copyright (C) 2000 John Marvin <jsm at parisc-linux.org> - * Copyright (C) 2000-2003 Paul Bame <bame at parisc-linux.org> - * Copyright (C) 2000 Philipp Rumpf <prumpf with tux.org> - * Copyright (C) 2000 Michael Ang <mang with subcarrier.org> - * Copyright (C) 2000 Grant Grundler <grundler with parisc-linux.org> - * Copyright (C) 2001-2002 Ryan Bradetich <rbrad at parisc-linux.org> - * Copyright (C) 2001 Helge Deller <deller at parisc-linux.org> - * Copyright (C) 2001 Thomas Bogendoerfer <tsbogend at parisc-linux.org> - * Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org> - * Copyright (C) 2010 Guy Martin <gmsoft at tuxicoman.be> + * Copyright (C) 2001-2022 Helge Deller <deller@gmx.de> */ -/* - * The PDC console is a simple console, which can be used for debugging - * boot related problems on HP PA-RISC machines. It is also useful when no - * other console works. - * - * This code uses the ROM (=PDC) based functions to read and write characters - * from and to PDC's boot path. - */ - -/* Define EARLY_BOOTUP_DEBUG to debug kernel related boot problems. - * On production kernels EARLY_BOOTUP_DEBUG should be undefined. */ -#define EARLY_BOOTUP_DEBUG - - -#include <linux/kernel.h> #include <linux/console.h> -#include <linux/string.h> #include <linux/init.h> -#include <linux/major.h> -#include <linux/tty.h> +#include <linux/serial_core.h> +#include <linux/kgdb.h> #include <asm/page.h> /* for PAGE0 */ #include <asm/pdc.h> /* for iodc_call() proto and friends */ static DEFINE_SPINLOCK(pdc_console_lock); -static struct console pdc_cons; static void pdc_console_write(struct console *co, const char *s, unsigned count) { @@ -54,7 +26,8 @@ static void pdc_console_write(struct console *co, const char *s, unsigned count) spin_unlock_irqrestore(&pdc_console_lock, flags); } -int pdc_console_poll_key(struct console *co) +#ifdef CONFIG_KGDB +static int kgdb_pdc_read_char(void) { int c; unsigned long flags; @@ -63,201 +36,40 @@ int pdc_console_poll_key(struct console *co) c = pdc_iodc_getc(); spin_unlock_irqrestore(&pdc_console_lock, flags); - return c; -} - -static int pdc_console_setup(struct console *co, char *options) -{ - return 0; -} - -#if defined(CONFIG_PDC_CONSOLE) -#include <linux/vt_kern.h> -#include <linux/tty_flip.h> - -#define PDC_CONS_POLL_DELAY (30 * HZ / 1000) - -static void pdc_console_poll(struct timer_list *unused); -static DEFINE_TIMER(pdc_console_timer, pdc_console_poll); -static struct tty_port tty_port; - -static int pdc_console_tty_open(struct tty_struct *tty, struct file *filp) -{ - tty_port_tty_set(&tty_port, tty); - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); - - return 0; + return (c <= 0) ? NO_POLL_CHAR : c; } -static void pdc_console_tty_close(struct tty_struct *tty, struct file *filp) +static void kgdb_pdc_write_char(u8 chr) { - if (tty->count == 1) { - del_timer_sync(&pdc_console_timer); - tty_port_tty_set(&tty_port, NULL); - } + if (PAGE0->mem_cons.cl_class != CL_DUPLEX) + pdc_console_write(NULL, &chr, 1); } -static int pdc_console_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) -{ - pdc_console_write(NULL, buf, count); - return count; -} - -static unsigned int pdc_console_tty_write_room(struct tty_struct *tty) -{ - return 32768; /* no limit, no buffer used */ -} - -static const struct tty_operations pdc_console_tty_ops = { - .open = pdc_console_tty_open, - .close = pdc_console_tty_close, - .write = pdc_console_tty_write, - .write_room = pdc_console_tty_write_room, +static struct kgdb_io kgdb_pdc_io_ops = { + .name = "kgdb_pdc", + .read_char = kgdb_pdc_read_char, + .write_char = kgdb_pdc_write_char, }; - -static void pdc_console_poll(struct timer_list *unused) -{ - int data, count = 0; - - while (1) { - data = pdc_console_poll_key(NULL); - if (data == -1) - break; - tty_insert_flip_char(&tty_port, data & 0xFF, TTY_NORMAL); - count ++; - } - - if (count) - tty_flip_buffer_push(&tty_port); - - if (pdc_cons.flags & CON_ENABLED) - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); -} - -static struct tty_driver *pdc_console_tty_driver; - -static int __init pdc_console_tty_driver_init(void) -{ - struct tty_driver *driver; - int err; - - /* Check if the console driver is still registered. - * It is unregistered if the pdc console was not selected as the - * primary console. */ - - struct console *tmp; - - console_lock(); - for_each_console(tmp) - if (tmp == &pdc_cons) - break; - console_unlock(); - - if (!tmp) { - printk(KERN_INFO "PDC console driver not registered anymore, not creating %s\n", pdc_cons.name); - return -ENODEV; - } - - printk(KERN_INFO "The PDC console driver is still registered, removing CON_BOOT flag\n"); - pdc_cons.flags &= ~CON_BOOT; - - driver = tty_alloc_driver(1, TTY_DRIVER_REAL_RAW | - TTY_DRIVER_RESET_TERMIOS); - if (IS_ERR(driver)) - return PTR_ERR(driver); - - tty_port_init(&tty_port); - - driver->driver_name = "pdc_cons"; - driver->name = "ttyB"; - driver->major = MUX_MAJOR; - driver->minor_start = 0; - driver->type = TTY_DRIVER_TYPE_SYSTEM; - driver->init_termios = tty_std_termios; - tty_set_operations(driver, &pdc_console_tty_ops); - tty_port_link_device(&tty_port, driver, 0); - - err = tty_register_driver(driver); - if (err) { - printk(KERN_ERR "Unable to register the PDC console TTY driver\n"); - tty_port_destroy(&tty_port); - tty_driver_kref_put(driver); - return err; - } - - pdc_console_tty_driver = driver; - - return 0; -} -device_initcall(pdc_console_tty_driver_init); - -static struct tty_driver * pdc_console_device (struct console *c, int *index) -{ - *index = c->index; - return pdc_console_tty_driver; -} -#else -#define pdc_console_device NULL #endif -static struct console pdc_cons = { - .name = "ttyB", - .write = pdc_console_write, - .device = pdc_console_device, - .setup = pdc_console_setup, - .flags = CON_BOOT | CON_PRINTBUFFER, - .index = -1, -}; - -static int pdc_console_initialized; - -static void pdc_console_init_force(void) +static int __init pdc_earlycon_setup(struct earlycon_device *device, + const char *opt) { - if (pdc_console_initialized) - return; - ++pdc_console_initialized; - + struct console *earlycon_console; + /* If the console is duplex then copy the COUT parameters to CIN. */ if (PAGE0->mem_cons.cl_class == CL_DUPLEX) memcpy(&PAGE0->mem_kbd, &PAGE0->mem_cons, sizeof(PAGE0->mem_cons)); - /* register the pdc console */ - register_console(&pdc_cons); -} + earlycon_console = device->con; + earlycon_console->write = pdc_console_write; + device->port.iotype = UPIO_MEM32BE; -void __init pdc_console_init(void) -{ -#if defined(EARLY_BOOTUP_DEBUG) || defined(CONFIG_PDC_CONSOLE) - pdc_console_init_force(); +#ifdef CONFIG_KGDB + kgdb_register_io_module(&kgdb_pdc_io_ops); #endif -#ifdef EARLY_BOOTUP_DEBUG - printk(KERN_INFO "Initialized PDC Console for debugging.\n"); -#endif -} - - -/* - * Used for emergencies. Currently only used if an HPMC occurs. If an - * HPMC occurs, it is possible that the current console may not be - * properly initialised after the PDC IO reset. This routine unregisters - * all of the current consoles, reinitializes the pdc console and - * registers it. - */ - -void pdc_console_restart(void) -{ - struct console *console; - - if (pdc_console_initialized) - return; - /* If we've already seen the output, don't bother to print it again */ - if (console_drivers != NULL) - pdc_cons.flags &= ~CON_PRINTBUFFER; - - while ((console = console_drivers) != NULL) - unregister_console(console_drivers); - - /* force registering the pdc console */ - pdc_console_init_force(); + return 0; } + +EARLYCON_DECLARE(pdc, pdc_earlycon_setup); diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index f005ddedb50e..375f38d6e1a4 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -70,6 +70,10 @@ void __init setup_cmdline(char **cmdline_p) strlcat(p, "tty0", COMMAND_LINE_SIZE); } + /* default to use early console */ + if (!strstr(p, "earlycon")) + strlcat(p, " earlycon=pdc", COMMAND_LINE_SIZE); + #ifdef CONFIG_BLK_DEV_INITRD if (boot_args[2] != 0) /* did palo pass us a ramdisk? */ { @@ -139,8 +143,6 @@ void __init setup_arch(char **cmdline_p) if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) panic("KERNEL_INITIAL_ORDER too small!"); - pdc_console_init(); - #ifdef CONFIG_64BIT if(parisc_narrow_firmware) { printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n"); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b78f1b9d45c1..f9696fbf646c 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -239,13 +239,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* maybe the kernel hasn't booted very far yet and hasn't been able - * to initialize the serial or STI console. In that case we should - * re-enable the pdc console, so that the user will be able to - * identify the problem. */ - if (!console_drivers) - pdc_console_restart(); - if (err) printk(KERN_CRIT "%s (pid %d): %s (code %ld)\n", current->comm, task_pid_nr(current), str, err); @@ -429,10 +422,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* restart pdc console if necessary */ - if (!console_drivers) - pdc_console_restart(); - /* Not all paths will gutter the processor... */ switch(code){ @@ -482,9 +471,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) unsigned long fault_space = 0; int si_code; - if (code == 1) - pdc_console_restart(); /* switch back to pdc if HPMC */ - else if (!irqs_disabled_flags(regs->gr[0])) + if (!irqs_disabled_flags(regs->gr[0])) local_irq_enable(); /* Security check: diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 9840d572da55..a1142496cd58 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -89,6 +89,22 @@ long compat_sys_rt_sigreturn(void); * responsible for combining parameter pairs. */ +#ifdef CONFIG_PPC32 +long sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +#endif #ifdef CONFIG_COMPAT long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ee2d76cb3187..9b6146056e48 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -73,6 +73,7 @@ obj-y := cputable.o syscalls.o \ obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o +obj-$(CONFIG_PPC32) += sys_ppc32.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 904a5608cbe3..978a173eb339 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -538,7 +538,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled lbz r11,PACAIRQHAPPENED(r13) andi. r10,r11,PACA_IRQ_MUST_HARD_MASK - beq 1f // No HARD_MASK pending + beq .Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending /* Must clear MSR_EE from _MSR */ #ifdef CONFIG_PPC_BOOK3S @@ -555,12 +555,23 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) b .Lfast_kernel_interrupt_return_\srr\() .Linterrupt_return_\srr\()_soft_enabled: + /* + * In the soft-enabled case, need to double-check that we have no + * pending interrupts that might have come in before we reached the + * restart section of code, and restart the exit so those can be + * handled. + * + * If there are none, it is be possible that the interrupt still + * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the + * interrupted context. This clear will not clobber a new pending + * interrupt coming in, because we're in the restart section, so + * such would return to the restart location. + */ #ifdef CONFIG_PPC_BOOK3S lbz r11,PACAIRQHAPPENED(r13) andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l bne- interrupt_return_\srr\()_kernel_restart #endif -1: li r11,0 stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index dcc3c9fd4cfd..1ab4a4d95aba 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls. + * sys_ppc32.c: 32-bit system calls with complex calling conventions. * * Copyright (C) 2001 IBM * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * - * These routines maintain argument size conversion between 32bit and 64bit - * environment. + * 32-bit system calls with 64-bit arguments pass those in register pairs. + * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual + * in generic compat syscalls is not always usable because the register + * pairing is constrained depending on preceding arguments. + * + * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER, + * the defined system call functions take the pt_regs as an argument, and there + * is a mapping macro which maps registers to arguments + * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit + * arguments. + * + * This file contains these system calls. */ #include <linux/kernel.h> @@ -47,7 +57,17 @@ #include <asm/syscalls.h> #include <asm/switch_to.h> -COMPAT_SYSCALL_DEFINE6(ppc_pread64, +#ifdef CONFIG_PPC32 +#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6 +#else +#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6 +#endif + +PPC32_SYSCALL_DEFINE6(ppc_pread64, unsigned int, fd, char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -55,7 +75,7 @@ COMPAT_SYSCALL_DEFINE6(ppc_pread64, return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, +PPC32_SYSCALL_DEFINE6(ppc_pwrite64, unsigned int, fd, const char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -63,28 +83,28 @@ COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE5(ppc_readahead, +PPC32_SYSCALL_DEFINE5(ppc_readahead, int, fd, u32, r4, u32, offset1, u32, offset2, u32, count) { return ksys_readahead(fd, merge_64(offset1, offset2), count); } -COMPAT_SYSCALL_DEFINE4(ppc_truncate64, +PPC32_SYSCALL_DEFINE4(ppc_truncate64, const char __user *, path, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_truncate(path, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE4(ppc_ftruncate64, +PPC32_SYSCALL_DEFINE4(ppc_ftruncate64, unsigned int, fd, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_ftruncate(fd, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE6(ppc32_fadvise64, +PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, int, fd, u32, unused, u32, offset1, u32, offset2, size_t, len, int, advice) { diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 2bca64f96164..e9e0df4f9a61 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_ppc_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_ppc_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 598006301620..e2f11f9c3f2a 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -508,10 +508,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) static int __kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, struct page *fault_page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *dpage, *spage; struct kvmppc_uvmem_page_pvt *pvt; unsigned long pfn; @@ -525,6 +525,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, mig.dst = &dst_pfn; mig.pgmap_owner = &kvmppc_uvmem_pgmap; mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + mig.fault_page = fault_page; /* The requested page is already paged-out, nothing to do */ if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) @@ -580,12 +581,14 @@ out_finalize: static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, + struct page *fault_page) { int ret; mutex_lock(&kvm->arch.uvmem_lock); - ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa); + ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, + fault_page); mutex_unlock(&kvm->arch.uvmem_lock); return ret; @@ -634,7 +637,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, pvt->remove_gfn = true; if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE, - PAGE_SHIFT, kvm, pvt->gpa)) + PAGE_SHIFT, kvm, pvt->gpa, NULL)) pr_err("Can't page out gpa:0x%lx addr:0x%lx\n", pvt->gpa, addr); } else { @@ -715,7 +718,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - lock_page(dpage); + zone_device_page_init(dpage); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); @@ -736,7 +739,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, bool pagein) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *spage; unsigned long pfn; struct page *dpage; @@ -994,7 +997,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) if (kvmppc_svm_page_out(vmf->vma, vmf->address, vmf->address + PAGE_SIZE, PAGE_SHIFT, - pvt->kvm, pvt->gpa)) + pvt->kvm, pvt->gpa, vmf->page)) return VM_FAULT_SIGBUS; else return 0; @@ -1065,7 +1068,7 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa, if (!vma || vma->vm_start > start || vma->vm_end < end) goto out; - if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa)) + if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL)) ret = H_SUCCESS; out: mmap_read_unlock(kvm->mm); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 14e143b946a3..92310202bdd7 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -7,7 +7,7 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o mobility.o rng.o \ pci.o pci_dlpar.o eeh_pseries.o msi.o \ - papr_platform_attributes.o + papr_platform_attributes.o dtl.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o @@ -19,7 +19,6 @@ obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o -obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 1b1977bc78e7..3f1cdccebc9c 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -18,6 +18,7 @@ #include <asm/plpar_wrappers.h> #include <asm/machdep.h> +#ifdef CONFIG_DTL struct dtl { struct dtl_entry *buf; int cpu; @@ -58,78 +59,6 @@ static DEFINE_PER_CPU(struct dtl_ring, dtl_rings); static atomic_t dtl_count; /* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. - */ -static notrace u64 scan_dispatch_log(u64 stop_tb) -{ - u64 i = local_paca->dtl_ridx; - struct dtl_entry *dtl = local_paca->dtl_curr; - struct dtl_entry *dtl_end = local_paca->dispatch_log_end; - struct lppaca *vpa = local_paca->lppaca_ptr; - u64 tb_delta; - u64 stolen = 0; - u64 dtb; - - if (!dtl) - return 0; - - if (i == be64_to_cpu(vpa->dtl_idx)) - return 0; - while (i < be64_to_cpu(vpa->dtl_idx)) { - dtb = be64_to_cpu(dtl->timebase); - tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + - be32_to_cpu(dtl->ready_to_enqueue_time); - barrier(); - if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { - /* buffer has overflowed */ - i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; - } - if (dtb > stop_tb) - break; - if (dtl_consumer) - dtl_consumer(dtl, i); - stolen += tb_delta; - ++i; - ++dtl; - if (dtl == dtl_end) - dtl = local_paca->dispatch_log; - } - local_paca->dtl_ridx = i; - local_paca->dtl_curr = dtl; - return stolen; -} - -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void notrace pseries_accumulate_stolen_time(void) -{ - u64 sst, ust; - struct cpu_accounting_data *acct = &local_paca->accounting; - - sst = scan_dispatch_log(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; -} - -u64 pseries_calculate_stolen_time(u64 stop_tb) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return 0; - - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - -/* * The cpu accounting code controls the DTL ring buffer, and we get * given entries as they are processed. */ @@ -436,3 +365,81 @@ static int dtl_init(void) return 0; } machine_arch_initcall(pseries, dtl_init); +#endif /* CONFIG_DTL */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +/* + * Scan the dispatch trace log and count up the stolen time. + * Should be called with interrupts disabled. + */ +static notrace u64 scan_dispatch_log(u64 stop_tb) +{ + u64 i = local_paca->dtl_ridx; + struct dtl_entry *dtl = local_paca->dtl_curr; + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + u64 tb_delta; + u64 stolen = 0; + u64 dtb; + + if (!dtl) + return 0; + + if (i == be64_to_cpu(vpa->dtl_idx)) + return 0; + while (i < be64_to_cpu(vpa->dtl_idx)) { + dtb = be64_to_cpu(dtl->timebase); + tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + + be32_to_cpu(dtl->ready_to_enqueue_time); + barrier(); + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { + /* buffer has overflowed */ + i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + if (dtb > stop_tb) + break; +#ifdef CONFIG_DTL + if (dtl_consumer) + dtl_consumer(dtl, i); +#endif + stolen += tb_delta; + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + local_paca->dtl_ridx = i; + local_paca->dtl_curr = dtl; + return stolen; +} + +/* + * Accumulate stolen time by scanning the dispatch trace log. + * Called on entry from user mode. + */ +void notrace pseries_accumulate_stolen_time(void) +{ + u64 sst, ust; + struct cpu_accounting_data *acct = &local_paca->accounting; + + sst = scan_dispatch_log(acct->starttime_user); + ust = scan_dispatch_log(acct->starttime); + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; +} + +u64 pseries_calculate_stolen_time(u64 stop_tb) +{ + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); + + return 0; +} + +#endif diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 56976e5674ee..6b48a3ae9843 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -70,6 +70,7 @@ config RISCV select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO + select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index e9bd21816ea9..1c8ec656e916 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -37,6 +37,7 @@ else endif ifeq ($(CONFIG_LD_IS_LLD),y) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax ifndef CONFIG_AS_IS_LLVM @@ -44,6 +45,7 @@ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS += -Wa,-mno-relax endif endif +endif # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile index 39aae7b04f1c..7427a20934f3 100644 --- a/arch/riscv/boot/dts/microchip/Makefile +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-icicle-kit.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-m100pfsevp.dtb dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 0d28858b83f2..24b1cfb9a73e 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -2,20 +2,21 @@ /* Copyright (c) 2020-2021 Microchip Technology Inc */ / { - compatible = "microchip,mpfs-icicle-reference-rtlv2203", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; - core_pwm0: pwm@41000000 { + core_pwm0: pwm@40000000 { compatible = "microchip,corepwm-rtl-v4"; - reg = <0x0 0x41000000 0x0 0xF0>; + reg = <0x0 0x40000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; clocks = <&fabric_clk3>; status = "disabled"; }; - i2c2: i2c@44000000 { + i2c2: i2c@40000200 { compatible = "microchip,corei2c-rtl-v7"; - reg = <0x0 0x44000000 0x0 0x1000>; + reg = <0x0 0x40000200 0x0 0x100>; #address-cells = <1>; #size-cells = <0>; clocks = <&fabric_clk3>; @@ -28,7 +29,7 @@ fabric_clk3: fabric-clk3 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <62500000>; + clock-frequency = <50000000>; }; fabric_clk1: fabric-clk1 { @@ -36,4 +37,34 @@ #clock-cells = <0>; clock-frequency = <125000000>; }; + + pcie: pcie@3000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x30 0x8000000 0x0 0x80000000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index f3f87ed2007f..ec7b7c2a3ce2 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -11,7 +11,8 @@ / { model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; aliases { ethernet0 = &mac1; @@ -32,15 +33,26 @@ ddrc_cache_lo: memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x0 0x2e000000>; + reg = <0x0 0x80000000 0x0 0x40000000>; status = "okay"; }; ddrc_cache_hi: memory@1000000000 { device_type = "memory"; - reg = <0x10 0x0 0x0 0x40000000>; + reg = <0x10 0x40000000 0x0 0x40000000>; status = "okay"; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss_payload: region@BFC00000 { + reg = <0x0 0xBFC00000 0x0 0x400000>; + no-map; + }; + }; }; &core_pwm0 { diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi new file mode 100644 index 000000000000..7b9ee13b6a3a --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts new file mode 100644 index 000000000000..184cb36a175e --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Original all-in-one devicetree: + * Copyright (C) 2021-2022 - Wolfgang Grandegger <wg@aries-embedded.de> + * Rewritten to use includes: + * Copyright (C) 2022 - Conor Dooley <conor.dooley@microchip.com> + */ +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-m100pfs-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + model = "Aries Embedded M100PFEVPS"; + compatible = "aries,m100pfsevp", "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + ethernet1 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + gpio0 = &gpio0; + gpio1 = &gpio2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = <MTIMER_FREQ>; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + ddrc_cache_hi: memory@1040000000 { + device_type = "memory"; + reg = <0x10 0x40000000 0x0 0x40000000>; + }; +}; + +&can0 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&gpio0 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>; + ngpios = <14>; + status = "okay"; + + pmic-irq-hog { + gpio-hog; + gpios = <13 0>; + input; + }; + + /* Set to low for eMMC, high for SD-card */ + mmc-sel-hog { + gpio-hog; + gpios = <12 0>; + output-high; + }; +}; + +&gpio2 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>, <27>, <28>, + <29>, <30>, <31>, <32>, + <33>, <34>, <35>, <36>, + <37>, <38>, <39>, <40>, + <41>, <42>, <43>, <44>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy1>; + phy1: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + max-frequency = <50000000>; + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + no-1-8-v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + disable-wp; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&pcie { + status = "okay"; +}; + +&qspi { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi index 49380c428ec9..67303bc0e451 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi @@ -13,4 +13,33 @@ #clock-cells = <0>; clock-frequency = <125000000>; }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi new file mode 100644 index 000000000000..8545baf4d129 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts new file mode 100644 index 000000000000..013cb666c72d --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-sev-kit-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PolarFire-SoC SEV Kit"; + compatible = "microchip,mpfs-sev-kit", "microchip,mpfs"; + + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = <MTIMER_FREQ>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + fabricbuf0ddrc: buffer@80000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x80000000 0x0 0x2000000>; + }; + + fabricbuf1ddrnc: buffer@c4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xc4000000 0x0 0x4000000>; + }; + + fabricbuf2ddrncwcb: buffer@d4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xd4000000 0x0 0x4000000>; + }; + }; + + ddrc_cache: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x0 0x0 0x76000000>; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&gpio2 { + interrupts = <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + phy1: ethernet-phy@9 { + reg = <9>; + }; + phy0: ethernet-phy@8 { + reg = <8>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy1>; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + status = "okay"; + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "otg"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 6d9d455fa160..8f463399a568 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -330,7 +330,7 @@ }; qspi: spi@21000000 { - compatible = "microchip,mpfs-qspi"; + compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2"; #address-cells = <1>; #size-cells = <0>; reg = <0x0 0x21000000 0x0 0x1000>; @@ -464,35 +464,6 @@ status = "disabled"; }; - pcie: pcie@2000000000 { - compatible = "microchip,pcie-host-1.0"; - #address-cells = <0x3>; - #interrupt-cells = <0x1>; - #size-cells = <0x2>; - device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; - bus-range = <0x0 0x7f>; - interrupt-parent = <&plic>; - interrupts = <119>; - interrupt-map = <0 0 0 1 &pcie_intc 0>, - <0 0 0 2 &pcie_intc 1>, - <0 0 0 3 &pcie_intc 2>, - <0 0 0 4 &pcie_intc 3>; - interrupt-map-mask = <0 0 0 7>; - clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; - clock-names = "fic0", "fic1", "fic3"; - ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; - msi-parent = <&pcie>; - msi-controller; - status = "disabled"; - pcie_intc: interrupt-controller { - #address-cells = <0>; - #interrupt-cells = <1>; - interrupt-controller; - }; - }; - mbox: mailbox@37020000 { compatible = "microchip,mpfs-mailbox"; reg = <0x0 0x37020000 0x0 0x1000>, <0x0 0x2000318C 0x0 0x40>; diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 96648c176f37..21546937db39 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -17,6 +17,9 @@ static bool errata_probe_pbmt(unsigned int stage, unsigned long arch_id, unsigned long impid) { + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT)) + return false; + if (arch_id != 0 || impid != 0) return false; @@ -30,7 +33,9 @@ static bool errata_probe_pbmt(unsigned int stage, static bool errata_probe_cmo(unsigned int stage, unsigned long arch_id, unsigned long impid) { -#ifdef CONFIG_ERRATA_THEAD_CMO + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_CMO)) + return false; + if (arch_id != 0 || impid != 0) return false; @@ -40,9 +45,6 @@ static bool errata_probe_cmo(unsigned int stage, riscv_cbom_block_size = L1_CACHE_BYTES; riscv_noncoherent_supported(); return true; -#else - return false; -#endif } static u32 thead_errata_probe(unsigned int stage, @@ -51,10 +53,10 @@ static u32 thead_errata_probe(unsigned int stage, u32 cpu_req_errata = 0; if (errata_probe_pbmt(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_PBMT); + cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); if (errata_probe_cmo(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_CMO); + cpu_req_errata |= BIT(ERRATA_THEAD_CMO); return cpu_req_errata; } diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 273ece6b622f..8a5c246b0a21 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -55,6 +55,8 @@ static inline void riscv_init_cbom_blocksize(void) { } #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); +#else +static inline void riscv_noncoherent_supported(void) {} #endif /* diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index 14fc7342490b..e7acffdf21d2 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -99,6 +99,10 @@ do { \ get_cache_size(2, CACHE_TYPE_UNIFIED)); \ NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \ get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHESIZE, \ + get_cache_size(3, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \ + get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \ } while (0) #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 69605a474270..92080a227937 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -101,9 +101,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) -#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count) -#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count) -#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -115,22 +115,22 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) -#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count) -#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count) -#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) -#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) -#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif #include <asm-generic/io.h> diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index cedcf8ea3c76..0099dc116168 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -16,7 +16,6 @@ typedef struct { atomic_long_t id; #endif void *vdso; - void *vdso_info; #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 32c73ba1d531..fb187a33ce58 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -30,8 +30,10 @@ #define AT_L1D_CACHEGEOMETRY 43 #define AT_L2_CACHESIZE 44 #define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 7 +#define AT_VECTOR_SIZE_ARCH 9 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 4d0dece5996c..fa427bdcf773 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -3,10 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/cpu.h> #include <linux/init.h> #include <linux/seq_file.h> #include <linux/of.h> +#include <asm/csr.h> #include <asm/hwcap.h> +#include <asm/sbi.h> #include <asm/smp.h> #include <asm/pgtable.h> @@ -68,6 +71,50 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) } #ifdef CONFIG_PROC_FS + +struct riscv_cpuinfo { + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; +}; +static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +static int riscv_cpuinfo_starting(unsigned int cpu) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); + ci->marchid = csr_read(CSR_MARCHID); + ci->mimpid = csr_read(CSR_MIMPID); +#else + ci->mvendorid = 0; + ci->marchid = 0; + ci->mimpid = 0; +#endif + + return 0; +} + +static int __init riscv_cpuinfo_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting", + riscv_cpuinfo_starting, NULL); + if (ret < 0) { + pr_err("cpuinfo: failed to register hotplug callbacks.\n"); + return ret; + } + + return 0; +} +device_initcall(riscv_cpuinfo_init); + #define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ { \ .uprop = #UPROP, \ @@ -186,6 +233,7 @@ static int c_show(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; struct device_node *node = of_get_cpu_node(cpu_id, NULL); + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); const char *compat, *isa; seq_printf(m, "processor\t: %lu\n", cpu_id); @@ -196,6 +244,9 @@ static int c_show(struct seq_file *m, void *v) if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); + seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); + seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); seq_puts(m, "\n"); of_node_put(node); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 9774f1271f93..694267d1fe81 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -254,35 +254,28 @@ void __init riscv_fill_hwcap(void) #ifdef CONFIG_RISCV_ALTERNATIVE static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_SVPBMT - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_SVPBMT)) + return false; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) return false; - default: - return riscv_isa_extension_available(NULL, SVPBMT); - } -#endif - return false; + return riscv_isa_extension_available(NULL, SVPBMT); } static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_ZICBOM - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM)) + return false; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + if (!riscv_isa_extension_available(NULL, ZICBOM)) return false; - default: - if (riscv_isa_extension_available(NULL, ZICBOM)) { - riscv_noncoherent_supported(); - return true; - } else { - return false; - } - } -#endif - return false; + riscv_noncoherent_supported(); + return true; } /* @@ -297,10 +290,10 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage) u32 cpu_req_feature = 0; if (cpufeature_probe_svpbmt(stage)) - cpu_req_feature |= (1U << CPUFEATURE_SVPBMT); + cpu_req_feature |= BIT(CPUFEATURE_SVPBMT); if (cpufeature_probe_zicbom(stage)) - cpu_req_feature |= (1U << CPUFEATURE_ZICBOM); + cpu_req_feature |= BIT(CPUFEATURE_ZICBOM); return cpu_req_feature; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 2dfc463b86bb..ad76bb59b059 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -252,10 +252,10 @@ static void __init parse_dtb(void) pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } - return; + } else { + pr_err("No DTB passed to the kernel\n"); } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 571556bb9261..5d3f2fbeb33c 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -18,9 +18,6 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; - if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 635e6ec26938..f3e96d60a2ff 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -33,6 +33,7 @@ void die(struct pt_regs *regs, const char *str) { static int die_counter; int ret; + long cause; oops_enter(); @@ -42,11 +43,13 @@ void die(struct pt_regs *regs, const char *str) pr_emerg("%s [#%d]\n", str, ++die_counter); print_modules(); - show_regs(regs); + if (regs) + show_regs(regs); - ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV); + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); - if (regs && kexec_should_crash(current)) + if (kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 692e7ae3dcb8..123d05255fcf 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -60,6 +60,11 @@ struct __vdso_info { struct vm_special_mapping *cm; }; +static struct __vdso_info vdso_info; +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info; +#endif + static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -115,15 +120,18 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) struct mm_struct *mm = task->mm; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); - struct __vdso_info *vdso_info = mm->context.vdso_info; mmap_read_lock(mm); for_each_vma(vmi, vma) { unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info->dm)) + if (vma_is_special_mapping(vma, vdso_info.dm)) zap_page_range(vma, vma->vm_start, size); +#ifdef CONFIG_COMPAT + if (vma_is_special_mapping(vma, compat_vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); +#endif } mmap_read_unlock(mm); @@ -265,7 +273,6 @@ static int __setup_additional_pages(struct mm_struct *mm, vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; - mm->context.vdso_info = (void *)vdso_info; ret = _install_special_mapping(mm, vdso_base, vdso_text_len, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index f2fbd1400b7c..d86f7cebd4a7 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -184,7 +184,8 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) } break; case EXC_LOAD_PAGE_FAULT: - if (!(vma->vm_flags & VM_READ)) { + /* Write implies read */ + if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { return true; } break; diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h index c37cc4f26f91..3fec3b8406e9 100644 --- a/arch/um/drivers/chan.h +++ b/arch/um/drivers/chan.h @@ -36,7 +36,6 @@ extern int console_write_chan(struct chan *chan, const char *buf, int len); extern int console_open_chan(struct line *line, struct console *co); extern void deactivate_chan(struct chan *chan, int irq); -extern void reactivate_chan(struct chan *chan, int irq); extern void chan_enable_winch(struct chan *chan, struct tty_port *port); extern int enable_chan(struct line *line); extern void close_chan(struct line *line); diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 8ca67a692683..5026e7b9adfe 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -283,7 +283,7 @@ struct unplugged_pages { }; static DEFINE_MUTEX(plug_mem_mutex); -static unsigned long long unplugged_pages_count = 0; +static unsigned long long unplugged_pages_count; static LIST_HEAD(unplugged_pages); static int unplug_index = UNPLUGGED_PER_PAGE; @@ -846,13 +846,12 @@ static int notify_panic(struct notifier_block *self, unsigned long unused1, mconsole_notify(notify_socket, MCONSOLE_PANIC, message, strlen(message) + 1); - return 0; + return NOTIFY_DONE; } static struct notifier_block panic_exit_notifier = { - .notifier_call = notify_panic, - .next = NULL, - .priority = 1 + .notifier_call = notify_panic, + .priority = INT_MAX, /* run as soon as possible */ }; static int add_notifier(void) diff --git a/arch/um/drivers/mmapper_kern.c b/arch/um/drivers/mmapper_kern.c index 0bf78ff89011..807cd3358740 100644 --- a/arch/um/drivers/mmapper_kern.c +++ b/arch/um/drivers/mmapper_kern.c @@ -122,7 +122,7 @@ static int __init mmapper_init(void) return 0; } -static void mmapper_exit(void) +static void __exit mmapper_exit(void) { misc_deregister(&mmapper_dev); } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 59331384c2d3..3d7836c46507 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -265,7 +265,7 @@ static void uml_net_poll_controller(struct net_device *dev) static void uml_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strscpy(info->driver, DRIVER_NAME, sizeof(info->driver)); } static const struct ethtool_ops uml_net_ethtool_ops = { diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c index 8514966778d5..277cea3d30eb 100644 --- a/arch/um/drivers/ssl.c +++ b/arch/um/drivers/ssl.c @@ -106,7 +106,7 @@ static const struct tty_operations ssl_ops = { /* Changed by ssl_init and referenced by ssl_exit, which are both serialized * by being an initcall and exitcall, respectively. */ -static int ssl_init_done = 0; +static int ssl_init_done; static void ssl_console_write(struct console *c, const char *string, unsigned len) diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c index 489d5a746ed3..1c239737d88e 100644 --- a/arch/um/drivers/stdio_console.c +++ b/arch/um/drivers/stdio_console.c @@ -88,7 +88,7 @@ static int con_remove(int n, char **error_out) } /* Set in an initcall, checked in an exitcall */ -static int con_init_done = 0; +static int con_init_done; static int con_install(struct tty_driver *driver, struct tty_struct *tty) { diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index eb2d2f0f0bcc..f4c1e6e97ad5 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1555,7 +1555,7 @@ static void do_io(struct io_thread_req *req, struct io_desc *desc) int kernel_fd = -1; /* Only changed by the io thread. XXX: currently unused. */ -static int io_count = 0; +static int io_count; int io_thread(void *arg) { diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 548265312743..ded7c47d2fbe 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1372,7 +1372,7 @@ static void vector_net_poll_controller(struct net_device *dev) static void vector_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strscpy(info->driver, DRIVER_NAME, sizeof(info->driver)); } static int vector_net_load_bpf_flash(struct net_device *dev, diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 027847023184..acb55b302b14 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -857,7 +857,7 @@ void *pci_root_bus_fwnode(struct pci_bus *bus) return um_pci_fwnode; } -static int um_pci_init(void) +static int __init um_pci_init(void) { int err, i; @@ -940,7 +940,7 @@ free: } module_init(um_pci_init); -static void um_pci_exit(void) +static void __exit um_pci_exit(void) { unregister_virtio_driver(&um_pci_virtio_driver); irq_domain_remove(um_pci_msi_domain); diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index e719af8bdf56..588930a0ced1 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -374,45 +374,48 @@ static irqreturn_t vu_req_read_message(struct virtio_uml_device *vu_dev, u8 extra_payload[512]; } msg; int rc; + irqreturn_t irq_rc = IRQ_NONE; - rc = vhost_user_recv_req(vu_dev, &msg.msg, - sizeof(msg.msg.payload) + - sizeof(msg.extra_payload)); - - vu_dev->recv_rc = rc; - if (rc) - return IRQ_NONE; - - switch (msg.msg.header.request) { - case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG: - vu_dev->config_changed_irq = true; - response = 0; - break; - case VHOST_USER_SLAVE_VRING_CALL: - virtio_device_for_each_vq((&vu_dev->vdev), vq) { - if (vq->index == msg.msg.payload.vring_state.index) { - response = 0; - vu_dev->vq_irq_vq_map |= BIT_ULL(vq->index); - break; + while (1) { + rc = vhost_user_recv_req(vu_dev, &msg.msg, + sizeof(msg.msg.payload) + + sizeof(msg.extra_payload)); + if (rc) + break; + + switch (msg.msg.header.request) { + case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG: + vu_dev->config_changed_irq = true; + response = 0; + break; + case VHOST_USER_SLAVE_VRING_CALL: + virtio_device_for_each_vq((&vu_dev->vdev), vq) { + if (vq->index == msg.msg.payload.vring_state.index) { + response = 0; + vu_dev->vq_irq_vq_map |= BIT_ULL(vq->index); + break; + } } + break; + case VHOST_USER_SLAVE_IOTLB_MSG: + /* not supported - VIRTIO_F_ACCESS_PLATFORM */ + case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: + /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ + default: + vu_err(vu_dev, "unexpected slave request %d\n", + msg.msg.header.request); } - break; - case VHOST_USER_SLAVE_IOTLB_MSG: - /* not supported - VIRTIO_F_ACCESS_PLATFORM */ - case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: - /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ - default: - vu_err(vu_dev, "unexpected slave request %d\n", - msg.msg.header.request); - } - - if (ev && !vu_dev->suspended) - time_travel_add_irq_event(ev); - if (msg.msg.header.flags & VHOST_USER_FLAG_NEED_REPLY) - vhost_user_reply(vu_dev, &msg.msg, response); + if (ev && !vu_dev->suspended) + time_travel_add_irq_event(ev); - return IRQ_HANDLED; + if (msg.msg.header.flags & VHOST_USER_FLAG_NEED_REPLY) + vhost_user_reply(vu_dev, &msg.msg, response); + irq_rc = IRQ_HANDLED; + }; + /* mask EAGAIN as we try non-blocking read until socket is empty */ + vu_dev->recv_rc = (rc == -EAGAIN) ? 