diff options
257 files changed, 3919 insertions, 1762 deletions
@@ -21,6 +21,7 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrew Morton <akpm@linux-foundation.org> Andrew Vasquez <andrew.vasquez@qlogic.com> Andy Adamson <andros@citi.umich.edu> +Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com> Archit Taneja <archit@ti.com> Arnaud Patard <arnaud.patard@rtp-net.org> Arnd Bergmann <arnd@arndb.de> diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt index 7b57fc087088..49585b6e1ea2 100644 --- a/Documentation/Intel-IOMMU.txt +++ b/Documentation/Intel-IOMMU.txt @@ -3,7 +3,7 @@ Linux IOMMU Support The architecture spec can be obtained from the below location. -http://www.intel.com/technology/virtualization/ +http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf This guide gives a quick cheat sheet for some basic understanding. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 053f613fc9a9..07e4cdf02407 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3025,7 +3025,7 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), which is the maximum number of possibly pending cpu-local interrupts. -4.90 KVM_SMI +4.96 KVM_SMI Capability: KVM_CAP_X86_SMM Architectures: x86 diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 4c23a68a0917..7a6a58ef8aaf 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -106,6 +106,15 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) endif +# -fstack-protector-strong triggers protection checks in this code, +# but it is being used too early to link to meaningful stack_chk logic. +nossp_flags := $(call cc-option, -fno-stack-protector) +CFLAGS_atags_to_fdt.o := $(nossp_flags) +CFLAGS_fdt.o := $(nossp_flags) +CFLAGS_fdt_ro.o := $(nossp_flags) +CFLAGS_fdt_rw.o := $(nossp_flags) +CFLAGS_fdt_wip.o := $(nossp_flags) + ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj) asflags-y := -DZIMAGE diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index ede692ffa32e..5dd2528e9e45 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -417,6 +417,7 @@ #define __NR_userfaultfd (__NR_SYSCALL_BASE+388) #define __NR_membarrier (__NR_SYSCALL_BASE+389) #define __NR_mlock2 (__NR_SYSCALL_BASE+390) +#define __NR_copy_file_range (__NR_SYSCALL_BASE+391) /* * The following SWIs are ARM private. diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index ac368bb068d1..dfc7cd6851ad 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -400,6 +400,7 @@ CALL(sys_userfaultfd) CALL(sys_membarrier) CALL(sys_mlock2) + CALL(sys_copy_file_range) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index cd822d8454c0..307237cfe728 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -27,6 +27,8 @@ $(warning LSE atomics not supported by binutils) endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 18ca9fb9e65f..86581f793e39 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -16,7 +16,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y CONFIG_CGROUP_HUGETLB=y # CONFIG_UTS_NS is not set # CONFIG_IPC_NS is not set @@ -37,15 +36,13 @@ CONFIG_ARCH_EXYNOS7=y CONFIG_ARCH_LAYERSCAPE=y CONFIG_ARCH_HISI=y CONFIG_ARCH_MEDIATEK=y +CONFIG_ARCH_QCOM=y CONFIG_ARCH_ROCKCHIP=y CONFIG_ARCH_SEATTLE=y CONFIG_ARCH_RENESAS=y CONFIG_ARCH_R8A7795=y CONFIG_ARCH_STRATIX10=y CONFIG_ARCH_TEGRA=y -CONFIG_ARCH_TEGRA_132_SOC=y -CONFIG_ARCH_TEGRA_210_SOC=y -CONFIG_ARCH_QCOM=y CONFIG_ARCH_SPRD=y CONFIG_ARCH_THUNDER=y CONFIG_ARCH_UNIPHIER=y @@ -54,14 +51,19 @@ CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZYNQMP=y CONFIG_PCI=y CONFIG_PCI_MSI=y +CONFIG_PCI_IOV=y +CONFIG_PCI_RCAR_GEN2_PCIE=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y -CONFIG_SMP=y +CONFIG_PCI_LAYERSCAPE=y +CONFIG_PCI_HISI=y +CONFIG_PCIE_QCOM=y CONFIG_SCHED_MC=y CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_XEN=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y @@ -100,7 +102,11 @@ CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y CONFIG_TUN=y CONFIG_VIRTIO_NET=y +CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y +CONFIG_E1000E=y +CONFIG_IGB=y +CONFIG_IGBVF=y CONFIG_SKY2=y CONFIG_RAVB=y CONFIG_SMC91X=y @@ -117,25 +123,23 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y CONFIG_SERIAL_8250_MT6577=y CONFIG_SERIAL_8250_UNIPHIER=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y CONFIG_SERIAL_SAMSUNG=y -CONFIG_SERIAL_SAMSUNG_UARTS_4=y -CONFIG_SERIAL_SAMSUNG_UARTS=4 CONFIG_SERIAL_SAMSUNG_CONSOLE=y +CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=11 CONFIG_SERIAL_SH_SCI_CONSOLE=y -CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_MSM=y CONFIG_SERIAL_MSM_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_XILINX_PS_UART=y CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y CONFIG_VIRTIO_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_I2C=y CONFIG_I2C_QUP=y +CONFIG_I2C_UNIPHIER_F=y CONFIG_I2C_RCAR=y CONFIG_SPI=y CONFIG_SPI_PL022=y @@ -176,8 +180,6 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_TEGRA=y CONFIG_MMC_SPI=y CONFIG_MMC_DW=y -CONFIG_MMC_DW_IDMAC=y -CONFIG_MMC_DW_PLTFM=y CONFIG_MMC_DW_EXYNOS=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y @@ -187,28 +189,33 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_CPU=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y +CONFIG_RTC_DRV_PL031=y CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y -CONFIG_RCAR_DMAC=y CONFIG_QCOM_BAM_DMA=y CONFIG_TEGRA20_APB_DMA=y +CONFIG_RCAR_DMAC=y +CONFIG_VFIO=y +CONFIG_VFIO_PCI=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_MMIO=y +CONFIG_XEN_GNTDEV=y +CONFIG_XEN_GRANT_DEV_ALLOC=y CONFIG_COMMON_CLK_CS2000_CP=y CONFIG_COMMON_CLK_QCOM=y CONFIG_MSM_GCC_8916=y CONFIG_HWSPINLOCK_QCOM=y -# CONFIG_IOMMU_SUPPORT is not set +CONFIG_ARM_SMMU=y CONFIG_QCOM_SMEM=y CONFIG_QCOM_SMD=y CONFIG_QCOM_SMD_RPM=y +CONFIG_ARCH_TEGRA_132_SOC=y +CONFIG_ARCH_TEGRA_210_SOC=y +CONFIG_HISILICON_IRQ_MBIGEN=y CONFIG_PHY_XGENE=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -# CONFIG_EXT3_FS_XATTR is not set -CONFIG_EXT4_FS=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y @@ -239,6 +246,7 @@ CONFIG_LOCKUP_DETECTOR=y # CONFIG_FTRACE is not set CONFIG_MEMTEST=y CONFIG_SECURITY=y +CONFIG_CRYPTO_ECHAINIV=y CONFIG_CRYPTO_ANSI_CPRNG=y CONFIG_ARM64_CRYPTO=y CONFIG_CRYPTO_SHA1_ARM64_CE=y diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 2d545d7aa80b..bf464de33f52 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -67,11 +67,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -81,7 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -153,6 +153,7 @@ extern struct page *empty_zero_page; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -163,8 +164,6 @@ extern struct page *empty_zero_page; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) #define pte_valid_young(pte) \ @@ -278,13 +277,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) - __sync_icache_dcache(pte, addr); + if (pte_valid(pte)) { if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte, addr); } /* diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ffe9c2b6431b..917d98108b3f 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -514,9 +514,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index bc2abb8b1599..999633bd7294 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -65,6 +65,16 @@ #ifdef CONFIG_EFI /* + * Prevent the symbol aliases below from being emitted into the kallsyms + * table, by forcing them to be absolute symbols (which are conveniently + * ignored by scripts/kallsyms) rather than section relative symbols. + * The distinction is only relevant for partial linking, and only for symbols + * that are defined within a section declaration (which is not the case for + * the definitions below) so the resulting values will be identical. + */ +#define KALLSYMS_HIDE(sym) ABSOLUTE(sym) + +/* * The EFI stub has its own symbol namespace prefixed by __efistub_, to * isolate it from the kernel proper. The following symbols are legally * accessed by the stub, so provide some aliases to make them accessible. @@ -73,25 +83,25 @@ * linked at. The routines below are all implemented in assembler in a * position independent manner */ -__efistub_memcmp = __pi_memcmp; -__efistub_memchr = __pi_memchr; -__efistub_memcpy = __pi_memcpy; -__efistub_memmove = __pi_memmove; -__efistub_memset = __pi_memset; -__efistub_strlen = __pi_strlen; -__efistub_strcmp = __pi_strcmp; -__efistub_strncmp = __pi_strncmp; -__efistub___flush_dcache_area = __pi___flush_dcache_area; +__efistub_memcmp = KALLSYMS_HIDE(__pi_memcmp); +__efistub_memchr = KALLSYMS_HIDE(__pi_memchr); +__efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub_memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub_memset = KALLSYMS_HIDE(__pi_memset); +__efistub_strlen = KALLSYMS_HIDE(__pi_strlen); +__efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); +__efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); +__efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); #ifdef CONFIG_KASAN -__efistub___memcpy = __pi_memcpy; -__efistub___memmove = __pi_memmove; -__efistub___memset = __pi_memset; +__efistub___memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub___memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub___memset = KALLSYMS_HIDE(__pi_memset); #endif -__efistub__text = _text; -__efistub__end = _end; -__efistub__edata = _edata; +__efistub__text = KALLSYMS_HIDE(_text); +__efistub__end = KALLSYMS_HIDE(_end); +__efistub__edata = KALLSYMS_HIDE(_edata); #endif diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 5a22a119a74c..0adbebbc2803 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -46,7 +46,7 @@ enum address_markers_idx { PCI_START_NR, PCI_END_NR, MODULES_START_NR, - MODUELS_END_NR, + MODULES_END_NR, KERNEL_SPACE_NR, }; diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index cf038c7d9fa9..cab7a5be40aa 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -120,6 +120,7 @@ static void __init cpu_set_ttbr1(unsigned long ttbr1) void __init kasan_init(void) { struct memblock_region *reg; + int i; /* * We are going to perform proper setup of shadow memory. @@ -155,6 +156,14 @@ void __init kasan_init(void) pfn_to_nid(virt_to_pfn(start))); } + /* + * KAsan may reuse the contents of kasan_zero_pte directly, so we + * should make sure that it maps the zero page read-only. + */ + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(&kasan_zero_pte[i], + pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + memset(kasan_zero_page, 0, PAGE_SIZE); cpu_set_ttbr1(__pa(swapper_pg_dir)); flush_tlb_all(); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 146bd99a7532..e6a30e1268a8 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -84,3 +84,15 @@ b.lo 9998b dsb \domain .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index a3d867e723b4..c164d2cb35c0 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,7 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -154,7 +154,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c index 5f2bc1e10eae..05757aed016c 100644 --- a/arch/mips/bcm63xx/nvram.c +++ b/arch/mips/bcm63xx/nvram.c @@ -19,6 +19,8 @@ #include <bcm63xx_nvram.h> +#define BCM63XX_DEFAULT_PSI_SIZE 64 + static struct bcm963xx_nvram nvram; static int mac_addr_used; @@ -85,3 +87,12 @@ int bcm63xx_nvram_get_mac_address(u8 *mac) return 0; } EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address); + +int bcm63xx_nvram_get_psi_size(void) +{ + if (nvram.psi_size > 0) + return nvram.psi_size; + + return BCM63XX_DEFAULT_PSI_SIZE; +} +EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size); diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h index 4e0b6bc1165e..348df49dcc9f 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h @@ -30,4 +30,6 @@ u8 *bcm63xx_nvram_get_name(void); */ int bcm63xx_nvram_get_mac_address(u8 *mac); +int bcm63xx_nvram_get_psi_size(void); + #endif /* BCM63XX_NVRAM_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 06f17e778c27..8d1c8162f0c1 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -50,7 +50,9 @@ * set of bits not changed in pmd_modify. */ #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ - _PAGE_ACCESSED | _PAGE_THP_HUGE) + _PAGE_ACCESSED | _PAGE_THP_HUGE | _PAGE_PTE | \ + _PAGE_SOFT_DIRTY) + #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8204b0c393aa..8d1c41d28318 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -223,7 +223,6 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) -#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 271fefbbe521..9d08d8cbed1a 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -38,8 +38,7 @@ #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS -#define KVM_USER_MEM_SLOTS 32 -#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS +#define KVM_USER_MEM_SLOTS 512 #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 5654ece02c0d..3fa9df70aa20 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -383,3 +383,4 @@ SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(mlock2) +SYSCALL(copy_file_range) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 6a5ace5fa0c8..1f2594d45605 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 379 +#define NR_syscalls 380 #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 12a05652377a..940290d45b08 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -389,5 +389,6 @@ #define __NR_userfaultfd 364 #define __NR_membarrier 365 #define __NR_mlock2 378 +#define __NR_copy_file_range 379 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..ca9e5371930e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); + if (loc) - goto out; + return loc; - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index db475d41b57a..f28754c497e5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -701,31 +701,3 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ - -#ifdef CONFIG_MODULES -#if defined(_CALL_ELF) && _CALL_ELF == 2 - -#ifdef CONFIG_MODVERSIONS -.weak __crc_TOC. -.section "___kcrctab+TOC.","a" -.globl __kcrctab_TOC. -__kcrctab_TOC.: - .llong __crc_TOC. -#endif - -/* - * Export a fake .TOC. since both modpost and depmod will complain otherwise. - * Both modpost and depmod strip the leading . so we do the same here. - */ -.section "__ksymtab_strings","a" -__kstrtab_TOC.: - .asciz "TOC." - -.section "___ksymtab+TOC.","a" -/* This symbol name is important: it's used by modpost to find exported syms */ -.globl __ksymtab_TOC. -__ksymtab_TOC.: - .llong 0 /* .value */ - .llong __kstrtab_TOC. -#endif /* ELFv2 */ -#endif /* MODULES */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 59663af9315f..ac64ffdb52c8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -326,7 +326,10 @@ static void dedotify_versions(struct modversion_info *vers, } } -/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ +/* + * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC. + * seem to be defined (value set later). + */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; @@ -334,8 +337,11 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) for (i = 1; i < numsyms; i++) { if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; - if (name[0] == '.') + if (name[0] == '.') { + if (strcmp(name+1, "TOC.") == 0) + syms[i].st_shndx = SHN_ABS; memmove(name, name+1, strlen(name)); + } } } } @@ -351,7 +357,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); for (i = 1; i < numsyms; i++) { - if (syms[i].st_shndx == SHN_UNDEF + if (syms[i].st_shndx == SHN_ABS && strcmp(strtab + syms[i].st_name, "TOC.") == 0) return &syms[i]; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 774a253ca4e1..9bf7031a67ff 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -377,15 +377,12 @@ no_seg_found: static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) { - struct kvmppc_vcpu_book3s *vcpu_book3s; u64 esid, esid_1t; int slb_nr; struct kvmppc_slb *slbe; dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb); - vcpu_book3s = to_book3s(vcpu); - esid = GET_ESID(rb); esid_1t = GET_ESID_1T(rb); slb_nr = rb & 0xfff; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cff207b72c46..baeddb06811d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -833,6 +833,24 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.sum_exits++; + /* + * This can happen if an interrupt occurs in the last stages + * of guest entry or the first stages of guest exit (i.e. after + * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV + * and before setting it to KVM_GUEST_MODE_HOST_HV). + * That can happen due to a bug, or due to a machine check + * occurring at just the wrong time. + */ + if (vcpu->arch.shregs.msr & MSR_HV) { + printk(KERN_EMERG "KVM trap in HV mode!\n"); + printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", + vcpu->arch.trap, kvmppc_get_pc(vcpu), + vcpu->arch.shregs.msr); + kvmppc_dump_regs(vcpu); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->hw.hardware_exit_reason = vcpu->arch.trap; + return RESUME_HOST; + } run->exit_reason = KVM_EXIT_UNKNOWN; run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..6ee26de9a1de 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) @@ -2404,6 +2404,8 @@ machine_check_realmode: * guest as machine check causing guest to crash. */ ld r11, VCPU_MSR(r9) + rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */ + bne mc_cont /* if so, exit to host */ andi. r10, r11, MSR_RI /* check for unrecoverable exception */ beq 1f /* Deliver a machine check to guest */ ld r10, VCPU_PC(r9) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 22d94c3e6fc4..d0f0a514b04e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -560,12 +560,12 @@ subsys_initcall(add_system_ram_resources); */ int devmem_is_allowed(unsigned long pfn) { + if (page_is_rtas_user_buf(pfn)) + return 1; if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; - if (page_is_rtas_user_buf(pfn)) - return 1; return 0; } #endif /* CONFIG_STRICT_DEVMEM */ diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 7d5e295255b7..9958ba8bf0d2 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -816,7 +816,7 @@ static struct power_pmu power8_pmu = { .get_constraint = power8_get_constraint, .get_alternatives = power8_get_alternatives, .disable_pmc = power8_disable_pmc, - .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S, + .flags = PPMU_HAS_SIER | PPMU_ARCH_207S, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, .cache_events = &power8_cache_events, diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 16aa0c779e07..595a275c36f8 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -8,6 +8,8 @@ #include <linux/types.h> +#define ARCH_IRQ_ENABLED (3UL << (BITS_PER_LONG - 8)) + /* store then OR system mask. */ #define __arch_local_irq_stosm(__or) \ ({ \ @@ -54,14 +56,17 @@ static inline notrace void arch_local_irq_enable(void) __arch_local_irq_stosm(0x03); } +/* This only restores external and I/O interrupt state */ static inline notrace void arch_local_irq_restore(unsigned long flags) { - __arch_local_irq_ssm(flags); + /* only disabled->disabled and disabled->enabled is valid */ + if (flags & ARCH_IRQ_ENABLED) + arch_local_irq_enable(); } static inline notrace bool arch_irqs_disabled_flags(unsigned long flags) { - return !(flags & (3UL << (BITS_PER_LONG - 8))); + return !(flags & ARCH_IRQ_ENABLED); } static inline notrace bool arch_irqs_disabled(void) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 6742414dbd6f..8959ebb6d2c9 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -546,7 +546,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; unsigned int host_acrs[NUM_ACRS]; struct fpu host_fpregs; - struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 1a9a98de5bde..69aa18be61af 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -8,10 +8,13 @@ #include <asm/pci_insn.h> /* I/O Map */ -#define ZPCI_IOMAP_MAX_ENTRIES 0x7fff -#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000ULL -#define ZPCI_IOMAP_ADDR_IDX_MASK 0x7fff000000000000ULL -#define ZPCI_IOMAP_ADDR_OFF_MASK 0x0000ffffffffffffULL +#define ZPCI_IOMAP_SHIFT 48 +#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL +#define ZPCI_IOMAP_ADDR_OFF_MASK ((1UL << ZPCI_IOMAP_SHIFT) - 1) +#define ZPCI_IOMAP_MAX_ENTRIES \ + ((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT)) +#define ZPCI_IOMAP_ADDR_IDX_MASK \ + (~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE) struct zpci_iomap_entry { u32 fh; @@ -21,8 +24,9 @@ struct zpci_iomap_entry { extern struct zpci_iomap_entry *zpci_iomap_start; +#define ZPCI_ADDR(idx) (ZPCI_IOMAP_ADDR_BASE | ((u64) idx << ZPCI_IOMAP_SHIFT)) #define ZPCI_IDX(addr) \ - (((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48) + (((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> ZPCI_IOMAP_SHIFT) #define ZPCI_OFFSET(addr) \ ((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index f16debf6a612..1c4fe129486d 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -166,14 +166,14 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; */ #define start_thread(regs, new_psw, new_stackp) do { \ regs->psw.mask = PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ execve_tail(); \ } while (0) #define start_thread31(regs, new_psw, new_stackp) do { \ regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ crst_table_downgrade(current->mm, 1UL << 31); \ execve_tail(); \ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index f00cd35c8ac4..99bc456cc26a 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -149,7 +149,7 @@ static inline int test_pt_regs_flag(struct pt_regs *regs, int flag) #define arch_has_block_step() (1) #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0) -#define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN) +#define instruction_pointer(regs) ((regs)->psw.addr) #define user_stack_pointer(regs)((regs)->gprs[15]) #define profile_pc(regs) instruction_pointer(regs) @@ -161,7 +161,7 @@ static inline long regs_return_value(struct pt_regs *regs) static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { - regs->psw.addr = val | PSW_ADDR_AMODE; + regs->psw.addr = val; } int regs_query_register_offset(const char *name); @@ -171,7 +171,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { - return regs->gprs[15] & PSW_ADDR_INSN; + return regs->gprs[15]; } #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 34ec202472c6..ab3aa6875a59 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -310,7 +310,8 @@ #define __NR_recvmsg 372 #define __NR_shutdown 373 #define __NR_mlock2 374 -#define NR_syscalls 375 +#define __NR_copy_file_range 375 +#define NR_syscalls 376 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index fac4eeddef91..ae2cda5eee5a 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -177,3 +177,4 @@ COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len); COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags); +COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index a92b39fd0e63..3986c9f62191 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -59,8 +59,6 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) struct save_area *sa; sa = (void *) memblock_alloc(sizeof(*sa), 8); - if (!sa) - return NULL; if (is_boot_cpu) list_add(&sa->list, &dump_save_areas); else diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 6fca0e46464e..c890a5589e59 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1470,7 +1470,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, except_str = "*"; else except_str = "-"; - caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN; + caller = (unsigned long) entry->caller; rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p ", area, (long long)time_spec.tv_sec, time_spec.tv_nsec / 1000, level, except_str, diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index dc8e20473484..02bd02ff648b 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -34,22 +34,21 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) unsigned long addr; while (1) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; printk("([<%016lx>] %pSR)\n", addr, (void *)addr); /* Follow the backchain. */ while (1) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; printk(" [<%016lx>] %pSR\n", addr, (void *)addr); } /* Zero backchain detected, check for interrupt frame. */ @@ -57,7 +56,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *) sp; - addr = regs->psw.addr & PSW_ADDR_INSN; + addr = regs->psw.addr; printk(" [<%016lx>] %pSR\n", addr, (void *)addr); low = sp; sp = regs->gprs[15]; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 20a5caf6d981..c55576bbaa1f 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -252,14 +252,14 @@ static void early_pgm_check_handler(void) unsigned long addr; addr = S390_lowcore.program_old_psw.addr; - fixup = search_exception_tables(addr & PSW_ADDR_INSN); + fixup = search_exception_tables(addr); if (!fixup) disabled_wait(0); /* Disable low address protection before storing into lowcore. */ __ctl_store(cr0, 0, 0); cr0_new = cr0 & ~(1UL << 28); __ctl_load(cr0_new, 0, 0); - S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE; + S390_lowcore.program_old_psw.addr = extable_fixup(fixup); __ctl_load(cr0, 0, 0); } @@ -268,9 +268,9 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; - psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler; + psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; - psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + psw.addr = (unsigned long) s390_base_pgm_handler; S390_lowcore.program_new_psw = psw; s390_base_pgm_handler_fn = early_pgm_check_handler; } diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index e0eaf11134b4..0f7bfeba6da6 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -203,7 +203,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE; + ip -= MCOUNT_INSN_SIZE; trace.func = ip; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to. */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 0a5a6b661b93..f20abdb5630a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2057,12 +2057,12 @@ void s390_reset_system(void) /* Set new machine check handler */ S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.mcck_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; + (unsigned long) s390_base_mcck_handler; /* Set new program check handler */ S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + (unsigned long) s390_base_pgm_handler; /* * Clear subchannel ID and number to signal new kernel that no CCW or diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 389db56a2208..250f5972536a 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -226,7 +226,7 @@ static void enable_singlestep(struct kprobe_ctlblk *kcb, __ctl_load(per_kprobe, 9, 11); regs->psw.mask |= PSW_MASK_PER; regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); - regs->psw.addr = ip | PSW_ADDR_AMODE; + regs->psw.addr = ip; } NOKPROBE_SYMBOL(enable_singlestep); @@ -238,7 +238,7 @@ static void disable_singlestep(struct kprobe_ctlblk *kcb, __ctl_load(kcb->kprobe_saved_ctl, 9, 11); regs->psw.mask &= ~PSW_MASK_PER; regs->psw.mask |= kcb->kprobe_saved_imask; - regs->psw.addr = ip | PSW_ADDR_AMODE; + regs->psw.addr = ip; } NOKPROBE_SYMBOL(disable_singlestep); @@ -310,7 +310,7 @@ static int kprobe_handler(struct pt_regs *regs) */ preempt_disable(); kcb = get_kprobe_ctlblk(); - p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2)); + p = get_kprobe((void *)(regs->psw.addr - 2)); if (p) { if (kprobe_running()) { @@ -460,7 +460,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) break; } - regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE; + regs->psw.addr = orig_ret_address; pop_kprobe(get_kprobe_ctlblk()); kretprobe_hash_unlock(current, &flags); @@ -490,7 +490,7 @@ NOKPROBE_SYMBOL(trampoline_probe_handler); static void resume_execution(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long ip = regs->psw.addr & PSW_ADDR_INSN; + unsigned long ip = regs->psw.addr; int fixup = probe_get_fixup_type(p->ainsn.insn); /* Check if the kprobes location is an enabled ftrace caller */ @@ -605,9 +605,9 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr) * In case the user-specified fault handler returned * zero, try to fix up. */ - entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + entry = search_exception_tables(regs->psw.addr); if (entry) { - regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(entry); return 1; } @@ -683,7 +683,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); /* setup return addr to the jprobe handler routine */ - regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) jp->entry; regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); /* r15 is the stack pointer */ diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 61595c1f0a0f..cfcba2dd9bb5 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -74,7 +74,7 @@ static unsigned long guest_is_user_mode(struct pt_regs *regs) static unsigned long instruction_pointer_guest(struct pt_regs *regs) { - return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN; + return sie_block(regs)->gpsw.addr; } unsigned long perf_instruction_pointer(struct pt_regs *regs) @@ -231,29 +231,27 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry, struct pt_regs *regs; while (1) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); /* Follow the backchain. */ while (1) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - perf_callchain_store(entry, - sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *) sp; - perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); low = sp; sp = regs->gprs[15]; } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 114ee8b96f17..2bba7df4ac51 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -56,10 +56,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return 0; low = task_stack_page(tsk); high = (struct stack_frame *) task_pt_regs(tsk); - sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN); + sf = (struct stack_frame *) tsk->thread.ksp; if (sf <= low || sf > high) return 0; - sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + sf = (struct stack_frame *) sf->back_chain; if (sf <= low || sf > high) return 0; return sf->gprs[8]; @@ -154,7 +154,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - frame->childregs.psw.addr = PSW_ADDR_AMODE | + frame->childregs.psw.addr = (unsigned long) kernel_thread_starter; frame->childregs.gprs[9] = new_stackp; /* function */ frame->childregs.gprs[10] = arg; @@ -220,14 +220,14 @@ unsigned long get_wchan(struct task_struct *p) return 0; low = task_stack_page(p); high = (struct stack_frame *) task_pt_regs(p); - sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN); + sf = (struct stack_frame *) p->thread.ksp; if (sf <= low || sf > high) return 0; for (count = 0; count < 16; count++) { - sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + sf = (struct stack_frame *) sf->back_chain; if (sf <= low || sf > high) return 0; - return_address = sf->gprs[8] & PSW_ADDR_INSN; + return_address = sf->gprs[8]; if (!in_sched_functions(return_address)) return return_address; } diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 01c37b36caf9..49b1c13bf6c9 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -84,7 +84,7 @@ void update_cr_regs(struct task_struct *task) if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) new.control |= PER_EVENT_IFETCH; new.start = 0; - new.end = PSW_ADDR_INSN; + new.end = -1UL; } /* Take care of the PER enablement bit in the PSW. */ @@ -148,7 +148,7 @@ static inline unsigned long __peek_user_per(struct task_struct *child, else if (addr == (addr_t) &dummy->cr11) /* End address of the active per set. */ return test_thread_flag(TIF_SINGLE_STEP) ? - PSW_ADDR_INSN : child->thread.per_user.end; + -1UL : child->thread.per_user.end; else if (addr == (addr_t) &dummy->bits) /* Single-step bit. */ return test_thread_flag(TIF_SINGLE_STEP) ? @@ -495,8 +495,6 @@ long arch_ptrace(struct task_struct *child, long request, } return 0; default: - /* Removing high order bit from addr (only for 31 bit). */ - addr &= PSW_ADDR_INSN; return ptrace_request(child, request, addr, data); } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c6878fbbcf13..9220db5c996a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -301,25 +301,21 @@ static void __init setup_lowcore(void) BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096); lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); lc->restart_psw.mask = PSW_KERNEL_BITS; - lc->restart_psw.addr = - PSW_ADDR_AMODE | (unsigned long) restart_int_handler; + lc->restart_psw.addr = (unsigned long) restart_int_handler; lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->external_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) ext_int_handler; + lc->external_new_psw.addr = (unsigned long) ext_int_handler; lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; + lc->svc_new_psw.addr = (unsigned long) system_call; lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; + lc->program_new_psw.addr = (unsigned long) pgm_check_handler; lc->mcck_new_psw.mask = PSW_KERNEL_BITS; - lc->mcck_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; + lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler; lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; + lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 028cc46cb82a..d82562cf0a0e 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -331,13 +331,13 @@ static int setup_frame(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE; + restorer = (unsigned long) ka->sa.sa_restorer; } else { /* Signal frame without vector registers are short ! */ __u16 __user *svc = (void __user *) frame + frame_size - 2; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc)) return -EFAULT; - restorer = (unsigned long) svc | PSW_ADDR_AMODE; + restorer = (unsigned long) svc; } /* Set up registers for signal handler */ @@ -347,7 +347,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) ka->sa.sa_handler; regs->gprs[2] = sig; regs->gprs[3] = (unsigned long) &frame->sc; @@ -394,13 +394,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ksig->ka.sa.sa_flags & SA_RESTORER) { - restorer = (unsigned long) - ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE; + restorer = (unsigned long) ksig->ka.sa.sa_restorer; } else { __u16 __user *svc = &frame->svc_insn; if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc)) return -EFAULT; - restorer = (unsigned long) svc | PSW_ADDR_AMODE; + restorer = (unsigned long) svc; } /* Create siginfo on the signal stack */ @@ -426,7 +425,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler; regs->gprs[2] = ksig->sig; regs->gprs[3] = (unsigned long) &frame->info; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a13468b9a913..3c65a8eae34d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -623,8 +623,6 @@ void __init smp_save_dump_cpus(void) return; /* Allocate a page as dumping area for the store status sigps */ page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31); - if (!page) - panic("could not allocate memory for save area\n"); /* Set multi-threading state to the previous system. */ pcpu_set_smt(sclp.mtid_prev); boot_cpu_addr = stap(); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 1785cd82253c..5acba3cb7220 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -21,12 +21,11 @@ static unsigned long save_context_stack(struct stack_trace *trace, unsigned long addr; while(1) { - sp &= PSW_ADDR_INSN; if (sp < low || sp > high) return sp; sf = (struct stack_frame *)sp; while(1) { - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; if (!trace->skip) trace->entries[trace->nr_entries++] = addr; else @@ -34,7 +33,7 @@ static unsigned long save_context_stack(struct stack_trace *trace, if (trace->nr_entries >= trace->max_entries) return sp; low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) @@ -46,7 +45,7 @@ static unsigned long save_context_stack(struct stack_trace *trace, if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *)sp; - addr = regs->psw.addr & PSW_ADDR_INSN; + addr = regs->psw.addr; if (savesched || !in_sched_functions(addr)) { if (!trace->skip) trace->entries[trace->nr_entries++] = addr; @@ -65,7 +64,7 @@ void save_stack_trace(struct stack_trace *trace) register unsigned long sp asm ("15"); unsigned long orig_sp, new_sp; - orig_sp = sp & PSW_ADDR_INSN; + orig_sp = sp; new_sp = save_context_stack(trace, orig_sp, S390_lowcore.panic_stack - PAGE_SIZE, S390_lowcore.panic_stack, 1); @@ -86,7 +85,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { unsigned long sp, low, high; - sp = tsk->thread.ksp & PSW_ADDR_INSN; + sp = tsk->thread.ksp; low = (unsigned long) task_stack_page(tsk); high = (unsigned long) task_pt_regs(tsk); save_context_stack(trace, sp, low, high, 0); diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 5378c3ea1b98..293d8b98fd52 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -383,3 +383,4 @@ SYSCALL(sys_recvfrom,compat_sys_recvfrom) SYSCALL(sys_recvmsg,compat_sys_recvmsg) SYSCALL(sys_shutdown,sys_shutdown) SYSCALL(sys_mlock2,compat_sys_mlock2) +SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */ diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index d69d648759c9..017eb03daee2 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -32,8 +32,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) address = *(unsigned long *)(current->thread.trap_tdb + 24); else address = regs->psw.addr; - return (void __user *) - ((address - (regs->int_code >> 16)) & PSW_ADDR_INSN); + return (void __user *) (address - (regs->int_code >> 16)); } static inline void report_user_fault(struct pt_regs *regs, int signr) @@ -46,7 +45,7 @@ static inline void report_user_fault(struct pt_regs *regs, int signr) return; printk("User process fault: interruption code %04x ilc:%d ", regs->int_code & 0xffff, regs->int_code >> 17); - print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN); + print_vma_addr("in ", regs->psw.addr); printk("\n"); show_regs(regs); } @@ -69,13 +68,13 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) report_user_fault(regs, si_signo); } else { const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + fixup = search_exception_tables(regs->psw.addr); if (fixup) - regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup); else { enum bug_trap_type btt; - btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs); + btt = report_bug(regs->psw.addr, regs); if (btt == BUG_TRAP_TYPE_WARN) return; die(regs, str); diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 5fce52cf0e57..5ea5af3c7db7 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -29,6 +29,7 @@ config KVM select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select SRCU + select KVM_VFIO ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index b3b553469650..d42fa38c2429 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -7,7 +7,7 @@ # as published by the Free Software Foundation. KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 47518a324d75..d697312ce9ee 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu) if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) { *cr9 &= ~PER_CONTROL_ALTERATION; *cr10 = 0; - *cr11 = PSW_ADDR_INSN; + *cr11 = -1UL; } else { *cr9 &= ~PER_CONTROL_ALTERATION; *cr9 |= PER_EVENT_STORE; @@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gcr[0] &= ~0x800ul; vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH; vcpu->arch.sie_block->gcr[10] = 0; - vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN; + vcpu->arch.sie_block->gcr[11] = -1UL; } if (guestdbg_hw_bp_enabled(vcpu)) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 835d60bedb54..4af21c771f9b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1423,44 +1423,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return 0; } -/* - * Backs up the current FP/VX register save area on a particular - * destination. Used to switch between different register save - * areas. - */ -static inline void save_fpu_to(struct fpu *dst) -{ - dst->fpc = current->thread.fpu.fpc; - dst->regs = current->thread.fpu.regs; -} - -/* - * Switches the FP/VX register save area from which to lazy - * restore register contents. - */ -static inline void load_fpu_from(struct fpu *from) -{ - current->thread.fpu.fpc = from->fpc; - current->thread.fpu.regs = from->regs; -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Save host register state */ save_fpu_regs(); - save_fpu_to(&vcpu->arch.host_fpregs); - - if (test_kvm_facility(vcpu->kvm, 129)) { - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - /* - * Use the register save area in the SIE-control block - * for register restore and save in kvm_arch_vcpu_put() - */ - current->thread.fpu.vxrs = - (__vector128 *)&vcpu->run->s.regs.vrs; - } else - load_fpu_from(&vcpu->arch.guest_fpregs); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + /* Depending on MACHINE_HAS_VX, data stored to vrs either + * has vector register or floating point register format. + */ + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; @@ -1476,19 +1450,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); + /* Save guest register state */ save_fpu_regs(); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - if (test_kvm_facility(vcpu->kvm, 129)) - /* - * kvm_arch_vcpu_load() set up the register save area to - * the &vcpu->run->s.regs.vrs and, thus, the vector registers - * are already saved. Only the floating-point control must be - * copied. - */ - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - else - save_fpu_to(&vcpu->arch.guest_fpregs); - load_fpu_from(&vcpu->arch.host_fpregs); + /* Restore host register state */ + current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; + current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); @@ -1506,8 +1474,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); vcpu->arch.sie_block->gcr[0] = 0xE0UL; vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; - vcpu->arch.guest_fpregs.fpc = 0; - asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + /* make sure the new fpc will be lazily loaded */ + save_fpu_regs(); + current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1648,17 +1617,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - /* - * Allocate a save area for floating-point registers. If the vector - * extension is available, register contents are saved in the SIE - * control block. The allocated save area is still required in - * particular places, for example, in kvm_s390_vcpu_store_status(). - */ - vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, - GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) - goto out_free_sie_block; - rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; @@ -1879,19 +1837,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + /* make sure the new values will be lazily loaded */ + save_fpu_regs(); if (test_fp_ctl(fpu->fpc)) return -EINVAL; - memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc; - save_fpu_regs(); - load_fpu_from(&vcpu->arch.guest_fpregs); + current->thread.fpu.fpc = fpu->fpc; + if (MACHINE_HAS_VX) + convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + else + memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); - fpu->fpc = vcpu->arch.guest_fpregs.fpc; + /* make sure we have the latest values */ + save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + else + memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2396,6 +2362,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) { unsigned char archmode = 1; + freg_t fprs[NUM_FPRS]; unsigned int px; u64 clkcomp; int rc; @@ -2411,8 +2378,16 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) gpa = px; } else gpa -= __LC_FPREGS_SAVE_AREA; - rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, - vcpu->arch.guest_fpregs.fprs, 128); + + /* manually convert vector registers if necessary */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + fprs, 128); + } else { + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.vrs, 128); + } rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA, @@ -2420,7 +2395,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA, &px, 4); rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA, - &vcpu->arch.guest_fpregs.fpc, 4); + &vcpu->run->s.regs.fpc, 4); rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA, &vcpu->arch.sie_block->todpr, 4); rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA, @@ -2443,19 +2418,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * it into the save area */ save_fpu_regs(); - if (test_kvm_facility(vcpu->kvm, 129)) { - /* - * If the vector extension is available, the vector registers - * which overlaps with floating-point registers are saved in - * the SIE-control block. Hence, extract the floating-point - * registers and the FPC value and store them in the - * guest_fpregs structure. - */ - vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc; - convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs, - current->thread.fpu.vxrs); - } else - save_fpu_to(&vcpu->arch.guest_fpregs); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 1b903f6ad54a..791a4146052c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -228,7 +228,7 @@ static inline void report_user_fault(struct pt_regs *regs, long signr) return; printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ", regs->int_code & 0xffff, regs->int_code >> 17); - print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN); + print_vma_addr(KERN_CONT "in ", regs->psw.addr); printk(KERN_CONT "\n"); printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n", regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long); @@ -256,9 +256,9 @@ static noinline void do_no_context(struct pt_regs *regs) const struct exception_table_entry *fixup; /* Are we prepared to handle this kernel fault? */ - fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + fixup = search_exception_tables(regs->psw.addr); if (fixup) { - regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup); return; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c722400c7697..73e290337092 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -98,7 +98,7 @@ void __init paging_init(void) __ctl_load(S390_lowcore.kernel_asce, 1, 1); __ctl_load(S390_lowcore.kernel_asce, 7, 7); __ctl_load(S390_lowcore.kernel_asce, 13, 13); - arch_local_irq_restore(4UL << (BITS_PER_LONG - 8)); + __arch_local_irq_stosm(0x04); sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index ea01477b4aa6..45c4daa49930 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -169,12 +169,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) { - if (is_compat_task() || (TASK_SIZE >= (1UL << 53))) + if (is_compat_task() || TASK_SIZE >= TASK_MAX_SIZE) return 0; if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, 1UL << 53); + return crst_table_upgrade(current->mm, TASK_MAX_SIZE); return 0; } @@ -189,9 +189,9 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm, TASK_MAX_SIZE); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -211,9 +211,9 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm, TASK_MAX_SIZE); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a809fa8e6f8b..5109827883ac 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -55,7 +55,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) unsigned long entry; int flush; - BUG_ON(limit > (1UL << 53)); + BUG_ON(limit > TASK_MAX_SIZE); flush = 0; repeat: table = crst_table_alloc(mm); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 43f32ce60aa3..2794845061c6 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -57,9 +57,7 @@ static __init pg_data_t *alloc_node_data(void) { pg_data_t *res; - res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 1); - if (!res) - panic("Could not allocate memory for node data!\n"); + res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8); memset(res, 0, sizeof(pg_data_t)); return res; } @@ -162,7 +160,7 @@ static int __init numa_init_late(void) register_one_node(nid); return 0; } -device_initcall(numa_init_late); +arch_initcall(numa_init_late); static int __init parse_debug(char *parm) { diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index 8a6811b2cdb9..fe0bfe370c45 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -16,24 +16,23 @@ __show_trace(unsigned int *depth, unsigned long sp, struct pt_regs *regs; while (*depth) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); /* Follow the backchain. */ while (*depth) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); } @@ -46,7 +45,7 @@ __show_trace(unsigned int *depth, unsigned long sp, return sp; regs = (struct pt_regs *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); low = sp; sp = regs->gprs[15]; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 11d4f277e9f6..8f19c8f9d660 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -68,9 +68,12 @@ static struct airq_struct zpci_airq = { .isc = PCI_ISC, }; -/* I/O Map */ +#define ZPCI_IOMAP_ENTRIES \ + min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT), \ + ZPCI_IOMAP_MAX_ENTRIES) + static DEFINE_SPINLOCK(zpci_iomap_lock); -static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); +static unsigned long *zpci_iomap_bitmap; struct zpci_iomap_entry *zpci_iomap_start; EXPORT_SYMBOL_GPL(zpci_iomap_start); @@ -265,27 +268,20 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev, unsigned long max) { struct zpci_dev *zdev = to_zpci(pdev); - u64 addr; int idx; - if ((bar & 7) != bar) + if (!pci_resource_len(pdev, bar)) return NULL; idx = zdev->bars[bar].map_idx; spin_lock(&zpci_iomap_lock); - if (zpci_iomap_start[idx].count++) { - BUG_ON(zpci_iomap_start[idx].fh != zdev->fh || - zpci_iomap_start[idx].bar != bar); - } else { - zpci_iomap_start[idx].fh = zdev->fh; - zpci_iomap_start[idx].bar = bar; - } /* Detect overrun */ - BUG_ON(!zpci_iomap_start[idx].count); + WARN_ON(!