0 : rc; + return irq_rc; } static irqreturn_t vu_req_interrupt(int irq, void *data) diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index e7c7b53a1435..91485119ae67 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -169,7 +169,7 @@ __uml_setup("iomem=", parse_iomem, ); /* - * This list is constructed in parse_iomem and addresses filled in in + * This list is constructed in parse_iomem and addresses filled in * setup_iomem, both of which run during early boot. Afterwards, it's * unchanged. */ diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index d9e023c78f56..8adf8e89b255 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -96,7 +96,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + return *pos < nr_cpu_ids ? cpu_data + *pos : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) @@ -132,7 +132,7 @@ static int have_root __initdata; static int have_console __initdata; /* Set in uml_mem_setup and modified in linux_main */ -long long physmem_size = 32 * 1024 * 1024; +long long physmem_size = 64 * 1024 * 1024; EXPORT_SYMBOL(physmem_size); static const char *usage_string = @@ -247,13 +247,13 @@ static int panic_exit(struct notifier_block *self, unsigned long unused1, bust_spinlocks(0); uml_exitcode = 1; os_dump_core(); - return 0; + + return NOTIFY_DONE; } static struct notifier_block panic_exit_notifier = { - .notifier_call = panic_exit, - .next = NULL, - .priority = 0 + .notifier_call = panic_exit, + .priority = INT_MAX - 1, /* run as 2nd notifier, won't return */ }; void uml_finishsetup(void) @@ -416,7 +416,7 @@ void __init setup_arch(char **cmdline_p) read_initrd(); paging_init(); - strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); + strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; setup_hostinfo(host_info, sizeof host_info); diff --git a/arch/um/kernel/umid.c b/arch/um/kernel/umid.c index 8031a038eb58..72bc60ade347 100644 --- a/arch/um/kernel/umid.c +++ b/arch/um/kernel/umid.c @@ -9,7 +9,7 @@ #include <os.h> /* Changed by set_umid_arg */ -static int umid_inited = 0; +static int umid_inited; static int __init set_umid_arg(char *name, int *add) { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7c74d8cba44f..966aab902d19 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,9 +52,6 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops; -#endif static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -546,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; - /* - * With writeback feature, zram does asynchronous IO so it's no longer - * synchronous device so let's remove synchronous io flag. Othewise, - * upper layer(e.g., swap) could wait IO completion rather than - * (submit and return), which will cause system sluggish. - * Furthermore, when the IO function returns(e.g., swap_readpage), - * upper layer expects IO was done so it could deallocate the page - * freely but in fact, IO is going on so finally could cause - * use-after-free when the IO is really done. - */ - zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -1270,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, struct bio_vec bvec; zram_slot_unlock(zram, index); + /* A null bio means rw_page was used, we must fallback to bio */ + if (!bio) + return -EOPNOTSUPP; bvec.bv_page = page; bvec.bv_len = PAGE_SIZE; @@ -1856,15 +1845,6 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops = { - .open = zram_open, - .submit_bio = zram_submit_bio, - .swap_slot_free_notify = zram_slot_free_notify, - .owner = THIS_MODULE -}; -#endif - static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index d429ba52a719..943ea67bf135 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -136,7 +136,6 @@ static int clk_generated_determine_rate(struct clk_hw *hw, { struct clk_generated *gck = to_clk_generated(hw); struct clk_hw *parent = NULL; - struct clk_rate_request req_parent = *req; long best_rate = -EINVAL; unsigned long min_rate, parent_rate; int best_diff = -1; @@ -192,7 +191,9 @@ static int clk_generated_determine_rate(struct clk_hw *hw, goto end; for (div = 1; div < GENERATED_MAX_DIV + 2; div++) { - req_parent.rate = req->rate * div; + struct clk_rate_request req_parent; + + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req->rate * div); if (__clk_determine_rate(parent, &req_parent)) continue; clk_generated_best_diff(req, parent, req_parent.rate, div, diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c index 164e2959c7cf..b7cd1924de52 100644 --- a/drivers/clk/at91/clk-master.c +++ b/drivers/clk/at91/clk-master.c @@ -581,7 +581,6 @@ static int clk_sama7g5_master_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct clk_master *master = to_clk_master(hw); - struct clk_rate_request req_parent = *req; struct clk_hw *parent; long best_rate = LONG_MIN, best_diff = LONG_MIN; unsigned long parent_rate; @@ -618,11 +617,15 @@ static int clk_sama7g5_master_determine_rate(struct clk_hw *hw, goto end; for (div = 0; div < MASTER_PRES_MAX + 1; div++) { + struct clk_rate_request req_parent; + unsigned long req_rate; + if (div == MASTER_PRES_MAX) - req_parent.rate = req->rate * 3; + req_rate = req->rate * 3; else - req_parent.rate = req->rate << div; + req_rate = req->rate << div; + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req_rate); if (__clk_determine_rate(parent, &req_parent)) continue; diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c index e14fa5ac734c..5104d4025484 100644 --- a/drivers/clk/at91/clk-peripheral.c +++ b/drivers/clk/at91/clk-peripheral.c @@ -269,7 +269,6 @@ static int clk_sam9x5_peripheral_determine_rate(struct clk_hw *hw, { struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); struct clk_hw *parent = clk_hw_get_parent(hw); - struct clk_rate_request req_parent = *req; unsigned long parent_rate = clk_hw_get_rate(parent); unsigned long tmp_rate; long best_rate = LONG_MIN; @@ -302,8 +301,9 @@ static int clk_sam9x5_peripheral_determine_rate(struct clk_hw *hw, goto end; for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) { - req_parent.rate = req->rate << shift; + struct clk_rate_request req_parent; + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req->rate << shift); if (__clk_determine_rate(parent, &req_parent)) continue; diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index b9c5f904f535..edfa94641bbf 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -85,10 +85,11 @@ static int clk_composite_determine_rate(struct clk_hw *hw, req->best_parent_hw = NULL; if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) { - struct clk_rate_request tmp_req = *req; + struct clk_rate_request tmp_req; parent = clk_hw_get_parent(mux_hw); + clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate); ret = clk_composite_determine_rate_for_parent(rate_hw, &tmp_req, parent, @@ -104,12 +105,13 @@ static int clk_composite_determine_rate(struct clk_hw *hw, } for (i = 0; i < clk_hw_get_num_parents(mux_hw); i++) { - struct clk_rate_request tmp_req = *req; + struct clk_rate_request tmp_req; parent = clk_hw_get_parent_by_index(mux_hw, i); if (!parent) continue; + clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate); ret = clk_composite_determine_rate_for_parent(rate_hw, &tmp_req, parent, diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index f6b2bf558486..a2c2b5203b0a 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -386,13 +386,13 @@ long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, const struct clk_div_table *table, u8 width, unsigned long flags) { - struct clk_rate_request req = { - .rate = rate, - .best_parent_rate = *prate, - .best_parent_hw = parent, - }; + struct clk_rate_request req; int ret; + clk_hw_init_rate_request(hw, &req, rate); + req.best_parent_rate = *prate; + req.best_parent_hw = parent; + ret = divider_determine_rate(hw, &req, table, width, flags); if (ret) return ret; @@ -408,13 +408,13 @@ long divider_ro_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, const struct clk_div_table *table, u8 width, unsigned long flags, unsigned int val) { - struct clk_rate_request req = { - .rate = rate, - .best_parent_rate = *prate, - .best_parent_hw = parent, - }; + struct clk_rate_request req; int ret; + clk_hw_init_rate_request(hw, &req, rate); + req.best_parent_rate = *prate; + req.best_parent_hw = parent; + ret = divider_ro_determine_rate(hw, &req, table, width, flags, val); if (ret) return ret; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index dd810bcd2700..c3c3f8c07258 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -536,6 +536,53 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now, return now <= rate && now > best; } +static void clk_core_init_rate_req(struct clk_core * const core, + struct clk_rate_request *req, + unsigned long rate); + +static int clk_core_round_rate_nolock(struct clk_core *core, + struct clk_rate_request *req); + +static bool clk_core_has_parent(struct clk_core *core, const struct clk_core *parent) +{ + struct clk_core *tmp; + unsigned int i; + + /* Optimize for the case where the parent is already the parent. */ + if (core->parent == parent) + return true; + + for (i = 0; i < core->num_parents; i++) { + tmp = clk_core_get_parent_by_index(core, i); + if (!tmp) + continue; + + if (tmp == parent) + return true; + } + + return false; +} + +static void +clk_core_forward_rate_req(struct clk_core *core, + const struct clk_rate_request *old_req, + struct clk_core *parent, + struct clk_rate_request *req, + unsigned long parent_rate) +{ + if (WARN_ON(!clk_core_has_parent(core, parent))) + return; + + clk_core_init_rate_req(parent, req, parent_rate); + + if (req->min_rate < old_req->min_rate) + req->min_rate = old_req->min_rate; + + if (req->max_rate > old_req->max_rate) + req->max_rate = old_req->max_rate; +} + int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags) @@ -543,14 +590,20 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_core *core = hw->core, *parent, *best_parent = NULL; int i, num_parents, ret; unsigned long best = 0; - struct clk_rate_request parent_req = *req; /* if NO_REPARENT flag set, pass through to current parent */ if (core->flags & CLK_SET_RATE_NO_REPARENT) { parent = core->parent; if (core->flags & CLK_SET_RATE_PARENT) { - ret = __clk_determine_rate(parent ? parent->hw : NULL, - &parent_req); + struct clk_rate_request parent_req; + + if (!parent) { + req->rate = 0; + return 0; + } + + clk_core_forward_rate_req(core, req, parent, &parent_req, req->rate); + ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) return ret; @@ -567,23 +620,29 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, /* find the parent that can provide the fastest rate <= rate */ num_parents = core->num_parents; for (i = 0; i < num_parents; i++) { + unsigned long parent_rate; + parent = clk_core_get_parent_by_index(core, i); if (!parent) continue; if (core->flags & CLK_SET_RATE_PARENT) { - parent_req = *req; - ret = __clk_determine_rate(parent->hw, &parent_req); + struct clk_rate_request parent_req; + + clk_core_forward_rate_req(core, req, parent, &parent_req, req->rate); + ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) continue; + + parent_rate = parent_req.rate; } else { - parent_req.rate = clk_core_get_rate_nolock(parent); + parent_rate = clk_core_get_rate_nolock(parent); } - if (mux_is_better_rate(req->rate, parent_req.rate, + if (mux_is_better_rate(req->rate, parent_rate, best, flags)) { best_parent = parent; - best = parent_req.rate; + best = parent_rate; } } @@ -625,6 +684,22 @@ static void clk_core_get_boundaries(struct clk_core *core, *max_rate = min(*max_rate, clk_user->max_rate); } +/* + * clk_hw_get_rate_range() - returns the clock rate range for a hw clk + * @hw: the hw clk we want to get the range from + * @min_rate: pointer to the variable that will hold the minimum + * @max_rate: pointer to the variable that will hold the maximum + * + * Fills the @min_rate and @max_rate variables with the minimum and + * maximum that clock can reach. + */ +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate) +{ + clk_core_get_boundaries(hw->core, min_rate, max_rate); +} +EXPORT_SYMBOL_GPL(clk_hw_get_rate_range); + static bool clk_core_check_boundaries(struct clk_core *core, unsigned long min_rate, unsigned long max_rate) @@ -1340,7 +1415,19 @@ static int clk_core_determine_round_nolock(struct clk_core *core, if (!core) return 0; - req->rate = clamp(req->rate, req->min_rate, req->max_rate); + /* + * Some clock providers hand-craft their clk_rate_requests and + * might not fill min_rate and max_rate. + * + * If it's the case, clamping the rate is equivalent to setting + * the rate to 0 which is bad. Skip the clamping but complain so + * that it gets fixed, hopefully. + */ + if (!req->min_rate && !req->max_rate) + pr_warn("%s: %s: clk_rate_request has initialized min or max rate.\n", + __func__, core->name); + else + req->rate = clamp(req->rate, req->min_rate, req->max_rate); /* * At this point, core protection will be disabled @@ -1367,13 +1454,19 @@ static int clk_core_determine_round_nolock(struct clk_core *core, } static void clk_core_init_rate_req(struct clk_core * const core, - struct clk_rate_request *req) + struct clk_rate_request *req, + unsigned long rate) { struct clk_core *parent; if (WARN_ON(!core || !req)) return; + memset(req, 0, sizeof(*req)); + + req->rate = rate; + clk_core_get_boundaries(core, &req->min_rate, &req->max_rate); + parent = core->parent; if (parent) { req->best_parent_hw = parent->hw; @@ -1384,6 +1477,51 @@ static void clk_core_init_rate_req(struct clk_core * const core, } } +/** + * clk_hw_init_rate_request - Initializes a clk_rate_request + * @hw: the clk for which we want to submit a rate request + * @req: the clk_rate_request structure we want to initialise + * @rate: the rate which is to be requested + * + * Initializes a clk_rate_request structure to submit to + * __clk_determine_rate() or similar functions. + */ +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate) +{ + if (WARN_ON(!hw || !req)) + return; + + clk_core_init_rate_req(hw->core, req, rate); +} +EXPORT_SYMBOL_GPL(clk_hw_init_rate_request); + +/** + * clk_hw_forward_rate_request - Forwards a clk_rate_request to a clock's parent + * @hw: the original clock that got the rate request + * @old_req: the original clk_rate_request structure we want to forward + * @parent: the clk we want to forward @old_req to + * @req: the clk_rate_request structure we want to initialise + * @parent_rate: The rate which is to be requested to @parent + * + * Initializes a clk_rate_request structure to submit to a clock parent + * in __clk_determine_rate() or similar functions. + */ +void clk_hw_forward_rate_request(const struct clk_hw *hw, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate) +{ + if (WARN_ON(!hw || !old_req || !parent || !req)) + return; + + clk_core_forward_rate_req(hw->core, old_req, + parent->core, req, + parent_rate); +} + static bool clk_core_can_round(struct clk_core * const core) { return core->ops->determine_rate || core->ops->round_rate; @@ -1392,6 +1530,8 @@ static bool clk_core_can_round(struct clk_core * const core) static int clk_core_round_rate_nolock(struct clk_core *core, struct clk_rate_request *req) { + int ret; + lockdep_assert_held(&prepare_lock); if (!core) { @@ -1399,12 +1539,22 @@ static int clk_core_round_rate_nolock(struct clk_core *core, return 0; } - clk_core_init_rate_req(core, req); - if (clk_core_can_round(core)) return clk_core_determine_round_nolock(core, req); - else if (core->flags & CLK_SET_RATE_PARENT) - return clk_core_round_rate_nolock(core->parent, req); + + if (core->flags & CLK_SET_RATE_PARENT) { + struct clk_rate_request parent_req; + + clk_core_forward_rate_req(core, req, core->parent, &parent_req, req->rate); + ret = clk_core_round_rate_nolock(core->parent, &parent_req); + if (ret) + return ret; + + req->best_parent_rate = parent_req.rate; + req->rate = parent_req.rate; + + return 0; + } req->rate = core->rate; return 0; @@ -1448,8 +1598,7 @@ unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate) int ret; struct clk_rate_request req; - clk_core_get_boundaries(hw->core, &req.min_rate, &req.max_rate); - req.rate = rate; + clk_core_init_rate_req(hw->core, &req, rate); ret = clk_core_round_rate_nolock(hw->core, &req); if (ret) @@ -1481,8 +1630,7 @@ long clk_round_rate(struct clk *clk, unsigned long rate) if (clk->exclusive_count) clk_core_rate_unprotect(clk->core); - clk_core_get_boundaries(clk->core, &req.min_rate, &req.max_rate); - req.rate = rate; + clk_core_init_rate_req(clk->core, &req, rate); ret = clk_core_round_rate_nolock(clk->core, &req); @@ -1611,6 +1759,7 @@ static unsigned long clk_recalc(struct clk_core *core, /** * __clk_recalc_rates * @core: first clk in the subtree + * @update_req: Whether req_rate should be updated with the new rate * @msg: notification type (see include/linux/clk.h) * * Walks the subtree of clks starting with clk and recalculates rates as it @@ -1620,7 +1769,8 @@ static unsigned long clk_recalc(struct clk_core *core, * clk_recalc_rates also propagates the POST_RATE_CHANGE notification, * if necessary. */ -static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) +static void __clk_recalc_rates(struct clk_core *core, bool update_req, + unsigned long msg) { unsigned long old_rate; unsigned long parent_rate = 0; @@ -1634,6 +1784,8 @@ static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) parent_rate = core->parent->rate; core->rate = clk_recalc(core, parent_rate); + if (update_req) + core->req_rate = core->rate; /* * ignore NOTIFY_STOP and NOTIFY_BAD return values for POST_RATE_CHANGE @@ -1643,13 +1795,13 @@ static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) __clk_notify(core, msg, old_rate, core->rate); hlist_for_each_entry(child, &core->children, child_node) - __clk_recalc_rates(child, msg); + __clk_recalc_rates(child, update_req, msg); } static unsigned long clk_core_get_rate_recalc(struct clk_core *core) { if (core && (core->flags & CLK_GET_RATE_NOCACHE)) - __clk_recalc_rates(core, 0); + __clk_recalc_rates(core, false, 0); return clk_core_get_rate_nolock(core); } @@ -1659,8 +1811,9 @@ static unsigned long clk_core_get_rate_recalc(struct clk_core *core) * @clk: the clk whose rate is being returned * * Simply returns the cached rate of the clk, unless CLK_GET_RATE_NOCACHE flag - * is set, which means a recalc_rate will be issued. - * If clk is NULL then returns 0. + * is set, which means a recalc_rate will be issued. Can be called regardless of + * the clock enabledness. If clk is NULL, or if an error occurred, then returns + * 0. */ unsigned long clk_get_rate(struct clk *clk) { @@ -1864,6 +2017,7 @@ static int __clk_set_parent(struct clk_core *core, struct clk_core *parent, flags = clk_enable_lock(); clk_reparent(core, old_parent); clk_enable_unlock(flags); + __clk_set_parent_after(core, old_parent, parent); return ret; @@ -1969,11 +2123,7 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core, if (clk_core_can_round(core)) { struct clk_rate_request req; - req.rate = rate; - req.min_rate = min_rate; - req.max_rate = max_rate; - - clk_core_init_rate_req(core, &req); + clk_core_init_rate_req(core, &req, rate); ret = clk_core_determine_round_nolock(core, &req); if (ret < 0) @@ -2172,8 +2322,7 @@ static unsigned long clk_core_req_round_rate_nolock(struct clk_core *core, if (cnt < 0) return cnt; - clk_core_get_boundaries(core, &req.min_rate, &req.max_rate); - req.rate = req_rate; + clk_core_init_rate_req(core, &req, req_rate); ret = clk_core_round_rate_nolock(core, &req); @@ -2324,19 +2473,15 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate) } EXPORT_SYMBOL_GPL(clk_set_rate_exclusive); -/** - * clk_set_rate_range - set a rate range for a clock source - * @clk: clock source - * @min: desired minimum clock rate in Hz, inclusive - * @max: desired maximum clock rate in Hz, inclusive - * - * Returns success (0) or negative errno. - */ -int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) +static int clk_set_rate_range_nolock(struct clk *clk, + unsigned long min, + unsigned long max) { int ret = 0; unsigned long old_min, old_max, rate; + lockdep_assert_held(&prepare_lock); + if (!clk) return 0; @@ -2349,8 +2494,6 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) return -EINVAL; } - clk_prepare_lock(); - if (clk->exclusive_count) clk_core_rate_unprotect(clk->core); @@ -2365,6 +2508,10 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) goto out; } + rate = clk->core->req_rate; + if (clk->core->flags & CLK_GET_RATE_NOCACHE) + rate = clk_core_get_rate_recalc(clk->core); + /* * Since the boundaries have been changed, let's give the * opportunity to the provider to adjust the clock rate based on @@ -2382,7 +2529,7 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) * - the determine_rate() callback does not really check for * this corner case when determining the rate */ - rate = clamp(clk->core->req_rate, min, max); + rate = clamp(rate, min, max); ret = clk_core_set_rate_nolock(clk->core, rate); if (ret) { /* rollback the changes */ @@ -2394,6 +2541,28 @@ out: if (clk->exclusive_count) clk_core_rate_protect(clk->core); + return ret; +} + +/** + * clk_set_rate_range - set a rate range for a clock source + * @clk: clock source + * @min: desired minimum clock rate in Hz, inclusive + * @max: desired maximum clock rate in Hz, inclusive + * + * Return: 0 for success or negative errno on failure. + */ +int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) +{ + int ret; + + if (!clk) + return 0; + + clk_prepare_lock(); + + ret = clk_set_rate_range_nolock(clk, min, max); + clk_prepare_unlock(); return ret; @@ -2473,7 +2642,7 @@ static void clk_core_reparent(struct clk_core *core, { clk_reparent(core, new_parent); __clk_recalc_accuracies(core); - __clk_recalc_rates(core, POST_RATE_CHANGE); + __clk_recalc_rates(core, true, POST_RATE_CHANGE); } void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent) @@ -2494,27 +2663,13 @@ void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent) * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent) +bool clk_has_parent(const struct clk *clk, const struct clk *parent) { - struct clk_core *core, *parent_core; - int i; - /* NULL clocks should be nops, so return success if either is NULL. */ if (!clk || !parent) return true; - core = clk->core; - parent_core = parent->core; - - /* Optimize for the case where the parent is already the parent. */ - if (core->parent == parent_core) - return true; - - for (i = 0; i < core->num_parents; i++) - if (!strcmp(core->parents[i].name, parent_core->name)) - return true; - - return false; + return clk_core_has_parent(clk->core, parent->core); } EXPORT_SYMBOL_GPL(clk_has_parent); @@ -2571,9 +2726,9 @@ static int clk_core_set_parent_nolock(struct clk_core *core, /* propagate rate an accuracy recalculation accordingly */ if (ret) { - __clk_recalc_rates(core, ABORT_RATE_CHANGE); + __clk_recalc_rates(core, true, ABORT_RATE_CHANGE); } else { - __clk_recalc_rates(core, POST_RATE_CHANGE); + __clk_recalc_rates(core, true, POST_RATE_CHANGE); __clk_recalc_accuracies(core); } @@ -3470,7 +3625,7 @@ static void clk_core_reparent_orphans_nolock(void) __clk_set_parent_before(orphan, parent); __clk_set_parent_after(orphan, parent, NULL); __clk_recalc_accuracies(orphan); - __clk_recalc_rates(orphan, 0); + __clk_recalc_rates(orphan, true, 0); /* * __clk_init_parent() will set the initial req_rate to @@ -4346,9 +4501,10 @@ void __clk_put(struct clk *clk) } hlist_del(&clk->clks_node); - if (clk->min_rate > clk->core->req_rate || - clk->max_rate < clk->core->req_rate) - clk_core_set_rate_nolock(clk->core, clk->core->req_rate); + + /* If we had any boundaries on that clock, let's drop them. */ + if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) + clk_set_rate_range_nolock(clk, 0, ULONG_MAX); owner = clk->core->owner; kref_put(&clk->core->ref, __clk_release); diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 6731a822f4e3..f9a5c2964c65 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -108,6 +108,39 @@ static const struct clk_ops clk_dummy_single_parent_ops = { .get_parent = clk_dummy_single_get_parent, }; +struct clk_multiple_parent_ctx { + struct clk_dummy_context parents_ctx[2]; + struct clk_hw hw; + u8 current_parent; +}; + +static int clk_multiple_parents_mux_set_parent(struct clk_hw *hw, u8 index) +{ + struct clk_multiple_parent_ctx *ctx = + container_of(hw, struct clk_multiple_parent_ctx, hw); + + if (index >= clk_hw_get_num_parents(hw)) + return -EINVAL; + + ctx->current_parent = index; + + return 0; +} + +static u8 clk_multiple_parents_mux_get_parent(struct clk_hw *hw) +{ + struct clk_multiple_parent_ctx *ctx = + container_of(hw, struct clk_multiple_parent_ctx, hw); + + return ctx->current_parent; +} + +static const struct clk_ops clk_multiple_parents_mux_ops = { + .get_parent = clk_multiple_parents_mux_get_parent, + .set_parent = clk_multiple_parents_mux_set_parent, + .determine_rate = __clk_mux_determine_rate_closest, +}; + static int clk_test_init_with_ops(struct kunit *test, const struct clk_ops *ops) { struct clk_dummy_context *ctx; @@ -160,12 +193,14 @@ static void clk_test_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, ctx->rate); + + clk_put(clk); } /* @@ -179,7 +214,7 @@ static void clk_test_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -189,6 +224,8 @@ static void clk_test_set_get_rate(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -202,7 +239,7 @@ static void clk_test_set_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -216,6 +253,8 @@ static void clk_test_set_set_get_rate(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -226,7 +265,7 @@ static void clk_test_round_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rounded_rate, set_rate; rounded_rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1); @@ -240,6 +279,8 @@ static void clk_test_round_set_get_rate(struct kunit *test) set_rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, set_rate, 0); KUNIT_EXPECT_EQ(test, rounded_rate, set_rate); + + clk_put(clk); } static struct kunit_case clk_test_cases[] = { @@ -250,6 +291,11 @@ static struct kunit_case clk_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate API with simple scenarios + */ static struct kunit_suite clk_test_suite = { .name = "clk-test", .init = clk_test_init, @@ -257,11 +303,912 @@ static struct kunit_suite clk_test_suite = { .test_cases = clk_test_cases, }; +static int clk_uncached_test_init(struct kunit *test) +{ + struct clk_dummy_context *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->rate = DUMMY_CLOCK_INIT_RATE; + ctx->hw.init = CLK_HW_INIT_NO_PARENT("test-clk", + &clk_dummy_rate_ops, + CLK_GET_RATE_NOCACHE); + + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +/* + * Test that for an uncached clock, the clock framework doesn't cache + * the rate and clk_get_rate() will return the underlying clock rate + * even if it changed. + */ +static void clk_test_uncached_get_rate(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + /* We change the rate behind the clock framework's back */ + ctx->rate = DUMMY_CLOCK_RATE_1; + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); +} + +/* + * Test that for an uncached clock, clk_set_rate_range() will work + * properly if the rate hasn't changed. + */ +static void clk_test_uncached_set_range(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + +/* + * Test that for an uncached clock, clk_set_rate_range() will work + * properly if the rate has changed in hardware. + * + * In this case, it means that if the rate wasn't initially in the range + * we're trying to set, but got changed at some point into the range + * without the kernel knowing about it, its rate shouldn't be affected. + */ +static void clk_test_uncached_updated_rate_set_range(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + /* We change the rate behind the clock framework's back */ + ctx->rate = DUMMY_CLOCK_RATE_1 + 1000; + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + + clk_put(clk); +} + +static struct kunit_case clk_uncached_test_cases[] = { + KUNIT_CASE(clk_test_uncached_get_rate), + KUNIT_CASE(clk_test_uncached_set_range), + KUNIT_CASE(clk_test_uncached_updated_rate_set_range), + {} +}; + +/* + * Test suite for a basic, uncached, rate clock, without any parent. + * + * These tests exercise the rate API with simple scenarios + */ +static struct kunit_suite clk_uncached_test_suite = { + .name = "clk-uncached-test", + .init = clk_uncached_test_init, + .exit = clk_test_exit, + .test_cases = clk_uncached_test_cases, +}; + +static int +clk_multiple_parents_mux_test_init(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx; + const char *parents[2] = { "parent-0", "parent-1"}; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->parents_ctx[0].hw); + if (ret) + return ret; + + ctx->parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->parents_ctx[1].hw); + if (ret) + return ret; + + ctx->current_parent = 0; + ctx->hw.init = CLK_HW_INIT_PARENTS("test-mux", parents, + &clk_multiple_parents_mux_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_multiple_parents_mux_test_exit(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parents_ctx[0].hw); + clk_hw_unregister(&ctx->parents_ctx[1].hw); +} + +/* + * Test that for a clock with multiple parents, clk_get_parent() + * actually returns the current one. + */ +static void +clk_test_multiple_parents_mux_get_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_is_match(clk_get_parent(clk), parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that for a clock with a multiple parents, clk_has_parent() + * actually reports all of them as parents. + */ +static void +clk_test_multiple_parents_mux_has_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + + parent = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + clk_put(parent); + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + clk_put(parent); + + clk_put(clk); +} + +/* + * Test that for a clock with a multiple parents, if we set a range on + * that clock and the parent is changed, its rate after the reparenting + * is still within the range we asked for. + * + * FIXME: clk_set_parent() only does the reparenting but doesn't + * reevaluate whether the new clock rate is within its boundaries or + * not. + */ +static void +clk_test_multiple_parents_mux_set_range_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent1, *parent2; + unsigned long rate; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent1 = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent1); + KUNIT_ASSERT_TRUE(test, clk_is_match(clk_get_parent(clk), parent1)); + + parent2 = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent2); + + ret = clk_set_rate(parent1, DUMMY_CLOCK_RATE_1); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate(parent2, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1 - 1000, + DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_parent(clk, parent2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + + clk_put(parent2); + clk_put(parent1); + clk_put(clk); +} + +static struct kunit_case clk_multiple_parents_mux_test_cases[] = { + KUNIT_CASE(clk_test_multiple_parents_mux_get_parent), + KUNIT_CASE(clk_test_multiple_parents_mux_has_parent), + KUNIT_CASE(clk_test_multiple_parents_mux_set_range_set_parent_get_rate), + {} +}; + +/* + * Test suite for a basic mux clock with two parents, with + * CLK_SET_RATE_PARENT on the child. + * + * These tests exercise the consumer API and check that the state of the + * child and parents are sane and consistent. + */ +static struct kunit_suite +clk_multiple_parents_mux_test_suite = { + .name = "clk-multiple-parents-mux-test", + .init = clk_multiple_parents_mux_test_init, + .exit = clk_multiple_parents_mux_test_exit, + .test_cases = clk_multiple_parents_mux_test_cases, +}; + +static int +clk_orphan_transparent_multiple_parent_mux_test_init(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx; + const char *parents[2] = { "missing-parent", "proper-parent"}; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("proper-parent", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[1].rate = DUMMY_CLOCK_INIT_RATE; + ret = clk_hw_register(NULL, &ctx->parents_ctx[1].hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT_PARENTS("test-orphan-mux", parents, + &clk_multiple_parents_mux_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_orphan_transparent_multiple_parent_mux_test_exit(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parents_ctx[1].hw); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet and is + * thus orphan, clk_get_parent() will return NULL. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_get_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + + KUNIT_EXPECT_PTR_EQ(test, clk_get_parent(clk), NULL); + + clk_put(clk); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet, + * calling clk_set_parent() to a valid parent will properly update the + * mux parent and its orphan status. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent, *new_parent; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent = clk_get_parent(clk); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + KUNIT_EXPECT_TRUE(test, clk_is_match(parent, new_parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_drop_range() on the mux won't affect the parent + * rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_drop_range(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_drop_range(clk); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent_rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, the rate of the mux and its new parent are consistent. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, rate); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_put() on the mux won't affect the parent rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_put(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk *clk, *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + clk = clk_hw_get_clk(&ctx->hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, clk); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + clk_put(clk); + + new_parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_set_rate_range() will affect the parent state if + * its rate is out of range. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_set_rate_range() won't affect the parent state if + * its rate is within range. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_untouched(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_INIT_RATE - 1000, + DUMMY_CLOCK_INIT_RATE + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet, + * calling clk_set_rate_range() will succeed, and will be taken into + * account when rounding a rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_range_round_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + int ret; + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan, was assigned and rate and + * then got switched to a valid parent, its rate is eventually within + * range. + * + * FIXME: Even though we update the rate as part of clk_set_parent(), we + * don't evaluate whether that new rate is within range and needs to be + * adjusted. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + clk_hw_set_rate_range(hw, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(parent); + clk_put(clk); +} + +static struct kunit_case clk_orphan_transparent_multiple_parent_mux_test_cases[] = { + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_get_parent), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_drop_range), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_put), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_untouched), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_round_rate), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate), + {} +}; + +/* + * Test suite for a basic mux clock with two parents. The default parent + * isn't registered, only the second parent is. By default, the clock + * will thus be orphan. + * + * These tests exercise the behaviour of the consumer API when dealing + * with an orphan clock, and how we deal with the transition to a valid + * parent. + */ +static struct kunit_suite clk_orphan_transparent_multiple_parent_mux_test_suite = { + .name = "clk-orphan-transparent-multiple-parent-mux-test", + .init = clk_orphan_transparent_multiple_parent_mux_test_init, + .exit = clk_orphan_transparent_multiple_parent_mux_test_exit, + .test_cases = clk_orphan_transparent_multiple_parent_mux_test_cases, +}; + struct clk_single_parent_ctx { struct clk_dummy_context parent_ctx; struct clk_hw hw; }; +static int clk_single_parent_mux_test_init(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parent_ctx.rate = DUMMY_CLOCK_INIT_RATE; + ctx->parent_ctx.hw.init = + CLK_HW_INIT_NO_PARENT("parent-clk", + &clk_dummy_rate_ops, + 0); + + ret = clk_hw_register(NULL, &ctx->parent_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT("test-clk", "parent-clk", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_single_parent_mux_test_exit(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parent_ctx.hw); +} + +/* + * Test that for a clock with a single parent, clk_get_parent() actually + * returns the parent. + */ +static void +clk_test_single_parent_mux_get_parent(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parent_ctx.hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_is_match(clk_get_parent(clk), parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that for a clock with a single parent, clk_has_parent() actually + * reports it as a parent. + */ +static void +clk_test_single_parent_mux_has_parent(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parent_ctx.hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set disjoints range on the parent and then the child, + * the second will return an error. + * + * FIXME: clk_set_rate_range() only considers the current clock when + * evaluating whether ranges are disjoints and not the upstream clocks + * ranges. + */ +static void +clk_test_single_parent_mux_set_range_disjoint_child_last(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, 1000, 2000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, 3000, 4000); + KUNIT_EXPECT_LT(test, ret, 0); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set disjoints range on the child and then the parent, + * the second will return an error. + * + * FIXME: clk_set_rate_range() only considers the current clock when + * evaluating whether ranges are disjoints and not the downstream clocks + * ranges. + */ +static void +clk_test_single_parent_mux_set_range_disjoint_parent_last(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(clk, 1000, 2000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(parent, 3000, 4000); + KUNIT_EXPECT_LT(test, ret, 0); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the parent and then call + * clk_round_rate(), the boundaries of the parent are taken into + * account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_parent_only(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the parent and a more restrictive one on + * the child, and then call clk_round_rate(), the boundaries of the + * two clocks are taken into account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_child_smaller(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_2 - 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_2 + 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the child and a more restrictive one on + * the parent, and then call clk_round_rate(), the boundaries of the + * two clocks are taken into account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_parent_smaller(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_2 - 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_2 + 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + clk_put(clk); +} + +static struct kunit_case clk_single_parent_mux_test_cases[] = { + KUNIT_CASE(clk_test_single_parent_mux_get_parent), + KUNIT_CASE(clk_test_single_parent_mux_has_parent), + KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_child_last), + KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_parent_last), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_child_smaller), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_parent_only), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_parent_smaller), + {} +}; + +/* + * Test suite for a basic mux clock with one parent, with + * CLK_SET_RATE_PARENT on the child. + * + * These tests exercise the consumer API and check that the state of the + * child and parent are sane and consistent. + */ +static struct kunit_suite +clk_single_parent_mux_test_suite = { + .name = "clk-single-parent-mux-test", + .init = clk_single_parent_mux_test_init, + .exit = clk_single_parent_mux_test_exit, + .test_cases = clk_single_parent_mux_test_cases, +}; + static int clk_orphan_transparent_single_parent_mux_test_init(struct kunit *test) { struct clk_single_parent_ctx *ctx; @@ -298,23 +1245,18 @@ static int clk_orphan_transparent_single_parent_mux_test_init(struct kunit *test return 0; } -static void clk_orphan_transparent_single_parent_mux_test_exit(struct kunit *test) -{ - struct clk_single_parent_ctx *ctx = test->priv; - - clk_hw_unregister(&ctx->hw); - clk_hw_unregister(&ctx->parent_ctx.hw); -} - /* * Test that a mux-only clock, with an initial rate within a range, * will still have the same rate after the range has been enforced. + * + * See: + * https://lore.kernel.org/linux-clk/7720158d-10a7-a17b-73a4-a8615c9c6d5c@collabora.com/ */ static void clk_test_orphan_transparent_parent_mux_set_range(struct kunit *test) { struct clk_single_parent_ctx *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate, new_rate; rate = clk_get_rate(clk); @@ -329,6 +1271,8 @@ static void clk_test_orphan_transparent_parent_mux_set_range(struct kunit *test) new_rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, new_rate, 0); KUNIT_EXPECT_EQ(test, rate, new_rate); + + clk_put(clk); } static struct kunit_case clk_orphan_transparent_single_parent_mux_test_cases[] = { @@ -336,13 +1280,151 @@ static struct kunit_case clk_orphan_transparent_single_parent_mux_test_cases[] = {} }; +/* + * Test suite for a basic mux clock with one parent. The parent is + * registered after its child. The clock will thus be an orphan when + * registered, but will no longer be when the tests run. + * + * These tests make sure a clock that used to be orphan has a sane, + * consistent, behaviour. + */ static struct kunit_suite clk_orphan_transparent_single_parent_test_suite = { .name = "clk-orphan-transparent-single-parent-test", .init = clk_orphan_transparent_single_parent_mux_test_init, - .exit = clk_orphan_transparent_single_parent_mux_test_exit, + .exit = clk_single_parent_mux_test_exit, .test_cases = clk_orphan_transparent_single_parent_mux_test_cases, }; +struct clk_single_parent_two_lvl_ctx { + struct clk_dummy_context parent_parent_ctx; + struct clk_dummy_context parent_ctx; + struct clk_hw hw; +}; + +static int +clk_orphan_two_level_root_last_test_init(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parent_ctx.hw.init = + CLK_HW_INIT("intermediate-parent", + "root-parent", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->parent_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = + CLK_HW_INIT("test-clk", "intermediate-parent", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + ctx->parent_parent_ctx.rate = DUMMY_CLOCK_INIT_RATE; + ctx->parent_parent_ctx.hw.init = + CLK_HW_INIT_NO_PARENT("root-parent", + &clk_dummy_rate_ops, + 0); + ret = clk_hw_register(NULL, &ctx->parent_parent_ctx.hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_orphan_two_level_root_last_test_exit(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parent_ctx.hw); + clk_hw_unregister(&ctx->parent_parent_ctx.hw); +} + +/* + * Test that, for a clock whose parent used to be orphan, clk_get_rate() + * will return the proper rate. + */ +static void +clk_orphan_two_level_root_last_test_get_rate(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + rate = clk_get_rate(clk); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + clk_put(clk); +} + +/* + * Test that, for a clock whose parent used to be orphan, + * clk_set_rate_range() won't affect its rate if it is already within + * range. + * + * See (for Exynos 4210): + * https://lore.kernel.org/linux-clk/366a0232-bb4a-c357-6aa8-636e398e05eb@samsung.com/ + */ +static void +clk_orphan_two_level_root_last_test_set_range(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + int ret; + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_INIT_RATE - 1000, + DUMMY_CLOCK_INIT_RATE + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + clk_put(clk); +} + +static struct kunit_case +clk_orphan_two_level_root_last_test_cases[] = { + KUNIT_CASE(clk_orphan_two_level_root_last_test_get_rate), + KUNIT_CASE(clk_orphan_two_level_root_last_test_set_range), + {} +}; + +/* + * Test suite for a basic, transparent, clock with a parent that is also + * such a clock. The parent's parent is registered last, while the + * parent and its child are registered in that order. The intermediate + * and leaf clocks will thus be orphan when registered, but the leaf + * clock itself will always have its parent and will never be + * reparented. Indeed, it's only orphan because its parent is. + * + * These tests exercise the behaviour of the consumer API when dealing + * with an orphan clock, and how we deal with the transition to a valid + * parent. + */ +static struct kunit_suite +clk_orphan_two_level_root_last_test_suite = { + .name = "clk-orphan-two-level-root-last-test", + .init = clk_orphan_two_level_root_last_test_init, + .exit = clk_orphan_two_level_root_last_test_exit, + .test_cases = clk_orphan_two_level_root_last_test_cases, +}; + /* * Test that clk_set_rate_range won't return an error for a valid range * and that it will make sure the rate of the clock is within the @@ -352,7 +1434,7 @@ static void clk_range_test_set_range(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -365,6 +1447,8 @@ static void clk_range_test_set_range(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -375,13 +1459,15 @@ static void clk_range_test_set_range_invalid(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); KUNIT_EXPECT_LT(test, clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_1), 0); + + clk_put(clk); } /* @@ -420,7 +1506,7 @@ static void clk_range_test_set_range_round_rate_lower(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rate; KUNIT_ASSERT_EQ(test, @@ -433,6 +1519,8 @@ static void clk_range_test_set_range_round_rate_lower(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -443,7 +1531,7 @@ static void clk_range_test_set_range_set_rate_lower(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -460,6 +1548,8 @@ static void clk_range_test_set_range_set_rate_lower(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -472,7 +1562,7 @@ static void clk_range_test_set_range_set_round_rate_consistent_lower(struct kuni { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rounded; KUNIT_ASSERT_EQ(test, @@ -489,6 +1579,8 @@ static void clk_range_test_set_range_set_round_rate_consistent_lower(struct kuni 0); KUNIT_EXPECT_EQ(test, rounded, clk_get_rate(clk)); + + clk_put(clk); } /* @@ -499,7 +1591,7 @@ static void clk_range_test_set_range_round_rate_higher(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rate; KUNIT_ASSERT_EQ(test, @@ -512,6 +1604,8 @@ static void clk_range_test_set_range_round_rate_higher(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -522,7 +1616,7 @@ static void clk_range_test_set_range_set_rate_higher(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -539,6 +1633,8 @@ static void clk_range_test_set_range_set_rate_higher(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -551,7 +1647,7 @@ static void clk_range_test_set_range_set_round_rate_consistent_higher(struct kun { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rounded; KUNIT_ASSERT_EQ(test, @@ -568,6 +1664,8 @@ static void clk_range_test_set_range_set_round_rate_consistent_higher(struct kun 0); KUNIT_EXPECT_EQ(test, rounded, clk_get_rate(clk)); + + clk_put(clk); } /* @@ -582,7 +1680,7 @@ static void clk_range_test_set_range_get_rate_raised(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -598,6 +1696,8 @@ static void clk_range_test_set_range_get_rate_raised(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -612,7 +1712,7 @@ static void clk_range_test_set_range_get_rate_lowered(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -628,6 +1728,8 @@ static void clk_range_test_set_range_get_rate_lowered(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } static struct kunit_case clk_range_test_cases[] = { @@ -645,6 +1747,12 @@ static struct kunit_case clk_range_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(). + */ static struct kunit_suite clk_range_test_suite = { .name = "clk-range-test", .init = clk_test_init, @@ -664,7 +1772,7 @@ static void clk_range_test_set_range_rate_maximized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -700,6 +1808,8 @@ static void clk_range_test_set_range_rate_maximized(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -714,7 +1824,7 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); struct clk *user1, *user2; unsigned long rate; @@ -758,14 +1868,79 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) clk_put(user2); clk_put(user1); + clk_put(clk); +} + +/* + * Test that if we have several subsequent calls to + * clk_set_rate_range(), across multiple users, the core will reevaluate + * whether a new rate is needed, including when a user drop its clock. + * + * With clk_dummy_maximize_rate_ops, this means that the rate will + * trail along the maximum as it evolves. + */ +static void clk_range_test_multiple_set_range_rate_put_maximized(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *user1, *user2; + unsigned long rate; + + user1 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); + + user2 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate(clk, DUMMY_CLOCK_RATE_2 + 1000), + 0); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user1, + 0, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user2, + 0, + DUMMY_CLOCK_RATE_1), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(user2); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(user1); + clk_put(clk); } static struct kunit_case clk_range_maximize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_maximized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_maximized), + KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_maximized), {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(), with a + * driver that will always try to run at the highest possible rate. + */ static struct kunit_suite clk_range_maximize_test_suite = { .name = "clk-range-maximize-test", .init = clk_maximize_test_init, @@ -785,7 +1960,7 @@ static void clk_range_test_set_range_rate_minimized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -821,6 +1996,8 @@ static void clk_range_test_set_range_rate_minimized(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -835,7 +2012,7 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); struct clk *user1, *user2; unsigned long rate; @@ -875,14 +2052,75 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) clk_put(user2); clk_put(user1); + clk_put(clk); +} + +/* + * Test that if we have several subsequent calls to + * clk_set_rate_range(), across multiple users, the core will reevaluate + * whether a new rate is needed, including when a user drop its clock. + * + * With clk_dummy_minimize_rate_ops, this means that the rate will + * trail along the minimum as it evolves. + */ +static void clk_range_test_multiple_set_range_rate_put_minimized(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *user1, *user2; + unsigned long rate; + + user1 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); + + user2 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user1, + DUMMY_CLOCK_RATE_1, + ULONG_MAX), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user2, + DUMMY_CLOCK_RATE_2, + ULONG_MAX), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(user2); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(user1); + clk_put(clk); } static struct kunit_case clk_range_minimize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_minimized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_minimized), + KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_minimized), {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(), with a + * driver that will always try to run at the lowest possible rate. + */ static struct kunit_suite clk_range_minimize_test_suite = { .name = "clk-range-minimize-test", .init = clk_minimize_test_init, @@ -890,11 +2128,284 @@ static struct kunit_suite clk_range_minimize_test_suite = { .test_cases = clk_range_minimize_test_cases, }; +struct clk_leaf_mux_ctx { + struct clk_multiple_parent_ctx mux_ctx; + struct clk_hw hw; +}; + +static int +clk_leaf_mux_set_rate_parent_test_init(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx; + const char *top_parents[2] = { "parent-0", "parent-1" }; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->mux_ctx.parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[0].hw); + if (ret) + return ret; + + ctx->mux_ctx.parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[1].hw); + if (ret) + return ret; + + ctx->mux_ctx.current_parent = 0; + ctx->mux_ctx.hw.init = CLK_HW_INIT_PARENTS("test-mux", top_parents, + &clk_multiple_parents_mux_ops, + 0); + ret = clk_hw_register(NULL, &ctx->mux_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT_HW("test-clock", &ctx->mux_ctx.hw, + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void clk_leaf_mux_set_rate_parent_test_exit(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->mux_ctx.hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[0].hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[1].hw); +} + +/* + * Test that, for a clock that will forward any rate request to its + * parent, the rate request structure returned by __clk_determine_rate + * is sane and will be what we expect. + */ +static void clk_leaf_mux_set_rate_parent_determine_rate(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk_rate_request req; + unsigned long rate; + int ret; + + rate = clk_get_rate(clk); + KUNIT_ASSERT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_hw_init_rate_request(hw, &req, DUMMY_CLOCK_RATE_2); + + ret = __clk_determine_rate(hw, &req); + KUNIT_ASSERT_EQ(test, ret, 0); + + KUNIT_EXPECT_EQ(test, req.rate, DUMMY_CLOCK_RATE_2); + KUNIT_EXPECT_EQ(test, req.best_parent_rate, DUMMY_CLOCK_RATE_2); + KUNIT_EXPECT_PTR_EQ(test, req.best_parent_hw, &ctx->mux_ctx.hw); + + clk_put(clk); +} + +static struct kunit_case clk_leaf_mux_set_rate_parent_test_cases[] = { + KUNIT_CASE(clk_leaf_mux_set_rate_parent_determine_rate), + {} +}; + +/* + * Test suite for a clock whose parent is a mux with multiple parents. + * The leaf clock has CLK_SET_RATE_PARENT, and will forward rate + * requests to the mux, which will then select which parent is the best + * fit for a given rate. + * + * These tests exercise the behaviour of muxes, and the proper selection + * of parents. + */ +static struct kunit_suite clk_leaf_mux_set_rate_parent_test_suite = { + .name = "clk-leaf-mux-set-rate-parent", + .init = clk_leaf_mux_set_rate_parent_test_init, + .exit = clk_leaf_mux_set_rate_parent_test_exit, + .test_cases = clk_leaf_mux_set_rate_parent_test_cases, +}; + +struct clk_mux_notifier_rate_change { + bool done; + unsigned long old_rate; + unsigned long new_rate; + wait_queue_head_t wq; +}; + +struct clk_mux_notifier_ctx { + struct clk_multiple_parent_ctx mux_ctx; + struct clk *clk; + struct notifier_block clk_nb; + struct clk_mux_notifier_rate_change pre_rate_change; + struct clk_mux_notifier_rate_change post_rate_change; +}; + +#define NOTIFIER_TIMEOUT_MS 100 + +static int clk_mux_notifier_callback(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct clk_notifier_data *clk_data = data; + struct clk_mux_notifier_ctx *ctx = container_of(nb, + struct clk_mux_notifier_ctx, + clk_nb); + + if (action & PRE_RATE_CHANGE) { + ctx->pre_rate_change.old_rate = clk_data->old_rate; + ctx->pre_rate_change.new_rate = clk_data->new_rate; + ctx->pre_rate_change.done = true; + wake_up_interruptible(&ctx->pre_rate_change.wq); + } + + if (action & POST_RATE_CHANGE) { + ctx->post_rate_change.old_rate = clk_data->old_rate; + ctx->post_rate_change.new_rate = clk_data->new_rate; + ctx->post_rate_change.done = true; + wake_up_interruptible(&ctx->post_rate_change.wq); + } + + return 0; +} + +static int clk_mux_notifier_test_init(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx; + const char *top_parents[2] = { "parent-0", "parent-1" }; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + ctx->clk_nb.notifier_call = clk_mux_notifier_callback; + init_waitqueue_head(&ctx->pre_rate_change.wq); + init_waitqueue_head(&ctx->post_rate_change.wq); + + ctx->mux_ctx.parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[0].hw); + if (ret) + return ret; + + ctx->mux_ctx.parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[1].hw); + if (ret) + return ret; + + ctx->mux_ctx.current_parent = 0; + ctx->mux_ctx.hw.init = CLK_HW_INIT_PARENTS("test-mux", top_parents, + &clk_multiple_parents_mux_ops, + 0); + ret = clk_hw_register(NULL, &ctx->mux_ctx.hw); + if (ret) + return ret; + + ctx->clk = clk_hw_get_clk(&ctx->mux_ctx.hw, NULL); + ret = clk_notifier_register(ctx->clk, &ctx->clk_nb); + if (ret) + return ret; + + return 0; +} + +static void clk_mux_notifier_test_exit(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx = test->priv; + struct clk *clk = ctx->clk; + + clk_notifier_unregister(clk, &ctx->clk_nb); + clk_put(clk); + + clk_hw_unregister(&ctx->mux_ctx.hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[0].hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[1].hw); +} + +/* + * Test that if the we have a notifier registered on a mux, the core + * will notify us when we switch to another parent, and with the proper + * old and new rates. + */ +static void clk_mux_notifier_set_parent_test(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->mux_ctx.hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *new_parent = clk_hw_get_clk(&ctx->mux_ctx.parents_ctx[1].hw, NULL); + int ret; + + ret = clk_set_parent(clk, new_parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = wait_event_interruptible_timeout(ctx->pre_rate_change.wq, + ctx->pre_rate_change.done, + msecs_to_jiffies(NOTIFIER_TIMEOUT_MS)); + KUNIT_ASSERT_GT(test, ret, 0); + + KUNIT_EXPECT_EQ(test, ctx->pre_rate_change.old_rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_EQ(test, ctx->pre_rate_change.new_rate, DUMMY_CLOCK_RATE_2); + + ret = wait_event_interruptible_timeout(ctx->post_rate_change.wq, + ctx->post_rate_change.done, + msecs_to_jiffies(NOTIFIER_TIMEOUT_MS)); + KUNIT_ASSERT_GT(test, ret, 0); + + KUNIT_EXPECT_EQ(test, ctx->post_rate_change.old_rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_EQ(test, ctx->post_rate_change.new_rate, DUMMY_CLOCK_RATE_2); + + clk_put(new_parent); + clk_put(clk); +} + +static struct kunit_case clk_mux_notifier_test_cases[] = { + KUNIT_CASE(clk_mux_notifier_set_parent_test), + {} +}; + +/* + * Test suite for a mux with multiple parents, and a notifier registered + * on the mux. + * + * These tests exercise the behaviour of notifiers. + */ +static struct kunit_suite clk_mux_notifier_test_suite = { + .name = "clk-mux-notifier", + .init = clk_mux_notifier_test_init, + .exit = clk_mux_notifier_test_exit, + .test_cases = clk_mux_notifier_test_cases, +}; + kunit_test_suites( + &clk_leaf_mux_set_rate_parent_test_suite, &clk_test_suite, + &clk_multiple_parents_mux_test_suite, + &clk_mux_notifier_test_suite, + &clk_orphan_transparent_multiple_parent_mux_test_suite, &clk_orphan_transparent_single_parent_test_suite, + &clk_orphan_two_level_root_last_test_suite, &clk_range_test_suite, &clk_range_maximize_test_suite, - &clk_range_minimize_test_suite + &clk_range_minimize_test_suite, + &clk_single_parent_mux_test_suite, + &clk_uncached_test_suite ); MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/mediatek/clk-mux.c b/drivers/clk/mediatek/clk-mux.c index 4421e4859257..ba1720b9e231 100644 --- a/drivers/clk/mediatek/clk-mux.c +++ b/drivers/clk/mediatek/clk-mux.c @@ -129,9 +129,18 @@ static int mtk_clk_mux_set_parent_setclr_lock(struct clk_hw *hw, u8 index) return 0; } +static int mtk_clk_mux_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + struct mtk_clk_mux *mux = to_mtk_clk_mux(hw); + + return clk_mux_determine_rate_flags(hw, req, mux->data->flags); +} + const struct clk_ops mtk_mux_clr_set_upd_ops = { .get_parent = mtk_clk_mux_get_parent, .set_parent = mtk_clk_mux_set_parent_setclr_lock, + .determine_rate = mtk_clk_mux_determine_rate, }; EXPORT_SYMBOL_GPL(mtk_mux_clr_set_upd_ops); @@ -141,6 +150,7 @@ const struct clk_ops mtk_mux_gate_clr_set_upd_ops = { .is_enabled = mtk_clk_mux_is_enabled, .get_parent = mtk_clk_mux_get_parent, .set_parent = mtk_clk_mux_set_parent_setclr_lock, + .determine_rate = mtk_clk_mux_determine_rate, }; EXPORT_SYMBOL_GPL(mtk_mux_gate_clr_set_upd_ops); diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 609c10f8d0d9..76551534f10d 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -915,6 +915,15 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, req->best_parent_hw = p2; } + clk_hw_get_rate_range(req->best_parent_hw, + &parent_req.min_rate, &parent_req.max_rate); + + if (req->min_rate > parent_req.min_rate) + parent_req.min_rate = req->min_rate; + + if (req->max_rate < parent_req.max_rate) + parent_req.max_rate = req->max_rate; + ret = __clk_determine_rate(req->best_parent_hw, &parent_req); if (ret) return ret; diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c index 657e1154bb9b..a9eb6a9ac445 100644 --- a/drivers/clk/qcom/gcc-msm8660.c +++ b/drivers/clk/qcom/gcc-msm8660.c @@ -2767,17 +2767,6 @@ MODULE_DEVICE_TABLE(of, gcc_msm8660_match_table); static int gcc_msm8660_probe(struct platform_device *pdev) { - int ret; - struct device *dev = &pdev->dev; - - ret = qcom_cc_register_board_clk(dev, "cxo_board", "cxo", 19200000); - if (ret) - return ret; - - ret = qcom_cc_register_board_clk(dev, "pxo_board", "pxo", 27000000); - if (ret) - return ret; - return qcom_cc_probe(pdev, &gcc_msm8660_desc); } diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index 41717ff707f6..ba8791303156 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -8,6 +8,7 @@ #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/clk/spear.h> #include <linux/err.h> #include <linux/io.h> #include <linux/of_platform.h> diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 490701ac9e93..c192a9141b86 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -7,6 +7,7 @@ */ #include <linux/clkdev.h> +#include <linux/clk/spear.h> #include <linux/io.h> #include <linux/spinlock_types.h> #include "clk.h" diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index f7405a58877e..73303458e886 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -1166,6 +1166,7 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA114_CLK_I2S3_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, { TEGRA114_CLK_I2S4_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, { TEGRA114_CLK_VIMCLK_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, + { TEGRA114_CLK_PWM, TEGRA114_CLK_PLL_P, 408000000, 0 }, /* must be the last entry */ { TEGRA114_CLK_CLK_MAX, TEGRA114_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index a9d4efcef2d4..6c46592d794e 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -1330,6 +1330,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = { { TEGRA124_CLK_I2S3_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, { TEGRA124_CLK_I2S4_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, { TEGRA124_CLK_VIMCLK_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, + { TEGRA124_CLK_PWM, TEGRA124_CLK_PLL_P, 408000000, 0 }, /* must be the last entry */ { TEGRA124_CLK_CLK_MAX, TEGRA124_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 8a4514f6d503..422d78247553 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -1044,6 +1044,7 @@ static struct tegra_clk_init_table init_table[] = { { TEGRA20_CLK_GR2D, TEGRA20_CLK_PLL_C, 300000000, 0 }, { TEGRA20_CLK_GR3D, TEGRA20_CLK_PLL_C, 300000000, 0 }, { TEGRA20_CLK_VDE, TEGRA20_CLK_PLL_C, 300000000, 0 }, + { TEGRA20_CLK_PWM, TEGRA20_CLK_PLL_P, 48000000, 0 }, /* must be the last entry */ { TEGRA20_CLK_CLK_MAX, TEGRA20_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 499f999e91e1..a3488aaac3f7 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -3597,6 +3597,7 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA210_CLK_VIMCLK_SYNC, TEGRA210_CLK_CLK_MAX, 24576000, 0 }, { TEGRA210_CLK_HDA, TEGRA210_CLK_PLL_P, 51000000, 0 }, { TEGRA210_CLK_HDA2CODEC_2X, TEGRA210_CLK_PLL_P, 48000000, 0 }, + { TEGRA210_CLK_PWM, TEGRA210_CLK_PLL_P, 48000000, 0 }, /* This MUST be the last entry. */ { TEGRA210_CLK_CLK_MAX, TEGRA210_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c index 168c07d5a5f2..60f1534711f1 100644 --- a/drivers/clk/tegra/clk-tegra30.c +++ b/drivers/clk/tegra/clk-tegra30.c @@ -1237,6 +1237,7 @@ static struct tegra_clk_init_table init_table[] = { { TEGRA30_CLK_VIMCLK_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 }, { TEGRA30_CLK_HDA, TEGRA30_CLK_PLL_P, 102000000, 0 }, { TEGRA30_CLK_HDA2CODEC_2X, TEGRA30_CLK_PLL_P, 48000000, 0 }, + { TEGRA30_CLK_PWM, TEGRA30_CLK_PLL_P, 48000000, 0 }, /* must be the last entry */ { TEGRA30_CLK_CLK_MAX, TEGRA30_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index acf31cc1dbcc..97086fab698e 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -48,7 +48,7 @@ void hmem_register_device(int target_nid, struct resource *r) rc = platform_device_add_data(pdev, &info, sizeof(info)); if (rc < 0) { pr_err("hmem memregion_info allocation failure for %pr\n", &res); - goto out_pdev; + goto out_resource; } rc = platform_device_add_resources(pdev, &res, 1); @@ -66,7 +66,7 @@ void hmem_register_device(int target_nid, struct resource *r) return; out_resource: - put_device(&pdev->dev); + platform_device_put(pdev); out_pdev: memregion_free(id); } diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 9b5e2a5eb0ae..da4438f3188c 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -363,7 +363,7 @@ static void dax_free_inode(struct inode *inode) { struct dax_device *dax_dev = to_dax_dev(inode); if (inode->i_rdev) - ida_simple_remove(&dax_minor_ida, iminor(inode)); + ida_free(&dax_minor_ida, iminor(inode)); kmem_cache_free(dax_cache, dax_dev); } @@ -445,7 +445,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); - minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); + minor = ida_alloc_max(&dax_minor_ida, MINORMASK, GFP_KERNEL); if (minor < 0) return ERR_PTR(-ENOMEM); @@ -459,7 +459,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) return dax_dev; err_dev: - ida_simple_remove(&dax_minor_ida, minor); + ida_free(&dax_minor_ida, minor); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 17562cf1fe97..456602d373b7 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -473,7 +473,7 @@ config EDAC_ALTERA_SDMMC config EDAC_SIFIVE bool "Sifive platform EDAC driver" - depends on EDAC=y && SIFIVE_L2 + depends on EDAC=y && SIFIVE_CCACHE help Support for error detection and correction on the SiFive SoCs. diff --git a/drivers/edac/sifive_edac.c b/drivers/edac/sifive_edac.c index ee800aec7d47..b844e2626fd5 100644 --- a/drivers/edac/sifive_edac.c +++ b/drivers/edac/sifive_edac.c @@ -2,7 +2,7 @@ /* * SiFive Platform EDAC Driver * - * Copyright (C) 2018-2019 SiFive, Inc. + * Copyright (C) 2018-2022 SiFive, Inc. * * This driver is partially based on octeon_edac-pc.c * @@ -10,7 +10,7 @@ #include <linux/edac.h> #include <linux/platform_device.h> #include "edac_module.h" -#include <soc/sifive/sifive_l2_cache.h> +#include <soc/sifive/sifive_ccache.h> #define DRVNAME "sifive_edac" @@ -32,9 +32,9 @@ int ecc_err_event(struct notifier_block *this, unsigned long event, void *ptr) p = container_of(this, struct sifive_edac_priv, notifier); - if (event == SIFIVE_L2_ERR_TYPE_UE) + if (event == SIFIVE_CCACHE_ERR_TYPE_UE) edac_device_handle_ue(p->dci, 0, 0, msg); - else if (event == SIFIVE_L2_ERR_TYPE_CE) + else if (event == SIFIVE_CCACHE_ERR_TYPE_CE) edac_device_handle_ce(p->dci, 0, 0, msg); return NOTIFY_OK; @@ -67,7 +67,7 @@ static int ecc_register(struct platform_device *pdev) goto err; } - register_sifive_l2_error_notifier(&p->notifier); + register_sifive_ccache_error_notifier(&p->notifier); return 0; @@ -81,7 +81,7 @@ static int ecc_unregister(struct platform_device *pdev) { struct sifive_edac_priv *p = platform_get_drvdata(pdev); - unregister_sifive_l2_error_notifier(&p->notifier); + unregister_sifive_ccache_error_notifier(&p->notifier); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(p->dci); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index c70c026c9a93..2797029bd500 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - lock_page(page); + zone_device_page_init(page); } static void @@ -410,7 +410,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t npages = (end - start) >> PAGE_SHIFT; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; dma_addr_t *scratch; void *buf; @@ -666,7 +666,7 @@ out_oom: static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; @@ -674,7 +674,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, unsigned long cpages = 0; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -697,6 +697,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.src = buf; migrate.dst = migrate.src + npages; + migrate.fault_page = fault_page; scratch = (dma_addr_t *)(migrate.dst + npages); kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid, @@ -764,7 +765,7 @@ out: * 0 - OK, otherwise error code */ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct amdgpu_device *adev; struct vm_area_struct *vma; @@ -805,7 +806,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, } next = min(vma->vm_end, end); - r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger); + r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger, + fault_page); if (r < 0) { pr_debug("failed %ld to migrate prange %p\n", r, prange); break; @@ -849,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc); do { - r = svm_migrate_vram_to_ram(prange, mm, trigger); + r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL); if (r) return r; } while (prange->actual_loc && --retries); @@ -950,7 +952,8 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) } r = svm_migrate_vram_to_ram(prange, vmf->vma->vm_mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + vmf->page); if (r) pr_debug("failed %d migrate svms 0x%p range 0x%p [0x%lx 0x%lx]\n", r, prange->svms, prange, prange->start, prange->last); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index b3f0754b32fa..a5d7e6d22264 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR { int svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc, struct mm_struct *mm, uint32_t trigger); int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger); + uint32_t trigger, struct page *fault_page); unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f5913ba22174..64fdf63093a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2913,13 +2913,15 @@ retry_write_locked: */ if (prange->actual_loc) r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); else r = 0; } } else { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); } if (r) { pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n", @@ -3278,7 +3280,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, return 0; if (!best_loc) { - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); + r = svm_migrate_vram_to_ram(prange, mm, + KFD_MIGRATE_TRIGGER_PREFETCH, NULL); *migrated = !r; return r; } @@ -3339,7 +3342,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mutex_lock(&prange->migrate_mutex); do { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_TTM_EVICTION); + KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL); } while (!r && prange->actual_loc && --retries); if (!r && prange->actual_loc) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f6a9e8fdd87d..c053cb79cd06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8310,8 +8310,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) crtc, dm_new_crtc_state, cur_crc_src)) DRM_DEBUG_DRIVER("Failed to configure crc source"); } -#endif } +#endif } for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 16356611b5b9..5fe209107246 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, - struct vm_fault *vmf, struct migrate_vma *args, - dma_addr_t *dma_addr) +static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage, + struct page *dpage, dma_addr_t *dma_addr) { struct device *dev = drm->dev->dev; - struct page *dpage, *spage; - struct nouveau_svmm *svmm; - - spage = migrate_pfn_to_page(args->src[0]); - if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) - return 0; - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); - if (!dpage) - return VM_FAULT_SIGBUS; lock_page(dpage); *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) - goto error_free_page; + return -EIO; - svmm = spage->zone_device_data; - mutex_lock(&svmm->mutex); - nouveau_svmm_invalidate(svmm, args->start, args->end); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, - NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) - goto error_dma_unmap; - mutex_unlock(&svmm->mutex); + NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) { + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + return -EIO; + } - args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; - -error_dma_unmap: - mutex_unlock(&svmm->mutex); - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); -error_free_page: - __free_page(dpage); - return VM_FAULT_SIGBUS; } static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) @@ -184,9 +164,11 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) struct nouveau_drm *drm = page_to_drm(vmf->page); struct nouveau_dmem *dmem = drm->dmem; struct nouveau_fence *fence; + struct nouveau_svmm *svmm; + struct page *spage, *dpage; unsigned long src = 0, dst = 0; dma_addr_t dma_addr = 0; - vm_fault_t ret; + vm_fault_t ret = 0; struct migrate_vma args = { .vma = vmf->vma, .start = vmf->address, @@ -207,9 +189,25 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!args.cpages) return 0; - ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); - if (ret || dst == 0) + spage = migrate_pfn_to_page(src); + if (!spage || !(src & MIGRATE_PFN_MIGRATE)) + goto done; + + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (!dpage) + goto done; + + dst = migrate_pfn(page_to_pfn(dpage)); + + svmm = spage->zone_device_data; + mutex_lock(&svmm->mutex); + nouveau_svmm_invalidate(svmm, args.start, args.end); + ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr); + mutex_unlock(&svmm->mutex); + if (ret) { + ret = VM_FAULT_SIGBUS; goto done; + } nouveau_fence_new(dmem->migrate.chan, false, &fence); migrate_vma_pages(&args); @@ -326,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - lock_page(page); + zone_device_page_init(page); return page; } @@ -369,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm) mutex_unlock(&drm->dmem->mutex); } +/* + * Evict all pages mapping a chunk. + */ +static void +nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) +{ + unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT; + unsigned long *src_pfns, *dst_pfns; + dma_addr_t *dma_addrs; + struct nouveau_fence *fence; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + + migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, + npages); + + for (i = 0; i < npages; i++) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + struct page *dpage; + + /* + * _GFP_NOFAIL because the GPU is going away and there + * is nothing sensible we can do if we can't copy the + * data back. + */ + dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + nouveau_dmem_copy_one(chunk->drm, + migrate_pfn_to_page(src_pfns[i]), dpage, + &dma_addrs[i]); + } + } + + nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence); + migrate_device_pages(src_pfns, dst_pfns, npages); + nouveau_dmem_fence_done(&fence); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); + for (i = 0; i < npages; i++) + dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); + kfree(dma_addrs); +} + void nouveau_dmem_fini(struct nouveau_drm *drm) { @@ -380,8 +424,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm) mutex_lock(&drm->dmem->mutex); list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) { + nouveau_dmem_evict_chunk(chunk); nouveau_bo_unpin(chunk->bo); nouveau_bo_ref(NULL, &chunk->bo); + WARN_ON(chunk->callocated); list_del(&chunk->list); memunmap_pages(&chunk->pagemap); release_mem_region(chunk->pagemap.range.start, diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 7850287dfe7a..351c81a929a6 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1379,6 +1379,9 @@ static int i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, i3c_bus_set_addr_slot_status(&master->bus, dev->info.dyn_addr, I3C_ADDR_SLOT_I3C_DEV); + if (old_dyn_addr) + i3c_bus_set_addr_slot_status(&master->bus, old_dyn_addr, + I3C_ADDR_SLOT_FREE); } if (master->ops->reattach_i3c_dev) { @@ -1908,10 +1911,6 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, i3c_master_free_i3c_dev(olddev); } - ret = i3c_master_reattach_i3c_dev(newdev, old_dyn_addr); - if (ret) - goto err_detach_dev; - /* * Depending on our previous state, the expected dynamic address might * differ: diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c index 00aecd67e348..a7e052c1db53 100644 --- a/drivers/leds/leds-pca963x.c +++ b/drivers/leds/leds-pca963x.c @@ -101,6 +101,7 @@ struct pca963x_led { struct pca963x *chip; struct led_classdev led_cdev; int led_num; /* 0 .. 15 potentially */ + bool blinking; u8 gdc; u8 gfrq; }; @@ -129,12 +130,21 @@ static int pca963x_brightness(struct pca963x_led *led, switch (brightness) { case LED_FULL: - val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + if (led->blinking) { + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + ret = i2c_smbus_write_byte_data(client, + PCA963X_PWM_BASE + + led->led_num, + LED_FULL); + } else { + val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + } ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; case LED_OFF: val = ledout & ~mask; ret = i2c_smbus_write_byte_data(client, ledout_addr, val); + led->blinking = false; break; default: ret = i2c_smbus_write_byte_data(client, @@ -144,7 +154,11 @@ static int pca963x_brightness(struct pca963x_led *led, if (ret < 0) return ret; - val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + if (led->blinking) + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + else + val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; } @@ -181,6 +195,7 @@ static void pca963x_blink(struct pca963x_led *led) } mutex_unlock(&led->chip->mutex); + led->blinking = true; } static int pca963x_power_state(struct pca963x_led *led) @@ -275,6 +290,8 @@ static int pca963x_blink_set(struct led_classdev *led_cdev, led->gfrq = gfrq; pca963x_blink(led); + led->led_cdev.brightness = LED_FULL; + pca963x_led_set(led_cdev, LED_FULL); *delay_on = time_on; *delay_off = time_off; @@ -337,6 +354,7 @@ static int pca963x_register_leds(struct i2c_client *client, led->led_cdev.brightness_set_blocking = pca963x_led_set; if (hw_blink) led->led_cdev.blink_set = pca963x_blink_set; + led->blinking = false; init_data.fwnode = child; /* for backwards compatibility */ diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 4cf67a2a0d04..75eaecc8639f 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -409,7 +409,7 @@ int ubiblock_create(struct ubi_volume_info *vi) ret = blk_mq_alloc_tag_set(&dev->tag_set); if (ret) { dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed"); - goto out_free_dev;; + goto out_free_dev; } @@ -441,7 +441,7 @@ int ubiblock_create(struct ubi_volume_info *vi) /* * Create one workqueue per volume (per registered block device). - * Rembember workqueues are cheap, they're not threads. + * Remember workqueues are cheap, they're not threads. */ dev->wq = alloc_workqueue("%s", 0, 0, gd->disk_name); if (!dev->wq) { diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index a32050fecabf..a901f8edfa41 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -807,6 +807,7 @@ static int autoresize(struct ubi_device *ubi, int vol_id) * @ubi_num: number to assign to the new UBI device * @vid_hdr_offset: VID header offset * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs + * @disable_fm: whether disable fastmap * * This function attaches MTD device @mtd_dev to UBI and assign @ubi_num number * to the newly created UBI device, unless @ubi_num is %UBI_DEV_NUM_AUTO, in @@ -814,11 +815,15 @@ static int autoresize(struct ubi_device *ubi, int vol_id) * automatically. Returns the new UBI device number in case of success and a * negative error code in case of failure. * + * If @disable_fm is true, ubi doesn't create new fastmap even the module param + * 'fm_autoconvert' is set, and existed old fastmap will be destroyed after + * doing full scanning. + * * Note, the invocations of this function has to be serialized by the * @ubi_devices_mutex. */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, - int vid_hdr_offset, int max_beb_per1024) + int vid_hdr_offset, int max_beb_per1024, bool disable_fm) { struct ubi_device *ubi; int i, err; @@ -921,7 +926,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, UBI_FM_MIN_POOL_SIZE); ubi->fm_wl_pool.max_size = ubi->fm_pool.max_size / 2; - ubi->fm_disabled = !fm_autoconvert; + ubi->fm_disabled = (!fm_autoconvert || disable_fm) ? 1 : 0; if (fm_debug) ubi_enable_dbg_chk_fastmap(ubi); @@ -962,7 +967,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, if (!ubi->fm_buf) goto out_free; #endif - err = ubi_attach(ubi, 0); + err = ubi_attach(ubi, disable_fm ? 1 : 0); if (err) { ubi_err(ubi, "failed to attach mtd%d, error %d", mtd->index, err); @@ -1242,7 +1247,8 @@ static int __init ubi_init(void) mutex_lock(&ubi_devices_mutex); err = ubi_attach_mtd_dev(mtd, p->ubi_num, - p->vid_hdr_offs, p->max_beb_per1024); + p->vid_hdr_offs, p->max_beb_per1024, + false); mutex_unlock(&ubi_devices_mutex); if (err < 0) { pr_err("UBI error: cannot attach mtd%d\n", diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index cc9a28cf9d82..f43430b9c1e6 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -672,7 +672,7 @@ static int verify_rsvol_req(const struct ubi_device *ubi, * @req: volumes re-name request * * This is a helper function for the volume re-name IOCTL which validates the - * the request, opens the volume and calls corresponding volumes management + * request, opens the volume and calls corresponding volumes management * function. Returns zero in case of success and a negative error code in case * of failure. */ @@ -1041,7 +1041,7 @@ static long ctrl_cdev_ioctl(struct file *file, unsigned int cmd, */ mutex_lock(&ubi_devices_mutex); err = ubi_attach_mtd_dev(mtd, req.ubi_num, req.vid_hdr_offset, - req.max_beb_per1024); + req.max_beb_per1024, !!req.disable_fm); mutex_unlock(&ubi_devices_mutex); if (err < 0) put_mtd_device(mtd); diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index ccc5979642b7..09c408c45a62 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -377,7 +377,7 @@ static int leb_write_lock(struct ubi_device *ubi, int vol_id, int lnum) * * This function locks a logical eraseblock for writing if there is no * contention and does nothing if there is contention. Returns %0 in case of - * success, %1 in case of contention, and and a negative error code in case of + * success, %1 in case of contention, and a negative error code in case of * failure. */ static int leb_write_trylock(struct ubi_device *ubi, int vol_id, int lnum) diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 6e95c4b1473e..ca2d9efe62c3 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -20,8 +20,7 @@ static inline unsigned long *init_seen(struct ubi_device *ubi) if (!ubi_dbg_chk_fastmap(ubi)) return NULL; - ret = kcalloc(BITS_TO_LONGS(ubi->peb_count), sizeof(unsigned long), - GFP_KERNEL); + ret = bitmap_zalloc(ubi->peb_count, GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); @@ -34,7 +33,7 @@ static inline unsigned long *init_seen(struct ubi_device *ubi) */ static inline void free_seen(unsigned long *seen) { - kfree(seen); + bitmap_free(seen); } /** @@ -1108,8 +1107,7 @@ int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count) if (!ubi->fast_attach) return 0; - vol->checkmap = kcalloc(BITS_TO_LONGS(leb_count), sizeof(unsigned long), - GFP_KERNEL); + vol->checkmap = bitmap_zalloc(leb_count, GFP_KERNEL); if (!vol->checkmap) return -ENOMEM; @@ -1118,7 +1116,7 @@ int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count) void ubi_fastmap_destroy_checkmap(struct ubi_volume *vol) { - kfree(vol->checkmap); + bitmap_free(vol->checkmap); } /** diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 8a7306cc1947..01b644861253 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -1147,7 +1147,7 @@ fail: * @ubi: UBI device description object * @pnum: the physical eraseblock number to check * - * This function returns zero if the erase counter header is all right and and + * This function returns zero if the erase counter header is all right and * a negative error code if not or if an error occurred. */ static int self_check_peb_ec_hdr(const struct ubi_device *ubi, int pnum) diff --git a/drivers/mtd/ubi/ubi-media.h b/drivers/mtd/ubi/ubi-media.h index 386db0598e95..2c9cd3b6434f 100644 --- a/drivers/mtd/ubi/ubi-media.h +++ b/drivers/mtd/ubi/ubi-media.h @@ -131,7 +131,7 @@ enum { * is changed radically. This field is duplicated in the volume identifier * header. * - * The @vid_hdr_offset and @data_offset fields contain the offset of the the + * The @vid_hdr_offset and @data_offset fields contain the offset of the * volume identifier header and user data, relative to the beginning of the * physical eraseblock. These values have to be the same for all physical * eraseblocks. diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 078112e23dfd..c8f1bd4fa100 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -86,7 +86,7 @@ void ubi_err(const struct ubi_device *ubi, const char *fmt, ...); * Error codes returned by the I/O sub-system. * * UBI_IO_FF: the read region of flash contains only 0xFFs - * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also also there was a data + * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also there was a data * integrity error reported by the MTD driver * (uncorrectable ECC error in case of NAND) * UBI_IO_BAD_HDR: the EC or VID header is corrupted (bad magic or CRC) @@ -281,7 +281,7 @@ struct ubi_eba_leb_desc { /** * struct ubi_volume - UBI volume description data structure. - * @dev: device object to make use of the the Linux device model + * @dev: device object to make use of the Linux device model * @cdev: character device object to create character device * @ubi: reference to the UBI device description object * @vol_id: volume ID @@ -439,7 +439,7 @@ struct ubi_debug_info { /** * struct ubi_device - UBI device description structure - * @dev: UBI device object to use the the Linux device model + * @dev: UBI device object to use the Linux device model * @cdev: character device object to create character device * @ubi_num: UBI device number * @ubi_name: UBI device name @@ -937,7 +937,8 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum, /* build.c */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, - int vid_hdr_offset, int max_beb_per1024); + int vid_hdr_offset, int max_beb_per1024, + bool disable_fm); int ubi_detach_mtd_dev(int ubi_num, int anyway); struct ubi_device *ubi_get_device(int ubi_num); void ubi_put_device(struct ubi_device *ubi); diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 6ea95ade4ca6..8fcc0bdf0635 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -623,7 +623,7 @@ void ubi_free_volume(struct ubi_device *ubi, struct ubi_volume *vol) * @ubi: UBI device description object * @vol_id: volume ID * - * Returns zero if volume is all right and a a negative error code if not. + * Returns zero if volume is all right and a negative error code if not. */ static int self_check_volume(struct ubi_device *ubi, int vol_id) { @@ -776,7 +776,7 @@ fail: * self_check_volumes - check information about all volumes. * @ubi: UBI device description object * - * Returns zero if volumes are all right and a a negative error code if not. + * Returns zero if volumes are all right and a negative error code if not. */ static int self_check_volumes(struct ubi_device *ubi) { diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 55bae06cf408..68eb0f21b3fe 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -376,7 +376,7 @@ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, * refill_wl_user_pool(). * @ubi: UBI device description object * - * This function returns a a wear leveling entry in case of success and + * This function returns a wear leveling entry in case of success and * NULL in case of failure. */ static struct ubi_wl_entry *wl_get_wle(struct ubi_device *ubi) @@ -429,7 +429,7 @@ static int prot_queue_del(struct ubi_device *ubi, int pnum) /** * sync_erase - synchronously erase a physical eraseblock. * @ubi: UBI device description object - * @e: the the physical eraseblock to erase + * @e: the physical eraseblock to erase * @torture: if the physical eraseblock has to be tortured * * This function returns zero in case of success and a negative error code in @@ -1016,7 +1016,7 @@ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) /* * If the ubi->scrub tree is not empty, scrubbing is needed, and the - * the WL worker has to be scheduled anyway. + * WL worker has to be scheduled anyway. */ if (!ubi->scrub.rb_node) { #ifdef CONFIG_MTD_UBI_FASTMAP @@ -1464,7 +1464,7 @@ static bool scrub_possible(struct ubi_device *ubi, struct ubi_wl_entry *e) * ubi_bitflip_check - Check an eraseblock for bitflips and scrub it if needed. * @ubi: UBI device description object * @pnum: the physical eraseblock to schedule - * @force: dont't read the block, assume bitflips happened and take action. + * @force: don't read the block, assume bitflips happened and take action. * * This function reads the given eraseblock and checks if bitflips occured. * In case of bitflips, the eraseblock is scheduled for scrubbing. diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index bbe5099c836d..c60ec0b373c5 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -170,15 +170,12 @@ EXPORT_SYMBOL(nvdimm_namespace_disk_name); const uuid_t *nd_dev_to_uuid(struct device *dev) { - if (!dev) - return &uuid_null; - - if (is_namespace_pmem(dev)) { + if (dev && is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); return nspm->uuid; - } else - return &uuid_null; + } + return &uuid_null; } EXPORT_SYMBOL(nd_dev_to_uuid); @@ -388,7 +385,7 @@ static resource_size_t init_dpa_allocation(struct nd_label_id *label_id, * * BLK-space is valid as long as it does not precede a PMEM * allocation in a given region. PMEM-space must be contiguous - * and adjacent to an existing existing allocation (if one + * and adjacent to an existing allocation (if one * exists). If reserving PMEM any space is valid. */ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, @@ -839,7 +836,6 @@ static ssize_t size_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); unsigned long long val; - uuid_t **uuid = NULL; int rc; rc = kstrtoull(buf, 0, &val); @@ -853,16 +849,12 @@ static ssize_t size_store(struct device *dev, if (rc >= 0) rc = nd_namespace_label_update(nd_region, dev); - if (is_namespace_pmem(dev)) { + /* setting size zero == 'delete namespace' */ + if (rc == 0 && val == 0 && is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - uuid = &nspm->uuid; - } - - if (rc == 0 && val == 0 && uuid) { - /* setting size zero == 'delete namespace' */ - kfree(*uuid); - *uuid = NULL; + kfree(nspm->uuid); + nspm->uuid = NULL; } dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 473a71bbd9c9..e0875d369762 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -509,16 +509,13 @@ static ssize_t align_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev); unsigned long val, dpa; - u32 remainder; + u32 mappings, remainder; int rc; rc = kstrtoul(buf, 0, &val); if (rc) return rc; - if (!nd_region->ndr_mappings) - return -ENXIO; - /* * Ensure space-align is evenly divisible by the region * interleave-width because the kernel