++zpci_iomap_start[idx].count); + zpci_iomap_start[idx].fh = zdev->fh; + zpci_iomap_start[idx].bar = bar; spin_unlock(&zpci_iomap_lock); - addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48); - return (void __iomem *) addr + offset; + return (void __iomem *) ZPCI_ADDR(idx) + offset; } EXPORT_SYMBOL(pci_iomap_range); @@ -297,12 +293,11 @@ EXPORT_SYMBOL(pci_iomap); void pci_iounmap(struct pci_dev *pdev, void __iomem *addr) { - unsigned int idx; + unsigned int idx = ZPCI_IDX(addr); - idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48; spin_lock(&zpci_iomap_lock); /* Detect underrun */ - BUG_ON(!zpci_iomap_start[idx].count); + WARN_ON(!zpci_iomap_start[idx].count); if (!--zpci_iomap_start[idx].count) { zpci_iomap_start[idx].fh = 0; zpci_iomap_start[idx].bar = 0; @@ -544,15 +539,15 @@ static void zpci_irq_exit(void) static int zpci_alloc_iomap(struct zpci_dev *zdev) { - int entry; + unsigned long entry; spin_lock(&zpci_iomap_lock); - entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); - if (entry == ZPCI_IOMAP_MAX_ENTRIES) { + entry = find_first_zero_bit(zpci_iomap_bitmap, ZPCI_IOMAP_ENTRIES); + if (entry == ZPCI_IOMAP_ENTRIES) { spin_unlock(&zpci_iomap_lock); return -ENOSPC; } - set_bit(entry, zpci_iomap); + set_bit(entry, zpci_iomap_bitmap); spin_unlock(&zpci_iomap_lock); return entry; } @@ -561,7 +556,7 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) { spin_lock(&zpci_iomap_lock); memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry)); - clear_bit(entry, zpci_iomap); + clear_bit(entry, zpci_iomap_bitmap); spin_unlock(&zpci_iomap_lock); } @@ -611,8 +606,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, if (zdev->bars[i].val & 4) flags |= IORESOURCE_MEM_64; - addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48); - + addr = ZPCI_ADDR(entry); size = 1UL << zdev->bars[i].size; res = __alloc_res(zdev, addr, size, flags); @@ -873,23 +867,30 @@ static int zpci_mem_init(void) zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), 16, 0, NULL); if (!zdev_fmb_cache) - goto error_zdev; + goto error_fmb; - /* TODO: use realloc */ - zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start), - GFP_KERNEL); + zpci_iomap_start = kcalloc(ZPCI_IOMAP_ENTRIES, + sizeof(*zpci_iomap_start), GFP_KERNEL); if (!zpci_iomap_start) goto error_iomap; - return 0; + zpci_iomap_bitmap = kcalloc(BITS_TO_LONGS(ZPCI_IOMAP_ENTRIES), + sizeof(*zpci_iomap_bitmap), GFP_KERNEL); + if (!zpci_iomap_bitmap) + goto error_iomap_bitmap; + + return 0; +error_iomap_bitmap: + kfree(zpci_iomap_start); error_iomap: kmem_cache_destroy(zdev_fmb_cache); -error_zdev: +error_fmb: return -ENOMEM; } static void zpci_mem_exit(void) { + kfree(zpci_iomap_bitmap); kfree(zpci_iomap_start); kmem_cache_destroy(zdev_fmb_cache); } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 369a3e05d468..b0e04751c5d5 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -53,6 +53,11 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); + + if (!pdev) + return; + + pdev->error_state = pci_channel_io_perm_failure; } void zpci_event_error(void *data) diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h index f887c6465a82..8a84e05adb2e 100644 --- a/arch/sh/include/asm/barrier.h +++ b/arch/sh/include/asm/barrier.h @@ -33,7 +33,6 @@ #endif #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -#define smp_store_mb(var, value) __smp_store_mb(var, value) #include <asm-generic/barrier.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 330e738ccfc1..9af2e6338400 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -509,11 +509,10 @@ config X86_INTEL_CE config X86_INTEL_MID bool "Intel MID platform support" - depends on X86_32 depends on X86_EXTENDED_PLATFORM depends on X86_PLATFORM_DEVICES depends on PCI - depends on PCI_GOANY + depends on X86_64 || (PCI_GOANY && X86_32) depends on X86_IO_APIC select SFI select I2C diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 881b4768644a..e7de5c9a4fbd 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM @@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -struct irq_desc; extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 04c27a013165..4432ab7f407c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -366,20 +366,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f25321894ad2..fdb0fbfb1197 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; struct irq_chip *chip; @@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot @@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void) /* Might be lapic_chip for irq 0 */ if (chip->irq_set_affinity) chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 908cb37da171..3b670df4ba7b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -31,7 +31,7 @@ struct apic_chip_data { struct irq_domain *x86_vector_domain; EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask; +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; static struct irq_chip lapic_controller; #ifdef CONFIG_X86_IO_APIC static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; @@ -118,35 +118,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; + int cpu, vector; - if (d->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + /* Get the possible target cpus for @mask/@cpu from the apic */ apic->vector_allocation_domain(cpu, vector_cpumask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; + if (cpumask_subset(vector_cpumask, d->domain)) { - err = 0; if (cpumask_equal(vector_cpumask, d->domain)) - break; + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(d->old_domain, d->domain, - vector_cpumask); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - cpumask_and(d->domain, d->domain, vector_cpumask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -158,45 +170,60 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(d->old_domain, d->old_domain, - vector_cpumask); - cpumask_andnot(vector_cpumask, mask, d->old_domain); - cpu = cpumask_first_and(vector_cpumask, - cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { + for_each_cpu(new_cpu, vector_searchmask) { if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (d->cfg.vector) { + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) cpumask_copy(d->old_domain, d->domain); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) + for_each_cpu(new_cpu, vector_searchmask) per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); - err = 0; - break; - } + goto update; - if (!err) { - /* cache destination APIC IDs into cfg->dest_apicid */ - err = apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid); +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, @@ -226,10 +253,8 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { struct irq_desc *desc; - unsigned long flags; int cpu, vector; - raw_spin_lock_irqsave(&vector_lock, flags); BUG_ON(!data->cfg.vector); vector = data->cfg.vector; @@ -239,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) data->cfg.vector = 0; cpumask_clear(data->domain); - if (likely(!data->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } desc = irq_to_desc(irq); for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { @@ -255,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) } } data->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); } void init_irq_alloc_info(struct irq_alloc_info *info, @@ -276,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { + struct apic_chip_data *apic_data; struct irq_data *irq_data; + unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); clear_irq_vector(virq + i, irq_data->chip_data); - free_apic_chip_data(irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); #ifdef CONFIG_X86_IO_APIC if (virq + i < nr_legacy_irqs()) legacy_irq_data[virq + i] = NULL; #endif - irq_domain_reset_irq_data(irq_data); } } } @@ -406,6 +438,8 @@ int __init arch_early_irq_init(void) arch_init_htirq_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); return arch_early_ioapic_init(); } @@ -494,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data, return -EINVAL; err = assign_irq_vector(irq, data, dest); - if (err) { - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(irq_data))) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - return IRQ_SET_MASK_OK; + return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { @@ -513,20 +540,12 @@ static struct irq_chip lapic_controller = { #ifdef CONFIG_SMP static void __send_cleanup_vector(struct apic_chip_data *data) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - - for_each_cpu_and(i, data->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } void send_cleanup_vector(struct irq_cfg *cfg) @@ -570,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (data->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) goto unlock; @@ -593,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; } __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } @@ -621,12 +654,48 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) +/* + * Called with @desc->lock held and interrupts disabled. + */ +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; - if (cfg) - __irq_complete_move(cfg, cfg->vector); + if (!cfg) + return; + + __irq_complete_move(cfg, cfg->vector); + + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * The cleanup cannot make progress because we hold @desc->lock. So in + * case @data->old_domain is not yet cleaned up, we need to drop the + * lock and acquire it again. @desc cannot go away, because the + * hotplug code holds the sparse irq lock. + */ + raw_spin_lock(&vector_lock); + /* Clean out all offline cpus (including ourself) first. */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + while (!cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + raw_spin_unlock(&desc->lock); + cpu_relax(); + raw_spin_lock(&desc->lock); + /* + * Reevaluate apic_chip_data. It might have been cleared after + * we dropped @desc->lock. + */ + data = apic_chip_data(irqdata); + if (!data) + return; + raw_spin_lock(&vector_lock); + } + raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d760c6bb37b5..624db00583f4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -889,7 +889,10 @@ void __init uv_system_init(void) return; } pr_info("UV: Found %s hub\n", hub); - map_low_mmrs(); + + /* We now only need to map the MMRs on UV1 */ + if (is_uv1_hub()) + map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index a667078a5180..fed2ab1f1065 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1960,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event) static int intel_alt_er(int idx, u64 config) { - int alt_idx; + int alt_idx = idx; + if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; @@ -2897,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu) return; if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { - void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - *onln = cpuc->shared_regs; + cpuc->kfree_on_online[0] = cpuc->shared_regs; cpuc->shared_regs = pc; break; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index f97f8075bf04..3bf41d413775 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -995,6 +995,9 @@ static int __init uncore_pci_init(void) case 87: /* Knights Landing */ ret = knl_uncore_pci_init(); break; + case 94: /* SkyLake */ + ret = skl_uncore_pci_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 07aa2d6bd710..a7086b862156 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -336,6 +336,7 @@ int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); +int skl_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 0b934820fafd..2bd030ddd0db 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -8,6 +8,7 @@ #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 #define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 +#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id skl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = { .id_table = bdw_uncore_pci_ids, }; +static struct pci_driver skl_uncore_pci_driver = { + .name = "skl_uncore", + .id_table = skl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ + IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */ { /* end marker */ } }; @@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int skl_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f129a9af6357..2c0f3407bd1f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -192,5 +192,13 @@ void __init x86_64_start_reservations(char *real_mode_data) reserve_ebda_region(); + switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_INTEL_MID: + x86_intel_mid_early_setup(); + break; + default: + break; + } + start_kernel(); } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f8062aaf5df9..61521dc19c10 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -462,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -470,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index fc6a4c8f6e2a..2440814b0069 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -1350,7 +1350,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 1c7380da65ff..2d66db8f80f9 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -8,6 +8,7 @@ #include <linux/memblock.h> #include <linux/bootmem.h> #include <linux/acpi.h> +#include <linux/dmi.h> #include <asm/efi.h> #include <asm/uv/uv.h> @@ -248,6 +249,16 @@ out: return ret; } +static const struct dmi_system_id sgi_uv1_dmi[] = { + { NULL, "SGI UV1", + { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + DMI_MATCH(DMI_BIOS_VENDOR, "SGI.COM"), + } + }, + { } /* NULL entry stops DMI scanning */ +}; + void __init efi_apply_memmap_quirks(void) { /* @@ -260,10 +271,8 @@ void __init efi_apply_memmap_quirks(void) efi_unmap_memmap(); } - /* - * UV doesn't support the new EFI pagetable mapping yet. - */ - if (is_uv_system()) + /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ + if (dmi_check_system(sgi_uv1_dmi)) set_bit(EFI_OLD_MEMMAP, &efi.flags); } diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 1bbc21e2e4ae..90bb997ed0a2 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -138,7 +138,7 @@ static void intel_mid_arch_setup(void) intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip](); else { intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL](); - pr_info("ARCH: Unknown SoC, assuming PENWELL!\n"); + pr_info("ARCH: Unknown SoC, assuming Penwell!\n"); } out: @@ -214,12 +214,10 @@ static inline int __init setup_x86_intel_mid_timer(char *arg) else if (strcmp("lapic_and_apbt", arg) == 0) intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT; else { - pr_warn("X86 INTEL_MID timer option %s not recognised" - " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", - arg); + pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", + arg); return -EINVAL; } return 0; } __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer); - diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index c1bdafaac3ca..c61b6c332e97 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -220,11 +220,12 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused) if (imr_is_enabled(&imr)) { base = imr_to_phys(imr.addr_lo); end = imr_to_phys(imr.addr_hi) + IMR_MASK; + size = end - base + 1; } else { base = 0; end = 0; + size = 0; } - size = end - base; seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx " "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i, &base, &end, size, imr.rmask, imr.wmask, @@ -579,6 +580,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) { phys_addr_t base = virt_to_phys(&_text); size_t size = virt_to_phys(&__end_rodata) - base; + unsigned long start, end; int i; int ret; @@ -586,18 +588,24 @@ static void __init imr_fixup_memmap(struct imr_device *idev) for (i = 0; i < idev->max_imr; i++) imr_clear(i); + start = (unsigned long)_text; + end = (unsigned long)__end_rodata - 1; + /* * Setup a locked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. + * + * We don't round up @size since it is already PAGE_SIZE aligned. + * See vmlinux.lds.S for details. */ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); if (ret < 0) { - pr_err("unable to setup IMR for kernel: (%p - %p)\n", - &_text, &__end_rodata); + pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } else { - pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n", - size / 1024, &_text, &__end_rodata); + pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } } diff --git a/block/blk-merge.c b/block/blk-merge.c index 1699df5b0493..888a7fec81f7 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -70,6 +70,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } +static inline unsigned get_max_io_size(struct request_queue *q, + struct bio *bio) +{ + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned mask = queue_logical_block_size(q) - 1; + + /* aligned to logical block size */ + sectors &= ~(mask >> 9); + + return sectors; +} + static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, @@ -81,6 +93,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, unsigned front_seg_size = bio->bi_seg_front_size; bool do_split = true; struct bio *new = NULL; + const unsigned max_sectors = get_max_io_size(q, bio); bio_for_each_segment(bv, bio, iter) { /* @@ -90,20 +103,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; - if (sectors + (bv.bv_len >> 9) > - blk_max_size_offset(q, bio->bi_iter.bi_sector)) { + if (sectors + (bv.bv_len >> 9) > max_sectors) { /* * Consider this a new segment if we're splitting in * the middle of this vector. */ if (nsegs < queue_max_segments(q) && - sectors < blk_max_size_offset(q, - bio->bi_iter.bi_sector)) { + sectors < max_sectors) { nsegs++; - sectors = blk_max_size_offset(q, - bio->bi_iter.bi_sector); + sectors = max_sectors; } - goto split; + if (sectors) + goto split; + /* Make this single bvec as the 1st segment */ } if (bvprvp && blk_queue_cluster(q)) { diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 90e2d54be526..1316ddd92fac 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -135,14 +135,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), }, }, - { - .callback = video_detect_force_vendor, - .ident = "Dell Inspiron 5737", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"), - }, - }, /* * These models have a working acpi_video backlight control, and using diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 47c43386786b..279e53989374 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -284,6 +284,7 @@ out_free_priv_data: return err; } +EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); /** * platform_msi_domain_free_irqs - Free MSI interrupts for @dev @@ -301,6 +302,7 @@ void platform_msi_domain_free_irqs(struct device *dev) msi_domain_free_irqs(dev->msi_domain, dev); platform_msi_free_descs(dev, 0, MAX_DEV_MSIS); } +EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); /** * platform_msi_get_host_data - Query the private data associated with diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 73d6e5d39e33..f437afa17f2b 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -558,10 +558,15 @@ static int platform_drv_probe(struct device *_dev) return ret; ret = dev_pm_domain_attach(_dev, true); - if (ret != -EPROBE_DEFER && drv->probe) { - ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); + if (ret != -EPROBE_DEFER) { + if (drv->probe) { + ret = drv->probe(dev); + if (ret) + dev_pm_domain_detach(_dev, true); + } else { + /* don't fail if just dev_pm_domain_attach failed */ + ret = 0; + } } if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 6ac9a7f33b64..784dbe897a5e 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -162,7 +162,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed) /** * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff(). - * @genpd: PM domait to power off. + * @genpd: PM domain to power off. * * Queue up the execution of genpd_poweroff() unless it's already been done * before. @@ -172,16 +172,15 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) queue_work(pm_wq, &genpd->power_off_work); } -static int genpd_poweron(struct generic_pm_domain *genpd); - /** * __genpd_poweron - Restore power to a given PM domain and its masters. * @genpd: PM domain to power up. + * @depth: nesting count for lockdep. * * Restore power to @genpd and all of its masters so that it is possible to * resume a device belonging to it. */ -static int __genpd_poweron(struct generic_pm_domain *genpd) +static int __genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth) { struct gpd_link *link; int ret = 0; @@ -196,11 +195,16 @@ static int __genpd_poweron(struct generic_pm_domain *genpd) * with it. */ list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_inc(link->master); + struct generic_pm_domain *master = link->master; + + genpd_sd_counter_inc(master); + + mutex_lock_nested(&master->lock, depth + 1); + ret = __genpd_poweron(master, depth + 1); + mutex_unlock(&master->lock); - ret = genpd_poweron(link->master); if (ret) { - genpd_sd_counter_dec(link->master); + genpd_sd_counter_dec(master); goto err; } } @@ -232,11 +236,12 @@ static int genpd_poweron(struct generic_pm_domain *genpd) int ret; mutex_lock(&genpd->lock); - ret = __genpd_poweron(genpd); + ret = __genpd_poweron(genpd, 0); mutex_unlock(&genpd->lock); return ret; } + static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev) { return GENPD_DEV_CALLBACK(genpd, int, save_state, dev); @@ -484,7 +489,7 @@ static int pm_genpd_runtime_resume(struct device *dev) } mutex_lock(&genpd->lock); - ret = __genpd_poweron(genpd); + ret = __genpd_poweron(genpd, 0); mutex_unlock(&genpd->lock); if (ret) @@ -1339,8 +1344,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, if (!link) return -ENOMEM; - mutex_lock(&genpd->lock); - mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING); + mutex_lock(&subdomain->lock); + mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); if (genpd->status == GPD_STATE_POWER_OFF && subdomain->status != GPD_STATE_POWER_OFF) { @@ -1363,8 +1368,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, genpd_sd_counter_inc(genpd); out: - mutex_unlock(&subdomain->lock); mutex_unlock(&genpd->lock); + mutex_unlock(&subdomain->lock); if (ret) kfree(link); return ret; @@ -1385,7 +1390,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) return -EINVAL; - mutex_lock(&genpd->lock); + mutex_lock(&subdomain->lock); + mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); if (!list_empty(&subdomain->slave_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, @@ -1398,22 +1404,19 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (link->slave != subdomain) continue; - mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING); - list_del(&link->master_node); list_del(&link->slave_node); kfree(link); if (subdomain->status != GPD_STATE_POWER_OFF) genpd_sd_counter_dec(genpd); - mutex_unlock(&subdomain->lock); - ret = 0; break; } out: mutex_unlock(&genpd->lock); + mutex_unlock(&subdomain->lock); return ret; } diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 56777f04d2d9..33db7406c0e2 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -30,6 +30,8 @@ config CLKSRC_MMIO config DIGICOLOR_TIMER bool "Digicolor timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + select CLKSRC_MMIO + depends on HAS_IOMEM help Enables the support for the digicolor timer driver. @@ -55,6 +57,7 @@ config ARMADA_370_XP_TIMER bool "Armada 370 and XP timer driver" if COMPILE_TEST depends on ARM select CLKSRC_OF + select CLKSRC_MMIO help Enables the support for the Armada 370 and XP timer driver. @@ -76,6 +79,7 @@ config ORION_TIMER config SUN4I_TIMER bool "Sun4i timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help Enables support for the Sun4i timer. @@ -89,6 +93,7 @@ config SUN5I_HSTIMER config TEGRA_TIMER bool "Tegra timer driver" if COMPILE_TEST + select CLKSRC_MMIO depends on ARM help Enables support for the Tegra driver. @@ -96,6 +101,7 @@ config TEGRA_TIMER config VT8500_TIMER bool "VT8500 timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help Enables support for the VT8500 driver. @@ -131,6 +137,7 @@ config CLKSRC_NOMADIK_MTU_SCHED_CLOCK config CLKSRC_DBX500_PRCMU bool "Clocksource PRCMU Timer" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help Use the always on PRCMU Timer as clocksource @@ -248,6 +255,7 @@ config CLKSRC_EXYNOS_MCT config CLKSRC_SAMSUNG_PWM bool "PWM timer drvier for Samsung S3C, S5P" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help This is a new clocksource driver for the PWM timer found in Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver @@ -257,12 +265,14 @@ config CLKSRC_SAMSUNG_PWM config FSL_FTM_TIMER bool "Freescale FlexTimer Module driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help Support for Freescale FlexTimer Module (FTM) timer. config VF_PIT_TIMER bool + select CLKSRC_MMIO help Support for Period Interrupt Timer on Freescale Vybrid Family SoCs. @@ -360,6 +370,7 @@ config