typically has no facility @@ -526,7 +523,8 @@ static ssize_t align_store(struct device *dev, * contribute to the tail capacity in system-physical-address * space for the namespace. */ - dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder); + mappings = max_t(u32, 1, nd_region->ndr_mappings); + dpa = div_u64_rem(val, mappings, &remainder); if (!is_power_of_2(dpa) || dpa < PAGE_SIZE || val > region_size(nd_region) || remainder) return -EINVAL; @@ -1096,7 +1094,7 @@ int nvdimm_flush(struct nd_region *nd_region, struct bio *bio) return rc; } /** - * nvdimm_flush - flush any posted write queues between the cpu and pmem media + * generic_nvdimm_flush() - flush any posted write queues between the cpu and pmem media * @nd_region: interleaved pmem region */ int generic_nvdimm_flush(struct nd_region *nd_region) diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index b5aa55c61461..8aefb60c42ff 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -408,7 +408,7 @@ static int security_overwrite(struct nvdimm *nvdimm, unsigned int keyid) return rc; } -void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) +static void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) { struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev); int rc; diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c index f54a6f450391..f0cb31198a8f 100644 --- a/drivers/parisc/eisa_enumerator.c +++ b/drivers/parisc/eisa_enumerator.c @@ -393,7 +393,7 @@ static int parse_slot_config(int slot, } if (p0 + function_len < pos) { - printk(KERN_ERR "eisa_enumerator: function %d length mis-match " + printk(KERN_ERR "eisa_enumerator: function %d length mismatch " "got %d, expected %d\n", num_func, pos-p0, function_len); res=-1; @@ -407,13 +407,13 @@ static int parse_slot_config(int slot, } if (pos != es->config_data_length) { - printk(KERN_ERR "eisa_enumerator: config data length mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: config data length mismatch got %d, expected %d\n", pos, es->config_data_length); res=-1; } if (num_func != es->num_functions) { - printk(KERN_ERR "eisa_enumerator: number of functions mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: number of functions mismatch got %d, expected %d\n", num_func, es->num_functions); res=-2; } @@ -451,7 +451,7 @@ static int init_slot(int slot, struct eeprom_eisa_slot_info *es) } if (es->eisa_slot_id != id) { print_eisa_id(id_string, id); - printk(KERN_ERR "EISA slot %d id mis-match: got %s", + printk(KERN_ERR "EISA slot %d id mismatch: got %s", slot, id_string); print_eisa_id(id_string, es->eisa_slot_id); diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index dc6a30ee6edf..b4096598dbcb 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1768,10 +1768,7 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res, } res->end = res->start + new_size - 1; - - /* If the resource is part of the add_list remove it now */ - if (add_list) - remove_from_list(add_list, res); + remove_from_list(add_list, res); } static void pci_bus_distribute_available_resources(struct pci_bus *bus, @@ -1926,8 +1923,6 @@ static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, if (!bridge->is_hotplug_bridge) return; - pci_dbg(bridge, "distributing available resources\n"); - /* Take the initial extra resources from the hotplug port */ available_io = bridge->resource[PCI_BRIDGE_IO_WINDOW]; available_mmio = bridge->resource[PCI_BRIDGE_MEM_WINDOW]; @@ -1939,59 +1934,6 @@ static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, available_mmio_pref); } -static bool pci_bridge_resources_not_assigned(struct pci_dev *dev) -{ - const struct resource *r; - - /* - * Check the child device's resources and if they are not yet - * assigned it means we are configuring them (not the boot - * firmware) so we should be able to extend the upstream - * bridge's (that's the hotplug downstream PCIe port) resources - * in the same way we do with the normal hotplug case. - */ - r = &dev->resource[PCI_BRIDGE_IO_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - r = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - r = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - - return true; -} - -static void pci_root_bus_distribute_available_resources(struct pci_bus *bus, - struct list_head *add_list) -{ - struct pci_dev *dev, *bridge = bus->self; - - for_each_pci_bridge(dev, bus) { - struct pci_bus *b; - - b = dev->subordinate; - if (!b) - continue; - - /* - * Need to check "bridge" here too because it is NULL - * in case of root bus. - */ - if (bridge && pci_bridge_resources_not_assigned(dev)) { - pci_bridge_distribute_available_resources(bridge, add_list); - /* - * There is only PCIe upstream port on the bus - * so we don't need to go futher. - */ - return; - } - - pci_root_bus_distribute_available_resources(b, add_list); - } -} - /* * First try will not touch PCI bridge res. * Second and later try will clear small leaf bridge res. @@ -2031,8 +1973,6 @@ again: */ __pci_bus_size_bridges(bus, add_list); - pci_root_bus_distribute_available_resources(bus, add_list); - /* Depth last, allocate resources and update the hardware. */ __pci_bus_assign_resources(bus, add_list, &fail_head); if (add_list) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 44c07ea487f4..341010f20b77 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -185,7 +185,7 @@ config APPLE_M1_CPU_PMU config ALIBABA_UNCORE_DRW_PMU tristate "Alibaba T-Head Yitian 710 DDR Sub-system Driveway PMU driver" - depends on ARM64 || COMPILE_TEST + depends on (ARM64 && ACPI) || COMPILE_TEST help Support for Driveway PMU events monitoring on Yitian 710 DDR Sub-system. diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c index 82729b874f09..a7689fecb49d 100644 --- a/drivers/perf/alibaba_uncore_drw_pmu.c +++ b/drivers/perf/alibaba_uncore_drw_pmu.c @@ -658,8 +658,8 @@ static int ali_drw_pmu_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); drw_pmu->cfg_base = devm_ioremap_resource(&pdev->dev, res); - if (!drw_pmu->cfg_base) - return -ENOMEM; + if (IS_ERR(drw_pmu->cfg_base)) + return PTR_ERR(drw_pmu->cfg_base); name = devm_kasprintf(drw_pmu->dev, GFP_KERNEL, "ali_drw_%llx", (u64) (res->start >> ALI_DRW_PMU_PA_SHIFT)); diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 15e5a47be7d5..3852c18362f5 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -652,8 +652,11 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) struct riscv_pmu *pmu = hlist_entry_safe(node, struct riscv_pmu, node); struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); - /* Enable the access for TIME csr only from the user mode now */ - csr_write(CSR_SCOUNTEREN, 0x2); + /* + * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace, + * as is necessary to maintain uABI compatibility. + */ + csr_write(CSR_SCOUNTEREN, 0x7); /* Stop all the counters so that they can be enabled from perf */ pmu_sbi_stop_all(pmu); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index b8de25118ad0..bb63edb507da 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -423,6 +423,7 @@ config RTC_DRV_ISL1208 config RTC_DRV_ISL12022 tristate "Intersil ISL12022" + select REGMAP_I2C help If you say yes here you get support for the Intersil ISL12022 RTC chip. diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index bdb1df843c78..610413b4e9ca 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1352,10 +1352,10 @@ static void cmos_check_acpi_rtc_status(struct device *dev, static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { - cmos_wake_setup(&pnp->dev); + int irq, ret; if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { - unsigned int irq = 0; + irq = 0; #ifdef CONFIG_X86 /* Some machines contain a PNP entry for the RTC, but * don't define the IRQ. It should always be safe to @@ -1364,13 +1364,17 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) if (nr_legacy_irqs()) irq = RTC_IRQ; #endif - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); } else { - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), - pnp_irq(pnp, 0)); + irq = pnp_irq(pnp, 0); } + + ret = cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); + if (ret) + return ret; + + cmos_wake_setup(&pnp->dev); + + return 0; } static void cmos_pnp_remove(struct pnp_dev *pnp) @@ -1454,10 +1458,9 @@ static inline void cmos_of_init(struct platform_device *pdev) {} static int __init cmos_platform_probe(struct platform_device *pdev) { struct resource *resource; - int irq; + int irq, ret; cmos_of_init(pdev); - cmos_wake_setup(&pdev->dev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -1467,7 +1470,13 @@ static int __init cmos_platform_probe(struct platform_device *pdev) if (irq < 0) irq = -1; - return cmos_do_probe(&pdev->dev, resource, irq); + ret = cmos_do_probe(&pdev->dev, resource, irq); + if (ret) + return ret; + + cmos_wake_setup(&pdev->dev); + + return 0; } static int cmos_platform_remove(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index a24331ba8a5f..5db9c737c022 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -132,7 +132,7 @@ ds1685_rtc_bin2bcd(struct ds1685_priv *rtc, u8 val, u8 bin_mask, u8 bcd_mask) } /** - * s1685_rtc_check_mday - check validity of the day of month. + * ds1685_rtc_check_mday - check validity of the day of month. * @rtc: pointer to the ds1685 rtc structure. * @mday: day of month. * diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c index c2717bb52b2b..c828bc8e05b9 100644 --- a/drivers/rtc/rtc-gamecube.c +++ b/drivers/rtc/rtc-gamecube.c @@ -265,18 +265,17 @@ static int gamecube_rtc_read_offset_from_sram(struct priv *d) * SRAM address as on previous consoles. */ ret = regmap_read(d->regmap, RTC_SRAM_BIAS, &d->rtc_bias); - if (ret) { - pr_err("failed to get the RTC bias\n"); - iounmap(hw_srnprot); - return -1; - } /* Reset SRAM access to how it was before, our job here is done. */ if (old != 0x7bf) iowrite32be(old, hw_srnprot); + iounmap(hw_srnprot); - return 0; + if (ret) + pr_err("failed to get the RTC bias\n"); + + return ret; } static const struct regmap_range rtc_rd_ranges[] = { diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 79461ded1a48..ca677c4265e6 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -16,6 +16,7 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/regmap.h> /* ISL register offsets */ #define ISL12022_REG_SC 0x00 @@ -42,83 +43,32 @@ static struct i2c_driver isl12022_driver; struct isl12022 { struct rtc_device *rtc; - - bool write_enabled; /* true if write enable is set */ + struct regmap *regmap; }; - -static int isl12022_read_regs(struct i2c_client *client, uint8_t reg, - uint8_t *data, size_t n) -{ - struct i2c_msg msgs[] = { - { - .addr = client->addr, - .flags = 0, - .len = 1, - .buf = data - }, /* setup read ptr */ - { - .addr = client->addr, - .flags = I2C_M_RD, - .len = n, - .buf = data - } - }; - - int ret; - - data[0] = reg; - ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (ret != ARRAY_SIZE(msgs)) { - dev_err(&client->dev, "%s: read error, ret=%d\n", - __func__, ret); - return -EIO; - } - - return 0; -} - - -static int isl12022_write_reg(struct i2c_client *client, - uint8_t reg, uint8_t val) -{ - uint8_t data[2] = { reg, val }; - int err; - - err = i2c_master_send(client, data, sizeof(data)); - if (err != sizeof(data)) { - dev_err(&client->dev, - "%s: err=%d addr=%02x, data=%02x\n", - __func__, err, data[0], data[1]); - return -EIO; - } - - return 0; -} - - /* * In the routines that deal directly with the isl12022 hardware, we use * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch. */ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); + struct isl12022 *isl12022 = dev_get_drvdata(dev); + struct regmap *regmap = isl12022->regmap; uint8_t buf[ISL12022_REG_INT + 1]; int ret; - ret = isl12022_read_regs(client, ISL12022_REG_SC, buf, sizeof(buf)); + ret = regmap_bulk_read(regmap, ISL12022_REG_SC, buf, sizeof(buf)); if (ret) return ret; if (buf[ISL12022_REG_SR] & (ISL12022_SR_LBAT85 | ISL12022_SR_LBAT75)) { - dev_warn(&client->dev, + dev_warn(dev, "voltage dropped below %u%%, " "date and time is not reliable.\n", buf[ISL12022_REG_SR] & ISL12022_SR_LBAT85 ? 85 : 75); } - dev_dbg(&client->dev, + dev_dbg(dev, "%s: raw data is sec=%02x, min=%02x, hr=%02x, " "mday=%02x, mon=%02x, year=%02x, wday=%02x, " "sr=%02x, int=%02x", @@ -141,65 +91,25 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) tm->tm_mon = bcd2bin(buf[ISL12022_REG_MO] & 0x1F) - 1; tm->tm_year = bcd2bin(buf[ISL12022_REG_YR]) + 100; - dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, " - "mday=%d, mon=%d, year=%d, wday=%d\n", - __func__, - tm->tm_sec, tm->tm_min, tm->tm_hour, - tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); + dev_dbg(dev, "%s: %ptR\n", __func__, tm); return 0; } static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); - struct isl12022 *isl12022 = i2c_get_clientdata(client); - size_t i; + struct isl12022 *isl12022 = dev_get_drvdata(dev); + struct regmap *regmap = isl12022->regmap; int ret; uint8_t buf[ISL12022_REG_DW + 1]; - dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, " - "mday=%d, mon=%d, year=%d, wday=%d\n", - __func__, - tm->tm_sec, tm->tm_min, tm->tm_hour, - tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); - - if (!isl12022->write_enabled) { - - ret = isl12022_read_regs(client, ISL12022_REG_INT, buf, 1); - if (ret) - return ret; - - /* Check if WRTC (write rtc enable) is set factory default is - * 0 (not set) */ - if (!(buf[0] & ISL12022_INT_WRTC)) { - dev_info(&client->dev, - "init write enable and 24 hour format\n"); - - /* Set the write enable bit. */ - ret = isl12022_write_reg(client, - ISL12022_REG_INT, - buf[0] | ISL12022_INT_WRTC); - if (ret) - return ret; - - /* Write to any RTC register to start RTC, we use the - * HR register, setting the MIL bit to use the 24 hour - * format. */ - ret = isl12022_read_regs(client, ISL12022_REG_HR, - buf, 1); - if (ret) - return ret; - - ret = isl12022_write_reg(client, - ISL12022_REG_HR, - buf[0] | ISL12022_HR_MIL); - if (ret) - return ret; - } - - isl12022->write_enabled = true; - } + dev_dbg(dev, "%s: %ptR\n", __func__, tm); + + /* Ensure the write enable bit is set. */ + ret = regmap_update_bits(regmap, ISL12022_REG_INT, + ISL12022_INT_WRTC, ISL12022_INT_WRTC); + if (ret) + return ret; /* hours, minutes and seconds */ buf[ISL12022_REG_SC] = bin2bcd(tm->tm_sec); @@ -216,15 +126,8 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) buf[ISL12022_REG_DW] = tm->tm_wday & 0x07; - /* write register's data */ - for (i = 0; i < ARRAY_SIZE(buf); i++) { - ret = isl12022_write_reg(client, ISL12022_REG_SC + i, - buf[ISL12022_REG_SC + i]); - if (ret) - return -EIO; - } - - return 0; + return regmap_bulk_write(isl12022->regmap, ISL12022_REG_SC, + buf, sizeof(buf)); } static const struct rtc_class_ops isl12022_rtc_ops = { @@ -232,6 +135,12 @@ static const struct rtc_class_ops isl12022_rtc_ops = { .set_time = isl12022_rtc_set_time, }; +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .use_single_write = true, +}; + static int isl12022_probe(struct i2c_client *client) { struct isl12022 *isl12022; @@ -243,13 +152,23 @@ static int isl12022_probe(struct i2c_client *client) GFP_KERNEL); if (!isl12022) return -ENOMEM; + dev_set_drvdata(&client->dev, isl12022); + + isl12022->regmap = devm_regmap_init_i2c(client, ®map_config); + if (IS_ERR(isl12022->regmap)) { + dev_err(&client->dev, "regmap allocation failed\n"); + return PTR_ERR(isl12022->regmap); + } + + isl12022->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(isl12022->rtc)) + return PTR_ERR(isl12022->rtc); - i2c_set_clientdata(client, isl12022); + isl12022->rtc->ops = &isl12022_rtc_ops; + isl12022->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + isl12022->rtc->range_max = RTC_TIMESTAMP_END_2099; - isl12022->rtc = devm_rtc_device_register(&client->dev, - isl12022_driver.driver.name, - &isl12022_rtc_ops, THIS_MODULE); - return PTR_ERR_OR_ZERO(isl12022->rtc); + return devm_rtc_register_device(isl12022->rtc); } #ifdef CONFIG_OF diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c index 6e51df72fd65..c383719292c7 100644 --- a/drivers/rtc/rtc-jz4740.c +++ b/drivers/rtc/rtc-jz4740.c @@ -257,11 +257,6 @@ static void jz4740_rtc_power_off(void) kernel_halt(); } -static void jz4740_rtc_clk_disable(void *data) -{ - clk_disable_unprepare(data); -} - static const struct of_device_id jz4740_rtc_of_match[] = { { .compatible = "ingenic,jz4740-rtc", .data = (void *)ID_JZ4740 }, { .compatible = "ingenic,jz4760-rtc", .data = (void *)ID_JZ4760 }, @@ -329,23 +324,9 @@ static int jz4740_rtc_probe(struct platform_device *pdev) if (IS_ERR(rtc->base)) return PTR_ERR(rtc->base); - clk = devm_clk_get(dev, "rtc"); - if (IS_ERR(clk)) { - dev_err(dev, "Failed to get RTC clock\n"); - return PTR_ERR(clk); - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "Failed to enable clock\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, jz4740_rtc_clk_disable, clk); - if (ret) { - dev_err(dev, "Failed to register devm action\n"); - return ret; - } + clk = devm_clk_get_enabled(dev, "rtc"); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "Failed to get RTC clock\n"); spin_lock_init(&rtc->lock); diff --git a/drivers/rtc/rtc-mpfs.c b/drivers/rtc/rtc-mpfs.c index f14d1925e0c9..2a479d44f198 100644 --- a/drivers/rtc/rtc-mpfs.c +++ b/drivers/rtc/rtc-mpfs.c @@ -193,23 +193,6 @@ static int mpfs_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) return 0; } -static inline struct clk *mpfs_rtc_init_clk(struct device *dev) -{ - struct clk *clk; - int ret; - - clk = devm_clk_get(dev, "rtc"); - if (IS_ERR(clk)) - return clk; - - ret = clk_prepare_enable(clk); - if (ret) - return ERR_PTR(ret); - - devm_add_action_or_reset(dev, (void (*) (void *))clk_disable_unprepare, clk); - return clk; -} - static irqreturn_t mpfs_rtc_wakeup_irq_handler(int irq, void *dev) { struct mpfs_rtc_dev *rtcdev = dev; @@ -233,7 +216,7 @@ static int mpfs_rtc_probe(struct platform_device *pdev) { struct mpfs_rtc_dev *rtcdev; struct clk *clk; - u32 prescaler; + unsigned long prescaler; int wakeup_irq, ret; rtcdev = devm_kzalloc(&pdev->dev, sizeof(struct mpfs_rtc_dev), GFP_KERNEL); @@ -251,7 +234,7 @@ static int mpfs_rtc_probe(struct platform_device *pdev) /* range is capped by alarm max, lower reg is 31:0 & upper is 10:0 */ rtcdev->rtc->range_max = GENMASK_ULL(42, 0); - clk = mpfs_rtc_init_clk(&pdev->dev); + clk = devm_clk_get_enabled(&pdev->dev, "rtc"); if (IS_ERR(clk)) return PTR_ERR(clk); @@ -275,14 +258,13 @@ static int mpfs_rtc_probe(struct platform_device *pdev) /* prescaler hardware adds 1 to reg value */ prescaler = clk_get_rate(devm_clk_get(&pdev->dev, "rtcref")) - 1; - if (prescaler > MAX_PRESCALER_COUNT) { - dev_dbg(&pdev->dev, "invalid prescaler %d\n", prescaler); + dev_dbg(&pdev->dev, "invalid prescaler %lu\n", prescaler); return -EINVAL; } writel(prescaler, rtcdev->base + PRESCALER_REG); - dev_info(&pdev->dev, "prescaler set to: 0x%X \r\n", prescaler); + dev_info(&pdev->dev, "prescaler set to: %lu\n", prescaler); device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, wakeup_irq); diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 53d4e253e81f..762cf03345f1 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -291,14 +291,6 @@ static const struct rtc_class_ops mxc_rtc_ops = { .alarm_irq_enable = mxc_rtc_alarm_irq_enable, }; -static void mxc_rtc_action(void *p) -{ - struct rtc_plat_data *pdata = p; - - clk_disable_unprepare(pdata->clk_ref); - clk_disable_unprepare(pdata->clk_ipg); -} - static int mxc_rtc_probe(struct platform_device *pdev) { struct rtc_device *rtc; @@ -341,33 +333,18 @@ static int mxc_rtc_probe(struct platform_device *pdev) rtc->range_max = (1 << 16) * 86400ULL - 1; } - pdata->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); + pdata->clk_ipg = devm_clk_get_enabled(&pdev->dev, "ipg"); if (IS_ERR(pdata->clk_ipg)) { dev_err(&pdev->dev, "unable to get ipg clock!\n"); return PTR_ERR(pdata->clk_ipg); } - ret = clk_prepare_enable(pdata->clk_ipg); - if (ret) - return ret; - - pdata->clk_ref = devm_clk_get(&pdev->dev, "ref"); + pdata->clk_ref = devm_clk_get_enabled(&pdev->dev, "ref"); if (IS_ERR(pdata->clk_ref)) { - clk_disable_unprepare(pdata->clk_ipg); dev_err(&pdev->dev, "unable to get ref clock!\n"); return PTR_ERR(pdata->clk_ref); } - ret = clk_prepare_enable(pdata->clk_ref); - if (ret) { - clk_disable_unprepare(pdata->clk_ipg); - return ret; - } - - ret = devm_add_action_or_reset(&pdev->dev, mxc_rtc_action, pdata); - if (ret) - return ret; - rate = clk_get_rate(pdata->clk_ref); if (rate == 32768) diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c index cdc623b3e365..dd170e3efd83 100644 --- a/drivers/rtc/rtc-rv3028.c +++ b/drivers/rtc/rtc-rv3028.c @@ -521,10 +521,9 @@ static int rv3028_param_get(struct device *dev, struct rtc_param *param) { struct rv3028_data *rv3028 = dev_get_drvdata(dev); int ret; + u32 value; switch(param->param) { - u32 value; - case RTC_PARAM_BACKUP_SWITCH_MODE: ret = regmap_read(rv3028->regmap, RV3028_BACKUP, &value); if (ret < 0) @@ -554,9 +553,9 @@ static int rv3028_param_get(struct device *dev, struct rtc_param *param) static int rv3028_param_set(struct device *dev, struct rtc_param *param) { struct rv3028_data *rv3028 = dev_get_drvdata(dev); + u8 mode; switch(param->param) { - u8 mode; case RTC_PARAM_BACKUP_SWITCH_MODE: switch (param->uvalue) { case RTC_BSM_DISABLED: diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c index 40c0f7ed36e0..aae40d20d086 100644 --- a/drivers/rtc/rtc-stmp3xxx.c +++ b/drivers/rtc/rtc-stmp3xxx.c @@ -107,6 +107,8 @@ static void stmp3xxx_wdt_register(struct platform_device *rtc_pdev) wdt_pdev->dev.parent = &rtc_pdev->dev; wdt_pdev->dev.platform_data = &wdt_pdata; rc = platform_device_add(wdt_pdev); + if (rc) + platform_device_put(wdt_pdev); } if (rc) diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c index 7a0f181d3fef..ba23163cc042 100644 --- a/drivers/rtc/rtc-ti-k3.c +++ b/drivers/rtc/rtc-ti-k3.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/sys_soc.h> #include <linux/property.h> #include <linux/regmap.h> #include <linux/rtc.h> @@ -45,14 +46,6 @@ #define K3RTC_MIN_OFFSET (-277761) #define K3RTC_MAX_OFFSET (277778) -/** - * struct ti_k3_rtc_soc_data - Private of compatible data for ti-k3-rtc - * @unlock_irq_erratum: Has erratum for unlock infinite IRQs (erratum i2327) - */ -struct ti_k3_rtc_soc_data { - const bool unlock_irq_erratum; -}; - static const struct regmap_config ti_k3_rtc_regmap_config = { .name = "peripheral-registers", .reg_bits = 32, @@ -118,7 +111,6 @@ static const struct reg_field ti_rtc_reg_fields[] = { * @rtc_dev: rtc device * @regmap: rtc mmio regmap * @r_fields: rtc register fields - * @soc: SoC compatible match data */ struct ti_k3_rtc { unsigned int irq; @@ -127,7 +119,6 @@ struct ti_k3_rtc { struct rtc_device *rtc_dev; struct regmap *regmap; struct regmap_field *r_fields[K3_RTC_MAX_FIELDS]; - const struct ti_k3_rtc_soc_data *soc; }; static int k3rtc_field_read(struct ti_k3_rtc *priv, enum ti_k3_rtc_fields f) @@ -190,11 +181,22 @@ static int k3rtc_unlock_rtc(struct ti_k3_rtc *priv) /* Skip fence since we are going to check the unlock bit as fence */ ret = regmap_field_read_poll_timeout(priv->r_fields[K3RTC_UNLOCK], ret, - !ret, 2, priv->sync_timeout_us); + ret, 2, priv->sync_timeout_us); return ret; } +/* + * This is the list of SoCs affected by TI's i2327 errata causing the RTC + * state-machine to break if not unlocked fast enough during boot. These + * SoCs must have the bootloader unlock this device very early in the + * boot-flow before we (Linux) can use this device. + */ +static const struct soc_device_attribute has_erratum_i2327[] = { + { .family = "AM62X", .revision = "SR1.0" }, + { /* sentinel */ } +}; + static int k3rtc_configure(struct device *dev) { int ret; @@ -208,7 +210,7 @@ static int k3rtc_configure(struct device *dev) * * In such occurrence, it is assumed that the RTC module is unusable */ - if (priv->soc->unlock_irq_erratum) { + if (soc_device_match(has_erratum_i2327)) { ret = k3rtc_check_unlocked(priv); /* If there is an error OR if we are locked, return error */ if (ret) { @@ -513,21 +515,12 @@ static struct nvmem_config ti_k3_rtc_nvmem_config = { static int k3rtc_get_32kclk(struct device *dev, struct ti_k3_rtc *priv) { - int ret; struct clk *clk; - clk = devm_clk_get(dev, "osc32k"); + clk = devm_clk_get_enabled(dev, "osc32k"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) - return ret; - - ret = devm_add_action_or_reset(dev, (void (*)(void *))clk_disable_unprepare, clk); - if (ret) - return ret; - priv->rate_32k = clk_get_rate(clk); /* Make sure we are exact 32k clock. Else, try to compensate delay */ @@ -542,24 +535,19 @@ static int k3rtc_get_32kclk(struct device *dev, struct ti_k3_rtc *priv) */ priv->sync_timeout_us = (u32)(DIV_ROUND_UP_ULL(1000000, priv->rate_32k) * 4); - return ret; + return 0; } static int k3rtc_get_vbusclk(struct device *dev, struct ti_k3_rtc *priv) { - int ret; struct clk *clk; /* Note: VBUS isn't a context clock, it is needed for hardware operation */ - clk = devm_clk_get(dev, "vbus"); + clk = devm_clk_get_enabled(dev, "vbus"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) - return ret; - - return devm_add_action_or_reset(dev, (void (*)(void *))clk_disable_unprepare, clk); + return 0; } static int ti_k3_rtc_probe(struct platform_device *pdev) @@ -602,8 +590,6 @@ static int ti_k3_rtc_probe(struct platform_device *pdev) if (IS_ERR(priv->rtc_dev)) return PTR_ERR(priv->rtc_dev); - priv->soc = of_device_get_match_data(dev); - priv->rtc_dev->ops = &ti_k3_rtc_ops; priv->rtc_dev->range_max = (1ULL << 48) - 1; /* 48Bit seconds */ ti_k3_rtc_nvmem_config.priv = priv; @@ -635,12 +621,8 @@ static int ti_k3_rtc_probe(struct platform_device *pdev) return devm_rtc_nvmem_register(priv->rtc_dev, &ti_k3_rtc_nvmem_config); } -static const struct ti_k3_rtc_soc_data ti_k3_am62_data = { - .unlock_irq_erratum = true, -}; - static const struct of_device_id ti_k3_rtc_of_match_table[] = { - {.compatible = "ti,am62-rtc", .data = &ti_k3_am62_data}, + {.compatible = "ti,am62-rtc" }, {} }; MODULE_DEVICE_TABLE(of, ti_k3_rtc_of_match_table); diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 68f49e2e964c..131293f7f152 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -15,12 +15,14 @@ #include <linux/cdev.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/kobject.h> #include <linux/uaccess.h> #include <asm/cio.h> #include <asm/ccwdev.h> #include <asm/debug.h> #include <asm/diag.h> +#include <asm/scsw.h> #include "vmur.h" @@ -78,6 +80,8 @@ static struct ccw_driver ur_driver = { static DEFINE_MUTEX(vmur_mutex); +static void ur_uevent(struct work_struct *ws); + /* * Allocation, freeing, getting and putting of urdev structures * @@ -108,6 +112,7 @@ static struct urdev *urdev_alloc(struct ccw_device *cdev) ccw_device_get_id(cdev, &urd->dev_id); mutex_init(&urd->io_mutex); init_waitqueue_head(&urd->wait); + INIT_WORK(&urd->uevent_work, ur_uevent); spin_lock_init(&urd->open_lock); refcount_set(&urd->ref_count, 1); urd->cdev = cdev; @@ -275,6 +280,18 @@ out: return rc; } +static void ur_uevent(struct work_struct *ws) +{ + struct urdev *urd = container_of(ws, struct urdev, uevent_work); + char *envp[] = { + "EVENT=unsol_de", /* Unsolicited device-end interrupt */ + NULL + }; + + kobject_uevent_env(&urd->cdev->dev.kobj, KOBJ_CHANGE, envp); + urdev_put(urd); +} + /* * ur interrupt handler, called from the ccw_device layer */ @@ -288,12 +305,21 @@ static void ur_int_handler(struct ccw_device *cdev, unsigned long intparm, intparm, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat, irb->scsw.cmd.count); } + urd = dev_get_drvdata(&cdev->dev); if (!intparm) { TRACE("ur_int_handler: unsolicited interrupt\n"); + + if (scsw_dstat(&irb->scsw) & DEV_STAT_DEV_END) { + /* + * Userspace might be interested in a transition to + * device-ready state. + */ + urdev_get(urd); + schedule_work(&urd->uevent_work); + } + return; } - urd = dev_get_drvdata(&cdev->dev); - BUG_ON(!urd); /* On special conditions irb is an error pointer */ if (IS_ERR(irb)) urd->io_request_rc = PTR_ERR(irb); @@ -809,7 +835,6 @@ static int ur_probe(struct ccw_device *cdev) rc = -ENOMEM; goto fail_urdev_put; } - cdev->handler = ur_int_handler; /* validate virtual unit record device */ urd->class = get_urd_class(urd); @@ -823,6 +848,7 @@ static int ur_probe(struct ccw_device *cdev) } spin_lock_irq(get_ccwdev_lock(cdev)); dev_set_drvdata(&cdev->dev, urd); + cdev->handler = ur_int_handler; spin_unlock_irq(get_ccwdev_lock(cdev)); mutex_unlock(&vmur_mutex); @@ -928,6 +954,10 @@ static int ur_set_offline_force(struct ccw_device *cdev, int force) rc = -EBUSY; goto fail_urdev_put; } + if (cancel_work_sync(&urd->uevent_work)) { + /* Work not run yet - need to release reference here */ + urdev_put(urd); + } device_destroy(vmur_class, urd->char_device->dev); cdev_del(urd->char_device); urd->char_device = NULL; @@ -963,6 +993,7 @@ static void ur_remove(struct ccw_device *cdev) spin_lock_irqsave(get_ccwdev_lock(cdev), flags); urdev_put(dev_get_drvdata(&cdev->dev)); dev_set_drvdata(&cdev->dev, NULL); + cdev->handler = NULL; spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); mutex_unlock(&vmur_mutex); diff --git a/drivers/s390/char/vmur.h b/drivers/s390/char/vmur.h index 608b0719ce17..92d17d7cb47b 100644 --- a/drivers/s390/char/vmur.h +++ b/drivers/s390/char/vmur.h @@ -13,6 +13,7 @@ #define _VMUR_H_ #include <linux/refcount.h> +#include <linux/workqueue.h> #define DEV_CLASS_UR_I 0x20 /* diag210 unit record input device class */ #define DEV_CLASS_UR_O 0x10 /* diag210 unit record output device class */ @@ -76,6 +77,7 @@ struct urdev { wait_queue_head_t wait; /* wait queue to serialize open */ int open_flag; /* "urdev is open" flag */ spinlock_t open_lock; /* serialize critical sections */ + struct work_struct uevent_work; /* work to send uevent */ }; /* diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig index 58cf8c40d08d..ed4c571f8771 100644 --- a/drivers/soc/sifive/Kconfig +++ b/drivers/soc/sifive/Kconfig @@ -2,9 +2,9 @@ if SOC_SIFIVE -config SIFIVE_L2 - bool "Sifive L2 Cache controller" +config SIFIVE_CCACHE + bool "Sifive Composable Cache controller" help - Support for the L2 cache controller on SiFive platforms. + Support for the composable cache controller on SiFive platforms. endif diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile index b5caff77938f..1f5dc339bf82 100644 --- a/drivers/soc/sifive/Makefile +++ b/drivers/soc/sifive/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_SIFIVE_L2) += sifive_l2_cache.o +obj-$(CONFIG_SIFIVE_CCACHE) += sifive_ccache.o diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c new file mode 100644 index 000000000000..1c171150e878 --- /dev/null +++ b/drivers/soc/sifive/sifive_ccache.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SiFive composable cache controller Driver + * + * Copyright (C) 2018-2022 SiFive, Inc. + * + */ + +#define pr_fmt(fmt) "CCACHE: " fmt + +#include <linux/debugfs.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> +#include <linux/device.h> +#include <linux/bitfield.h> +#include <asm/cacheinfo.h> +#include <soc/sifive/sifive_ccache.h> + +#define SIFIVE_CCACHE_DIRECCFIX_LOW 0x100 +#define SIFIVE_CCACHE_DIRECCFIX_HIGH 0x104 +#define SIFIVE_CCACHE_DIRECCFIX_COUNT 0x108 + +#define SIFIVE_CCACHE_DIRECCFAIL_LOW 0x120 +#define SIFIVE_CCACHE_DIRECCFAIL_HIGH 0x124 +#define SIFIVE_CCACHE_DIRECCFAIL_COUNT 0x128 + +#define SIFIVE_CCACHE_DATECCFIX_LOW 0x140 +#define SIFIVE_CCACHE_DATECCFIX_HIGH 0x144 +#define SIFIVE_CCACHE_DATECCFIX_COUNT 0x148 + +#define SIFIVE_CCACHE_DATECCFAIL_LOW 0x160 +#define SIFIVE_CCACHE_DATECCFAIL_HIGH 0x164 +#define SIFIVE_CCACHE_DATECCFAIL_COUNT 0x168 + +#define SIFIVE_CCACHE_CONFIG 0x00 +#define SIFIVE_CCACHE_CONFIG_BANK_MASK GENMASK_ULL(7, 0) +#define SIFIVE_CCACHE_CONFIG_WAYS_MASK GENMASK_ULL(15, 8) +#define SIFIVE_CCACHE_CONFIG_SETS_MASK GENMASK_ULL(23, 16) +#define SIFIVE_CCACHE_CONFIG_BLKS_MASK GENMASK_ULL(31, 24) + +#define SIFIVE_CCACHE_WAYENABLE 0x08 +#define SIFIVE_CCACHE_ECCINJECTERR 0x40 + +#define SIFIVE_CCACHE_MAX_ECCINTR 4 + +static void __iomem *ccache_base; +static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR]; +static struct riscv_cacheinfo_ops ccache_cache_ops; +static int level; + +enum { + DIR_CORR = 0, + DATA_CORR, + DATA_UNCORR, + DIR_UNCORR, +}; + +#ifdef CONFIG_DEBUG_FS +static struct dentry *sifive_test; + +static ssize_t ccache_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + unsigned int val; + + if (kstrtouint_from_user(data, count, 0, &val)) + return -EINVAL; + if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) + writel(val, ccache_base + SIFIVE_CCACHE_ECCINJECTERR); + else + return -EINVAL; + return count; +} + +static const struct file_operations ccache_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = ccache_write +}; + +static void setup_sifive_debug(void) +{ + sifive_test = debugfs_create_dir("sifive_ccache_cache", NULL); + + debugfs_create_file("sifive_debug_inject_error", 0200, + sifive_test, NULL, &ccache_fops); +} +#endif + +static void ccache_config_read(void) +{ + u32 cfg; + + cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG); + pr_info("%llu banks, %llu ways, sets/bank=%llu, bytes/block=%llu\n", + FIELD_GET(SIFIVE_CCACHE_CONFIG_BANK_MASK, cfg), + FIELD_GET(SIFIVE_CCACHE_CONFIG_WAYS_MASK, cfg), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_SETS_MASK, cfg)), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_BLKS_MASK, cfg))); + + cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); + pr_info("Index of the largest way enabled: %u\n", cfg); +} + +static const struct of_device_id sifive_ccache_ids[] = { + { .compatible = "sifive,fu540-c000-ccache" }, + { .compatible = "sifive,fu740-c000-ccache" }, + { .compatible = "sifive,ccache0" }, + { /* end of table */ } +}; + +static ATOMIC_NOTIFIER_HEAD(ccache_err_chain); + +int register_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(register_sifive_ccache_error_notifier); + +int unregister_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_sifive_ccache_error_notifier); + +static int ccache_largest_wayenabled(void) +{ + return readl(ccache_base + SIFIVE_CCACHE_WAYENABLE) & 0xFF; +} + +static ssize_t number_of_ways_enabled_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", ccache_largest_wayenabled()); +} + +static DEVICE_ATTR_RO(number_of_ways_enabled); + +static struct attribute *priv_attrs[] = { + &dev_attr_number_of_ways_enabled.attr, + NULL, +}; + +static const struct attribute_group priv_attr_group = { + .attrs = priv_attrs, +}; + +static const struct attribute_group *ccache_get_priv_group(struct cacheinfo + *this_leaf) +{ + /* We want to use private group for composable cache only */ + if (this_leaf->level == level) + return &priv_attr_group; + else + return NULL; +} + +static irqreturn_t ccache_int_handler(int irq, void *device) +{ + unsigned int add_h, add_l; + + if (irq == g_irq[DIR_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_LOW); + pr_err("DirError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DirError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DirECCFix"); + } + if (irq == g_irq[DIR_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_LOW); + /* Reading this register clears the DirFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DirECCFail"); + panic("CCACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); + } + if (irq == g_irq[DATA_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_LOW); + pr_err("DataError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DatECCFix"); + } + if (irq == g_irq[DATA_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_LOW); + pr_err("DataFail @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DatECCFail"); + } + + return IRQ_HANDLED; +} + +static int __init sifive_ccache_init(void) +{ + struct device_node *np; + struct resource res; + int i, rc, intr_num; + + np = of_find_matching_node(NULL, sifive_ccache_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + ccache_base = ioremap(res.start, resource_size(&res)); + if (!ccache_base) + return -ENOMEM; + + if (of_property_read_u32(np, "cache-level", &level)) + return -ENOENT; + + intr_num = of_property_count_u32_elems(np, "interrupts"); + if (!intr_num) { + pr_err("No interrupts property\n"); + return -ENODEV; + } + + for (i = 0; i < intr_num; i++) { + g_irq[i] = irq_of_parse_and_map(np, i); + rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc", + NULL); + if (rc) { + pr_err("Could not request IRQ %d\n", g_irq[i]); + return rc; + } + } + + ccache_config_read(); + + ccache_cache_ops.get_priv_group = ccache_get_priv_group; + riscv_set_cacheinfo_ops(&ccache_cache_ops); + +#ifdef CONFIG_DEBUG_FS + setup_sifive_debug(); +#endif + return 0; +} + +device_initcall(sifive_ccache_init); diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c deleted file mode 100644 index 59640a1d0b28..000000000000 --- a/drivers/soc/sifive/sifive_l2_cache.c +++ /dev/null @@ -1,237 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * SiFive L2 cache controller Driver - * - * Copyright (C) 2018-2019 SiFive, Inc. - * - */ -#include <linux/debugfs.h> -#include <linux/interrupt.h> -#include <linux/of_irq.h> -#include <linux/of_address.h> -#include <linux/device.h> -#include <asm/cacheinfo.h> -#include <soc/sifive/sifive_l2_cache.h> - -#define SIFIVE_L2_DIRECCFIX_LOW 0x100 -#define SIFIVE_L2_DIRECCFIX_HIGH 0x104 -#define SIFIVE_L2_DIRECCFIX_COUNT 0x108 - -#define SIFIVE_L2_DIRECCFAIL_LOW 0x120 -#define SIFIVE_L2_DIRECCFAIL_HIGH 0x124 -#define SIFIVE_L2_DIRECCFAIL_COUNT 0x128 - -#define SIFIVE_L2_DATECCFIX_LOW 0x140 -#define SIFIVE_L2_DATECCFIX_HIGH 0x144 -#define SIFIVE_L2_DATECCFIX_COUNT 0x148 - -#define SIFIVE_L2_DATECCFAIL_LOW 0x160 -#define SIFIVE_L2_DATECCFAIL_HIGH 0x164 -#define SIFIVE_L2_DATECCFAIL_COUNT 0x168 - -#define SIFIVE_L2_CONFIG 0x00 -#define SIFIVE_L2_WAYENABLE 0x08 -#define SIFIVE_L2_ECCINJECTERR 0x40 - -#define SIFIVE_L2_MAX_ECCINTR 4 - -static void __iomem *l2_base; -static int g_irq[SIFIVE_L2_MAX_ECCINTR]; -static struct riscv_cacheinfo_ops l2_cache_ops; - -enum { - DIR_CORR = 0, - DATA_CORR, - DATA_UNCORR, - DIR_UNCORR, -}; - -#ifdef CONFIG_DEBUG_FS -static struct dentry *sifive_test; - -static ssize_t l2_write(struct file *file, const char __user *data, - size_t count, loff_t *ppos) -{ - unsigned int val; - - if (kstrtouint_from_user(data, count, 0, &val)) - return -EINVAL; - if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) - writel(val, l2_base + SIFIVE_L2_ECCINJECTERR); - else - return -EINVAL; - return count; -} - -static const struct file_operations l2_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = l2_write -}; - -static void setup_sifive_debug(void) -{ - sifive_test = debugfs_create_dir("sifive_l2_cache", NULL); - - debugfs_create_file("sifive_debug_inject_error", 0200, - sifive_test, NULL, &l2_fops); -} -#endif - -static void l2_config_read(void) -{ - u32 regval, val; - - regval = readl(l2_base + SIFIVE_L2_CONFIG); - val = regval & 0xFF; - pr_info("L2CACHE: No. of Banks in the cache: %d\n", val); - val = (regval & 0xFF00) >> 8; - pr_info("L2CACHE: No. of ways per bank: %d\n", val); - val = (regval & 0xFF0000) >> 16; - pr_info("L2CACHE: Sets per bank: %llu\n", (uint64_t)1 << val); - val = (regval & 0xFF000000) >> 24; - pr_info("L2CACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val); - - regval = readl(l2_base + SIFIVE_L2_WAYENABLE); - pr_info("L2CACHE: Index of the largest way enabled: %d\n", regval); -} - -static const struct of_device_id sifive_l2_ids[] = { - { .compatible = "sifive,fu540-c000-ccache" }, - { .compatible = "sifive,fu740-c000-ccache" }, - { /* end of table */ }, -}; - -static ATOMIC_NOTIFIER_HEAD(l2_err_chain); - -int register_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(register_sifive_l2_error_notifier); - -int unregister_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(unregister_sifive_l2_error_notifier); - -static int l2_largest_wayenabled(void) -{ - return readl(l2_base + SIFIVE_L2_WAYENABLE) & 0xFF; -} - -static ssize_t number_of_ways_enabled_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", l2_largest_wayenabled()); -} - -static DEVICE_ATTR_RO(number_of_ways_enabled); - -static struct attribute *priv_attrs[] = { - &dev_attr_number_of_ways_enabled.attr, - NULL, -}; - -static const struct attribute_group priv_attr_group = { - .attrs = priv_attrs, -}; - -static const struct attribute_group *l2_get_priv_group(struct cacheinfo *this_leaf) -{ - /* We want to use private group for L2 cache only */ - if (this_leaf->level == 2) - return &priv_attr_group; - else - return NULL; -} - -static irqreturn_t l2_int_handler(int irq, void *device) -{ - unsigned int add_h, add_l; - - if (irq == g_irq[DIR_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFIX_LOW); - pr_err("L2CACHE: DirError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DirError interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DirECCFix"); - } - if (irq == g_irq[DIR_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFAIL_LOW); - /* Reading this register clears the DirFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DirECCFail"); - panic("L2CACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); - } - if (irq == g_irq[DATA_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFIX_LOW); - pr_err("L2CACHE: DataError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataError interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DatECCFix"); - } - if (irq == g_irq[DATA_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFAIL_LOW); - pr_err("L2CACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DatECCFail"); - } - - return IRQ_HANDLED; -} - -static int __init sifive_l2_init(void) -{ - struct device_node *np; - struct resource res; - int i, rc, intr_num; - - np = of_find_matching_node(NULL, sifive_l2_ids); - if (!np) - return -ENODEV; - - if (of_address_to_resource(np, 0, &res)) - return -ENODEV; - - l2_base = ioremap(res.start, resource_size(&res)); - if (!l2_base) - return -ENOMEM; - - intr_num = of_property_count_u32_elems(np, "interrupts"); - if (!intr_num) { - pr_err("L2CACHE: no interrupts property\n"); - return -ENODEV; - } - - for (i = 0; i < intr_num; i++) { - g_irq[i] = irq_of_parse_and_map(np, i); - rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL); - if (rc) { - pr_err("L2CACHE: Could not request IRQ %d\n", g_irq[i]); - return rc; - } - } - - l2_config_read(); - - l2_cache_ops.get_priv_group = l2_get_priv_group; - riscv_set_cacheinfo_ops(&l2_cache_ops); - -#ifdef CONFIG_DEBUG_FS - setup_sifive_debug(); -#endif - return 0; -} -device_initcall(sifive_l2_init); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 13cdd9def087..434f83168546 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -603,21 +603,6 @@ config SERIAL_MUX_CONSOLE select SERIAL_CORE_CONSOLE default y -config PDC_CONSOLE - bool "PDC software console support" - depends on PARISC && !SERIAL_MUX && VT - help - Saying Y here will enable the software based PDC console to be - used as the system console. This is useful for machines in - which the hardware based console has not been written yet. The - following steps must be completed to use the PDC console: - - 1. create the device entry (mknod /dev/ttyB0 c 11 0) - 2. Edit the /etc/inittab to start a getty listening on /dev/ttyB0 - 3. Add device ttyB0 to /etc/securetty (if you want to log on as - root on this console.) - 4. Change the kernel command console parameter to: console=ttyB0 - config SERIAL_SUNSAB tristate "Sun Siemens SAB82532 serial support" depends on SPARC && PCI diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 38a861e22c33..7753e586e65a 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1298,7 +1298,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) - fix->smem_len = yres*fix->line_length; + fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); fix->accel = FB_ACCEL_NONE; diff --git a/fs/cifs/cached_dir.c b/fs/cifs/cached_dir.c index b705dac383f9..fe88b67c863f 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/cifs/cached_dir.c @@ -5,13 +5,98 @@ * Copyright (c) 2022, Ronnie Sahlberg <lsahlber@redhat.com> */ +#include <linux/namei.h> #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" #include "smb2proto.h" #include "cached_dir.h" -struct cached_fid *init_cached_dir(const char *path); +static struct cached_fid *init_cached_dir(const char *path); +static void free_cached_dir(struct cached_fid *cfid); + +static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, + const char *path, + bool lookup_only) +{ + struct cached_fid *cfid; + + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (!strcmp(cfid->path, path)) { + /* + * If it doesn't have a lease it is either not yet + * fully cached or it may be in the process of + * being deleted due to a lease break. + */ + if (!cfid->has_lease) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + kref_get(&cfid->refcount); + spin_unlock(&cfids->cfid_list_lock); + return cfid; + } + } + if (lookup_only) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + if (cfids->num_entries >= MAX_CACHED_FIDS) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + cfid = init_cached_dir(path); + if (cfid == NULL) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + cfid->cfids = cfids; + cfids->num_entries++; + list_add(&cfid->entry, &cfids->entries); + cfid->on_list = true; + kref_get(&cfid->refcount); + spin_unlock(&cfids->cfid_list_lock); + return cfid; +} + +static struct dentry * +path_to_dentry(struct cifs_sb_info *cifs_sb, const char *path) +{ + struct dentry *dentry; + const char *s, *p; + char sep; + + sep = CIFS_DIR_SEP(cifs_sb); + dentry = dget(cifs_sb->root); + s = path; + + do { + struct inode *dir = d_inode(dentry); + struct dentry *child; + + if (!S_ISDIR(dir->i_mode)) { + dput(dentry); + dentry = ERR_PTR(-ENOTDIR); + break; + } + + /* skip separators */ + while (*s == sep) + s++; + if (!*s) + break; + p = s++; + /* next separator */ + while (*s && *s != sep) + s++; + + child = lookup_positive_unlocked(p, dentry, s - p); + dput(dentry); + dentry = child; + } while (!IS_ERR(dentry)); + return dentry; +} /* * Open the and cache a directory handle. @@ -33,61 +118,57 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; struct kvec qi_iov[1]; int rc, flags = 0; - __le16 utf16_path = 0; /* Null - since an open of top of share */ + __le16 *utf16_path = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_II; struct cifs_fid *pfid; - struct dentry *dentry; + struct dentry *dentry = NULL; struct cached_fid *cfid; + struct cached_fids *cfids; - if (tcon == NULL || tcon->nohandlecache || + if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache || is_smb1_server(tcon->ses->server)) return -EOPNOTSUPP; ses = tcon->ses; server = ses->server; + cfids = tcon->cfids; + + if (!server->ops->new_lease_key) + return -EIO; if (cifs_sb->root == NULL) return -ENOENT; - if (!path[0]) - dentry = cifs_sb->root; - else - return -ENOENT; + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return -ENOMEM; - cfid = tcon->cfids->cfid; + cfid = find_or_create_cached_dir(cfids, path, lookup_only); if (cfid == NULL) { - cfid = init_cached_dir(path); - tcon->cfids->cfid = cfid; + kfree(utf16_path); + return -ENOENT; } - if (cfid == NULL) - return -ENOMEM; - - mutex_lock(&cfid->fid_mutex); - if (cfid->is_valid) { - cifs_dbg(FYI, "found a cached root file handle\n"); + /* + * At this point we either have a lease already and we can just + * return it. If not we are guaranteed to be the only thread accessing + * this cfid. + */ + if (cfid->has_lease) { *ret_cfid = cfid; - kref_get(&cfid->refcount); - mutex_unlock(&cfid->fid_mutex); + kfree(utf16_path); return 0; } /* * We do not hold the lock for the open because in case - * SMB2_open needs to reconnect, it will end up calling - * cifs_mark_open_files_invalid() which takes the lock again - * thus causing a deadlock + * SMB2_open needs to reconnect. + * This is safe because no other thread will be able to get a ref + * to the cfid until we have finished opening the file and (possibly) + * acquired a lease. */ - mutex_unlock(&cfid->fid_mutex); - - if (lookup_only) - return -ENOENT; - if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - if (!server->ops->new_lease_key) - return -EIO; - pfid = &cfid->fid; server->ops->new_lease_key(pfid); @@ -108,7 +189,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.reconnect = false; rc = SMB2_open_init(tcon, server, - &rqst[0], &oplock, &oparms, &utf16_path); + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto oshr_free; smb2_set_next_command(tcon, &rqst[0]); @@ -131,47 +212,13 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, rc = compound_send_recv(xid, ses, server, flags, 2, rqst, resp_buftype, rsp_iov); - mutex_lock(&cfid->fid_mutex); - - /* - * Now we need to check again as the cached root might have - * been successfully re-opened from a concurrent process - */ - - if (cfid->is_valid) { - /* work was already done */ - - /* stash fids for close() later */ - struct cifs_fid fid = { - .persistent_fid = pfid->persistent_fid, - .volatile_fid = pfid->volatile_fid, - }; - - /* - * caller expects this func to set the fid in cfid to valid - * cached root, so increment the refcount. - */ - kref_get(&cfid->refcount); - - mutex_unlock(&cfid->fid_mutex); - - if (rc == 0) { - /* close extra handle outside of crit sec */ - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - } - rc = 0; - goto oshr_free; - } - - /* Cached root is still invalid, continue normaly */ - if (rc) { if (rc == -EREMCHG) { tcon->need_reconnect = true; pr_warn_once("server share %s deleted\n", tcon->tree_name); } - goto oshr_exit; + goto oshr_free; } atomic_inc(&tcon->num_remote_opens); @@ -183,31 +230,18 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - cfid->tcon = tcon; - cfid->is_valid = true; - cfid->dentry = dentry; - if (dentry) - dget(dentry); - kref_init(&cfid->refcount); + if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) + goto oshr_free; - /* BB TBD check to see if oplock level check can be removed below */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { - /* - * See commit 2f94a3125b87. Increment the refcount when we - * get a lease for root, release it if lease break occurs - */ - kref_get(&cfid->refcount); - cfid->has_lease = true; - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); - } else - goto oshr_exit; + + smb2_parse_contexts(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key, &oplock, + NULL, NULL); qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) - goto oshr_exit; + goto oshr_free; if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), @@ -215,15 +249,40 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, (char *)&cfid->file_all_info)) cfid->file_all_info_is_valid = true; + if (!path[0]) + dentry = dget(cifs_sb->root); + else { + dentry = path_to_dentry(cifs_sb, path); + if (IS_ERR(dentry)) + goto oshr_free; + } + cfid->dentry = dentry; + cfid->tcon = tcon; cfid->time = jiffies; + cfid->is_open = true; + cfid->has_lease = true; -oshr_exit: - mutex_unlock(&cfid->fid_mutex); oshr_free: + kfree(utf16_path); SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + spin_lock(&cfids->cfid_list_lock); + if (!cfid->has_lease) { + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + rc = -ENOENT; + } + spin_unlock(&cfids->cfid_list_lock); + if (rc) { + free_cached_dir(cfid); + cfid = NULL; + } + if (rc == 0) *ret_cfid = cfid; @@ -235,20 +294,22 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon, struct cached_fid **ret_cfid) { struct cached_fid *cfid; + struct cached_fids *cfids = tcon->cfids; - cfid = tcon->cfids->cfid; - if (cfid == NULL) + if (cfids == NULL) return -ENOENT; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry == dentry) { - cifs_dbg(FYI, "found a cached root file handle by dentry\n"); - *ret_cfid = cfid; - kref_get(&cfid->refcount); - mutex_unlock(&cfid->fid_mutex); - return 0; + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (dentry && cfid->dentry == dentry) { + cifs_dbg(FYI, "found a cached root file handle by dentry\n"); + kref_get(&cfid->refcount); + *ret_cfid = cfid; + spin_unlock(&cfids->cfid_list_lock); + return 0; + } } - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfids->cfid_list_lock); return -ENOENT; } @@ -257,63 +318,29 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); - struct cached_dirent *dirent, *q; - if (cfid->is_valid) { - cifs_dbg(FYI, "clear cached root file handle\n"); - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, - cfid->fid.volatile_fid); + spin_lock(&cfid->cfids->cfid_list_lock); + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfid->cfids->num_entries--; } + spin_unlock(&cfid->cfids->cfid_list_lock); - /* - * We only check validity above to send SMB2_close, - * but we still need to invalidate these entries - * when this function is called - */ - cfid->is_valid = false; - cfid->file_all_info_is_valid = false; - cfid->has_lease = false; - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - /* - * Delete all cached dirent names - */ - mutex_lock(&cfid->dirents.de_mutex); - list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { - list_del(&dirent->entry); - kfree(dirent->name); - kfree(dirent); + dput(cfid->dentry); + cfid->dentry = NULL; + + if (cfid->is_open) { + SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + cfid->fid.volatile_fid); } - cfid->dirents.is_valid = 0; - cfid->dirents.is_failed = 0; - cfid->dirents.ctx = NULL; - cfid->dirents.pos = 0; - mutex_unlock(&cfid->dirents.de_mutex); + free_cached_dir(cfid); } void close_cached_dir(struct cached_fid *cfid) { - mutex_lock(&cfid->fid_mutex); kref_put(&cfid->refcount, smb2_close_cached_fid); - mutex_unlock(&cfid->fid_mutex); -} - -void close_cached_dir_lease_locked(struct cached_fid *cfid) -{ - if (cfid->has_lease) { - cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); - } -} - -void close_cached_dir_lease(struct cached_fid *cfid) -{ - mutex_lock(&cfid->fid_mutex); - close_cached_dir_lease_locked(cfid); - mutex_unlock(&cfid->fid_mutex); } /* @@ -326,41 +353,62 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb) struct cached_fid *cfid; struct cifs_tcon *tcon; struct tcon_link *tlink; + struct cached_fids *cfids; for (node = rb_first(root); node; node = rb_next(node)) { tlink = rb_entry(node, struct tcon_link, tl_rbnode); tcon = tlink_tcon(tlink); if (IS_ERR(tcon)) continue; - cfid = tcon->cfids->cfid; - if (cfid == NULL) + cfids = tcon->cfids; + if (cfids == NULL) continue; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { + list_for_each_entry(cfid, &cfids->entries, entry) { dput(cfid->dentry); cfid->dentry = NULL; } - mutex_unlock(&cfid->fid_mutex); } } /* - * Invalidate and close all cached dirs when a TCON has been reset + * Invalidate all cached dirs when a TCON has been reset * due to a session loss. */ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) { - struct cached_fid *cfid = tcon->cfids->cfid; - - if (cfid == NULL) - return; - - mutex_lock(&cfid->fid_mutex); - cfid->is_valid = false; - /* cached handle is not valid, so SMB2_CLOSE won't be sent below */ - close_cached_dir_lease_locked(cfid); - memset(&cfid->fid, 0, sizeof(struct cifs_fid)); - mutex_unlock(&cfid->fid_mutex); + struct cached_fids *cfids = tcon->cfids; + struct cached_fid *cfid, *q; + struct list_head entry; + + INIT_LIST_HEAD(&entry); + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + list_del(&cfid->entry); + list_add(&cfid->entry, &entry); + cfids->num_entries--; + cfid->is_open = false; + /* To prevent race with smb2_cached_lease_break() */ + kref_get(&cfid->refcount); + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + cfid->on_list = false; + list_del(&cfid->entry); + cancel_work_sync(&cfid->lease_break); + if (cfid->has_lease) { + /* + * We lease was never cancelled from the server so we + * need to drop the reference. + */ + spin_lock(&cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); + } + /* Drop the extra reference opened above*/ + kref_put(&cfid->refcount, smb2_close_cached_fid); + } } static void @@ -369,51 +417,83 @@ smb2_cached_lease_break(struct work_struct *work) struct cached_fid *cfid = container_of(work, struct cached_fid, lease_break); - close_cached_dir_lease(cfid); + spin_lock(&cfid->cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfid->cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); } int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]) { - struct cached_fid *cfid = tcon->cfids->cfid; + struct cached_fids *cfids = tcon->cfids; + struct cached_fid *cfid; - if (cfid == NULL) + if (cfids == NULL) return false; - if (cfid->is_valid && - !memcmp(lease_key, - cfid->fid.lease_key, - SMB2_LEASE_KEY_SIZE)) { - cfid->time = 0; - INIT_WORK(&cfid->lease_break, - smb2_cached_lease_break); - queue_work(cifsiod_wq, - &cfid->lease_break); - return true; + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (cfid->has_lease && + !memcmp(lease_key, + cfid->fid.lease_key, + SMB2_LEASE_KEY_SIZE)) { + cfid->time = 0; + /* + * We found a lease remove it from the list + * so no threads can access it. + */ + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + + queue_work(cifsiod_wq, + &cfid->lease_break); + spin_unlock(&cfids->cfid_list_lock); + return true; + } } + spin_unlock(&cfids->cfid_list_lock); return false; } -struct cached_fid *init_cached_dir(const char *path) +static struct cached_fid *init_cached_dir(const char *path) { struct cached_fid *cfid; - cfid = kzalloc(sizeof(*cfid), GFP_KERNEL); + cfid = kzalloc(sizeof(*cfid), GFP_ATOMIC); if (!cfid) return NULL; - cfid->path = kstrdup(path, GFP_KERNEL); + cfid->path = kstrdup(path, GFP_ATOMIC); if (!cfid->path) { kfree(cfid); return NULL; } + INIT_WORK(&cfid->lease_break, smb2_cached_lease_break); + INIT_LIST_HEAD(&cfid->entry); INIT_LIST_HEAD(&cfid->dirents.entries); mutex_init(&cfid->dirents.de_mutex); - mutex_init(&cfid->fid_mutex); + spin_lock_init(&cfid->fid_lock); + kref_init(&cfid->refcount); return cfid; } -void free_cached_dir(struct cached_fid *cfid) +static void free_cached_dir(struct cached_fid *cfid) { + struct cached_dirent *dirent, *q; + + dput(cfid->dentry); + cfid->dentry = NULL; + + /* + * Delete all cached dirent names + */ + list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { + list_del(&dirent->entry); + kfree(dirent->name); + kfree(dirent); + } + kfree(cfid->path); cfid->path = NULL; kfree(cfid); @@ -426,15 +506,34 @@ struct cached_fids *init_cached_dirs(void) cfids = kzalloc(sizeof(*cfids), GFP_KERNEL); if (!cfids) return NULL; - mutex_init(&cfids->cfid_list_mutex); + spin_lock_init(&cfids->cfid_list_lock); + INIT_LIST_HEAD(&cfids->entries); return cfids; } +/* + * Called from tconInfoFree when we are tearing down the tcon. + * There are no active users or open files/directories at this point. + */ void free_cached_dirs(struct cached_fids *cfids) { - if (cfids->cfid) { - free_cached_dir(cfids->cfid); - cfids->cfid = NULL; + struct cached_fid *cfid, *q; + struct list_head entry; + + INIT_LIST_HEAD(&entry); + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + cfid->on_list = false; + cfid->is_open = false; + list_del(&cfid->entry); + list_add(&cfid->entry, &entry); + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + list_del(&cfid->entry); + free_cached_dir(cfid); } + kfree(cfids); } diff --git a/fs/cifs/cached_dir.h b/fs/cifs/cached_dir.h index bdf6c3866653..e536304ca2ce 100644 --- a/fs/cifs/cached_dir.h +++ b/fs/cifs/cached_dir.h @@ -31,14 +31,17 @@ struct cached_dirents { }; struct cached_fid { + struct list_head entry; + struct cached_fids *cfids; const char *path; - bool is_valid:1; /* Do we have a useable root fid */ - bool file_all_info_is_valid:1; bool has_lease:1; + bool is_open:1; + bool on_list:1; + bool file_all_info_is_valid:1; unsigned long time; /* jiffies of when lease was taken */ struct kref refcount; struct cifs_fid fid; - struct mutex fid_mutex; + spinlock_t fid_lock; struct cifs_tcon *tcon; struct dentry *dentry; struct work_struct lease_break; @@ -46,9 +49,14 @@ struct cached_fid { struct cached_dirents dirents; }; +#define MAX_CACHED_FIDS 16 struct cached_fids { - struct mutex cfid_list_mutex; - struct cached_fid *cfid; + /* Must be held when: + * - accessing the cfids->entries list + */ + spinlock_t cfid_list_lock; + int num_entries; + struct list_head entries; }; extern struct cached_fids *init_cached_dirs(void); @@ -61,8 +69,6 @@ extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon, struct dentry *dentry, struct cached_fid **cfid); extern void close_cached_dir(struct cached_fid *cfid); -extern void close_cached_dir_lease(struct cached_fid *cfid); -extern void close_cached_dir_lease_locked(struct cached_fid *cfid); extern void close_all_cached_dirs(struct cifs_sb_info *cifs_sb); extern void invalidate_all_cached_dirs(struct cifs_tcon *tcon); extern int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]); diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index b87cbbe6d2d4..d86d78d5bfdc 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -91,6 +91,13 @@ struct smb3_notify { bool watch_tree; } __packed; +struct smb3_notify_info { + __u32 completion_filter; + bool watch_tree; + __u32 data_len; /* size of notify data below */ + __u8 notify_data[]; +} __packed; + #define CIFS_IOCTL_MAGIC 0xCF #define CIFS_IOC_COPYCHUNK_FILE _IOW(CIFS_IOCTL_MAGIC, 3, int) #define CIFS_IOC_SET_INTEGRITY _IO(CIFS_IOCTL_MAGIC, 4) @@ -100,6 +107,7 @@ struct smb3_notify { #define CIFS_DUMP_KEY _IOWR(CIFS_IOCTL_MAGIC, 8, struct smb3_key_debug_info) #define CIFS_IOC_NOTIFY _IOW(CIFS_IOCTL_MAGIC, 9, struct smb3_notify) #define CIFS_DUMP_FULL_KEY _IOWR(CIFS_IOCTL_MAGIC, 10, struct smb3_full_key_debug_info) +#define CIFS_IOC_NOTIFY_INFO _IOWR(CIFS_IOCTL_MAGIC, 11, struct smb3_notify_info) #define CIFS_IOC_SHUTDOWN _IOR ('X', 125, __u32) /* diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8042d7280dec..c6ac19223ddc 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -396,6 +396,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->epoch = 0; spin_lock_init(&cifs_inode->open_file_lock); generate_random_uuid(cifs_inode->lease_key); + cifs_inode->symlink_target = NULL; /* * Can not set i_flags here - they get immediately overwritten to zero @@ -412,7 +413,11 @@ cifs_alloc_inode(struct super_block *sb) static void cifs_free_inode(struct inode *inode) { - kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); + struct cifsInodeInfo *cinode = CIFS_I(inode); + + if (S_ISLNK(inode->i_mode)) + kfree(cinode->symlink_target); + kmem_cache_free(cifs_inode_cachep, cinode); } static void @@ -1139,7 +1144,7 @@ const struct inode_operations cifs_file_inode_ops = { }; const struct inode_operations cifs_symlink_inode_ops = { - .get_link = cifs_get_link, + .get_link = simple_get_link, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 52ddf4163b98..1420acf987f0 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -185,6 +185,19 @@ struct cifs_cred { struct cifs_ace *aces; }; +struct cifs_open_info_data { + char *symlink_target; + union { + struct smb2_file_all_info fi; + struct smb311_posix_qinfo posix_fi; + }; +}; + +static inline void cifs_free_open_info(struct cifs_open_info_data *data) +{ + kfree(data->symlink_target); +} + /* ***************************************************************** * Except the CIFS PDUs themselves all the @@ -307,20 +320,20 @@ struct smb_version_operations { int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); /* query path data from the server */ - int (*query_path_info)(const unsigned int, struct cifs_tcon *, - struct cifs_sb_info *, const char *, - FILE_ALL_INFO *, bool *, bool *); + int (*query_path_info)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); /* query file data from the server */ - int (*query_file_info)(const unsigned int, struct cifs_tcon *, - struct cifs_fid *, FILE_ALL_INFO *); + int (*query_file_info)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data); /* query reparse tag from srv to determine which type of special file */ int (*query_reparse_tag)(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *path, __u32 *reparse_tag); /* get server index number */ - int (*get_srv_inum)(const unsigned int, struct cifs_tcon *, - struct cifs_sb_info *, const char *, - u64 *uniqueid, FILE_ALL_INFO *); + int (*get_srv_inum)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, u64 *uniqueid, + struct cifs_open_info_data *data); /* set size by path */ int (*set_path_size)(const unsigned int, struct cifs_tcon *, const char *, __u64, struct cifs_sb_info *, bool); @@ -369,8 +382,8 @@ struct smb_version_operations { struct cifs_sb_info *, const char *, char **, bool); /* open a file for non-posix mounts */ - int (*open)(const unsigned int, struct cifs_open_parms *, - __u32 *, FILE_ALL_INFO *); + int (*open)(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf); /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ @@ -441,7 +454,7 @@ struct smb_version_operations { int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *src_file, void __user *); int (*notify)(const unsigned int xid, struct file *pfile, - void __user *pbuf); + void __user *pbuf, bool return_changes); int (*query_mf_symlink)(unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const unsigned char *, char *, unsigned int *); @@ -1123,6 +1136,7 @@ struct cifs_fattr { struct timespec64 cf_mtime; struct timespec64 cf_ctime; u32 cf_cifstag; + char *cf_symlink_target; }; /* @@ -1385,6 +1399,7 @@ struct cifsFileInfo { struct work_struct put; /* work for the final part of _put */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ + char *symlink_target; }; struct cifs_io_parms { @@ -1543,6 +1558,7 @@ struct cifsInodeInfo { struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ + char *symlink_target; }; static inline struct cifsInodeInfo * @@ -2111,4 +2127,14 @@ static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses) return sizeof(ses->workstation_name); } +static inline void move_cifs_info_to_smb2(struct smb2_file_all_info *dst, const FILE_ALL_INFO *src) +{ + memcpy(dst, src, (size_t)((u8 *)&src->AccessFlags - (u8 *)src)); + dst->AccessFlags = src->AccessFlags; + dst->CurrentByteOffset = src->CurrentByteOffset; + dst->Mode = src->Mode; + dst->AlignmentRequirement = src->AlignmentRequirement; + dst->FileNameLength = src->FileNameLength; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 84ec71bdfacd..83e83d8beabb 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -182,10 +182,9 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile, extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); extern void cifs_down_write(struct rw_semaphore *sem); -extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, - struct file *file, - struct tcon_link *tlink, - __u32 oplock); +struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, + struct tcon_link *tlink, __u32 oplock, + const char *symlink_target); extern int cifs_posix_open(const char *full_path, struct inode **inode, struct super_block *sb, int mode, unsigned int f_flags, __u32 *oplock, __u16 *netfid, @@ -200,9 +199,9 @@ extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr); -extern int cifs_get_inode_info(struct inode **inode, const char *full_path, - FILE_ALL_INFO *data, struct super_block *sb, - int xid, const struct cifs_fid *fid); +int cifs_get_inode_info(struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct super_block *sb, int xid, + const struct cifs_fid *fid); extern int smb311_posix_get_inode_info(struct inode **pinode, const char *search_path, struct super_block *sb, unsigned int xid); extern int cifs_get_inode_info_unix(struct inode **pinode, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 7a808e41b1b8..1724066c1536 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -2305,7 +2305,7 @@ int CIFSSMBRenameOpenFile(const unsigned int xid, struct cifs_tcon *pTcon, remap); } rename_info->target_name_len = cpu_to_le32(2 * len_of_str); - count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str); + count = sizeof(struct set_file_rename) + (2 * len_of_str); byte_count += count; pSMB->DataCount = cpu_to_le16(count); pSMB->TotalDataCount = pSMB->DataCount; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 40900aace416..ffb291579bb9 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2832,9 +2832,12 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * sessinit is sent but no second negprot */ struct rfc1002_session_packet *ses_init_buf; + unsigned int req_noscope_len; struct smb_hdr *smb_buf; + ses_init_buf = kzalloc(sizeof(struct rfc1002_session_packet), GFP_KERNEL); + if (ses_init_buf) { ses_init_buf->trailer.session_req.called_len = 32; @@ -2870,8 +2873,12 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) ses_init_buf->trailer.session_req.scope2 = 0; smb_buf = (struct smb_hdr *)ses_init_buf; - /* sizeof RFC1002_SESSION_REQUEST with no scope */ - smb_buf->smb_buf_length = cpu_to_be32(0x81000044); + /* sizeof RFC1002_SESSION_REQUEST with no scopes */ + req_noscope_len = sizeof(struct rfc1002_session_packet) - 2; + + /* == cpu_to_be32(0x81000044) */ + smb_buf->smb_buf_length = + cpu_to_be32((RFC1002_SESSION_REQUEST << 24) | req_noscope_len); rc = smb_send(server, smb_buf, 0x44); kfree(ses_init_buf); /* @@ -3922,12 +3929,11 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, pSMB->AndXCommand = 0xFF; pSMB->Flags = cpu_to_le16(TCON_EXTENDED_SECINFO); bcc_ptr = &pSMB->Password[0]; - if (tcon->pipe || (ses->server->sec_mode & SECMODE_USER)) { - pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ - *bcc_ptr = 0; /* password is null byte */ - bcc_ptr++; /* skip password */ - /* already aligned so no need to do it below */ - } + + pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ + *bcc_ptr = 0; /* password is null byte */ + bcc_ptr++; /* skip password */ + /* already aligned so no need to do it below */ if (ses->server->sign) smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f58869306309..a5c73c2af3a2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -165,10 +165,9 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon) /* Inode operations in similar order to how they appear in Linux file fs.h */ -static int -cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, - struct tcon_link *tlink, unsigned oflags, umode_t mode, - __u32 *oplock, struct cifs_fid *fid) +static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, + struct tcon_link *tlink, unsigned int oflags, umode_t mode, __u32 *oplock, + struct cifs_fid *fid, struct cifs_open_info_data *buf) { int rc = -ENOENT; int create_options = CREATE_NOT_DIR; @@ -177,7 +176,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, struct cifs_tcon *tcon = tlink_tcon(tlink); const char *full_path; void *page = alloc_dentry_path(); - FILE_ALL_INFO *buf = NULL; struct inode *newinode = NULL; int disposition; struct TCP_Server_Info *server = tcon->ses->server; @@ -290,12 +288,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, goto out; } - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - /* * if we're not using unix extensions, see if we need to set * ATTR_READONLY on the create call @@ -364,8 +356,7 @@ cifs_create_get_file_info: { #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* TODO: Add support for calling POSIX query info here, but passing in fid */ - rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, - xid, fid); + rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, xid, fid); if (newinode) { if (server->ops->set_lease_key) server->ops->set_lease_key(newinode, fid); @@ -402,7 +393,6 @@ cifs_create_set_dentry: d_add(direntry, newinode); out: - kfree(buf); free_dentry_path(page); return rc; @@ -423,10 +413,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, struct tcon_link *tlink; struct cifs_tcon *tcon; struct TCP_Server_Info *server; - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; __u32 oplock; struct cifsFileInfo *file_info; + struct cifs_open_info_data buf = {}; if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb)))) return -EIO; @@ -484,8 +475,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, cifs_add_pending_open(&fid, tlink, &open); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid); - + &oplock, &fid, &buf); if (rc) { cifs_del_pending_open(&open); goto out; @@ -510,7 +500,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, file->f_op = &cifs_file_direct_ops; } - file_info = cifs_new_fileinfo(&fid, file, tlink, oplock); + file_info = cifs_new_fileinfo(&fid, file, tlink, oplock, buf.symlink_target); if (file_info == NULL) { if (server->ops->close) server->ops->close(xid, tcon, &fid); @@ -526,6 +516,7 @@ out: cifs_put_tlink(tlink); out_free_xid: free_xid(xid); + cifs_free_open_info(&buf); return rc; } @@ -547,6 +538,7 @@ int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, struct TCP_Server_Info *server; struct cifs_fid fid; __u32 oplock; + struct cifs_open_info_data buf = {}; cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %pd and dentry = 0x%p\n", inode, direntry, direntry); @@ -565,11 +557,11 @@ int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, if (server->ops->new_lease_key) server->ops->new_lease_key(&fid); - rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid); + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, &oplock, &fid, &buf); if (!rc && server->ops->close) server->ops->close(xid, tcon, &fid); + cifs_free_open_info(&buf); cifs_put_tlink(tlink); out_free_xid: free_xid(xid); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7d756721e1a6..f6ffee514c34 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -209,16 +209,14 @@ posix_open_ret: } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -static int -cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, - struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock, - struct cifs_fid *fid, unsigned int xid) +static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, + struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock, + struct cifs_fid *fid, unsigned int xid, struct cifs_open_info_data *buf) { int rc; int desired_access; int disposition; int create_options = CREATE_NOT_DIR; - FILE_ALL_INFO *buf; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; @@ -255,10 +253,6 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci /* BB pass O_SYNC flag through on file attributes .. BB */ - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (!buf) - return -ENOMEM; - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (f_flags & O_SYNC) create_options |= CREATE_WRITE_THROUGH; @@ -276,9 +270,8 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci oparms.reconnect = false; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) - goto out; + return rc; /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -294,8 +287,6 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci rc = -EOPENSTALE; } -out: - kfree(buf); return rc; } @@ -325,9 +316,9 @@ cifs_down_write(struct rw_semaphore *sem) static void cifsFileInfo_put_work(struct work_struct *work); -struct cifsFileInfo * -cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, - struct tcon_link *tlink, __u32 oplock) +struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, + struct tcon_link *tlink, __u32 oplock, + const char *symlink_target) { struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); @@ -347,6 +338,15 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, return NULL; } + if (symlink_target) { + cfile->symlink_target = kstrdup(symlink_target, GFP_KERNEL); + if (!cfile->symlink_target) { + kfree(fdlocks); + kfree(cfile); + return NULL; + } + } + INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; @@ -440,6 +440,7 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file) cifs_put_tlink(cifs_file->tlink); dput(cifs_file->dentry); cifs_sb_deactive(sb); + kfree(cifs_file->symlink_target); kfree(cifs_file); } @@ -488,7 +489,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifsInodeInfo *cifsi = CIFS_I(inode); struct super_block *sb = inode->i_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; @@ -570,8 +571,9 @@ int cifs_open(struct inode *inode, struct file *file) void *page; const char *full_path; bool posix_open_ok = false; - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; + struct cifs_open_info_data data = {}; xid = get_xid(); @@ -662,15 +664,15 @@ int cifs_open(struct inode *inode, struct file *file) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &fid); - rc = cifs_nt_open(full_path, inode, cifs_sb, tcon, - file->f_flags, &oplock, &fid, xid); + rc = cifs_nt_open(full_path, inode, cifs_sb, tcon, file->f_flags, &oplock, &fid, + xid, &data); if (rc) { cifs_del_pending_open(&open); goto out; } } - cfile = cifs_new_fileinfo(&fid, file, tlink, oplock); + cfile = cifs_new_fileinfo(&fid, file, tlink, oplock, data.symlink_target); if (cfile == NULL) { if (server->ops->close) server->ops->close(xid, tcon, &fid); @@ -712,6 +714,7 @@ out: free_dentry_path(page); free_xid(xid); cifs_put_tlink(tlink); + cifs_free_open_info(&data); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ad10c61ab5c9..7cf96e581d24 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -210,6 +210,17 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) */ inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9; } + + if (S_ISLNK(fattr->cf_mode)) { + kfree(cifs_i->symlink_target); + cifs_i->symlink_target = fattr->cf_symlink_target; + fattr->cf_symlink_target = NULL; + + if (unlikely(!cifs_i->symlink_target)) + inode->i_link = ERR_PTR(-EOPNOTSUPP); + else + inode->i_link = cifs_i->symlink_target; + } spin_unlock(&inode->i_lock); if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL) @@ -347,13 +358,20 @@ cifs_get_file_info_unix(struct file *filp) int rc; unsigned int xid; FILE_UNIX_BASIC_INFO find_data; - struct cifs_fattr fattr; + struct cifs_fattr fattr = {}; struct inode *inode = file_inode(filp); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsFileInfo *cfile = filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); xid = get_xid(); + + if (cfile->symlink_target) { + fattr.cf_symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!fattr.cf_symlink_target) + return -ENOMEM; + } + rc = CIFSSMBUnixQFileInfo(xid, tcon, cfile->fid.netfid, &find_data); if (!rc) { cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb); @@ -378,6 +396,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, FILE_UNIX_BASIC_INFO find_data; struct cifs_fattr fattr; struct cifs_tcon *tcon; + struct TCP_Server_Info *server; struct tcon_link *tlink; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); @@ -387,10 +406,12 @@ int cifs_get_inode_info_unix(struct inode **pinode, if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); + server = tcon->ses->server; /* could have done a find first instead but this returns more info */ rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data, cifs_sb->local_nls, cifs_remap(cifs_sb)); + cifs_dbg(FYI, "%s: query path info: rc = %d\n", __func__, rc); cifs_put_tlink(tlink); if (!rc) { @@ -410,6 +431,17 @@ int cifs_get_inode_info_unix(struct inode **pinode, cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc); } + if (S_ISLNK(fattr.cf_mode) && !fattr.cf_symlink_target) { + if (!server->ops->query_symlink) + return -EOPNOTSUPP; + rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, + &fattr.cf_symlink_target, false); + if (rc) { + cifs_dbg(FYI, "%s: query_symlink: %d\n", __func__, rc); + goto cgiiu_exit; + } + } + if (*pinode == NULL) { /* get new inode */ cifs_fill_uniqueid(sb, &fattr); @@ -432,6 +464,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, } cgiiu_exit: + kfree(fattr.cf_symlink_target); return rc; } #else @@ -601,10 +634,10 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, } /* Fill a cifs_fattr struct with info from POSIX info struct */ -static void -smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo *info, - struct super_block *sb, bool adjust_tz, bool symlink) +static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct cifs_open_info_data *data, + struct super_block *sb, bool adjust_tz, bool symlink) { + struct smb311_posix_qinfo *info = &data->posix_fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -639,6 +672,8 @@ smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo * if (symlink) { fattr->cf_mode |= S_IFLNK; fattr->cf_dtype = DT_LNK; + fattr->cf_symlink_target = data->symlink_target; + data->symlink_target = NULL; } else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { fattr->cf_mode |= S_IFDIR; fattr->cf_dtype = DT_DIR; @@ -655,13 +690,11 @@ smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo * fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); } - -/* Fill a cifs_fattr struct with info from FILE_ALL_INFO */ -static void -cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, - struct super_block *sb, bool adjust_tz, - bool symlink, u32 reparse_tag) +static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, struct cifs_open_info_data *data, + struct super_block *sb, bool adjust_tz, bool symlink, + u32 reparse_tag) { + struct smb2_file_all_info *info = &data->fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -703,7 +736,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, } else if (reparse_tag == IO_REPARSE_TAG_LX_BLK) { fattr->cf_mode |= S_IFBLK | cifs_sb->ctx->file_mode; fattr->cf_dtype = DT_BLK; - } else if (symlink) { /* TODO add more reparse tag checks */ + } else if (symlink || reparse_tag == IO_REPARSE_TAG_SYMLINK || + reparse_tag == IO_REPARSE_TAG_NFS) { fattr->cf_mode = S_IFLNK; fattr->cf_dtype = DT_LNK; } else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { @@ -735,6 +769,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, } } + if (S_ISLNK(fattr->cf_mode)) { + fattr->cf_symlink_target = data->symlink_target; + data->symlink_target = NULL; + } + fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; } @@ -744,23 +783,28 @@ cifs_get_file_info(struct file *filp) { int rc; unsigned int xid; - FILE_ALL_INFO find_data; + struct cifs_open_info_data data = {}; struct cifs_fattr fattr; struct inode *inode = file_inode(filp); struct cifsFileInfo *cfile = filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; + bool symlink = false; + u32 tag = 0; if (!server->ops->query_file_info) return -ENOSYS; xid = get_xid(); - rc = server->ops->query_file_info(xid, tcon, &cfile->fid, &find_data); + rc = server->ops->query_file_info(xid, tcon, cfile, &data); switch (rc) { case 0: /* TODO: add support to query reparse tag */ - cifs_all_info_to_fattr(&fattr, &find_data, inode->i_sb, false, - false, 0 /* no reparse tag */); + if (data.symlink_target) { + symlink = true; + tag = IO_REPARSE_TAG_SYMLINK; + } + cifs_open_info_to_fattr(&fattr, &data, inode->i_sb, false, symlink, tag); break; case -EREMOTE: cifs_create_dfs_fattr(&fattr, inode->i_sb); @@ -789,6 +833,7 @@ cifs_get_file_info(struct file *filp) /* if filetype is different, return error */ rc = cifs_fattr_to_inode(inode, &fattr); cgfi_exit: + cifs_free_open_info(&data); free_xid(xid); return rc; } @@ -860,14 +905,9 @@ cifs_backup_query_path_info(int xid, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -static void -cifs_set_fattr_ino(int xid, - struct cifs_tcon *tcon, - struct super_block *sb, - struct inode **inode, - const char *full_path, - FILE_ALL_INFO *data, - struct cifs_fattr *fattr) +static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_block *sb, + struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct cifs_fattr *fattr) { struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct TCP_Server_Info *server = tcon->ses->server; @@ -885,11 +925,8 @@ cifs_set_fattr_ino(int xid, * If we have an inode pass a NULL tcon to ensure we don't * make a round trip to the server. This only works for SMB2+. */ - rc = server->ops->get_srv_inum(xid, - *inode ? NULL : tcon, - cifs_sb, full_path, - &fattr->cf_uniqueid, - data); + rc = server->ops->get_srv_inum(xid, *inode ? NULL : tcon, cifs_sb, full_path, + &fattr->cf_uniqueid, data); if (rc) { /* * If that fails reuse existing ino or generate one @@ -923,14 +960,10 @@ static inline bool is_inode_cache_good(struct inode *ino) return ino && CIFS_CACHE_READ(CIFS_I(ino)) && CIFS_I(ino)->time != 0; } -int -cifs_get_inode_info(struct inode **inode, - const char *full_path, - FILE_ALL_INFO *in_data, - struct super_block *sb, int xid, - const struct cifs_fid *fid) +int cifs_get_inode_info(struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct super_block *sb, int xid, + const struct cifs_fid *fid) { - struct cifs_tcon *tcon; struct TCP_Server_Info *server; struct tcon_link *tlink; @@ -938,8 +971,7 @@ cifs_get_inode_info(struct inode **inode, bool adjust_tz = false; struct cifs_fattr fattr = {0}; bool is_reparse_point = false; - FILE_ALL_INFO *data = in_data; - FILE_ALL_INFO *tmp_data = NULL; + struct cifs_open_info_data tmp_data = {}; void *smb1_backup_rsp_buf = NULL; int rc = 0; int tmprc = 0; @@ -960,21 +992,15 @@ cifs_get_inode_info(struct inode **inode, cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); goto out; } - tmp_data = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (!tmp_data) { - rc = -ENOMEM; - goto out; - } - rc = server->ops->query_path_info(xid, tcon, cifs_sb, - full_path, tmp_data, - &adjust_tz, &is_reparse_point); + rc = server->ops->query_path_info(xid, tcon, cifs_sb, full_path, &tmp_data, + &adjust_tz, &is_reparse_point); #ifdef CONFIG_CIFS_DFS_UPCALL if (rc == -ENOENT && is_tcon_dfs(tcon)) rc = cifs_dfs_query_info_nonascii_quirk(xid, tcon, cifs_sb, full_path); #endif - data = tmp_data; + data = &tmp_data; } /* @@ -988,14 +1014,24 @@ cifs_get_inode_info(struct inode **inode, * since we have to check if its reparse tag matches a known * special file type e.g. symlink or fifo or char etc. */ - if ((le32_to_cpu(data->Attributes) & ATTR_REPARSE) && - server->ops->query_reparse_tag) { - rc = server->ops->query_reparse_tag(xid, tcon, cifs_sb, - full_path, &reparse_tag); - cifs_dbg(FYI, "reparse tag 0x%x\n", reparse_tag); + if (is_reparse_point && data->symlink_target) { + reparse_tag = IO_REPARSE_TAG_SYMLINK; + } else if ((le32_to_cpu(data->fi.Attributes) & ATTR_REPARSE) && + server->ops->query_reparse_tag) { + tmprc = server->ops->query_reparse_tag(xid, tcon, cifs_sb, full_path, + &reparse_tag); + if (tmprc) + cifs_dbg(FYI, "%s: query_reparse_tag: rc = %d\n", __func__, tmprc); + if (server->ops->query_symlink) { + tmprc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, + &data->symlink_target, + is_reparse_point); + if (tmprc) + cifs_dbg(FYI, "%s: query_symlink: rc = %d\n", __func__, + tmprc); + } } - cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz, - is_reparse_point, reparse_tag); + cifs_open_info_to_fattr(&fattr, data, sb, adjust_tz, is_reparse_point, reparse_tag); break; case -EREMOTE: /* DFS link, no metadata available on this server */ @@ -1014,18 +1050,20 @@ cifs_get_inode_info(struct inode **inode, */ if (backup_cred(cifs_sb) && is_smb1_server(server)) { /* for easier reading */ + FILE_ALL_INFO *fi; FILE_DIRECTORY_INFO *fdi; SEARCH_ID_FULL_DIR_INFO *si; rc = cifs_backup_query_path_info(xid, tcon, sb, full_path, &smb1_backup_rsp_buf, - &data); + &fi); if (rc) goto out; - fdi = (FILE_DIRECTORY_INFO *)data; - si = (SEARCH_ID_FULL_DIR_INFO *)data; + move_cifs_info_to_smb2(&data->fi, fi); + fdi = (FILE_DIRECTORY_INFO *)fi; + si = (SEARCH_ID_FULL_DIR_INFO *)fi; cifs_dir_info_to_fattr(&fattr, fdi, cifs_sb); fattr.cf_uniqueid = le64_to_cpu(si->UniqueId); @@ -1123,7 +1161,8 @@ handle_mnt_opt: out: cifs_buf_release(smb1_backup_rsp_buf); cifs_put_tlink(tlink); - kfree(tmp_data); + cifs_free_open_info(&tmp_data); + kfree(fattr.cf_symlink_target); return rc; } @@ -1138,7 +1177,7 @@ smb311_posix_get_inode_info(struct inode **inode, bool adjust_tz = false; struct cifs_fattr fattr = {0}; bool symlink = false; - struct smb311_posix_qinfo *data = NULL; + struct cifs_open_info_data data = {}; int rc = 0; int tmprc = 0; @@ -1155,15 +1194,9 @@ smb311_posix_get_inode_info(struct inode **inode, cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); goto out; } - data = kmalloc(sizeof(struct smb311_posix_qinfo), GFP_KERNEL); - if (!data) { - rc = -ENOMEM; - goto out; - } - rc = smb311_posix_query_path_info(xid, tcon, cifs_sb, - full_path, data, - &adjust_tz, &symlink); + rc = smb311_posix_query_path_info(xid, tcon, cifs_sb, full_path, &data, &adjust_tz, + &symlink); /* * 2. Convert it to internal cifs metadata (fattr) @@ -1171,7 +1204,7 @@ smb311_posix_get_inode_info(struct inode **inode, switch (rc) { case 0: - smb311_posix_info_to_fattr(&fattr, data, sb, adjust_tz, symlink); + smb311_posix_info_to_fattr(&fattr, &data, sb, adjust_tz, symlink); break; case -EREMOTE: /* DFS link, no metadata available on this server */ @@ -1228,7 +1261,8 @@ smb311_posix_get_inode_info(struct inode **inode, } out: cifs_put_tlink(tlink); - kfree(data); + cifs_free_open_info(&data); + kfree(fattr.cf_symlink_target); return rc; } @@ -2265,13 +2299,13 @@ cifs_dentry_needs_reval(struct dentry *dentry) return true; if (!open_cached_dir_by_dentry(tcon, dentry->d_parent, &cfid)) { - mutex_lock(&cfid->fid_mutex); + spin_lock(&cfid->fid_lock); if (cfid->time && cifs_i->time > cfid->time) { - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfid->fid_lock); close_cached_dir(cfid); return false; } - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfid->fid_lock); close_cached_dir(cfid); } /* diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index b6e6e5d6c8dd..89d5fa887364 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -484,12 +484,35 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) tcon = tlink_tcon(tlink); if (tcon && tcon->ses->server->ops->notify) { rc = tcon->ses->server->ops->notify(xid, - filep, (void __user *)arg); + filep, (void __user *)arg, + false /* no ret data */); cifs_dbg(FYI, "ioctl notify rc %d\n", rc); } else rc = -EOPNOTSUPP; cifs_put_tlink(tlink); break; + case CIFS_IOC_NOTIFY_INFO: + if (!S_ISDIR(inode->i_mode)) { + /* Notify can only be done on directories */ + rc = -EOPNOTSUPP; + break; + } + cifs_sb = CIFS_SB(inode->i_sb); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + break; + } + tcon = tlink_tcon(tlink); + if (tcon && tcon->ses->server->ops->notify) { + rc = tcon->ses->server->ops->notify(xid, + filep, (void __user *)arg, + true /* return details */); + cifs_dbg(FYI, "ioctl notify info rc %d\n", rc); + } else + rc = -EOPNOTSUPP; + cifs_put_tlink(tlink); + break; case CIFS_IOC_SHUTDOWN: rc = cifs_shutdown(inode->i_sb, arg); break; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index cd29c296cec6..bd374feeccaa 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -201,40 +201,6 @@ out: return rc; } -static int -query_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const unsigned char *path, - char **symlinkinfo) -{ - int rc; - u8 *buf = NULL; - unsigned int link_len = 0; - unsigned int bytes_read = 0; - - buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (tcon->ses->server->ops->query_mf_symlink) - rc = tcon->ses->server->ops->query_mf_symlink(xid, tcon, - cifs_sb, path, buf, &bytes_read); - else - rc = -ENOSYS; - - if (rc) - goto out; - - if (bytes_read == 0) { /* not a symlink */ - rc = -EINVAL; - goto out; - } - - rc = parse_mf_symlink(buf, bytes_read, &link_len, symlinkinfo); -out: - kfree(buf); - return rc; -} - int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, @@ -244,6 +210,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, u8 *buf = NULL; unsigned int link_len = 0; unsigned int bytes_read = 0; + char *symlink = NULL; if (!couldbe_mf_symlink(fattr)) /* it's not a symlink */ @@ -265,7 +232,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, if (bytes_read == 0) /* not a symlink */ goto out; - rc = parse_mf_symlink(buf, bytes_read, &link_len, NULL); + rc = parse_mf_symlink(buf, bytes_read, &link_len, &symlink); if (rc == -EINVAL) { /* it's not a symlink */ rc = 0; @@ -280,6 +247,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO; fattr->cf_dtype = DT_LNK; + fattr->cf_symlink_target = symlink; out: kfree(buf); return rc; @@ -599,75 +567,6 @@ cifs_hl_exit: return rc; } -const char * -cifs_get_link(struct dentry *direntry, struct inode *inode, - struct delayed_call *done) -{ - int rc = -ENOMEM; - unsigned int xid; - const char *full_path; - void *page; - char *target_path = NULL; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct tcon_link *tlink = NULL; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; - - if (!direntry) - return ERR_PTR(-ECHILD); - - xid = get_xid(); - - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) { - free_xid(xid); - return ERR_CAST(tlink); - } - tcon = tlink_tcon(tlink); - server = tcon->ses->server; - - page = alloc_dentry_path(); - full_path = build_path_from_dentry(direntry, page); - if (IS_ERR(full_path)) { - free_xid(xid); - cifs_put_tlink(tlink); - free_dentry_path(page); - return ERR_CAST(full_path); - } - - cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode); - - rc = -EACCES; - /* - * First try Minshall+French Symlinks, if configured - * and fallback to UNIX Extensions Symlinks. - */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) - rc = query_mf_symlink(xid, tcon, cifs_sb, full_path, - &target_path); - - if (rc != 0 && server->ops->query_symlink) { - struct cifsInodeInfo *cifsi = CIFS_I(inode); - bool reparse_point = false; - - if (cifsi->cifsAttrs & ATTR_REPARSE) - reparse_point = true; - - rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, - &target_path, reparse_point); - } - - free_dentry_path(page); - free_xid(xid); - cifs_put_tlink(tlink); - if (rc != 0) { - kfree(target_path); - return ERR_PTR(rc); - } - set_delayed_call(done, kfree_link, target_path); - return target_path; -} - int cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, struct dentry *direntry, const char *symname) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 8e060c00c969..2d75ba5aaa8a 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -844,17 +844,34 @@ static bool emit_cached_dirents(struct cached_dirents *cde, struct dir_context *ctx) { struct cached_dirent *dirent; - int rc; + bool rc; list_for_each_entry(dirent, &cde->entries, entry) { - if (ctx->pos >= dirent->pos) + /* + * Skip all early entries prior to the current lseek() + * position. + */ + if (ctx->pos > dirent->pos) continue; + /* + * We recorded the current ->pos value for the dirent + * when we stored it in the cache. + * However, this sequence of ->pos values may have holes + * in it, for example dot-dirs returned from the server + * are suppressed. + * Handle this bu forcing ctx->pos to be the same as the + * ->pos of the current dirent we emit from the cache. + * This means that when we emit these entries from the cache + * we now emit them with the same ->pos value as in the + * initial scan. + */ ctx->pos = dirent->pos; rc = dir_emit(ctx, dirent->name, dirent->namelen, dirent->fattr.cf_uniqueid, dirent->fattr.cf_dtype); if (!rc) return rc; + ctx->pos++; } return true; } @@ -994,6 +1011,8 @@ static int cifs_filldir(char *find_entry, struct file *file, cifs_unix_basic_to_fattr(&fattr, &((FILE_UNIX_INFO *)find_entry)->basic, cifs_sb); + if (S_ISLNK(fattr.cf_mode)) + fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; break; case SMB_FIND_FILE_INFO_STANDARD: cifs_std_info_to_fattr(&fattr, @@ -1202,10 +1221,10 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) ctx->pos, tmp_buf); cifs_save_resume_key(current_entry, cifsFile); break; - } else - current_entry = - nxt_dir_entry(current_entry, end_of_smb, - cifsFile->srch_inf.info_level); + } + current_entry = + nxt_dir_entry(current_entry, end_of_smb, + cifsFile->srch_inf.info_level); } kfree(tmp_buf); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index f1c3c6d9146c..0435d1dfa9e1 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -601,11 +601,6 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, /* BB FIXME add check that strings total less than 335 or will need to send them as arrays */ - /* unicode strings, must be word aligned before the call */ -/* if ((long) bcc_ptr % 2) { - *bcc_ptr = 0; - bcc_ptr++; - } */ /* copy user */ if (ses->user_name == NULL) { /* null user mount */ @@ -1213,16 +1208,18 @@ out_free_smb_buf: static void sess_free_buffer(struct sess_data *sess_data) { - int i; + struct kvec *iov = sess_data->iov; - /* zero the session data before freeing, as it might contain sensitive info (keys, etc) */ - for (i = 0; i < 3; i++) - if (sess_data->iov[i].iov_base) - memzero_explicit(sess_data->iov[i].iov_base, sess_data->iov[i].iov_len); + /* + * Zero the session data before freeing, as it might contain sensitive info (keys, etc). + * Note that iov[1] is already freed by caller. + */ + if (sess_data->buf0_type != CIFS_NO_BUFFER && iov[0].iov_base) + memzero_explicit(iov[0].iov_base, iov[0].iov_len); - free_rsp_buf(sess_data->buf0_type, sess_data->iov[0].iov_base); + free_rsp_buf(sess_data->buf0_type, iov[0].iov_base); sess_data->buf0_type = CIFS_NO_BUFFER; - kfree(sess_data->iov[2].iov_base); + kfree_sensitive(iov[2].iov_base); } static int @@ -1324,7 +1321,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) } if (ses->capabilities & CAP_UNICODE) { - if (sess_data->iov[0].iov_len % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1364,7 +1361,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } @@ -1448,8 +1445,7 @@ sess_auth_kerberos(struct sess_data *sess_data) if (ses->capabilities & CAP_UNICODE) { /* unicode strings must be word aligned */ - if ((sess_data->iov[0].iov_len - + sess_data->iov[1].iov_len) % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1500,7 +1496,7 @@ sess_auth_kerberos(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } @@ -1552,7 +1548,7 @@ _sess_auth_rawntlmssp_assemble_req(struct sess_data *sess_data) bcc_ptr = sess_data->iov[2].iov_base; /* unicode strings must be word aligned */ - if ((sess_data->iov[0].iov_len + sess_data->iov[1].iov_len) % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1753,7 +1749,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index f36b2d2d40ca..50480751e521 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -542,31 +542,32 @@ cifs_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - FILE_ALL_INFO *data, bool *adjustTZ, bool *symlink) +static int cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjustTZ, bool *symlink) { int rc; + FILE_ALL_INFO fi = {}; *symlink = false; /* could do find first instead but this returns more info */ - rc = CIFSSMBQPathInfo(xid, tcon, full_path, data, 0 /* not legacy */, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */, cifs_sb->local_nls, + cifs_remap(cifs_sb)); /* * BB optimize code so we do not make the above call when server claims * no NT SMB support and the above call failed at least once - set flag * in tcon or mount. */ if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) { - rc = SMBQueryInformation(xid, tcon, full_path, data, - cifs_sb->local_nls, + rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls, cifs_remap(cifs_sb)); + if (!rc) + move_cifs_info_to_smb2(&data->fi, &fi); *adjustTZ = true; } - if (!rc && (le32_to_cpu(data->Attributes) & ATTR_REPARSE)) { + if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) { int tmprc; int oplock = 0; struct cifs_fid fid; @@ -592,10 +593,9 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - u64 *uniqueid, FILE_ALL_INFO *data) +static int cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + u64 *uniqueid, struct cifs_open_info_data *unused) { /* * We can not use the IndexNumber field by default from Windows or @@ -613,11 +613,22 @@ cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, cifs_remap(cifs_sb)); } -static int -cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_fid *fid, FILE_ALL_INFO *data) +static int cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data) { - return CIFSSMBQFileInfo(xid, tcon, fid->netfid, data); + int rc; + FILE_ALL_INFO fi = {}; + + if (cfile->symlink_target) { + data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!data->symlink_target) + return -ENOMEM; + } + + rc = CIFSSMBQFileInfo(xid, tcon, cfile->fid.netfid, &fi); + if (!rc) + move_cifs_info_to_smb2(&data->fi, &fi); + return rc; } static void @@ -702,19 +713,20 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, cifsInode->cifsAttrs = dosattrs; } -static int -cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf) +static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf) { + FILE_ALL_INFO *fi = buf; + if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS)) return SMBLegacyOpen(xid, oparms->tcon, oparms->path, oparms->disposition, oparms->desired_access, oparms->create_options, - &oparms->fid->netfid, oplock, buf, + &oparms->fid->netfid, oplock, fi, oparms->cifs_sb->local_nls, cifs_remap(oparms->cifs_sb)); - return CIFS_open(xid, oparms, oplock, buf); + return CIFS_open(xid, oparms, oplock, fi); } static void diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 9dfd2dd612c2..ffbd9a99fc12 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -20,40 +20,125 @@ #include "cifs_unicode.h" #include "fscache.h" #include "smb2proto.h" +#include "smb2status.h" -int -smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf) +static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) +{ + struct smb2_err_rsp *err = iov->iov_base; + struct smb2_symlink_err_rsp *sym = ERR_PTR(-EINVAL); + u32 len; + + if (err->ErrorContextCount) { + struct smb2_error_context_rsp *p, *end; + + len = (u32)err->ErrorContextCount * (offsetof(struct smb2_error_context_rsp, + ErrorContextData) + + sizeof(struct smb2_symlink_err_rsp)); + if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err)) + return ERR_PTR(-EINVAL); + + p = (struct smb2_error_context_rsp *)err->ErrorData; + end = (struct smb2_error_context_rsp *)((u8 *)err + iov->iov_len); + do { + if (le32_to_cpu(p->ErrorId) == SMB2_ERROR_ID_DEFAULT) { + sym = (struct smb2_symlink_err_rsp *)&p->ErrorContextData; + break; + } + cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", + __func__, le32_to_cpu(p->ErrorId)); + + len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + p = (struct smb2_error_context_rsp *)((u8 *)&p->ErrorContextData + len); + } while (p < end); + } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && + iov->iov_len >= SMB2_SYMLINK_STRUCT_SIZE) { + sym = (struct smb2_symlink_err_rsp *)err->ErrorData; + } + + if (!IS_ERR(sym) && (le32_to_cpu(sym->SymLinkErrorTag) != SYMLINK_ERROR_TAG || + le32_to_cpu(sym->ReparseTag) != IO_REPARSE_TAG_SYMLINK)) + sym = ERR_PTR(-EINVAL); + + return sym; +} + +int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, char **path) +{ + struct smb2_symlink_err_rsp *sym; + unsigned int sub_offs, sub_len; + unsigned int print_offs, print_len; + char *s; + + if (!cifs_sb || !iov || !iov->iov_base || !iov->iov_len || !path) + return -EINVAL; + + sym = symlink_data(iov); + if (IS_ERR(sym)) + return PTR_ERR(sym); + + sub_len = le16_to_cpu(sym->SubstituteNameLength); + sub_offs = le16_to_cpu(sym->SubstituteNameOffset); + print_len = le16_to_cpu(sym->PrintNameLength); + print_offs = le16_to_cpu(sym->PrintNameOffset); + + if (iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offs + sub_len || + iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + print_offs + print_len) + return -EINVAL; + + s = cifs_strndup_from_utf16((char *)sym->PathBuffer + sub_offs, sub_len, true, + cifs_sb->local_nls); + if (!s) + return -ENOMEM; + convert_delimiter(s, '/'); + cifs_dbg(FYI, "%s: symlink target: %s\n", __func__, s); + + *path = s; + return 0; +} + +int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, void *buf) { int rc; __le16 *smb2_path; - struct smb2_file_all_info *smb2_data = NULL; __u8 smb2_oplock; + struct cifs_open_info_data *data = buf; + struct smb2_file_all_info file_info = {}; + struct smb2_file_all_info *smb2_data = data ? &file_info : NULL; + struct kvec err_iov = {}; + int err_buftype = CIFS_NO_BUFFER; struct cifs_fid *fid = oparms->fid; struct network_resiliency_req nr_ioctl_req; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); - if (smb2_path == NULL) { - rc = -ENOMEM; - goto out; - } - - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) { - rc = -ENOMEM; - goto out; - } + if (smb2_path == NULL) + return -ENOMEM; oparms->desired_access |= FILE_READ_ATTRIBUTES; smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; - rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, - NULL, NULL); + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + &err_buftype); + if (rc && data) { + struct smb2_hdr *hdr = err_iov.iov_base; + + if (unlikely(!err_iov.iov_base || err_buftype == CIFS_NO_BUFFER)) + rc = -ENOMEM; + else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK) { + rc = smb2_parse_symlink_response(oparms->cifs_sb, &err_iov, + &data->symlink_target); + if (!rc) { + memset(smb2_data, 0, sizeof(*smb2_data)); + oparms->create_options |= OPEN_REPARSE_POINT; + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, + NULL, NULL, NULL); + oparms->create_options &= ~OPEN_REPARSE_POINT; + } + } + } + if (rc) goto out; - if (oparms->tcon->use_resilient) { /* default timeout is 0, servers pick default (120 seconds) */ nr_ioctl_req.Timeout = @@ -73,7 +158,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = 0; } - if (buf) { + if (smb2_data) { /* if open response does not have IndexNumber field - get it */ if (smb2_data->IndexNumber == 0) { rc = SMB2_get_srv_num(xid, oparms->tcon, @@ -89,12 +174,12 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = 0; } } - move_smb2_info_to_cifs(buf, smb2_data); + memcpy(&data->fi, smb2_data, sizeof(data->fi)); } *oplock = smb2_oplock; out: - kfree(smb2_data); + free_rsp_buf(err_buftype, err_iov.iov_base); kfree(smb2_path); return rc; } diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index bb3e3d5a0cda..a6640e6ea58b 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -24,6 +24,7 @@ #include "smb2pdu.h" #include "smb2proto.h" #include "cached_dir.h" +#include "smb2status.h" static void free_set_inf_compound(struct smb_rqst *rqst) @@ -50,13 +51,15 @@ struct cop_vars { /* * note: If cfile is passed, the reference to it is dropped here. * So make sure that you do not reuse cfile after return from this func. + * + * If passing @err_iov and @err_buftype, ensure to make them both large enough (>= 3) to hold all + * error responses. Caller is also responsible for freeing them up. */ -static int -smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - __u32 desired_access, __u32 create_disposition, - __u32 create_options, umode_t mode, void *ptr, int command, - struct cifsFileInfo *cfile) +static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + __u32 desired_access, __u32 create_disposition, __u32 create_options, + umode_t mode, void *ptr, int command, struct cifsFileInfo *cfile, + struct kvec *err_iov, int *err_buftype) { struct cop_vars *vars = NULL; struct kvec *rsp_iov; @@ -70,6 +73,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, int num_rqst = 0; int resp_buftype[3]; struct smb2_query_info_rsp *qi_rsp = NULL; + struct cifs_open_info_data *idata; int flags = 0; __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; unsigned int size[2]; @@ -385,14 +389,19 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, switch (command) { case SMB2_OP_QUERY_INFO: + idata = ptr; + if (rc == 0 && cfile && cfile->symlink_target) { + idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!idata->symlink_target) + rc = -ENOMEM; + } if (rc == 0) { qi_rsp = (struct smb2_query_info_rsp *) rsp_iov[1].iov_base; rc = smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), le32_to_cpu(qi_rsp->OutputBufferLength), - &rsp_iov[1], sizeof(struct smb2_file_all_info), - ptr); + &rsp_iov[1], sizeof(idata->fi), (char *)&idata->fi); } if (rqst[1].rq_iov) SMB2_query_info_free(&rqst[1]); @@ -406,13 +415,20 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, tcon->tid); break; case SMB2_OP_POSIX_QUERY_INFO: + idata = ptr; + if (rc == 0 && cfile && cfile->symlink_target) { + idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!idata->symlink_target) + rc = -ENOMEM; + } if (rc == 0) { qi_rsp = (struct smb2_query_info_rsp *) rsp_iov[1].iov_base; rc = smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), le32_to_cpu(qi_rsp->OutputBufferLength), - &rsp_iov[1], sizeof(struct smb311_posix_qinfo) /* add SIDs */, ptr); + &rsp_iov[1], sizeof(idata->posix_fi) /* add SIDs */, + (char *)&idata->posix_fi); } if (rqst[1].rq_iov) SMB2_query_info_free(&rqst[1]); @@ -477,42 +493,33 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, free_set_inf_compound(rqst); break; } - free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); - free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); - free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + + if (rc && err_iov && err_buftype) { + memcpy(err_iov, rsp_iov, 3 * sizeof(*err_iov)); + memcpy(err_buftype, resp_buftype, 3 * sizeof(*err_buftype)); + } else { + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + } kfree(vars); return rc; } -void -move_smb2_info_to_cifs(FILE_ALL_INFO *dst, struct smb2_file_all_info *src) -{ - memcpy(dst, src, (size_t)(&src->CurrentByteOffset) - (size_t)src); - dst->CurrentByteOffset = src->CurrentByteOffset; - dst->Mode = src->Mode; - dst->AlignmentRequirement = src->AlignmentRequirement; - dst->IndexNumber1 = 0; /* we don't use it */ -} - -int -smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - FILE_ALL_INFO *data, bool *adjust_tz, bool *reparse) +int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse) { int rc; - struct smb2_file_all_info *smb2_data; __u32 create_options = 0; struct cifsFileInfo *cfile; struct cached_fid *cfid = NULL; + struct kvec err_iov[3] = {}; + int err_buftype[3] = {}; *adjust_tz = false; *reparse = false; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; - if (strcmp(full_path, "")) rc = -ENOENT; else @@ -520,63 +527,58 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, /* If it is a root and its handle is cached then use it */ if (!rc) { if (cfid->file_all_info_is_valid) { - move_smb2_info_to_cifs(data, - &cfid->file_all_info); + memcpy(&data->fi, &cfid->file_all_info, sizeof(data->fi)); } else { - rc = SMB2_query_info(xid, tcon, - cfid->fid.persistent_fid, - cfid->fid.volatile_fid, smb2_data); - if (!rc) - move_smb2_info_to_cifs(data, smb2_data); + rc = SMB2_query_info(xid, tcon, cfid->fid.persistent_fid, + cfid->fid.volatile_fid, &data->fi); } close_cached_dir(cfid); - goto out; + return rc; } cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, - ACL_NO_MODE, smb2_data, SMB2_OP_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, + create_options, ACL_NO_MODE, data, SMB2_OP_QUERY_INFO, cfile, + err_iov, err_buftype); if (rc == -EOPNOTSUPP) { + if (err_iov[0].iov_base && err_buftype[0] != CIFS_NO_BUFFER && + ((struct smb2_hdr *)err_iov[0].iov_base)->Command == SMB2_CREATE && + ((struct smb2_hdr *)err_iov[0].iov_base)->Status == STATUS_STOPPED_ON_SYMLINK) { + rc = smb2_parse_symlink_response(cifs_sb, err_iov, &data->symlink_target); + if (rc) + goto out; + } *reparse = true; create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, create_options, ACL_NO_MODE, data, + SMB2_OP_QUERY_INFO, cfile, NULL, NULL); } - if (rc) - goto out; - move_smb2_info_to_cifs(data, smb2_data); out: - kfree(smb2_data); + free_rsp_buf(err_buftype[0], err_iov[0].iov_base); + free_rsp_buf(err_buftype[1], err_iov[1].iov_base); + free_rsp_buf(err_buftype[2], err_iov[2].iov_base); return rc; } -int -smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - struct smb311_posix_qinfo *data, bool *adjust_tz, bool *reparse) +int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse) { int rc; __u32 create_options = 0; struct cifsFileInfo *cfile; - struct smb311_posix_qinfo *smb2_data; + struct kvec err_iov[3] = {}; + int err_buftype[3] = {}; *adjust_tz = false; *reparse = false; - /* BB TODO: Make struct larger when add support for parsing owner SIDs */ - smb2_data = kzalloc(sizeof(struct smb311_posix_qinfo), - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; - /* * BB TODO: Add support for using the cached root handle. * Create SMB2_query_posix_info worker function to do non-compounded query @@ -585,29 +587,32 @@ smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, - ACL_NO_MODE, smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, + create_options, ACL_NO_MODE, data, SMB2_OP_POSIX_QUERY_INFO, cfile, + err_iov, err_buftype); if (rc == -EOPNOTSUPP) { /* BB TODO: When support for special files added to Samba re-verify this path */ + if (err_iov[0].iov_base && err_buftype[0] != CIFS_NO_BUFFER && + ((struct smb2_hdr *)err_iov[0].iov_base)->Command == SMB2_CREATE && + ((struct smb2_hdr *)err_iov[0].iov_base)->Status == STATUS_STOPPED_ON_SYMLINK) { + rc = smb2_parse_symlink_response(cifs_sb, err_iov, &data->symlink_target); + if (rc) + goto out; + } *reparse = true; create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, create_options, ACL_NO_MODE, data, + SMB2_OP_POSIX_QUERY_INFO, cfile, NULL, NULL); } - if (rc) - goto out; - - /* TODO: will need to allow for the 2 SIDs when add support for getting owner UID/GID */ - memcpy(data, smb2_data, sizeof(struct smb311_posix_qinfo)); out: - kfree(smb2_data); + free_rsp_buf(err_buftype[0], err_iov[0].iov_base); + free_rsp_buf(err_buftype[1], err_iov[1].iov_base); + free_rsp_buf(err_buftype[2], err_iov[2].iov_base); return rc; } @@ -619,7 +624,7 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode, return smb2_compound_op(xid, tcon, cifs_sb, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, mode, NULL, SMB2_OP_MKDIR, - NULL); + NULL, NULL, NULL); } void @@ -641,7 +646,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE, - &data, SMB2_OP_SET_INFO, cfile); + &data, SMB2_OP_SET_INFO, cfile, NULL, NULL); if (tmprc == 0) cifs_i->cifsAttrs = dosattrs; } @@ -652,7 +657,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, { return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE, - NULL, SMB2_OP_RMDIR, NULL); + NULL, SMB2_OP_RMDIR, NULL, NULL, NULL); } int @@ -661,7 +666,7 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, { return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE, NULL, SMB2_OP_DELETE, NULL); + ACL_NO_MODE, NULL, SMB2_OP_DELETE, NULL, NULL, NULL); } static int @@ -680,7 +685,7 @@ smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, } rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access, FILE_OPEN, 0, ACL_NO_MODE, smb2_to_name, - command, cfile); + command, cfile, NULL, NULL); smb2_rename_path: kfree(smb2_to_name); return rc; @@ -720,7 +725,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); return smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE, - &eof, SMB2_OP_SET_EOF, cfile); + &eof, SMB2_OP_SET_EOF, cfile, NULL, NULL); } int @@ -746,7 +751,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path, cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, - 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile); + 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile, + NULL, NULL); cifs_put_tlink(tlink); return rc; } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 7db5c09ecceb..a38720477966 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -248,7 +248,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) * Some windows servers (win2016) will pad also the final * PDU in a compound to 8 bytes. */ - if (((calc_len + 7) & ~7) == len) + if (ALIGN(calc_len, 8) == len) return 0; /* diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 5187250c5f66..17b25153cb68 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -550,7 +550,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, /* avoid spamming logs every 10 minutes, so log only in mount */ if ((ses->chan_max > 1) && in_mount) cifs_dbg(VFS, - "empty network interface list returned by server %s\n", + "multichannel not available\n" + "Empty network interface list returned by server %s\n", ses->server->hostname); rc = -EINVAL; goto out; @@ -800,7 +801,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, rc = open_cached_dir(xid, tcon, full_path, cifs_sb, true, &cfid); if (!rc) { - if (cfid->is_valid) { + if (cfid->has_lease) { close_cached_dir(cfid); return 0; } @@ -830,33 +831,25 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -smb2_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - u64 *uniqueid, FILE_ALL_INFO *data) +static int smb2_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + u64 *uniqueid, struct cifs_open_info_data *data) { - *uniqueid = le64_to_cpu(data->IndexNumber); + *uniqueid = le64_to_cpu(data->fi.IndexNumber); return 0; } -static int -smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_fid *fid, FILE_ALL_INFO *data) +static int smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data) { - int rc; - struct smb2_file_all_info *smb2_data; - - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; + struct cifs_fid *fid = &cfile->fid; - rc = SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, - smb2_data); - if (!rc) - move_smb2_info_to_cifs(data, smb2_data); - kfree(smb2_data); - return rc; + if (cfile->symlink_target) { + data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!data->symlink_target) + return -ENOMEM; + } + return SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, &data->fi); } #ifdef CONFIG_CIFS_XATTR @@ -2025,9 +2018,10 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, static int smb3_notify(const unsigned int xid, struct file *pfile, - void __user *ioc_buf) + void __user *ioc_buf, bool return_changes) { - struct smb3_notify notify; + struct smb3_notify_info notify; + struct smb3_notify_info __user *pnotify_buf; struct dentry *dentry = pfile->f_path.dentry; struct inode *inode = file_inode(pfile); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -2035,10 +2029,12 @@ smb3_notify(const unsigned int xid, struct file *pfile, struct cifs_fid fid; struct cifs_tcon *tcon; const unsigned char *path; + char *returned_ioctl_info = NULL; void *page = alloc_dentry_path(); __le16 *utf16_path = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_NONE; int rc = 0; + __u32 ret_len = 0; path = build_path_from_dentry(dentry, page); if (IS_ERR(path)) { @@ -2052,9 +2048,17 @@ smb3_notify(const unsigned int xid, struct file *pfile, goto notify_exit; } - if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify))) { - rc = -EFAULT; - goto notify_exit; + if (return_changes) { + if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify_info))) { + rc = -EFAULT; + goto notify_exit; + } + } else { + if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify))) { + rc = -EFAULT; + goto notify_exit; + } + notify.data_len = 0; } tcon = cifs_sb_master_tcon(cifs_sb); @@ -2071,12 +2075,22 @@ smb3_notify(const unsigned int xid, struct file *pfile, goto notify_exit; rc = SMB2_change_notify(xid, tcon, fid.persistent_fid, fid.volatile_fid, - notify.watch_tree, notify.completion_filter); + notify.watch_tree, notify.completion_filter, + notify.data_len, &returned_ioctl_info, &ret_len); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); cifs_dbg(FYI, "change notify for path %s rc %d\n", path, rc); - + if (return_changes && (ret_len > 0) && (notify.data_len > 0)) { + if (ret_len > notify.data_len) + ret_len = notify.data_len; + pnotify_buf = (struct smb3_notify_info __user *)ioc_buf; + if (copy_to_user(pnotify_buf->notify_data, returned_ioctl_info, ret_len)) + rc = -EFAULT; + else if (copy_to_user(&pnotify_buf->data_len, &ret_len, sizeof(ret_len))) + rc = -EFAULT; + } + kfree(returned_ioctl_info); notify_exit: free_dentry_path(page); kfree(utf16_path); @@ -2827,9 +2841,6 @@ parse_reparse_point(struct reparse_data_buffer *buf, } } -#define SMB2_SYMLINK_STRUCT_SIZE \ - (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) - static int smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -2841,13 +2852,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; struct kvec err_iov = {NULL, 0}; - struct smb2_err_rsp *err_buf = NULL; - struct smb2_symlink_err_rsp *symlink; struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); - unsigned int sub_len; - unsigned int sub_offset; - unsigned int print_len; - unsigned int print_offset; int flags = CIFS_CP_CREATE_CLOSE_OP; struct smb_rqst rqst[3]; int resp_buftype[3]; @@ -2964,47 +2969,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, goto querty_exit; } - err_buf = err_iov.iov_base; - if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) || - err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE) { - rc = -EINVAL; - goto querty_exit; - } - - symlink = (struct smb2_symlink_err_rsp *)err_buf->ErrorData; - if (le32_to_cpu(symlink->SymLinkErrorTag) != SYMLINK_ERROR_TAG || - le32_to_cpu(symlink->ReparseTag) != IO_REPARSE_TAG_SYMLINK) { - rc = -EINVAL; - goto querty_exit; - } - - /* open must fail on symlink - reset rc */ - rc = 0; - sub_len = le16_to_cpu(symlink->SubstituteNameLength); - sub_offset = le16_to_cpu(symlink->SubstituteNameOffset); - print_len = le16_to_cpu(symlink->PrintNameLength); - print_offset = le16_to_cpu(symlink->PrintNameOffset); - - if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) { - rc = -EINVAL; - goto querty_exit; - } - - if (err_iov.iov_len < - SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) { - rc = -EINVAL; - goto querty_exit; - } - - *target_path = cifs_strndup_from_utf16( - (char *)symlink->PathBuffer + sub_offset, - sub_len, true, cifs_sb->local_nls); - if (!(*target_path)) { - rc = -ENOMEM; - goto querty_exit; - } - convert_delimiter(*target_path, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + rc = smb2_parse_symlink_response(cifs_sb, &err_iov, target_path); querty_exit: cifs_dbg(FYI, "query symlink rc %d\n", rc); @@ -5114,7 +5079,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); int rc = -EPERM; - FILE_ALL_INFO *buf = NULL; + struct cifs_open_info_data buf = {}; struct cifs_io_parms io_parms = {0}; __u32 oplock = 0; struct cifs_fid fid; @@ -5130,7 +5095,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, * and was used by default in earlier versions of Windows */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) - goto out; + return rc; /* * TODO: Add ability to create instead via reparse point. Windows (e.g. @@ -5139,16 +5104,10 @@ smb2_make_node(unsigned int xid, struct inode *inode, */ if (!S_ISCHR(mode) && !S_ISBLK(mode)) - goto out; + return rc; cifs_dbg(FYI, "sfu compat create special file\n"); - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; @@ -5163,21 +5122,21 @@ smb2_make_node(unsigned int xid, struct inode *inode, oplock = REQ_OPLOCK; else oplock = 0; - rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf); if (rc) - goto out; + return rc; /* * BB Do not bother to decode buf since no local inode yet to put * timestamps in, but we can reuse it safely. */ - pdev = (struct win_dev *)buf; + pdev = (struct win_dev *)&buf.fi; io_parms.pid = current->tgid; io_parms.tcon = tcon; io_parms.offset = 0; io_parms.length = sizeof(struct win_dev); - iov[1].iov_base = buf; + iov[1].iov_base = &buf.fi; iov[1].iov_len = sizeof(struct win_dev); if (S_ISCHR(mode)) { memcpy(pdev->type, "IntxCHR", 8); @@ -5196,8 +5155,8 @@ smb2_make_node(unsigned int xid, struct inode *inode, d_drop(dentry); /* FIXME: add code here to set EAs */ -out: - kfree(buf); + + cifs_free_open_info(&buf); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b3c4d2e54eaa..a2384509ea84 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -466,15 +466,14 @@ build_signing_ctxt(struct smb2_signing_capabilities *pneg_ctxt) /* * Context Data length must be rounded to multiple of 8 for some servers */ - pneg_ctxt->DataLength = cpu_to_le16(DIV_ROUND_UP( - sizeof(struct smb2_signing_capabilities) - - sizeof(struct smb2_neg_context) + - (num_algs * 2 /* sizeof u16 */), 8) * 8); + pneg_ctxt->DataLength = cpu_to_le16(ALIGN(sizeof(struct smb2_signing_capabilities) - + sizeof(struct smb2_neg_context) + + (num_algs * sizeof(u16)), 8)); pneg_ctxt->SigningAlgorithmCount = cpu_to_le16(num_algs); pneg_ctxt->SigningAlgorithms[0] = cpu_to_le16(SIGNING_ALG_AES_CMAC); - ctxt_len += 2 /* sizeof le16 */ * num_algs; - ctxt_len = DIV_ROUND_UP(ctxt_len, 8) * 8; + ctxt_len += sizeof(__le16) * num_algs; + ctxt_len = ALIGN(ctxt_len, 8); return ctxt_len; /* TBD add SIGNING_ALG_AES_GMAC and/or SIGNING_ALG_HMAC_SHA256 */ } @@ -511,8 +510,7 @@ build_netname_ctxt(struct smb2_netname_neg_context *pneg_ctxt, char *hostname) /* copy up to max of first 100 bytes of server name to NetName field */ pneg_ctxt->DataLength = cpu_to_le16(2 * cifs_strtoUTF16(pneg_ctxt->NetName, hostname, 100, cp)); /* context size is DataLength + minimal smb2_neg_context */ - return DIV_ROUND_UP(le16_to_cpu(pneg_ctxt->DataLength) + - sizeof(struct smb2_neg_context), 8) * 8; + return ALIGN(le16_to_cpu(pneg_ctxt->DataLength) + sizeof(struct smb2_neg_context), 8); } static void @@ -557,18 +555,18 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, * round up total_len of fixed part of SMB3 negotiate request to 8 * byte boundary before adding negotiate contexts */ - *total_len = roundup(*total_len, 8); + *total_len = ALIGN(*total_len, 8); pneg_ctxt = (*total_len) + (char *)req; req->NegotiateContextOffset = cpu_to_le32(*total_len); build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt); - ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_preauth_neg_context), 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_preauth_neg_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt); - ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_encryption_neg_context), 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_encryption_neg_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; @@ -595,9 +593,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, if (server->compress_algorithm) { build_compression_ctxt((struct smb2_compression_capabilities_context *) pneg_ctxt); - ctxt_len = DIV_ROUND_UP( - sizeof(struct smb2_compression_capabilities_context), - 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_compression_capabilities_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; neg_context_count++; @@ -780,7 +776,7 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, if (rc) break; /* offsets must be 8 byte aligned */ - clen = (clen + 7) & ~0x7; + clen = ALIGN(clen, 8); offset += clen + sizeof(struct smb2_neg_context); len_of_ctxts -= clen; } @@ -2424,9 +2420,9 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; - struct smb3_acl acl; + struct smb3_acl acl = {}; - *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); + *len = round_up(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); if (set_owner) { /* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */ @@ -2497,10 +2493,11 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ acl.AclSize = cpu_to_le16(acl_size); acl.AceCount = cpu_to_le16(ace_count); + /* acl.Sbz1 and Sbz2 MBZ so are not set here, but initialized above */ memcpy(aclptr, &acl, sizeof(struct smb3_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); - *len = roundup(ptr - (__u8 *)buf, 8); + *len = round_up((unsigned int)(ptr - (__u8 *)buf), 8); return buf; } @@ -2594,7 +2591,7 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, * final path needs to be 8-byte aligned as specified in * MS-SMB2 2.2.13 SMB2 CREATE Request. */ - *out_size = roundup(*out_len * sizeof(__le16), 8); + *out_size = round_up(*out_len * sizeof(__le16), 8); *out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL); if (!*out_path) return -ENOMEM; @@ -2839,9 +2836,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2; /* MUST set path len (NameLength) to 0 opening root of share */ req->NameLength = cpu_to_le16(uni_path_len - 2); - copy_size = uni_path_len; - if (copy_size % 8 != 0) - copy_size = roundup(copy_size, 8); + copy_size = round_up(uni_path_len, 8); copy_path = kzalloc(copy_size, GFP_KERNEL); if (!copy_path) return -ENOMEM; @@ -3485,7 +3480,7 @@ smb2_validate_and_copy_iov(unsigned int offset, unsigned int buffer_length, if (rc) return rc; - memcpy(data, begin_of_buf, buffer_length); + memcpy(data, begin_of_buf, minbufsize); return 0; } @@ -3609,7 +3604,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, rc = smb2_validate_and_copy_iov(le16_to_cpu(rsp->OutputBufferOffset), le32_to_cpu(rsp->OutputBufferLength), - &rsp_iov, min_len, *data); + &rsp_iov, dlen ? *dlen : min_len, *data); if (rc && allocated) { kfree(*data); *data = NULL; @@ -3715,11 +3710,13 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, bool watch_tree, - u32 completion_filter) + u32 completion_filter, u32 max_out_data_len, char **out_data, + u32 *plen /* returned data len */) { struct cifs_ses *ses = tcon->ses; struct TCP_Server_Info *server = cifs_pick_channel(ses); struct smb_rqst rqst; + struct smb2_change_notify_rsp *smb_rsp; struct kvec iov[1]; struct kvec rsp_iov = {NULL, 0}; int resp_buftype = CIFS_NO_BUFFER; @@ -3735,6 +3732,9 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, memset(&rqst, 0, sizeof(struct smb_rqst)); memset(&iov, 0, sizeof(iov)); + if (plen) + *plen = 0; + rqst.rq_iov = iov; rqst.rq_nvec = 1; @@ -3753,9 +3753,28 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, cifs_stats_fail_inc(tcon, SMB2_CHANGE_NOTIFY_HE); trace_smb3_notify_err(xid, persistent_fid, tcon->tid, ses->Suid, (u8)watch_tree, completion_filter, rc); - } else + } else { trace_smb3_notify_done(xid, persistent_fid, tcon->tid, - ses->Suid, (u8)watch_tree, completion_filter); + ses->Suid, (u8)watch_tree, completion_filter); + /* validate that notify information is plausible */ + if ((rsp_iov.iov_base == NULL) || + (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp))) + goto cnotify_exit; + + smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; + + smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov, + sizeof(struct file_notify_information)); + + *out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL); + if (*out_data == NULL) { + rc = -ENOMEM; + goto cnotify_exit; + } else + *plen = le32_to_cpu(smb_rsp->OutputBufferLength); + } cnotify_exit: if (rqst.rq_iov) @@ -4103,7 +4122,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, if (request_type & CHAINED_REQUEST) { if (!(request_type & END_OF_CHAIN)) { /* next 8-byte aligned request */ - *total_len = DIV_ROUND_UP(*total_len, 8) * 8; + *total_len = ALIGN(*total_len, 8); shdr->NextCommand = cpu_to_le32(*total_len); } else /* END_OF_CHAIN */ shdr->NextCommand = 0; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f57881b8464f..1237bb86e93a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -56,6 +56,9 @@ struct smb2_rdma_crypto_transform { #define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL +#define SMB2_SYMLINK_STRUCT_SIZE \ + (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) + #define SYMLINK_ERROR_TAG 0x4c4d5953 struct smb2_symlink_err_rsp { diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3f740f24b96a..be21b5d26f67 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -53,16 +53,12 @@ extern bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv); extern int smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid); - -extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst, - struct smb2_file_all_info *src); extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *path, __u32 *reparse_tag); -extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, - const char *full_path, FILE_ALL_INFO *data, - bool *adjust_tz, bool *symlink); +int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); extern int smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, __u64 size, struct cifs_sb_info *cifs_sb, bool set_alloc); @@ -95,9 +91,9 @@ extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_read); -extern int smb2_open_file(const unsigned int xid, - struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf); +int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, char **path); +int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf); extern int smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); @@ -148,7 +144,8 @@ extern int SMB2_ioctl_init(struct cifs_tcon *tcon, extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, bool watch_tree, - u32 completion_filter); + u32 completion_filter, u32 max_out_data_len, + char **out_data, u32 *plen /* returned data len */); extern int __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, @@ -278,9 +275,9 @@ extern int smb2_query_info_compound(const unsigned int xid, struct kvec *rsp, int *buftype, struct cifs_sb_info *cifs_sb); /* query path info from the server using SMB311 POSIX extensions*/ -extern int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *sb, const char *path, struct smb311_posix_qinfo *qinf, - bool *adjust_tx, bool *symlink); +int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); int posix_info_parse(const void *beg, const void *end, struct smb2_posix_info_parsed *out); int posix_info_sid_size(const void *beg, const void *end); diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 20cadfb740dc..3c640bd7ecae 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -363,13 +363,14 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index f0805e51b3fe..c352fff88a5e 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -258,13 +258,14 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 07881b76d42f..277468783fee 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -103,7 +103,7 @@ static char *__dentry_name(struct dentry *dentry, char *name) */ BUG_ON(p + strlen(p) + 1 != name + PATH_MAX); - strlcpy(name, root, PATH_MAX); + strscpy(name, root, PATH_MAX); if (len > p - name) { __putname(name); return NULL; diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index c57b46a352d8..3125e76376ee 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -24,6 +24,17 @@ static bool ubifs_crypt_empty_dir(struct inode *inode) return ubifs_check_dir_empty(inode) == 0; } +/** + * ubifs_encrypt - Encrypt data. + * @inode: inode which refers to the data node + * @dn: data node to encrypt + * @in_len: length of data to be compressed + * @out_len: allocated memory size for the data area of @dn + * @block: logical block number of the block + * + * This function encrypt a possibly-compressed data in the data node. + * The encrypted data length will store in @out_len. + */ int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, unsigned int in_len, unsigned int *out_len, int block) { diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index f59acd6a3615..0f29cf201136 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -68,13 +68,14 @@ static int inherit_flags(const struct inode *dir, umode_t mode) * @c: UBIFS file-system description object * @dir: parent directory inode * @mode: inode mode flags + * @is_xattr: whether the inode is xattr inode * * This function finds an unused inode number, allocates new inode and * initializes it. Returns new inode in case of success and an error code in * case of failure. */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, - umode_t mode) + umode_t mode, bool is_xattr) { int err; struct inode *inode; @@ -99,10 +100,12 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, current_time(inode); inode->i_mapping->nrpages = 0; - err = fscrypt_prepare_new_inode(dir, inode, &encrypted); - if (err) { - ubifs_err(c, "fscrypt_prepare_new_inode failed: %i", err); - goto out_iput; + if (!is_xattr) { + err = fscrypt_prepare_new_inode(dir, inode, &encrypted); + if (err) { + ubifs_err(c, "fscrypt_prepare_new_inode failed: %i", err); + goto out_iput; + } } switch (mode & S_IFMT) { @@ -309,7 +312,7 @@ static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; @@ -370,7 +373,7 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) if (err) return ERR_PTR(err); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_free; @@ -463,7 +466,7 @@ static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return err; } - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_budg; @@ -873,7 +876,7 @@ out_fname: } /** - * check_dir_empty - check if a directory is empty or not. + * ubifs_check_dir_empty - check if a directory is empty or not. * @dir: VFS inode object of the directory to check * * This function checks if directory @dir is empty. Returns zero if the @@ -1005,7 +1008,7 @@ static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, S_IFDIR | mode); + inode = ubifs_new_inode(c, dir, S_IFDIR | mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; @@ -1092,7 +1095,7 @@ static int ubifs_mknod(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { kfree(dev); err = PTR_ERR(inode); @@ -1174,7 +1177,7 @@ static int ubifs_symlink(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, S_IFLNK | S_IRWXUGO); + inode = ubifs_new_inode(c, dir, S_IFLNK | S_IRWXUGO, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 75dab0ae3939..2b1d7c4297bf 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1472,23 +1472,25 @@ out_free: * @block: data block number * @dn: data node to re-compress * @new_len: new length + * @dn_size: size of the data node @dn in memory * * This function is used when an inode is truncated and the last data node of * the inode has to be re-compressed/encrypted and re-written. */ static int truncate_data_node(const struct ubifs_info *c, const struct inode *inode, unsigned int block, struct ubifs_data_node *dn, - int *new_len) + int *new_len, int dn_size) { void *buf; - int err, dlen, compr_type, out_len, old_dlen; + int err, dlen, compr_type, out_len, data_size; out_len = le32_to_cpu(dn->size); buf = kmalloc_array(out_len, WORST_COMPR_FACTOR, GFP_NOFS); if (!buf) return -ENOMEM; - dlen = old_dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; + dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; + data_size = dn_size - UBIFS_DATA_NODE_SZ; compr_type = le16_to_cpu(dn->compr_type); if (IS_ENCRYPTED(inode)) { @@ -1508,11 +1510,11 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in } if (IS_ENCRYPTED(inode)) { - err = ubifs_encrypt(inode, dn, out_len, &old_dlen, block); + err = ubifs_encrypt(inode, dn, out_len, &data_size, block); if (err) goto out; - out_len = old_dlen; + out_len = data_size; } else { dn->compr_size = 0; } @@ -1550,6 +1552,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, struct ubifs_trun_node *trun; struct ubifs_data_node *dn; int err, dlen, len, lnum, offs, bit, sz, sync = IS_SYNC(inode); + int dn_size; struct ubifs_inode *ui = ubifs_inode(inode); ino_t inum = inode->i_ino; unsigned int blk; @@ -1562,10 +1565,13 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, ubifs_assert(c, S_ISREG(inode->i_mode)); ubifs_assert(c, mutex_is_locked(&ui->ui_mutex)); - sz = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ + - UBIFS_MAX_DATA_NODE_SZ * WORST_COMPR_FACTOR; + dn_size = COMPRESSED_DATA_NODE_BUF_SZ; - sz += ubifs_auth_node_sz(c); + if (IS_ENCRYPTED(inode)) + dn_size += UBIFS_CIPHER_BLOCK_SIZE; + + sz = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ + + dn_size + ubifs_auth_node_sz(c); ino = kmalloc(sz, GFP_NOFS); if (!ino) @@ -1596,15 +1602,15 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, if (dn_len <= 0 || dn_len > UBIFS_BLOCK_SIZE) { ubifs_err(c, "bad data node (block %u, inode %lu)", blk, inode->i_ino); - ubifs_dump_node(c, dn, sz - UBIFS_INO_NODE_SZ - - UBIFS_TRUN_NODE_SZ); + ubifs_dump_node(c, dn, dn_size); goto out_free; } if (dn_len <= dlen) dlen = 0; /* Nothing to do */ else { - err = truncate_data_node(c, inode, blk, dn, &dlen); + err = truncate_data_node(c, inode, blk, dn, + &dlen, dn_size); if (err) goto out_free; } diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 7d6d2f152e03..478bbbb5382f 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -2026,7 +2026,7 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, - umode_t mode); + umode_t mode, bool is_xattr); int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int ubifs_check_dir_empty(struct inode *dir); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e4c4761aff7f..3db8486e3725 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -110,7 +110,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, if (err) return err; - inode = ubifs_new_inode(c, host, S_IFREG | S_IRWXUGO); + inode = ubifs_new_inode(c, host, S_IFREG | S_IRWXUGO, true); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_budg; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..6e01f10f0d88 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 23b102b4349e..f2a9f2274c3b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -682,11 +682,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2108b5695327..267cd06b54a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,15 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * @@ -118,8 +129,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually @@ -1303,6 +1315,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); diff --git a/include/linux/clk.h b/include/linux/clk.h index c13061cabdfc..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -799,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 3484309b59bf..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include <linux/bits.h> + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2f065ad97541..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -174,8 +174,9 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -188,8 +189,9 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } @@ -229,8 +231,9 @@ static inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -260,8 +263,8 @@ static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - /* n is a prior cpu */ - cpumask_check(n + 1); + if (n != -1) + cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, diff --git a/include/linux/damon.h b/include/linux/damon.h index ed5470f50bab..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,6 +484,12 @@ static inline struct damon_region *damon_first_region(struct damon_target *t) return list_first_entry(&t->regions_list, struct damon_region, list); } +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 704a04f5a074..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -197,11 +199,24 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/poll.h> #include <linux/cgroup-defs.h> +#include <linux/cgroup.h> struct seq_file; struct css_set; @@ -18,10 +19,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); @@ -34,9 +31,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -58,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -16,13 +16,6 @@ enum psi_task_count { NR_MEMSTALL, NR_RUNNING, /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, - /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. * For memory it's not so simple because of page reclaimers: @@ -32,22 +25,27 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -63,11 +61,17 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -147,6 +151,9 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -188,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 77f68f8b795c..ffb6eb55cd13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -870,8 +870,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ diff --git a/include/soc/sifive/sifive_ccache.h b/include/soc/sifive/sifive_ccache.h new file mode 100644 index 000000000000..4d4ed49388a0 --- /dev/null +++ b/include/soc/sifive/sifive_ccache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive Composable Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_CCACHE_H +#define __SOC_SIFIVE_CCACHE_H + +extern int register_sifive_ccache_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_ccache_error_notifier(struct notifier_block *nb); + +#define SIFIVE_CCACHE_ERR_TYPE_CE 0 +#define SIFIVE_CCACHE_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_CCACHE_H */ diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h deleted file mode 100644 index 92ade10ed67e..000000000000 --- a/include/soc/sifive/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef __SOC_SIFIVE_L2_CACHE_H -#define __SOC_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* __SOC_SIFIVE_L2_CACHE_H */ diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index ddff03e546e9..35778f953a3f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -592,11 +592,11 @@ int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, #define snd_hdac_stream_readb(dev, reg) \ snd_hdac_reg_readb((dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readb_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readb, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readl_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readl, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) /* update a register, pass without AZX_REG_ prefix */ #define snd_hdac_stream_updatel(dev, reg, mask, val) \ diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index b69e9ba6742b..dcb179de4358 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -247,6 +247,7 @@ enum { * @vid_hdr_offset: VID header offset (use defaults if %0) * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs * @padding: reserved for future, not used, has to be zeroed + * @disable_fm: whether disable fastmap * * This data structure is used to specify MTD device UBI has to attach and the * parameters it has to use. The number which should be assigned to the new UBI @@ -281,13 +282,18 @@ enum { * eraseblocks for new bad eraseblocks, but attempts to use available * eraseblocks (if any). The accepted range is 0-768. If 0 is given, the * default kernel value of %CONFIG_MTD_UBI_BEB_LIMIT will be used. + * + * If @disable_fm is not zero, ubi doesn't create new fastmap even the module + * param 'fm_autoconvert' is set, and existed old fastmap will be destroyed + * after doing full scanning. */ struct ubi_attach_req { __s32 ubi_num; __s32 mtd_num; __s32 vid_hdr_offset; __s16 max_beb_per1024; - __s8 padding[10]; + __s8 disable_fm; + __s8 padding[9]; }; /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 764bdd5fd8d1..7f486677ab1f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3698,27 +3698,27 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } -static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, enum psi_res res) +static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; @@ -3738,7 +3738,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return -EBUSY; } - psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); @@ -3755,21 +3755,86 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_IO); + return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_MEM); + return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); + return pressure_write(of, buf, nbytes, PSI_CPU); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + return psi_show(seq, psi, PSI_IRQ); +} + +static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return pressure_write(of, buf, nbytes, PSI_IRQ); +} +#endif + +static int cgroup_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + seq_printf(seq, "%d\n", psi->enabled); + + return 0; +} + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + ssize_t ret; + int enable; + struct cgroup *cgrp; + struct psi_group *psi; + + ret = kstrtoint(strstrip(buf), 0, &enable); + if (ret) + return ret; + + if (enable < 0 || enable > 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + psi = cgroup_psi(cgrp); + if (psi->enabled != enable) { + int i; + + /* show or hide {cpu,memory,io,irq}.pressure files */ + for (i = 0; i < NR_PSI_RESOURCES; i++) + cgroup_file_show(&cgrp->psi_files[i], enable); + + psi->enabled = enable; + if (enable) + psi_cgroup_restart(psi); + } + + cgroup_kn_unlock(of->kn); + + return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, @@ -3789,6 +3854,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) bool cgroup_psi_enabled(void) { + if (static_branch_likely(&psi_disabled)) + return false; + return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } @@ -5175,6 +5243,7 @@ static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5182,6 +5251,7 @@ static struct cftype cgroup_psi_files[] = { }, { .name = "memory.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5189,11 +5259,27 @@ static struct cftype cgroup_psi_files[] = { }, { .name = "cpu.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + { + .name = "irq.pressure", + .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), + .seq_show = cgroup_irq_pressure_show, + .write = cgroup_irq_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#endif + { + .name = "cgroup.pressure", + .seq_show = cgroup_pressure_show, + .write = cgroup_pressure_write, + }, #endif /* CONFIG_PSI */ { } /* terminate */ }; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e4ce124ec701..5800b0623ff3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -701,6 +701,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; + psi_account_irqtime(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7f6030091aee..ee2ecc081422 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -181,6 +181,7 @@ static void group_init(struct psi_group *group) { int cpu; + group->enabled = true; for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->avg_last_update = sched_clock(); @@ -201,6 +202,7 @@ void __init psi_init(void) { if (!psi_enable) { static_branch_enable(&psi_disabled); + static_branch_disable(&psi_cgroups_enabled); return; } @@ -211,7 +213,7 @@ void __init psi_init(void) group_init(&psi_system); } -static bool test_state(unsigned int *tasks, enum psi_states state) +static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu) { switch (state) { case PSI_IO_SOME: @@ -224,9 +226,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state) return unlikely(tasks[NR_MEMSTALL] && tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); case PSI_CPU_SOME: - return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] > oncpu); case PSI_CPU_FULL: - return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] && !oncpu); case PSI_NONIDLE: return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || tasks[NR_RUNNING]; @@ -688,35 +690,53 @@ static void psi_group_change(struct psi_group *group, int cpu, bool wake_clock) { struct psi_group_cpu *groupc; - u32 state_mask = 0; unsigned int t, m; enum psi_states s; + u32 state_mask; groupc = per_cpu_ptr(group->pcpu, cpu); /* - * First we assess the aggregate resource states this CPU's - * tasks have been in since the last change, and account any - * SOME and FULL time these may have resulted in. - * - * Then we update the task counts according to the state + * First we update the task counts according to the state * change requested through the @clear and @set bits. + * + * Then if the cgroup PSI stats accounting enabled, we + * assess the aggregate resource states this CPU's tasks + * have been in since the last change, and account any + * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); - record_times(groupc, now); + /* + * Start with TSK_ONCPU, which doesn't have a corresponding + * task count - it's just a boolean flag directly encoded in + * the state mask. Clear, set, or carry the current state if + * no changes are requested. + */ + if (unlikely(clear & TSK_ONCPU)) { + state_mask = 0; + clear &= ~TSK_ONCPU; + } else if (unlikely(set & TSK_ONCPU)) { + state_mask = PSI_ONCPU; + set &= ~TSK_ONCPU; + } else { + state_mask = groupc->state_mask & PSI_ONCPU; + } + /* + * The rest of the state mask is calculated based on the task + * counts. Update those first, then construct the mask. + */ for (t = 0, m = clear; m; m &= ~(1 << t), t++) { if (!(m & (1 << t))) continue; if (groupc->tasks[t]) { groupc->tasks[t]--; } else if (!psi_bug) { - printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n", + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n", cpu, t, groupc->tasks[0], groupc->tasks[1], groupc->tasks[2], - groupc->tasks[3], groupc->tasks[4], - clear, set); + groupc->tasks[3], clear, set); psi_bug = 1; } } @@ -725,9 +745,25 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++; - /* Calculate state mask representing active states */ + if (!group->enabled) { + /* + * On the first group change after disabling PSI, conclude + * the current state and flush its time. This is unlikely + * to matter to the user, but aggregation (get_recent_times) + * may have already incorporated the live state into times_prev; + * avoid a delta sample underflow when PSI is later re-enabled. + */ + if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE))) + record_times(groupc, now); + + groupc->state_mask = state_mask; + + write_seqcount_end(&groupc->seq); + return; + } + for (s = 0; s < NR_PSI_STATES; s++) { - if (test_state(groupc->tasks, s)) + if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU)) state_mask |= (1 << s); } @@ -739,9 +775,11 @@ static void psi_group_change(struct psi_group *group, int cpu, * task in a cgroup is in_memstall, the corresponding groupc * on that cpu is in PSI_MEM_FULL state. */ - if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall)) + if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall)) state_mask |= (1 << PSI_MEM_FULL); + record_times(groupc, now); + groupc->state_mask = state_mask; write_seqcount_end(&groupc->seq); @@ -753,27 +791,12 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->avgs_work, PSI_FREQ); } -static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +static inline struct psi_group *task_psi_group(struct task_struct *task) { - if (*iter == &psi_system) - return NULL; - #ifdef CONFIG_CGROUPS - if (static_branch_likely(&psi_cgroups_enabled)) { - struct cgroup *cgroup = NULL; - - if (!*iter) - cgroup = task->cgroups->dfl_cgrp; - else - cgroup = cgroup_parent(*iter); - - if (cgroup && cgroup_parent(cgroup)) { - *iter = cgroup; - return cgroup_psi(cgroup); - } - } + if (static_branch_likely(&psi_cgroups_enabled)) + return cgroup_psi(task_dfl_cgroup(task)); #endif - *iter = &psi_system; return &psi_system; } @@ -796,8 +819,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - bool wake_clock = true; - void *iter = NULL; u64 now; if (!task->pid) @@ -806,19 +827,11 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); now = cpu_clock(cpu); - /* - * Periodic aggregation shuts off if there is a period of no - * task changes, so we wake it back up if necessary. However, - * don't do this if the task change is the aggregation worker - * itself going to sleep, or we'll ping-pong forever. - */ - if (unlikely((clear & TSK_RUNNING) && - (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_avgs_work)) - wake_clock = false; - while ((group = iterate_groups(task, &iter))) - psi_group_change(group, cpu, clear, set, now, wake_clock); + group = task_psi_group(task); + do { + psi_group_change(group, cpu, clear, set, now, true); + } while ((group = group->parent)); } void psi_task_switch(struct task_struct *prev, struct task_struct *next, @@ -826,34 +839,30 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - void *iter; u64 now = cpu_clock(cpu); if (next->pid) { - bool identical_state; - psi_flags_change(next, 0, TSK_ONCPU); /* - * When switching between tasks that have an identical - * runtime state, the cgroup that contains both tasks - * we reach the first common ancestor. Iterate @next's - * ancestors only until we encounter @prev's ONCPU. + * Set TSK_ONCPU on @next's cgroups. If @next shares any + * ancestors with @prev, those will already have @prev's + * TSK_ONCPU bit set, and we can stop the iteration there. */ - identical_state = prev->psi_flags == next->psi_flags; - iter = NULL; - while ((group = iterate_groups(next, &iter))) { - if (identical_state && - per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) { + group = task_psi_group(next); + do { + if (per_cpu_ptr(group->pcpu, cpu)->state_mask & + PSI_ONCPU) { common = group; break; } psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); - } + } while ((group = group->parent)); } if (prev->pid) { int clear = TSK_ONCPU, set = 0; + bool wake_clock = true; /* * When we're going to sleep, psi_dequeue() lets us @@ -867,26 +876,74 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((prev->flags & PF_WQ_WORKER) && + wq_worker_last_func(prev) == psi_avgs_work)) + wake_clock = false; } psi_flags_change(prev, clear, set); - iter = NULL; - while ((group = iterate_groups(prev, &iter)) && group != common) - psi_group_change(group, cpu, clear, set, now, true); + group = task_psi_group(prev); + do { + if (group == common) + break; + psi_group_change(group, cpu, clear, set, now, wake_clock); + } while ((group = group->parent)); /* - * TSK_ONCPU is handled up to the common ancestor. If we're tasked - * with dequeuing too, finish that for the rest of the hierarchy. + * TSK_ONCPU is handled up to the common ancestor. If there are + * any other differences between the two tasks (e.g. prev goes + * to sleep, or only one task is memstall), finish propagating + * those differences all the way up to the root. */ - if (sleep) { + if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; - for (; group; group = iterate_groups(prev, &iter)) - psi_group_change(group, cpu, clear, set, now, true); + for (; group; group = group->parent) + psi_group_change(group, cpu, clear, set, now, wake_clock); } } } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +void psi_account_irqtime(struct task_struct *task, u32 delta) +{ + int cpu = task_cpu(task); + struct psi_group *group; + struct psi_group_cpu *groupc; + u64 now; + + if (!task->pid) + return; + + now = cpu_clock(cpu); + + group = task_psi_group(task); + do { + if (!group->enabled) + continue; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + write_seqcount_begin(&groupc->seq); + + record_times(groupc, now); + groupc->times[PSI_IRQ_FULL] += delta; + + write_seqcount_end(&groupc->seq); + + if (group->poll_states & (1 << PSI_IRQ_FULL)) + psi_schedule_poll_work(group, 1); + } while ((group = group->parent)); +} +#endif + /** * psi_memstall_enter - mark the beginning of a memory stall section * @flags: flags to handle nested sections @@ -952,7 +1009,7 @@ EXPORT_SYMBOL_GPL(psi_memstall_leave); #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return 0; cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); @@ -965,12 +1022,13 @@ int psi_cgroup_alloc(struct cgroup *cgroup) return -ENOMEM; } group_init(cgroup->psi); + cgroup->psi->parent = cgroup_psi(cgroup_parent(cgroup)); return 0; } void psi_cgroup_free(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return; cancel_delayed_work_sync(&cgroup->psi->avgs_work); @@ -998,7 +1056,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (static_branch_likely(&psi_disabled)) { + if (!static_branch_likely(&psi_cgroups_enabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -1046,10 +1104,45 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) task_rq_unlock(rq, task, &rf); } + +void psi_cgroup_restart(struct psi_group *group) +{ + int cpu; + + /* + * After we disable psi_group->enabled, we don't actually + * stop percpu tasks accounting in each psi_group_cpu, + * instead only stop test_state() loop, record_times() + * and averaging worker, see psi_group_change() for details. + * + * When disable cgroup PSI, this function has nothing to sync + * since cgroup pressure files are hidden and percpu psi_group_cpu + * would see !psi_group->enabled and only do task accounting. + * + * When re-enable cgroup PSI, this function use psi_group_change() + * to get correct state mask from test_state() loop on tasks[], + * and restart groupc->state_start from now, use .clear = .set = 0 + * here since no task status really changed. + */ + if (!group->enabled) + return; + + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + u64 now; + + rq_lock_irq(rq, &rf); + now = cpu_clock(cpu); + psi_group_change(group, cpu, 0, 0, now, true); + rq_unlock_irq(rq, &rf); + } +} #endif /* CONFIG_CGROUPS */ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { + bool only_full = false; int full; u64 now; @@ -1064,7 +1157,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock); - for (full = 0; full < 2; full++) { +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + only_full = res == PSI_IRQ; +#endif + + for (full = 0; full < 2 - only_full; full++) { unsigned long avg[3] = { 0, }; u64 total = 0; int w; @@ -1078,7 +1175,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", - full ? "full" : "some", + full || only_full ? "full" : "some", LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), @@ -1106,6 +1203,11 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, else return ERR_PTR(-EINVAL); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + if (res == PSI_IRQ && --state != PSI_IRQ_FULL) + return ERR_PTR(-EINVAL); +#endif + if (state >= PSI_NONIDLE) return ERR_PTR(-EINVAL); @@ -1390,6 +1492,33 @@ static const struct proc_ops psi_cpu_proc_ops = { .proc_release = psi_fop_release, }; +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int psi_irq_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IRQ); +} + +static int psi_irq_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_irq_show); +} + +static ssize_t psi_irq_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_IRQ); +} + +static const struct proc_ops psi_irq_proc_ops = { + .proc_open = psi_irq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_irq_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, +}; +#endif + static int __init psi_proc_init(void) { if (psi_enable) { @@ -1397,6 +1526,9 @@ static int __init psi_proc_init(void) proc_create("pressure/io", 0666, NULL, &psi_io_proc_ops); proc_create("pressure/memory", 0666, NULL, &psi_memory_proc_ops); proc_create("pressure/cpu", 0666, NULL, &psi_cpu_proc_ops); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + proc_create("pressure/irq", 0666, NULL, &psi_irq_proc_ops); +#endif } return 0; } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baa839c1ba96..84a188913cc9 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -107,6 +107,11 @@ __schedstats_from_se(struct sched_entity *se) } #ifdef CONFIG_PSI +void psi_task_change(struct task_struct *task, int clear, int set); +void psi_task_switch(struct task_struct *prev, struct task_struct *next, + bool sleep); +void psi_account_irqtime(struct task_struct *task, u32 delta); + /* * PSI tracks state that persists across sleeps, such as iowaits and * memory stalls. As a result, it has to distinguish between sleeps, @@ -201,6 +206,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {} static inline void psi_sched_switch(struct task_struct *prev, struct task_struct *next, bool sleep) {} +static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {} #endif /* CONFIG_PSI */ #ifdef CONFIG_SCHED_INFO diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 73178b0e43a4..3fc7abffc7aa 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -231,6 +231,11 @@ config DEBUG_INFO in the "Debug information" choice below, indicating that debug information will be generated for build targets. +# Clang is known to generate .{s,u}leb128 with symbol deltas with DWARF5, which +# some targets may not support: https://sourceware.org/bugzilla/show_bug.cgi?id=27215 +config AS_HAS_NON_CONST_LEB128 + def_bool $(as-instr,.uleb128 .Lexpr_end4 - .Lexpr_start3\n.Lexpr_start3:\n.Lexpr_end4:) + choice prompt "Debug information" depends on DEBUG_KERNEL @@ -253,6 +258,7 @@ config DEBUG_INFO_NONE config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT bool "Rely on the toolchain's implicit default DWARF version" select DEBUG_INFO + depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128) help The implicit default version of DWARF debug info produced by a toolchain changes over time. @@ -264,7 +270,7 @@ config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT config DEBUG_INFO_DWARF4 bool "Generate DWARF Version 4 debuginfo" select DEBUG_INFO - depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502) help Generate DWARF v4 debug info. This requires gcc 4.5+, binutils 2.35.2 if using clang without clang's integrated assembler, and gdb 7.0+. @@ -276,7 +282,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" select DEBUG_INFO - depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128) help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc 5.0+ accepts the -gdwarf-5 flag but only had partial support for some diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 05dae05b6cc9..3b9a44008433 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -121,7 +121,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" - depends on VT && KGDB_KDB + depends on VT && KGDB_KDB && !PARISC default n help KDB can use a PS/2 type keyboard for an input device diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 6a33f6b1b465..67e6f83fe0f8 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -100,6 +100,7 @@ struct dmirror { struct dmirror_chunk { struct dev_pagemap pagemap; struct dmirror_device *mdevice; + bool remove; }; /* @@ -192,11 +193,15 @@ static int dmirror_fops_release(struct inode *inode, struct file *filp) return 0; } +static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page) +{ + return container_of(page->pgmap, struct dmirror_chunk, pagemap); +} + static struct dmirror_device *dmirror_page_to_device(struct page *page) { - return container_of(page->pgmap, struct dmirror_chunk, - pagemap)->mdevice; + return dmirror_page_to_chunk(page)->mdevice; } static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range) @@ -627,8 +632,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) goto error; } + zone_device_page_init(dpage); dpage->zone_device_data = rpage; - lock_page(dpage); return dpage; error: @@ -907,7 +912,7 @@ static int dmirror_migrate_to_system(struct dmirror *dmirror, struct vm_area_struct *vma; unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -968,7 +973,7 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror, unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; struct dmirror_bounce bounce; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -1218,6 +1223,85 @@ static int dmirror_snapshot(struct dmirror *dmirror, return ret; } +static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) +{ + unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT; + unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT; + unsigned long npages = end_pfn - start_pfn + 1; + unsigned long i; + unsigned long *src_pfns; + unsigned long *dst_pfns; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + + migrate_device_range(src_pfns, start_pfn, npages); + for (i = 0; i < npages; i++) { + struct page *dpage, *spage; + + spage = migrate_pfn_to_page(src_pfns[i]); + if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + + if (WARN_ON(!is_device_private_page(spage) && + !is_device_coherent_page(spage))) + continue; + spage = BACKING_PAGE(spage); + dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL); + lock_page(dpage); + copy_highpage(dpage, spage); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + if (src_pfns[i] & MIGRATE_PFN_WRITE) + dst_pfns[i] |= MIGRATE_PFN_WRITE; + } + migrate_device_pages(src_pfns, dst_pfns, npages); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); +} + +/* Removes free pages from the free list so they can't be re-allocated */ +static void dmirror_remove_free_pages(struct dmirror_chunk *devmem) +{ + struct dmirror_device *mdevice = devmem->mdevice; + struct page *page; + + for (page = mdevice->free_pages; page; page = page->zone_device_data) + if (dmirror_page_to_chunk(page) == devmem) + mdevice->free_pages = page->zone_device_data; +} + +static void dmirror_device_remove_chunks(struct dmirror_device *mdevice) +{ + unsigned int i; + + mutex_lock(&mdevice->devmem_lock); + if (mdevice->devmem_chunks) { + for (i = 0; i < mdevice->devmem_count; i++) { + struct dmirror_chunk *devmem = + mdevice->devmem_chunks[i]; + + spin_lock(&mdevice->lock); + devmem->remove = true; + dmirror_remove_free_pages(devmem); + spin_unlock(&mdevice->lock); + + dmirror_device_evict_chunk(devmem); + memunmap_pages(&devmem->pagemap); + if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) + release_mem_region(devmem->pagemap.range.start, + range_len(&devmem->pagemap.range)); + kfree(devmem); + } + mdevice->devmem_count = 0; + mdevice->devmem_capacity = 0; + mdevice->free_pages = NULL; + kfree(mdevice->devmem_chunks); + mdevice->devmem_chunks = NULL; + } + mutex_unlock(&mdevice->devmem_lock); +} + static long dmirror_fops_unlocked_ioctl(struct file *filp, unsigned int command, unsigned long arg) @@ -1272,6 +1356,11 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_snapshot(dmirror, &cmd); break; + case HMM_DMIRROR_RELEASE: + dmirror_device_remove_chunks(dmirror->mdevice); + ret = 0; + break; + default: return -EINVAL; } @@ -1326,15 +1415,19 @@ static void dmirror_devmem_free(struct page *page) mdevice = dmirror_page_to_device(page); spin_lock(&mdevice->lock); - mdevice->cfree++; - page->zone_device_data = mdevice->free_pages; - mdevice->free_pages = page; + + /* Return page to our allocator if not freeing the chunk */ + if (!dmirror_page_to_chunk(page)->remove) { + mdevice->cfree++; + page->zone_device_data = mdevice->free_pages; + mdevice->free_pages = page; + } spin_unlock(&mdevice->lock); } static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) { - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long src_pfns = 0; unsigned long dst_pfns = 0; struct page *rpage; @@ -1357,6 +1450,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) args.dst = &dst_pfns; args.pgmap_owner = dmirror->mdevice; args.flags = dmirror_select_device(dmirror); + args.fault_page = vmf->page; if (migrate_vma_setup(&args)) return VM_FAULT_SIGBUS; @@ -1407,22 +1501,7 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id) static void dmirror_device_remove(struct dmirror_device *mdevice) { - unsigned int i; - - if (mdevice->devmem_chunks) { - for (i = 0; i < mdevice->devmem_count; i++) { - struct dmirror_chunk *devmem = - mdevice->devmem_chunks[i]; - - memunmap_pages(&devmem->pagemap); - if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) - release_mem_region(devmem->pagemap.range.start, - range_len(&devmem->pagemap.range)); - kfree(devmem); - } - kfree(mdevice->devmem_chunks); - } - + dmirror_device_remove_chunks(mdevice); cdev_device_del(&mdevice->cdevice, &mdevice->device); } diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index e31d58c9034a..8c818a2cf4f6 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -36,6 +36,7 @@ struct hmm_dmirror_cmd { #define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd) #define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) #define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_RELEASE _IOWR('H', 0x07, struct hmm_dmirror_cmd) /* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. diff --git a/lib/test_meminit.c b/lib/test_meminit.c index c95db11a6906..60e1984c060f 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -67,17 +67,24 @@ static int __init do_alloc_pages_order(int order, int *total_failures) size_t size = PAGE_SIZE << order; page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); fill_with_garbage(buf, size); __free_pages(page, order); page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); __free_pages(page, order); return 1; +err: + (*total_failures)++; + return 1; } /* Test the page allocator by calling alloc_pages with different orders. */ @@ -100,15 +107,22 @@ static int __init do_kmalloc_size(size_t size, int *total_failures) void *buf; buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; fill_with_garbage(buf, size); kfree(buf); buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); kfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test vmalloc() with given parameters. */ @@ -117,15 +131,22 @@ static int __init do_vmalloc_size(size_t size, int *total_failures) void *buf; buf = vmalloc(size); + if (!buf) + goto err; fill_with_garbage(buf, size); vfree(buf); buf = vmalloc(size); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); vfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test kmalloc()/vmalloc() by allocating objects of different sizes. */ diff --git a/mm/compaction.c b/mm/compaction.c index 2dd02c4683c4..c51f7f545afe 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1847,7 +1847,6 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; - set_pageblock_skip(freepage); break; } } diff --git a/mm/damon/core.c b/mm/damon/core.c index 8e1ab38d0f1f..36d098d06c55 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -491,7 +491,7 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) - sz += r->ar.end - r->ar.start; + sz += damon_sz_region(r); } if (ctx->attrs.min_nr_regions) @@ -674,7 +674,7 @@ static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); return s->pattern.min_sz_region <= sz && sz <= s->pattern.max_sz_region && s->pattern.min_nr_accesses <= r->nr_accesses && @@ -702,7 +702,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - unsigned long sz = r->ar.end - r->ar.start; + unsigned long sz = damon_sz_region(r); struct timespec64 begin, end; unsigned long sz_applied = 0; @@ -731,14 +731,14 @@ static void damon_do_apply_schemes(struct damon_ctx *c, sz = ALIGN_DOWN(quota->charge_addr_from - r->ar.start, DAMON_MIN_REGION); if (!sz) { - if (r->ar.end - r->ar.start <= - DAMON_MIN_REGION) + if (damon_sz_region(r) <= + DAMON_MIN_REGION) continue; sz = DAMON_MIN_REGION; } damon_split_region_at(t, r, sz); r = damon_next_region(r); - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); } quota->charge_target_from = NULL; quota->charge_addr_from = 0; @@ -843,8 +843,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) continue; score = c->ops.get_scheme_score( c, t, r, s); - quota->histogram[score] += - r->ar.end - r->ar.start; + quota->histogram[score] += damon_sz_region(r); if (score > max_score) max_score = score; } @@ -865,18 +864,13 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -static inline unsigned long sz_damon_region(struct damon_region *r) -{ - return r->ar.end - r->ar.start; -} - /* * Merge two adjacent regions into one region */ static void damon_merge_two_regions(struct damon_target *t, struct damon_region *l, struct damon_region *r) { - unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r); l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); @@ -905,7 +899,7 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, if (prev && prev->ar.end == r->ar.start && abs(prev->nr_accesses - r->nr_accesses) <= thres && - sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_sz_region(prev) + damon_sz_region(r) <= sz_limit) damon_merge_two_regions(t, prev, r); else prev = r; @@ -963,7 +957,7 @@ static void damon_split_regions_of(struct damon_target *t, int nr_subs) int i; damon_for_each_region_safe(r, next, t) { - sz_region = r->ar.end - r->ar.start; + sz_region = damon_sz_region(r); for (i = 0; i < nr_subs - 1 && sz_region > 2 * DAMON_MIN_REGION; i++) { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index ea94e0b2c311..15f03df66db6 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -72,7 +72,7 @@ static int damon_va_evenly_split_region(struct damon_target *t, return -EINVAL; orig_end = r->ar.end; - sz_orig = r->ar.end - r->ar.start; + sz_orig = damon_sz_region(r); sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); if (!sz_piece) @@ -618,7 +618,7 @@ static unsigned long damos_madvise(struct damon_target *target, { struct mm_struct *mm; unsigned long start = PAGE_ALIGN(r->ar.start); - unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long len = PAGE_ALIGN(damon_sz_region(r)); unsigned long applied; mm = damon_get_mm(target); diff --git a/mm/highmem.c b/mm/highmem.c index c707d7202d5f..db251e77f98f 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -30,6 +30,17 @@ #include <asm/tlbflush.h> #include <linux/vmalloc.h> +#ifdef CONFIG_KMAP_LOCAL +static inline int kmap_local_calc_idx(int idx) +{ + return idx + KM_MAX_IDX * smp_processor_id(); +} + +#ifndef arch_kmap_local_map_idx +#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) +#endif +#endif /* CONFIG_KMAP_LOCAL */ + /* * Virtual_count is not a pure "count". * 0 means that it is not mapped, and has not been mapped @@ -142,12 +153,29 @@ pte_t *pkmap_page_table; struct page *__kmap_to_page(void *vaddr) { + unsigned long base = (unsigned long) vaddr & PAGE_MASK; + struct kmap_ctrl *kctrl = ¤t->kmap_ctrl; unsigned long addr = (unsigned long)vaddr; + int i; + + /* kmap() mappings */ + if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) && + addr < PKMAP_ADDR(LAST_PKMAP))) + return pte_page(pkmap_page_table[PKMAP_NR(addr)]); - if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) { - int i = PKMAP_NR(addr); + /* kmap_local_page() mappings */ + if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) && + base < __fix_to_virt(FIX_KMAP_BEGIN))) { + for (i = 0; i < kctrl->idx; i++) { + unsigned long base_addr; + int idx; - return pte_page(pkmap_page_table[i]); + idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); + base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + + if (base_addr == base) + return pte_page(kctrl->pteval[i]); + } } return virt_to_page(vaddr); @@ -462,10 +490,6 @@ static inline void kmap_local_idx_pop(void) # define arch_kmap_local_post_unmap(vaddr) do { } while (0) #endif -#ifndef arch_kmap_local_map_idx -#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) -#endif - #ifndef arch_kmap_local_unmap_idx #define arch_kmap_local_unmap_idx(idx, vaddr) kmap_local_calc_idx(idx) #endif @@ -494,11 +518,6 @@ static inline bool kmap_high_unmap_local(unsigned long vaddr) return false; } -static inline int kmap_local_calc_idx(int idx) -{ - return idx + KM_MAX_IDX * smp_processor_id(); -} - static pte_t *__kmap_pte; static pte_t *kmap_get_pte(unsigned long vaddr, int idx) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 57b7b0b5d9eb..b586cdd75930 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,6 +5096,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to @@ -5107,6 +5108,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); else +#endif huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; @@ -5135,11 +5137,13 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5531,6 +5535,23 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, return handle_userfault(&vmf, reason); } +/* + * Recheck pte with pgtable lock. Returns true if pte didn't change, or + * false if pte changed or is changing. + */ +static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, + pte_t *ptep, pte_t old_pte) +{ + spinlock_t *ptl; + bool same; + + ptl = huge_pte_lock(h, mm, ptep); + same = pte_same(huge_ptep_get(ptep), old_pte); + spin_unlock(ptl); + + return same; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -5571,10 +5592,33 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (idx >= size) goto out; /* Check for page in userfault range */ - if (userfaultfd_missing(vma)) - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MISSING); + if (userfaultfd_missing(vma)) { + /* + * Since hugetlb_no_page() was examining pte + * without pgtable lock, we need to re-test under + * lock because the pte may not be stable and could + * have changed from under us. Try to detect + * either changed or during-changing ptes and retry + * properly when needed. + * + * Note that userfaultfd is actually fine with + * false positives (e.g. caused by pte changed), + * but not wrong logical events (e.g. caused by + * reading a pte during changing). The latter can + * confuse the userspace, so the strictness is very + * much preferred. E.g., MISSING event should + * never happen on the page after UFFDIO_COPY has + * correctly installed the page and returned. + */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MISSING); + } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { @@ -5590,11 +5634,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * here. Before returning error, get ptl and make * sure there really is no pte entry. */ - ptl = huge_pte_lock(h, mm, ptep); - ret = 0; - if (huge_pte_none(huge_ptep_get(ptep))) + if (hugetlb_pte_stable(h, mm, ptep, old_pte)) ret = vmf_error(PTR_ERR(page)); - spin_unlock(ptl); + else + ret = 0; goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); @@ -5640,9 +5683,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (userfaultfd_minor(vma)) { unlock_page(page); put_page(page); - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MINOR); + /* See comment in userfaultfd_missing() block above */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MINOR); } } @@ -6804,7 +6852,7 @@ void hugetlb_vma_lock_release(struct kref *kref) kfree(vma_lock); } -void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) +static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index f25692def781..57e4c72aa8bd 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -295,6 +295,9 @@ static void krealloc_more_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* All offsets up to size2 must be accessible. */ ptr2[size1 - 1] = 'x'; ptr2[size1] = 'x'; @@ -327,6 +330,9 @@ static void krealloc_less_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* Must be accessible for all modes. */ ptr2[size2 - 1] = 'x'; @@ -540,13 +546,14 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) { char *ptr; size_t size = 64; - volatile size_t invalid_size = size; + size_t invalid_size = size; ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); OPTIMIZER_HIDE_VAR(ptr); + OPTIMIZER_HIDE_VAR(invalid_size); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); kfree(ptr); diff --git a/mm/memory.c b/mm/memory.c index df678fa30cdb..f88c351aecd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1393,10 +1393,12 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, struct zap_details *details, pte_t pteval) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (zap_drop_file_uffd_wp(details)) return; pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +#endif } static unsigned long zap_pte_range(struct mmu_gather *tlb, @@ -3748,7 +3750,21 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); - ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + spin_unlock(vmf->ptl); + goto out; + } + + /* + * Get a page reference while we know the page can't be + * freed. + */ + get_page(vmf->page); + pte_unmap_unlock(vmf->pte, vmf->ptl); + vmf->page->pgmap->ops->migrate_to_ram(vmf); + put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else if (is_swapin_error_entry(entry)) { @@ -4118,7 +4134,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { - update_mmu_cache(vma, vmf->address, vmf->pte); + update_mmu_tlb(vma, vmf->address, vmf->pte); goto release; } diff --git a/mm/memremap.c b/mm/memremap.c index 25029a474d30..421bec3a29ee 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -138,8 +138,11 @@ void memunmap_pages(struct dev_pagemap *pgmap) int i; percpu_ref_kill(&pgmap->ref); - for (i = 0; i < pgmap->nr_range; i++) - percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + for (i = 0; i < pgmap->nr_range; i++) + percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + wait_for_completion(&pgmap->done); for (i = 0; i < pgmap->nr_range; i++) @@ -264,7 +267,9 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: @@ -502,11 +507,28 @@ void free_zone_device_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_COHERENT) + /* + * Reset the page count to 1 to prepare for handing out the page + * again. + */ + set_page_count(page, 1); + else + put_dev_pagemap(page->pgmap); +} + +void zone_device_page_init(struct page *page) +{ /* - * Reset the page count to 1 to prepare for handing out the page again. + * Drivers shouldn't be allocating pages after calling + * memunmap_pages(). */ + WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref)); set_page_count(page, 1); + lock_page(page); } +EXPORT_SYMBOL_GPL(zone_device_page_init); #ifdef CONFIG_FS_DAX bool __put_devmap_managed_page_refs(struct page *page, int refs) diff --git a/mm/migrate.c b/mm/migrate.c index c228afba0963..1379e1912772 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -625,6 +625,25 @@ EXPORT_SYMBOL(folio_migrate_copy); * Migration functions ***********************************************************/ +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count) +{ + int rc; + + BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ + + rc = folio_migrate_mapping(mapping, dst, src, extra_count); + + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (mode != MIGRATE_SYNC_NO_COPY) + folio_migrate_copy(dst, src); + else + folio_migrate_flags(dst, src); + return MIGRATEPAGE_SUCCESS; +} + /** * migrate_folio() - Simple folio migration. * @mapping: The address_space containing the folio. @@ -640,20 +659,7 @@ EXPORT_SYMBOL(folio_migrate_copy); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { - int rc; - - BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ - - rc = folio_migrate_mapping(mapping, dst, src, 0); - - if (rc != MIGRATEPAGE_SUCCESS) - return rc; - - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); - return MIGRATEPAGE_SUCCESS; + return migrate_folio_extra(mapping, dst, src, mode, 0); } EXPORT_SYMBOL(migrate_folio); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 5ab6ab9d2ed8..6fa682eef7a0 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -325,14 +325,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * folio_migrate_mapping(), except that here we allow migration of a * ZONE_DEVICE page. */ -static bool migrate_vma_check_page(struct page *page) +static bool migrate_vma_check_page(struct page *page, struct page *fault_page) { /* * One extra ref because caller holds an extra reference, either from * isolate_lru_page() for a regular page, or migrate_vma_collect() for * a device page. */ - int extra = 1; + int extra = 1 + (page == fault_page); /* * FIXME support THP (transparent huge page), it is bit more complex to @@ -357,26 +357,20 @@ static bool migrate_vma_check_page(struct page *page) } /* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Isolate pages from the LRU and replace mappings (CPU page table pte) with a - * special migration pte entry and check if it has been pinned. Pinned pages are - * restored because we cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. + * Unmaps pages for migration. Returns number of unmapped pages. */ -static void migrate_vma_unmap(struct migrate_vma *migrate) +static unsigned long migrate_device_unmap(unsigned long *src_pfns, + unsigned long npages, + struct page *fault_page) { - const unsigned long npages = migrate->npages; unsigned long i, restore = 0; bool allow_drain = true; + unsigned long unmapped = 0; lru_add_drain(); for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; if (!page) @@ -391,8 +385,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } @@ -405,34 +398,55 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) if (folio_mapped(folio)) try_to_migrate(folio, 0); - if (page_mapped(page) || !migrate_vma_check_page(page)) { + if (page_mapped(page) || + !migrate_vma_check_page(page, fault_page)) { if (!is_zone_device_page(page)) { get_page(page); putback_lru_page(page); } - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } + + unmapped++; } for (i = 0; i < npages && restore; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + if (!page || (src_pfns[i] & MIGRATE_PFN_MIGRATE)) continue; folio = page_folio(page); remove_migration_ptes(folio, folio, false); - migrate->src[i] = 0; + src_pfns[i] = 0; folio_unlock(folio); folio_put(folio); restore--; } + + return unmapped; +} + +/* + * migrate_vma_unmap() - replace page mapping with special migration pte entry + * @migrate: migrate struct containing all migration information + * + * Isolate pages from the LRU and replace mappings (CPU page table pte) with a + * special migration pte entry and check if it has been pinned. Pinned pages are + * restored because we cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. + */ +static void migrate_vma_unmap(struct migrate_vma *migrate) +{ + migrate->cpages = migrate_device_unmap(migrate->src, migrate->npages, + migrate->fault_page); } /** @@ -517,6 +531,8 @@ int migrate_vma_setup(struct migrate_vma *args) return -EINVAL; if (!args->src || !args->dst) return -EINVAL; + if (args->fault_page && !is_device_private_page(args->fault_page)) + return -EINVAL; memset(args->src, 0, sizeof(*args->src) * nr_pages); args->cpages = 0; @@ -677,42 +693,38 @@ abort: *src &= ~MIGRATE_PFN_MIGRATE; } -/** - * migrate_vma_pages() - migrate meta-data from src page to dst page - * @migrate: migrate struct containing all migration information - * - * This migrates struct page meta-data from source struct page to destination - * struct page. This effectively finishes the migration from source page to the - * destination page. - */ -void migrate_vma_pages(struct migrate_vma *migrate) +static void __migrate_device_pages(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages, + struct migrate_vma *migrate) { - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; struct mmu_notifier_range range; - unsigned long addr, i; + unsigned long i; bool notified = false; - for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) { - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + for (i = 0; i < npages; i++) { + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct address_space *mapping; int r; if (!newpage) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } if (!page) { + unsigned long addr; + + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + /* * The only time there is no vma is when called from * migrate_device_coherent_page(). However this isn't * called if the page could not be unmapped. */ - VM_BUG_ON(!migrate->vma); - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; + VM_BUG_ON(!migrate); + addr = migrate->start + i*PAGE_SIZE; if (!notified) { notified = true; @@ -723,7 +735,7 @@ void migrate_vma_pages(struct migrate_vma *migrate) mmu_notifier_invalidate_range_start(&range); } migrate_vma_insert_page(migrate, addr, newpage, - &migrate->src[i]); + &src_pfns[i]); continue; } @@ -736,21 +748,26 @@ void migrate_vma_pages(struct migrate_vma *migrate) * device private or coherent memory. */ if (mapping) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } } else if (is_zone_device_page(newpage)) { /* * Other types of ZONE_DEVICE page are not supported. */ - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } - r = migrate_folio(mapping, page_folio(newpage), - page_folio(page), MIGRATE_SYNC_NO_COPY); + if (migrate && migrate->fault_page == page) + r = migrate_folio_extra(mapping, page_folio(newpage), + page_folio(page), + MIGRATE_SYNC_NO_COPY, 1); + else + r = migrate_folio(mapping, page_folio(newpage), + page_folio(page), MIGRATE_SYNC_NO_COPY); if (r != MIGRATEPAGE_SUCCESS) - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; } /* @@ -761,28 +778,56 @@ void migrate_vma_pages(struct migrate_vma *migrate) if (notified) mmu_notifier_invalidate_range_only_end(&range); } -EXPORT_SYMBOL(migrate_vma_pages); /** - * migrate_vma_finalize() - restore CPU page table entry + * migrate_device_pages() - migrate meta-data from src page to dst page + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range + * + * Equivalent to migrate_vma_pages(). This is called to migrate struct page + * meta-data from source struct page to destination. + */ +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages) +{ + __migrate_device_pages(src_pfns, dst_pfns, npages, NULL); +} +EXPORT_SYMBOL(migrate_device_pages); + +/** + * migrate_vma_pages() - migrate meta-data from src page to dst page * @migrate: migrate struct containing all migration information * - * This replaces the special migration pte entry with either a mapping to the - * new page if migration was successful for that page, or to the original page - * otherwise. + * This migrates struct page meta-data from source struct page to destination + * struct page. This effectively finishes the migration from source page to the + * destination page. + */ +void migrate_vma_pages(struct migrate_vma *migrate) +{ + __migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate); +} +EXPORT_SYMBOL(migrate_vma_pages); + +/* + * migrate_device_finalize() - complete page migration + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range * - * This also unlocks the pages and puts them back on the lru, or drops the extra - * refcount, for device pages. + * Completes migration of the page by removing special migration entries. + * Drivers must ensure copying of page data is complete and visible to the CPU + * before calling this. */ -void migrate_vma_finalize(struct migrate_vma *migrate) +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages) { - const unsigned long npages = migrate->npages; unsigned long i; for (i = 0; i < npages; i++) { struct folio *dst, *src; - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); if (!page) { if (newpage) { @@ -792,7 +837,7 @@ void migrate_vma_finalize(struct migrate_vma *migrate) continue; } - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) { + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE) || !newpage) { if (newpage) { unlock_page(newpage); put_page(newpage); @@ -819,8 +864,72 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } } } +EXPORT_SYMBOL(migrate_device_finalize); + +/** + * migrate_vma_finalize() - restore CPU page table entry + * @migrate: migrate struct containing all migration information + * + * This replaces the special migration pte entry with either a mapping to the + * new page if migration was successful for that page, or to the original page + * otherwise. + * + * This also unlocks the pages and puts them back on the lru, or drops the extra + * refcount, for device pages. + */ +void migrate_vma_finalize(struct migrate_vma *migrate) +{ + migrate_device_finalize(migrate->src, migrate->dst, migrate->npages); +} EXPORT_SYMBOL(migrate_vma_finalize); +/** + * migrate_device_range() - migrate device private pfns to normal memory. + * @src_pfns: array large enough to hold migrating source device private pfns. + * @start: starting pfn in the range to migrate. + * @npages: number of pages to migrate. + * + * migrate_vma_setup() is similar in concept to migrate_vma_setup() except that + * instead of looking up pages based on virtual address mappings a range of + * device pfns that should be migrated to system memory is used instead. + * + * This is useful when a driver needs to free device memory but doesn't know the + * virtual mappings of every page that may be in device memory. For example this + * is often the case when a driver is being unloaded or unbound from a device. + * + * Like migrate_vma_setup() this function will take a reference and lock any + * migrating pages that aren't free before unmapping them. Drivers may then + * allocate destination pages and start copying data from the device to CPU + * memory before calling migrate_device_pages(). + */ +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages) +{ + unsigned long i, pfn; + + for (pfn = start, i = 0; i < npages; pfn++, i++) { + struct page *page = pfn_to_page(pfn); + + if (!get_page_unless_zero(page)) { + src_pfns[i] = 0; + continue; + } + + if (!trylock_page(page)) { + src_pfns[i] = 0; + put_page(page); + continue; + } + + src_pfns[i] = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; + } + + migrate_device_unmap(src_pfns, npages, NULL); + + return 0; +} +EXPORT_SYMBOL(migrate_device_range); + /* * Migrate a device coherent page back to normal memory. The caller should have * a reference on page which will be copied to the new page if migration is @@ -829,25 +938,19 @@ EXPORT_SYMBOL(migrate_vma_finalize); int migrate_device_coherent_page(struct page *page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma args; struct page *dpage; WARN_ON_ONCE(PageCompound(page)); lock_page(page); src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; - args.src = &src_pfn; - args.dst = &dst_pfn; - args.cpages = 1; - args.npages = 1; - args.vma = NULL; /* * We don't have a VMA and don't need to walk the page tables to find * the source page. So call migrate_vma_unmap() directly to unmap the * page as migrate_vma_setup() will fail if args.vma == NULL. */ - migrate_vma_unmap(&args); + migrate_device_unmap(&src_pfn, 1, NULL); if (!(src_pfn & MIGRATE_PFN_MIGRATE)) return -EBUSY; @@ -857,10 +960,10 @@ int migrate_device_coherent_page(struct page *page) dst_pfn = migrate_pfn(page_to_pfn(dpage)); } - migrate_vma_pages(&args); + migrate_device_pages(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) copy_highpage(dpage, page); - migrate_vma_finalize(&args); + migrate_device_finalize(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) return 0; diff --git a/mm/mmap.c b/mm/mmap.c index 6e447544f07d..bf2122af94e7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2673,7 +2673,7 @@ cannot_expand: if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) - goto unmap_and_free_vma; + goto close_and_free_vma; else goto free_vma; } @@ -2742,6 +2742,9 @@ expanded: validate_mm(mm); return addr; +close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL; @@ -2942,17 +2945,18 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, if (vma && (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) && ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) { - mas->index = vma->vm_start; - mas->last = addr + len - 1; - vma_adjust_trans_huge(vma, addr, addr + len, 0); + mas_set_range(mas, vma->vm_start, addr + len - 1); + if (mas_preallocate(mas, vma, GFP_KERNEL)) + return -ENOMEM; + + vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); if (vma->anon_vma) { anon_vma_lock_write(vma->anon_vma); anon_vma_interval_tree_pre_update_vma(vma); } vma->vm_end = addr + len; vma->vm_flags |= VM_SOFTDIRTY; - if (mas_store_gfp(mas, vma, GFP_KERNEL)) - goto mas_expand_failed; + mas_store_prealloc(mas, vma); if (vma->anon_vma) { anon_vma_interval_tree_post_update_vma(vma); @@ -2993,13 +2997,6 @@ mas_store_fail: vma_alloc_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; - -mas_expand_failed: - if (vma->anon_vma) { - anon_vma_interval_tree_post_update_vma(vma); - anon_vma_unlock_write(vma->anon_vma); - } - return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) @@ -3240,6 +3237,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); + + if (new_vma->vm_file) + fput(new_vma->vm_file); + + unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index a71924bd38c0..add4244e5790 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -1,6 +1,7 @@ #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/kernel.h> +#include <linux/kmsan-checks.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/mm_inline.h> @@ -265,6 +266,15 @@ void tlb_flush_mmu(struct mmu_gather *tlb) static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { + /* + * struct mmu_gather contains 7 1-bit fields packed into a 32-bit + * unsigned int value. The remaining 25 bits remain uninitialized + * and are never used, but KMSAN updates the origin for them in + * zap_pXX_range() in mm/memory.c, thus creating very long origin + * chains. This is technically correct, but consumes too much memory. + * Unpoisoning the whole structure will prevent creating such chains. + */ + kmsan_unpoison_memory(tlb, sizeof(*tlb)); tlb->mm = mm; tlb->fullmm = fullmm; diff --git a/mm/mprotect.c b/mm/mprotect.c index 461dcbd4f21a..668bfaa6ed2a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -267,6 +267,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, } else { /* It must be an none page, or what else?.. */ WARN_ON_ONCE(!pte_none(oldpte)); +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { /* * For file-backed mem, we need to be able to @@ -278,6 +279,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, make_pte_marker(PTE_MARKER_UFFD_WP)); pages++; } +#endif } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ac2c9f12a7b2..e20ade858e71 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3446,7 +3446,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, int pindex; bool free_high; - __count_vm_event(PGFREE); + __count_vm_events(PGFREE, 1 << order); pindex = order_to_pindex(migratetype, order); list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; @@ -3803,7 +3803,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, pcp_spin_unlock_irqrestore(pcp, flags); pcp_trylock_finish(UP_flags); if (page) { - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone, 1); } return page; @@ -6823,6 +6823,14 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); } /* diff --git a/mm/slab.c b/mm/slab.c index a5486ff8362a..d1f6e2c64c2e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1619,7 +1619,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slab) * although actual page can be freed in rcu context */ if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->freelist_cache, freelist); + kfree(freelist); } /* @@ -1671,21 +1671,27 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, if (flags & CFLGS_OFF_SLAB) { struct kmem_cache *freelist_cache; size_t freelist_size; + size_t freelist_cache_size; freelist_size = num * sizeof(freelist_idx_t); - freelist_cache = kmalloc_slab(freelist_size, 0u); - if (!freelist_cache) - continue; - - /* - * Needed to avoid possible looping condition - * in cache_grow_begin() - */ - if (OFF_SLAB(freelist_cache)) - continue; + if (freelist_size > KMALLOC_MAX_CACHE_SIZE) { + freelist_cache_size = PAGE_SIZE << get_order(freelist_size); + } else { + freelist_cache = kmalloc_slab(freelist_size, 0u); + if (!freelist_cache) + continue; + freelist_cache_size = freelist_cache->size; + + /* + * Needed to avoid possible looping condition + * in cache_grow_begin() + */ + if (OFF_SLAB(freelist_cache)) + continue; + } /* check if off slab has enough benefit */ - if (freelist_cache->size > cachep->size / 2) + if (freelist_cache_size > cachep->size / 2) continue; } @@ -2061,11 +2067,6 @@ done: cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); #endif - if (OFF_SLAB(cachep)) { - cachep->freelist_cache = - kmalloc_slab(cachep->freelist_size, 0u); - } - err = setup_cpu_cache(cachep, gfp); if (err) { __kmem_cache_release(cachep); @@ -2292,7 +2293,7 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, freelist = NULL; else if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ - freelist = kmem_cache_alloc_node(cachep->freelist_cache, + freelist = kmalloc_node(cachep->freelist_size, local_flags, nodeid); } else { /* We will use last bytes at the slab for freelist */ diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 22adbf89cb31..41f3602fc8de 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -140,7 +140,7 @@ $(obj)/%.symtypes : $(src)/%.c FORCE # LLVM assembly # Generate .ll files from .c quiet_cmd_cc_ll_c = CC $(quiet_modtag) $@ - cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -o $@ $< + cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -fno-discard-value-names -o $@ $< $(obj)/%.ll: $(src)/%.c FORCE $(call if_changed_dep,cc_ll_c) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 7740ce3b29e8..8489a3402eb8 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -119,7 +119,7 @@ quiet_cmd_modpost = MODPOST $@ echo >&2 "WARNING: $(missing-input) is missing."; \ echo >&2 " Modules may not have dependencies or modversions."; \ echo >&2 " You may get many unresolved symbol warnings.";) \ - sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) $(vmlinux.o-if-present) -T - + sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) -T - $(vmlinux.o-if-present) targets += $(output-symdump) $(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(moudle.symvers-if-present) $(MODPOST) FORCE diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py index bb78c9bde55c..56f2ec8f0f40 100755 --- a/scripts/clang-tools/run-clang-tools.py +++ b/scripts/clang-tools/run-clang-tools.py @@ -45,13 +45,14 @@ def init(l, a): def run_analysis(entry): # Disable all checks, then re-enable the ones we want - checks = "-checks=-*," + checks = [] + checks.append("-checks=-*") if args.type == "clang-tidy": - checks += "linuxkernel-*" + checks.append("linuxkernel-*") else: - checks += "clang-analyzer-*" - checks += ",-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling" - p = subprocess.run(["clang-tidy", "-p", args.path, checks, entry["file"]], + checks.append("clang-analyzer-*") + checks.append("-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling") + p = subprocess.run(["clang-tidy", "-p", args.path, ",".join(checks), entry["file"]], stdout=subprocess.PIPE, stderr=subprocess.STDOUT, cwd=entry["directory"]) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index c920c1b18e7a..70392fd2fd29 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -97,8 +97,6 @@ $M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE cp .config %{buildroot}/boot/config-$KERNELRELEASE - bzip2 -9 --keep vmlinux - mv vmlinux.bz2 %{buildroot}/boot/vmlinux-$KERNELRELEASE.bz2 $S$M rm -f %{buildroot}/lib/modules/$KERNELRELEASE/build $S$M rm -f %{buildroot}/lib/modules/$KERNELRELEASE/source $S$M mkdir -p %{buildroot}/usr/src/kernels/$KERNELRELEASE diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6963d5a487b3..d8edb6055072 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1899,10 +1899,8 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi) snd_info_free_entry(rmidi->proc_entry); rmidi->proc_entry = NULL; - mutex_lock(®ister_mutex); if (rmidi->ops && rmidi->ops->dev_unregister) rmidi->ops->dev_unregister(rmidi); - mutex_unlock(®ister_mutex); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT]); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT]); diff --git a/sound/core/sound_oss.c b/sound/core/sound_oss.c index 7ed0a2a91035..2751bf2ff61b 100644 --- a/sound/core/sound_oss.c +++ b/sound/core/sound_oss.c @@ -162,7 +162,6 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) mutex_unlock(&sound_oss_mutex); return -ENOENT; } - unregister_sound_special(minor); switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); @@ -174,12 +173,18 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } - if (track2 >= 0) { - unregister_sound_special(track2); + if (track2 >= 0) snd_oss_minors[track2] = NULL; - } snd_oss_minors[minor] = NULL; mutex_unlock(&sound_oss_mutex); + + /* call unregister_sound_special() outside sound_oss_mutex; + * otherwise may deadlock, as it can trigger the release of a card + */ + unregister_sound_special(minor); + if (track2 >= 0) + unregister_sound_special(track2); + kfree(mptr); return 0; } diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 3952f2853703..e5f0549bf06d 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -91,20 +91,18 @@ static const struct reg_sequence cs35l41_hda_mute[] = { { CS35L41_AMP_DIG_VOL_CTRL, 0x0000A678 }, // AMP_VOL_PCM Mute }; -static int cs35l41_control_add(struct cs_dsp_coeff_ctl *cs_ctl) +static void cs35l41_add_controls(struct cs35l41_hda *cs35l41) { - struct cs35l41_hda *cs35l41 = container_of(cs_ctl->dsp, struct cs35l41_hda, cs_dsp); struct hda_cs_dsp_ctl_info info; info.device_name = cs35l41->amp_name; info.fw_type = cs35l41->firmware_type; info.card = cs35l41->codec->card; - return hda_cs_dsp_control_add(cs_ctl, &info); + hda_cs_dsp_add_controls(&cs35l41->cs_dsp, &info); } static const struct cs_dsp_client_ops client_ops = { - .control_add = cs35l41_control_add, .control_remove = hda_cs_dsp_control_remove, }; @@ -435,6 +433,8 @@ static int cs35l41_init_dsp(struct cs35l41_hda *cs35l41) if (ret) goto err_release; + cs35l41_add_controls(cs35l41); + ret = cs35l41_save_calibration(cs35l41); err_release: @@ -461,9 +461,12 @@ static void cs35l41_remove_dsp(struct cs35l41_hda *cs35l41) struct cs_dsp *dsp = &cs35l41->cs_dsp; cancel_work_sync(&cs35l41->fw_load_work); + + mutex_lock(&cs35l41->fw_mutex); cs35l41_shutdown_dsp(cs35l41); cs_dsp_remove(dsp); cs35l41->halo_initialized = false; + mutex_unlock(&cs35l41->fw_mutex); } /* Protection release cycle to get the speaker out of Safe-Mode */ @@ -487,10 +490,10 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) struct regmap *reg = cs35l41->regmap; int ret = 0; - mutex_lock(&cs35l41->fw_mutex); - switch (action) { case HDA_GEN_PCM_ACT_OPEN: + pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); cs35l41->playback_started = true; if (cs35l41->firmware_running) { regmap_multi_reg_write(reg, cs35l41_hda_config_dsp, @@ -508,15 +511,21 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) CS35L41_AMP_EN_MASK, 1 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) regmap_write(reg, CS35L41_GPIO1_CTRL1, 0x00008001); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_PREPARE: + mutex_lock(&cs35l41->fw_mutex); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 1); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLEANUP: + mutex_lock(&cs35l41->fw_mutex); regmap_multi_reg_write(reg, cs35l41_hda_mute, ARRAY_SIZE(cs35l41_hda_mute)); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 0); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLOSE: + mutex_lock(&cs35l41->fw_mutex); ret = regmap_update_bits(reg, CS35L41_PWR_CTRL2, CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) @@ -530,14 +539,16 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) } cs35l41_irq_release(cs35l41); cs35l41->playback_started = false; + mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); break; default: dev_warn(cs35l41->dev, "Playback action not supported: %d\n", action); break; } - mutex_unlock(&cs35l41->fw_mutex); - if (ret) dev_err(cs35l41->dev, "Regmap access fail: %d\n", ret); } @@ -562,45 +573,148 @@ static int cs35l41_hda_channel_map(struct device *dev, unsigned int tx_num, unsi rx_slot); } +static void cs35l41_ready_for_reset(struct cs35l41_hda *cs35l41) +{ + mutex_lock(&cs35l41->fw_mutex); + if (cs35l41->firmware_running) { + + regcache_cache_only(cs35l41->regmap, false); + + cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + cs35l41_shutdown_dsp(cs35l41); + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + + regcache_cache_only(cs35l41->regmap, true); + regcache_mark_dirty(cs35l41->regmap); + } + mutex_unlock(&cs35l41->fw_mutex); +} + +static int cs35l41_system_suspend(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Suspend\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Suspend not supported\n"); + return -EINVAL; + } + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + + /* Shutdown DSP before system suspend */ + cs35l41_ready_for_reset(cs35l41); + + /* + * Reset GPIO may be shared, so cannot reset here. + * However beyond this point, amps may be powered down. + */ + return 0; +} + +static int cs35l41_system_resume(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Resume\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Resume not supported\n"); + return -EINVAL; + } + + if (cs35l41->reset_gpio) { + usleep_range(2000, 2100); + gpiod_set_value_cansleep(cs35l41->reset_gpio, 1); + } + + usleep_range(2000, 2100); + + ret = pm_runtime_force_resume(dev); + + mutex_lock(&cs35l41->fw_mutex); + if (!ret && cs35l41->request_fw_load && !cs35l41->fw_request_ongoing) { + cs35l41->fw_request_ongoing = true; + schedule_work(&cs35l41->fw_load_work); + } + mutex_unlock(&cs35l41->fw_mutex); + + return ret; +} + static int cs35l41_runtime_suspend(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret = 0; - dev_dbg(cs35l41->dev, "Suspend\n"); + dev_dbg(cs35l41->dev, "Runtime Suspend\n"); - if (!cs35l41->firmware_running) + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_dbg(cs35l41->dev, "Runtime Suspend not supported\n"); return 0; + } - if (cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type) < 0) - return 0; + mutex_lock(&cs35l41->fw_mutex); + + if (cs35l41->playback_started) { + regmap_multi_reg_write(cs35l41->regmap, cs35l41_hda_mute, + ARRAY_SIZE(cs35l41_hda_mute)); + cs35l41_global_enable(cs35l41->regmap, cs35l41->hw_cfg.bst_type, 0); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) + regmap_write(cs35l41->regmap, CS35L41_GPIO1_CTRL1, 0x00000001); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_VMON_EN_MASK | CS35L41_IMON_EN_MASK, + 0 << CS35L41_VMON_EN_SHIFT | 0 << CS35L41_IMON_EN_SHIFT); + cs35l41->playback_started = false; + } + + if (cs35l41->firmware_running) { + ret = cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, + cs35l41->hw_cfg.bst_type); + if (ret) + goto err; + } else { + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + } regcache_cache_only(cs35l41->regmap, true); regcache_mark_dirty(cs35l41->regmap); - return 0; +err: + mutex_unlock(&cs35l41->fw_mutex); + + return ret; } static int cs35l41_runtime_resume(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); - int ret; + int ret = 0; - dev_dbg(cs35l41->dev, "Resume.\n"); + dev_dbg(cs35l41->dev, "Runtime Resume\n"); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { - dev_dbg(cs35l41->dev, "System does not support Resume\n"); + dev_dbg(cs35l41->dev, "Runtime Resume not supported\n"); return 0; } - if (!cs35l41->firmware_running) - return 0; + mutex_lock(&cs35l41->fw_mutex); regcache_cache_only(cs35l41->regmap, false); - ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); - if (ret) { - regcache_cache_only(cs35l41->regmap, true); - return ret; + if (cs35l41->firmware_running) { + ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + if (ret) { + dev_warn(cs35l41->dev, "Unable to exit Hibernate."); + goto err; + } } /* Test key needs to be unlocked to allow the OTP settings to re-apply */ @@ -609,26 +723,16 @@ static int cs35l41_runtime_resume(struct device *dev) cs35l41_test_key_lock(cs35l41->dev, cs35l41->regmap); if (ret) { dev_err(cs35l41->dev, "Failed to restore register cache: %d\n", ret); - return ret; + goto err; } if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) cs35l41_init_boost(cs35l41->dev, cs35l41->regmap, &cs35l41->hw_cfg); - return 0; -} - -static int cs35l41_hda_suspend_hook(struct device *dev) -{ - dev_dbg(dev, "Request Suspend\n"); - pm_runtime_mark_last_busy(dev); - return pm_runtime_put_autosuspend(dev); -} +err: + mutex_unlock(&cs35l41->fw_mutex); -static int cs35l41_hda_resume_hook(struct device *dev) -{ - dev_dbg(dev, "Request Resume\n"); - return pm_runtime_get_sync(dev); + return ret; } static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41) @@ -678,8 +782,6 @@ clean_dsp: static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) { - pm_runtime_get_sync(cs35l41->dev); - if (cs35l41->firmware_running && !load) { dev_dbg(cs35l41->dev, "Unloading Firmware\n"); cs35l41_shutdown_dsp(cs35l41); @@ -689,9 +791,6 @@ static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) } else { dev_dbg(cs35l41->dev, "Unable to Load firmware.\n"); } - - pm_runtime_mark_last_busy(cs35l41->dev); - pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_get(struct snd_kcontrol *kcontrol, @@ -707,16 +806,21 @@ static void cs35l41_fw_load_work(struct work_struct *work) { struct cs35l41_hda *cs35l41 = container_of(work, struct cs35l41_hda, fw_load_work); + pm_runtime_get_sync(cs35l41->dev); + mutex_lock(&cs35l41->fw_mutex); /* Recheck if playback is ongoing, mutex will block playback during firmware loading */ if (cs35l41->playback_started) - dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback\n"); + dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback. Retrying...\n"); else cs35l41_load_firmware(cs35l41, cs35l41->request_fw_load); cs35l41->fw_request_ongoing = false; mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(cs35l41->dev); + pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_put(struct snd_kcontrol *kcontrol, @@ -840,6 +944,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); + comps->dev = dev; if (!cs35l41->acpi_subsystem_id) cs35l41->acpi_subsystem_id = kasprintf(GFP_KERNEL, "%.8x", @@ -852,10 +958,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas if (firmware_autostart) { dev_dbg(cs35l41->dev, "Firmware Autostart.\n"); cs35l41->request_fw_load = true; - mutex_lock(&cs35l41->fw_mutex); if (cs35l41_smart_amp(cs35l41) < 0) dev_warn(cs35l41->dev, "Cannot Run Firmware, reverting to dsp bypass...\n"); - mutex_unlock(&cs35l41->fw_mutex); } else { dev_dbg(cs35l41->dev, "Firmware Autostart is disabled.\n"); } @@ -863,8 +967,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas ret = cs35l41_create_controls(cs35l41); comps->playback_hook = cs35l41_hda_playback_hook; - comps->suspend_hook = cs35l41_hda_suspend_hook; - comps->resume_hook = cs35l41_hda_resume_hook; + + mutex_unlock(&cs35l41->fw_mutex); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); @@ -1433,6 +1537,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41); const struct dev_pm_ops cs35l41_hda_pm_ops = { RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume) }; EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41); diff --git a/sound/pci/hda/hda_component.h b/sound/pci/hda/hda_component.h index 1223621bd62c..534e845b9cd1 100644 --- a/sound/pci/hda/hda_component.h +++ b/sound/pci/hda/hda_component.h @@ -16,6 +16,4 @@ struct hda_component { char name[HDA_MAX_NAME_SIZE]; struct hda_codec *codec; void (*playback_hook)(struct device *dev, int action); - int (*suspend_hook)(struct device *dev); - int (*resume_hook)(struct device *dev); }; diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 89ee549cb7d5..1622a22f96f6 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -97,7 +97,7 @@ static unsigned int wmfw_convert_flags(unsigned int in) return out; } -static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) +static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) { struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; struct snd_kcontrol_new kcontrol = {0}; @@ -107,7 +107,7 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char if (cs_ctl->len > ADSP_MAX_STD_CTRL_SIZE) { dev_err(cs_ctl->dsp->dev, "KControl %s: length %zu exceeds maximum %d\n", name, cs_ctl->len, ADSP_MAX_STD_CTRL_SIZE); - return -EINVAL; + return; } kcontrol.name = name; @@ -120,24 +120,21 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char /* Save ctl inside private_data, ctl is owned by cs_dsp, * and will be freed when cs_dsp removes the control */ kctl = snd_ctl_new1(&kcontrol, (void *)ctl); - if (!kctl) { - ret = -ENOMEM; - return ret; - } + if (!kctl) + return; ret = snd_ctl_add(ctl->card, kctl); if (ret) { dev_err(cs_ctl->dsp->dev, "Failed to add KControl %s = %d\n", kcontrol.name, ret); - return ret; + return; } dev_dbg(cs_ctl->dsp->dev, "Added KControl: %s\n", kcontrol.name); ctl->kctl = kctl; - - return 0; } -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info) +static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, + const struct hda_cs_dsp_ctl_info *info) { struct cs_dsp *cs_dsp = cs_ctl->dsp; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; @@ -145,13 +142,10 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct const char *region_name; int ret; - if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) - return 0; - region_name = cs_dsp_mem_region_name(cs_ctl->alg_region.type); if (!region_name) { - dev_err(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); - return -EINVAL; + dev_warn(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); + return; } ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %.12s %x", info->device_name, @@ -171,22 +165,39 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); if (!ctl) - return -ENOMEM; + return; ctl->cs_ctl = cs_ctl; ctl->card = info->card; cs_ctl->priv = ctl; - ret = hda_cs_dsp_add_kcontrol(ctl, name); - if (ret) { - dev_err(cs_dsp->dev, "Error (%d) adding control %s\n", ret, name); - kfree(ctl); - return ret; - } + hda_cs_dsp_add_kcontrol(ctl, name); +} - return 0; +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info) +{ + struct cs_dsp_coeff_ctl *cs_ctl; + + /* + * pwr_lock would cause mutex inversion with ALSA control lock compared + * to the get/put functions. + * It is safe to walk the list without holding a mutex because entries + * are persistent and only cs_dsp_power_up() or cs_dsp_remove() can + * change the list. + */ + lockdep_assert_not_held(&dsp->pwr_lock); + + list_for_each_entry(cs_ctl, &dsp->ctl_list, list) { + if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) + continue; + + if (cs_ctl->priv) + continue; + + hda_cs_dsp_control_add(cs_ctl, info); + } } -EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_add, SND_HDA_CS_DSP_CONTROLS); +EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_add_controls, SND_HDA_CS_DSP_CONTROLS); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) { @@ -203,19 +214,18 @@ int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, struct hda_cs_dsp_coeff_ctl *ctl; int ret; + mutex_lock(&dsp->pwr_lock); cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; - - ctl = cs_ctl->priv; - ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); + mutex_unlock(&dsp->pwr_lock); if (ret) return ret; if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) return 0; + ctl = cs_ctl->priv; + snd_ctl_notify(ctl->card, SNDRV_CTL_EVENT_MASK_VALUE, &ctl->kctl->id); return 0; @@ -225,13 +235,14 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_write_ctl, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_read_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl; + int ret; - cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; + mutex_lock(&dsp->pwr_lock); + ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(dsp, name, type, alg), 0, buf, len); + mutex_unlock(&dsp->pwr_lock); + + return ret; - return cs_dsp_coeff_read_ctrl(cs_ctl, 0, buf, len); } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_read_ctl, SND_HDA_CS_DSP_CONTROLS); diff --git a/sound/pci/hda/hda_cs_dsp_ctl.h b/sound/pci/hda/hda_cs_dsp_ctl.h index 4babc69cf2f0..2cf93359c4f2 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.h +++ b/sound/pci/hda/hda_cs_dsp_ctl.h @@ -29,7 +29,7 @@ struct hda_cs_dsp_ctl_info { extern const char * const hda_cs_dsp_fw_ids[HDA_CS_DSP_NUM_FW]; -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info); +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl); int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, const void *buf, size_t len); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bce82b834cec..e6c4bb5fa041 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4022,22 +4022,16 @@ static void alc5505_dsp_init(struct hda_codec *codec) static int alc269_suspend(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->has_alc5505_dsp) alc5505_dsp_suspend(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].suspend_hook) - spec->comps[i].suspend_hook(spec->comps[i].dev); - return alc_suspend(codec); } static int alc269_resume(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->codec_variant == ALC269_TYPE_ALC269VB) alc269vb_toggle_power_output(codec, 0); @@ -4068,10 +4062,6 @@ static int alc269_resume(struct hda_codec *codec) if (spec->has_alc5505_dsp) alc5505_dsp_resume(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - return 0; } #endif /* CONFIG_PM */ @@ -6664,19 +6654,12 @@ static int comp_bind(struct device *dev) { struct hda_codec *cdc = dev_to_hda_codec(dev); struct alc_spec *spec = cdc->spec; - int ret, i; + int ret; ret = component_bind_all(dev, spec->comps); if (ret) return ret; - if (snd_hdac_is_power_on(&cdc->core)) { - codec_dbg(cdc, "Resuming after bind.\n"); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - } - return 0; } @@ -8449,11 +8432,13 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_ASUS_G533Z_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x90170120 }, + { 0x14, 0x90170152 }, /* Speaker Surround Playback Switch */ + { 0x19, 0x03a19020 }, /* Mic Boost Volume */ + { 0x1a, 0x03a11c30 }, /* Mic Boost Volume */ + { 0x1e, 0x90170151 }, /* Rear jack, IN OUT EAPD Detect */ + { 0x21, 0x03211420 }, { } }, - .chained = true, - .chain_id = ALC294_FIXUP_ASUS_G513_PINS, }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, @@ -9198,7 +9183,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), - SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), @@ -9422,6 +9406,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -9443,6 +9428,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), diff --git a/sound/usb/card.h b/sound/usb/card.h index ca75f2206170..40061550105a 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -129,7 +129,8 @@ struct snd_usb_endpoint { in a stream */ bool implicit_fb_sync; /* syncs with implicit feedback */ bool lowlatency_playback; /* low-latency playback mode */ - bool need_setup; /* (re-)need for configure? */ + bool need_setup; /* (re-)need for hw_params? */ + bool need_prepare; /* (re-)need for prepare? */ /* for hw constraints */ const struct audioformat *cur_audiofmt; diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 48a3843a08f1..d0b8d61d1d22 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -32,6 +32,7 @@ struct snd_usb_iface_ref { unsigned char iface; bool need_setup; int opened; + int altset; struct list_head list; }; @@ -823,6 +824,7 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip, ep->implicit_fb_sync = fp->implicit_fb; ep->need_setup = true; + ep->need_prepare = true; usb_audio_dbg(chip, " channels=%d, rate=%d, format=%s, period_bytes=%d, periods=%d, implicit_fb=%d\n", ep->cur_channels, ep->cur_rate, @@ -899,6 +901,9 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, int altset = set ? ep->altsetting : 0; int err; + if (ep->iface_ref->altset == altset) + return 0; + usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n", ep->iface, altset, ep->ep_num); err = usb_set_interface(chip->dev, ep->iface, altset); @@ -910,6 +915,7 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, if (chip->quirk_flags & QUIRK_FLAG_IFACE_DELAY) msleep(50); + ep->iface_ref->altset = altset; return 0; } @@ -947,7 +953,7 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip, /* Prepare for suspening EP, called from the main suspend handler */ void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep) { - ep->need_setup = true; + ep->need_prepare = true; if (ep->iface_ref) ep->iface_ref->need_setup = true; if (ep->clock_ref) @@ -1330,12 +1336,16 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, struct snd_usb_endpoint *ep) { const struct audioformat *fmt = ep->cur_audiofmt; - int err; + int err = 0; + + mutex_lock(&chip->mutex); + if (!ep->need_setup) + goto unlock; /* release old buffers, if any */ err = release_urbs(ep, false); if (err < 0) - return err; + goto unlock; ep->datainterval = fmt->datainterval; ep->maxpacksize = fmt->maxpacksize; @@ -1373,13 +1383,21 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, usb_audio_dbg(chip, "Set up %d URBS, ret=%d\n", ep->nurbs, err); if (err < 0) - return err; + goto unlock; /* some unit conversions in runtime */ ep->maxframesize = ep->maxpacksize / ep->cur_frame_bytes; ep->curframesize = ep->curpacksize / ep->cur_frame_bytes; - return update_clock_ref_rate(chip, ep); + err = update_clock_ref_rate(chip, ep); + if (err >= 0) { + ep->need_setup = false; + err = 0; + } + + unlock: + mutex_unlock(&chip->mutex); + return err; } static int init_sample_rate(struct snd_usb_audio *chip, @@ -1426,7 +1444,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, mutex_lock(&chip->mutex); if (WARN_ON(!ep->iface_ref)) goto unlock; - if (!ep->need_setup) + if (!ep->need_prepare) goto unlock; /* If the interface has been already set up, just set EP parameters */ @@ -1480,7 +1498,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, ep->iface_ref->need_setup = false; done: - ep->need_setup = false; + ep->need_prepare = false; err = 1; unlock: diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 7d722265dcd7..4adaad1b822f 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1054,6 +1054,55 @@ TEST_F(hmm, migrate_fault) hmm_buffer_free(buffer); } +TEST_F(hmm, migrate_release) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Release device memory. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_RELEASE, buffer, npages); + ASSERT_EQ(ret, 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + /* * Migrate anonymous shared memory to device private memory. */ diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 74babdbc02e5..297f250c1d95 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -774,7 +774,27 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, continue_range(uffd, msg->arg.pagefault.address, page_size); stats->minor_faults++; } else { - /* Missing page faults */ + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); |