CLKSRC_TANGO_XTAL config CLKSRC_PXA bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help This enables OST0 support available on PXA and SA-11x0 @@ -394,6 +405,7 @@ config CLKSRC_ST_LPC bool "Low power clocksource found in the LPC" if COMPILE_TEST select CLKSRC_OF if OF depends on HAS_IOMEM + select CLKSRC_MMIO help Enable this option to use the Low Power controller timer as clocksource. diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 6ee91401918e..4da2af9694a2 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -98,7 +98,8 @@ static int tc_shutdown(struct clock_event_device *d) __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); - clk_disable(tcd->clk); + if (!clockevent_state_detached(d)) + clk_disable(tcd->clk); return 0; } diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 9bc37c437874..0ca74d070058 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -142,15 +142,16 @@ static int allocate_resources(int cpu, struct device **cdev, try_again: cpu_reg = regulator_get_optional(cpu_dev, reg); - if (IS_ERR(cpu_reg)) { + ret = PTR_ERR_OR_ZERO(cpu_reg); + if (ret) { /* * If cpu's regulator supply node is present, but regulator is * not yet registered, we should try defering probe. */ - if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) { + if (ret == -EPROBE_DEFER) { dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n", cpu); - return -EPROBE_DEFER; + return ret; } /* Try with "cpu-supply" */ @@ -159,18 +160,16 @@ try_again: goto try_again; } - dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n", - cpu, PTR_ERR(cpu_reg)); + dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret); } cpu_clk = clk_get(cpu_dev, NULL); - if (IS_ERR(cpu_clk)) { + ret = PTR_ERR_OR_ZERO(cpu_clk); + if (ret) { /* put regulator */ if (!IS_ERR(cpu_reg)) regulator_put(cpu_reg); - ret = PTR_ERR(cpu_clk); - /* * If cpu's clk node is present, but clock is not yet * registered, we should try defering probe. diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index c35e7da1ed7a..e979ec78b695 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -48,11 +48,11 @@ static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy, bool active) { do { - policy = list_next_entry(policy, policy_list); - /* No more policies in the list */ - if (&policy->policy_list == &cpufreq_policy_list) + if (list_is_last(&policy->policy_list, &cpufreq_policy_list)) return NULL; + + policy = list_next_entry(policy, policy_list); } while (!suitable_policy(policy, active)); return policy; diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index bab3a514ec12..e0d111024d48 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -387,16 +387,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy, if (!have_governor_per_policy()) cdata->gdbs_data = dbs_data; + policy->governor_data = dbs_data; + ret = sysfs_create_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); if (ret) goto reset_gdbs_data; - policy->governor_data = dbs_data; - return 0; reset_gdbs_data: + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, !policy->governor->initialized); @@ -417,16 +419,19 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy, if (!cdbs->shared || cdbs->shared->policy) return -EBUSY; - policy->governor_data = NULL; if (!--dbs_data->usage_count) { sysfs_remove_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, policy->governor->initialized == 1); kfree(dbs_data); + } else { + policy->governor_data = NULL; } free_common_dbs_info(policy, cdata); diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c index 1d99c97defa9..096377232747 100644 --- a/drivers/cpufreq/pxa2xx-cpufreq.c +++ b/drivers/cpufreq/pxa2xx-cpufreq.c @@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void) } } #else -static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq) +static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq) { return 0; } diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c index 344058f8501a..d5657d50ac40 100644 --- a/drivers/cpuidle/coupled.c +++ b/drivers/cpuidle/coupled.c @@ -119,7 +119,6 @@ struct cpuidle_coupled { #define CPUIDLE_COUPLED_NOT_IDLE (-1) -static DEFINE_MUTEX(cpuidle_coupled_lock); static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); /* diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 046423b0c5ca..f996efc56605 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -153,7 +153,7 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) * be frozen safely. */ index = find_deepest_state(drv, dev, UINT_MAX, 0, true); - if (index >= 0) + if (index > 0) enter_freeze_proper(drv, dev, index); return index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 313b0cc8d676..82edf95b7740 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -2278,60 +2278,60 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_dpm_enable_bapm(adev, e) (adev)->pm.funcs->enable_bapm((adev), (e)) #define amdgpu_dpm_get_temperature(adev) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_temperature((adev)->powerplay.pp_handle) : \ - (adev)->pm.funcs->get_temperature((adev)) + (adev)->pm.funcs->get_temperature((adev))) #define amdgpu_dpm_set_fan_control_mode(adev, m) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->set_fan_control_mode((adev)->powerplay.pp_handle, (m)) : \ - (adev)->pm.funcs->set_fan_control_mode((adev), (m)) + (adev)->pm.funcs->set_fan_control_mode((adev), (m))) #define amdgpu_dpm_get_fan_control_mode(adev) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_fan_control_mode((adev)->powerplay.pp_handle) : \ - (adev)->pm.funcs->get_fan_control_mode((adev)) + (adev)->pm.funcs->get_fan_control_mode((adev))) #define amdgpu_dpm_set_fan_speed_percent(adev, s) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->set_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \ - (adev)->pm.funcs->set_fan_speed_percent((adev), (s)) + (adev)->pm.funcs->set_fan_speed_percent((adev), (s))) #define amdgpu_dpm_get_fan_speed_percent(adev, s) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \ - (adev)->pm.funcs->get_fan_speed_percent((adev), (s)) + (adev)->pm.funcs->get_fan_speed_percent((adev), (s))) #define amdgpu_dpm_get_sclk(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_sclk((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->get_sclk((adev), (l)) + (adev)->pm.funcs->get_sclk((adev), (l))) #define amdgpu_dpm_get_mclk(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_mclk((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->get_mclk((adev), (l)) + (adev)->pm.funcs->get_mclk((adev), (l))) #define amdgpu_dpm_force_performance_level(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->force_performance_level((adev), (l)) + (adev)->pm.funcs->force_performance_level((adev), (l))) #define amdgpu_dpm_powergate_uvd(adev, g) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)) : \ - (adev)->pm.funcs->powergate_uvd((adev), (g)) + (adev)->pm.funcs->powergate_uvd((adev), (g))) #define amdgpu_dpm_powergate_vce(adev, g) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)) : \ - (adev)->pm.funcs->powergate_vce((adev), (g)) + (adev)->pm.funcs->powergate_vce((adev), (g))) #define amdgpu_dpm_debugfs_print_current_performance_level(adev, m) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->print_current_performance_level((adev)->powerplay.pp_handle, (m)) : \ - (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m)) + (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m))) #define amdgpu_dpm_get_current_power_state(adev) \ (adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 6f89f8e034d0..b882e8175615 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -478,9 +478,9 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; unsigned i; - amdgpu_vm_move_pt_bos_in_lru(parser->adev, &fpriv->vm); - if (!error) { + amdgpu_vm_move_pt_bos_in_lru(parser->adev, &fpriv->vm); + /* Sort the buffer list from the smallest to largest buffer, * which affects the order of buffers in the LRU list. * This assures that the smallest buffers are added first diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index cfb6caad2a73..919146780a15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -333,6 +333,10 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev) if (!adev->mode_info.mode_config_initialized) return 0; + /* don't init fbdev if there are no connectors */ + if (list_empty(&adev->ddev->mode_config.connector_list)) + return 0; + /* select 8 bpp console on low vram cards */ if (adev->mc.real_vram_size <= (32*1024*1024)) bpp_sel = 8; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c3ce103b6a33..a2a16acee34d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -399,7 +399,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, } if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; - if (lpfn && lpfn < bo->placements[i].lpfn) + if (!bo->placements[i].lpfn || + (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index 5ee9a0690278..b9d0d55f6b47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -99,13 +99,24 @@ static int amdgpu_pp_early_init(void *handle) #ifdef CONFIG_DRM_AMD_POWERPLAY switch (adev->asic_type) { - case CHIP_TONGA: - case CHIP_FIJI: - adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; - break; - default: - adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; - break; + case CHIP_TONGA: + case CHIP_FIJI: + adev->pp_enabled = (amdgpu_powerplay == 0) ? false : true; + break; + case CHIP_CARRIZO: + case CHIP_STONEY: + adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; + break; + /* These chips don't have powerplay implemenations */ + case CHIP_BONAIRE: + case CHIP_HAWAII: + case CHIP_KABINI: + case CHIP_MULLINS: + case CHIP_KAVERI: + case CHIP_TOPAZ: + default: + adev->pp_enabled = false; + break; } #else adev->pp_enabled = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 78e9b0f14661..d1f234dd2126 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -487,7 +487,7 @@ static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data) seq_printf(m, "rptr: 0x%08x [%5d]\n", rptr, rptr); - rptr_next = ~0; + rptr_next = le32_to_cpu(*ring->next_rptr_cpu_addr); seq_printf(m, "driver's copy of the wptr: 0x%08x [%5d]\n", ring->wptr, ring->wptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index aefc668e6b5d..9599f7559b3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1282,7 +1282,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT * 8); - unsigned pd_size, pd_entries, pts_size; + unsigned pd_size, pd_entries; int i, r; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { @@ -1300,8 +1300,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) pd_entries = amdgpu_vm_num_pdes(adev); /* allocate page table array */ - pts_size = pd_entries * sizeof(struct amdgpu_vm_pt); - vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + vm->page_tables = drm_calloc_large(pd_entries, sizeof(struct amdgpu_vm_pt)); if (vm->page_tables == NULL) { DRM_ERROR("Cannot allocate memory for page table array\n"); return -ENOMEM; @@ -1361,7 +1360,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < amdgpu_vm_num_pdes(adev); i++) amdgpu_bo_unref(&vm->page_tables[i].entry.robj); - kfree(vm->page_tables); + drm_free_large(vm->page_tables); amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 13235d84e5a6..95c0cdfbd1b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4186,7 +4186,18 @@ static int gfx_v8_0_soft_reset(void *handle) gfx_v8_0_cp_gfx_enable(adev, false); /* Disable MEC parsing/prefetching */ - /* XXX todo */ + gfx_v8_0_cp_compute_enable(adev, false); + + if (grbm_soft_reset || srbm_soft_reset) { + tmp = RREG32(mmGMCON_DEBUG); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_STALL, 1); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_CLEAR, 1); + WREG32(mmGMCON_DEBUG, tmp); + + udelay(50); + } if (grbm_soft_reset) { tmp = RREG32(mmGRBM_SOFT_RESET); @@ -4215,6 +4226,16 @@ static int gfx_v8_0_soft_reset(void *handle) WREG32(mmSRBM_SOFT_RESET, tmp); tmp = RREG32(mmSRBM_SOFT_RESET); } + + if (grbm_soft_reset || srbm_soft_reset) { + tmp = RREG32(mmGMCON_DEBUG); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_STALL, 0); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_CLEAR, 0); + WREG32(mmGMCON_DEBUG, tmp); + } + /* Wait a little for things to settle down */ udelay(50); gfx_v8_0_print_status((void *)adev); diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index f4a1346525fe..0497784b3652 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -122,25 +122,12 @@ static int tonga_dpm_hw_fini(void *handle) static int tonga_dpm_suspend(void *handle) { - return 0; + return tonga_dpm_hw_fini(handle); } static int tonga_dpm_resume(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - mutex_lock(&adev->pm.mutex); - - ret = tonga_smu_start(adev); - if (ret) { - DRM_ERROR("SMU start failed\n"); - goto fail; - } - -fail: - mutex_unlock(&adev->pm.mutex); - return ret; + return tonga_dpm_hw_init(handle); } static int tonga_dpm_set_clockgating_state(void *handle, diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index 8f5d5edcf193..aa67244a77ae 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -64,6 +64,11 @@ static int pp_sw_init(void *handle) if (ret == 0) ret = hwmgr->hwmgr_func->backend_init(hwmgr); + if (ret) + printk("amdgpu: powerplay initialization failed\n"); + else + printk("amdgpu: powerplay initialized\n"); + return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c index 873a8d264d5c..ec222c665602 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c @@ -272,6 +272,9 @@ static int cz_start_smu(struct pp_smumgr *smumgr) UCODE_ID_CP_MEC_JT1_MASK | UCODE_ID_CP_MEC_JT2_MASK; + if (smumgr->chip_id == CHIP_STONEY) + fw_to_check &= ~(UCODE_ID_SDMA1_MASK | UCODE_ID_CP_MEC_JT2_MASK); + cz_request_smu_load_fw(smumgr); cz_check_fw_load_finish(smumgr, fw_to_check); @@ -282,7 +285,7 @@ static int cz_start_smu(struct pp_smumgr *smumgr) return ret; } -static uint8_t cz_translate_firmware_enum_to_arg( +static uint8_t cz_translate_firmware_enum_to_arg(struct pp_smumgr *smumgr, enum cz_scratch_entry firmware_enum) { uint8_t ret = 0; @@ -292,7 +295,10 @@ static uint8_t cz_translate_firmware_enum_to_arg( ret = UCODE_ID_SDMA0; break; case CZ_SCRATCH_ENTRY_UCODE_ID_SDMA1: - ret = UCODE_ID_SDMA1; + if (smumgr->chip_id == CHIP_STONEY) + ret = UCODE_ID_SDMA0; + else + ret = UCODE_ID_SDMA1; break; case CZ_SCRATCH_ENTRY_UCODE_ID_CP_CE: ret = UCODE_ID_CP_CE; @@ -307,7 +313,10 @@ static uint8_t cz_translate_firmware_enum_to_arg( ret = UCODE_ID_CP_MEC_JT1; break; case CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2: - ret = UCODE_ID_CP_MEC_JT2; + if (smumgr->chip_id == CHIP_STONEY) + ret = UCODE_ID_CP_MEC_JT1; + else + ret = UCODE_ID_CP_MEC_JT2; break; case CZ_SCRATCH_ENTRY_UCODE_ID_GMCON_RENG: ret = UCODE_ID_GMCON_RENG; @@ -396,7 +405,7 @@ static int cz_smu_populate_single_scratch_task( struct SMU_Task *task = &toc->tasks[cz_smu->toc_entry_used_count++]; task->type = type; - task->arg = cz_translate_firmware_enum_to_arg(fw_enum); + task->arg = cz_translate_firmware_enum_to_arg(smumgr, fw_enum); task->next = is_last ? END_OF_TASK_LIST : cz_smu->toc_entry_used_count; for (i = 0; i < cz_smu->scratch_buffer_length; i++) @@ -433,7 +442,7 @@ static int cz_smu_populate_single_ucode_load_task( struct SMU_Task *task = &toc->tasks[cz_smu->toc_entry_used_count++]; task->type = TASK_TYPE_UCODE_LOAD; - task->arg = cz_translate_firmware_enum_to_arg(fw_enum); + task->arg = cz_translate_firmware_enum_to_arg(smumgr, fw_enum); task->next = is_last ? END_OF_TASK_LIST : cz_smu->toc_entry_used_count; for (i = 0; i < cz_smu->driver_buffer_length; i++) @@ -509,8 +518,14 @@ static int cz_smu_construct_toc_for_vddgfx_exit(struct pp_smumgr *smumgr) CZ_SCRATCH_ENTRY_UCODE_ID_CP_ME, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); - cz_smu_populate_single_ucode_load_task(smumgr, + + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2, false); + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_RLC_G, false); @@ -551,7 +566,11 @@ static int cz_smu_construct_toc_for_bootup(struct pp_smumgr *smumgr) cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_SDMA0, false); - cz_smu_populate_single_ucode_load_task(smumgr, + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_SDMA0, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_SDMA1, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_CE, false); @@ -561,7 +580,11 @@ static int cz_smu_construct_toc_for_bootup(struct pp_smumgr *smumgr) CZ_SCRATCH_ENTRY_UCODE_ID_CP_ME, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); - cz_smu_populate_single_ucode_load_task(smumgr, + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_RLC_G, true); @@ -618,7 +641,7 @@ static int cz_smu_populate_firmware_entries(struct pp_smumgr *smumgr) for (i = 0; i < sizeof(firmware_list)/sizeof(*firmware_list); i++) { - firmware_type = cz_translate_firmware_enum_to_arg( + firmware_type = cz_translate_firmware_enum_to_arg(smumgr, firmware_list[i]); ucode_id = cz_convert_fw_type_to_cgs(firmware_type); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 57cccd68ca52..7c523060a076 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -946,9 +946,23 @@ static void wait_for_fences(struct drm_device *dev, } } -static bool framebuffer_changed(struct drm_device *dev, - struct drm_atomic_state *old_state, - struct drm_crtc *crtc) +/** + * drm_atomic_helper_framebuffer_changed - check if framebuffer has changed + * @dev: DRM device + * @old_state: atomic state object with old state structures + * @crtc: DRM crtc + * + * Checks whether the framebuffer used for this CRTC changes as a result of + * the atomic update. This is useful for drivers which cannot use + * drm_atomic_helper_wait_for_vblanks() and need to reimplement its + * functionality. + * + * Returns: + * true if the framebuffer changed. + */ +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc) { struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -965,6 +979,7 @@ static bool framebuffer_changed(struct drm_device *dev, return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed); /** * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs @@ -999,7 +1014,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue; - if (!framebuffer_changed(dev, old_state, crtc)) + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) continue; ret = drm_crtc_vblank_get(crtc); diff --git a/drivers/gpu/drm/etnaviv/common.xml.h b/drivers/gpu/drm/etnaviv/common.xml.h index 9e585d51fb78..e881482b5971 100644 --- a/drivers/gpu/drm/etnaviv/common.xml.h +++ b/drivers/gpu/drm/etnaviv/common.xml.h @@ -8,8 +8,8 @@ http://0x04.net/cgit/index.cgi/rules-ng-ng git clone git://0x04.net/rules-ng-ng The rules-ng-ng source files this header was generated from are: -- state_vg.xml ( 5973 bytes, from 2015-03-25 11:26:01) -- common.xml ( 18437 bytes, from 2015-03-25 11:27:41) +- state_hi.xml ( 24309 bytes, from 2015-12-12 09:02:53) +- common.xml ( 18379 bytes, from 2015-12-12 09:02:53) Copyright (C) 2015 */ @@ -30,15 +30,19 @@ Copyright (C) 2015 #define ENDIAN_MODE_NO_SWAP 0x00000000 #define ENDIAN_MODE_SWAP_16 0x00000001 #define ENDIAN_MODE_SWAP_32 0x00000002 +#define chipModel_GC200 0x00000200 #define chipModel_GC300 0x00000300 #define chipModel_GC320 0x00000320 +#define chipModel_GC328 0x00000328 #define chipModel_GC350 0x00000350 #define chipModel_GC355 0x00000355 #define chipModel_GC400 0x00000400 #define chipModel_GC410 0x00000410 #define chipModel_GC420 0x00000420 +#define chipModel_GC428 0x00000428 #define chipModel_GC450 0x00000450 #define chipModel_GC500 0x00000500 +#define chipModel_GC520 0x00000520 #define chipModel_GC530 0x00000530 #define chipModel_GC600 0x00000600 #define chipModel_GC700 0x00000700 @@ -46,9 +50,16 @@ Copyright (C) 2015 #define chipModel_GC860 0x00000860 #define chipModel_GC880 0x00000880 #define chipModel_GC1000 0x00001000 +#define chipModel_GC1500 0x00001500 #define chipModel_GC2000 0x00002000 #define chipModel_GC2100 0x00002100 +#define chipModel_GC2200 0x00002200 +#define chipModel_GC2500 0x00002500 +#define chipModel_GC3000 0x00003000 #define chipModel_GC4000 0x00004000 +#define chipModel_GC5000 0x00005000 +#define chipModel_GC5200 0x00005200 +#define chipModel_GC6400 0x00006400 #define RGBA_BITS_R 0x00000001 #define RGBA_BITS_G 0x00000002 #define RGBA_BITS_B 0x00000004 @@ -160,7 +171,7 @@ Copyright (C) 2015 #define chipMinorFeatures2_UNK8 0x00000100 #define chipMinorFeatures2_UNK9 0x00000200 #define chipMinorFeatures2_UNK10 0x00000400 -#define chipMinorFeatures2_SAMPLERBASE_16 0x00000800 +#define chipMinorFeatures2_HALTI1 0x00000800 #define chipMinorFeatures2_UNK12 0x00001000 #define chipMinorFeatures2_UNK13 0x00002000 #define chipMinorFeatures2_UNK14 0x00004000 @@ -189,7 +200,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK5 0x00000020 #define chipMinorFeatures3_UNK6 0x00000040 #define chipMinorFeatures3_UNK7 0x00000080 -#define chipMinorFeatures3_UNK8 0x00000100 +#define chipMinorFeatures3_FAST_MSAA 0x00000100 #define chipMinorFeatures3_UNK9 0x00000200 #define chipMinorFeatures3_BUG_FIXES10 0x00000400 #define chipMinorFeatures3_UNK11 0x00000800 @@ -199,7 +210,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK15 0x00008000 #define chipMinorFeatures3_UNK16 0x00010000 #define chipMinorFeatures3_UNK17 0x00020000 -#define chipMinorFeatures3_UNK18 0x00040000 +#define chipMinorFeatures3_ACE 0x00040000 #define chipMinorFeatures3_UNK19 0x00080000 #define chipMinorFeatures3_UNK20 0x00100000 #define chipMinorFeatures3_UNK21 0x00200000 @@ -207,7 +218,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK23 0x00800000 #define chipMinorFeatures3_UNK24 0x01000000 #define chipMinorFeatures3_UNK25 0x02000000 -#define chipMinorFeatures3_UNK26 0x04000000 +#define chipMinorFeatures3_NEW_HZ 0x04000000 #define chipMinorFeatures3_UNK27 0x08000000 #define chipMinorFeatures3_UNK28 0x10000000 #define chipMinorFeatures3_UNK29 0x20000000 @@ -229,9 +240,9 @@ Copyright (C) 2015 #define chipMinorFeatures4_UNK13 0x00002000 #define chipMinorFeatures4_UNK14 0x00004000 #define chipMinorFeatures4_UNK15 0x00008000 -#define chipMinorFeatures4_UNK16 0x00010000 +#define chipMinorFeatures4_HALTI2 0x00010000 #define chipMinorFeatures4_UNK17 0x00020000 -#define chipMinorFeatures4_UNK18 0x00040000 +#define chipMinorFeatures4_SMALL_MSAA 0x00040000 #define chipMinorFeatures4_UNK19 0x00080000 #define chipMinorFeatures4_UNK20 0x00100000 #define chipMinorFeatures4_UNK21 0x00200000 @@ -245,5 +256,37 @@ Copyright (C) 2015 #define chipMinorFeatures4_UNK29 0x20000000 #define chipMinorFeatures4_UNK30 0x40000000 #define chipMinorFeatures4_UNK31 0x80000000 +#define chipMinorFeatures5_UNK0 0x00000001 +#define chipMinorFeatures5_UNK1 0x00000002 +#define chipMinorFeatures5_UNK2 0x00000004 +#define chipMinorFeatures5_UNK3 0x00000008 +#define chipMinorFeatures5_UNK4 0x00000010 +#define chipMinorFeatures5_UNK5 0x00000020 +#define chipMinorFeatures5_UNK6 0x00000040 +#define chipMinorFeatures5_UNK7 0x00000080 +#define chipMinorFeatures5_UNK8 0x00000100 +#define chipMinorFeatures5_HALTI3 0x00000200 +#define chipMinorFeatures5_UNK10 0x00000400 +#define chipMinorFeatures5_UNK11 0x00000800 +#define chipMinorFeatures5_UNK12 0x00001000 +#define chipMinorFeatures5_UNK13 0x00002000 +#define chipMinorFeatures5_UNK14 0x00004000 +#define chipMinorFeatures5_UNK15 0x00008000 +#define chipMinorFeatures5_UNK16 0x00010000 +#define chipMinorFeatures5_UNK17 0x00020000 +#define chipMinorFeatures5_UNK18 0x00040000 +#define chipMinorFeatures5_UNK19 0x00080000 +#define chipMinorFeatures5_UNK20 0x00100000 +#define chipMinorFeatures5_UNK21 0x00200000 +#define chipMinorFeatures5_UNK22 0x00400000 +#define chipMinorFeatures5_UNK23 0x00800000 +#define chipMinorFeatures5_UNK24 0x01000000 +#define chipMinorFeatures5_UNK25 0x02000000 +#define chipMinorFeatures5_UNK26 0x04000000 +#define chipMinorFeatures5_UNK27 0x08000000 +#define chipMinorFeatures5_UNK28 0x10000000 +#define chipMinorFeatures5_UNK29 0x20000000 +#define chipMinorFeatures5_UNK30 0x40000000 +#define chipMinorFeatures5_UNK31 0x80000000 #endif /* COMMON_XML */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 5c89ebb52fd2..e8858985f01e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -668,7 +668,6 @@ static struct platform_driver etnaviv_platform_driver = { .probe = etnaviv_pdev_probe, .remove = etnaviv_pdev_remove, .driver = { - .owner = THIS_MODULE, .name = "etnaviv", .of_match_table = dt_match, }, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h index d6bd438bd5be..1cd6046e76b1 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h @@ -85,7 +85,7 @@ struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); int etnaviv_gem_prime_pin(struct drm_gem_object *obj); void etnaviv_gem_prime_unpin(struct drm_gem_object *obj); -void *etnaviv_gem_vaddr(struct drm_gem_object *obj); +void *etnaviv_gem_vmap(struct drm_gem_object *obj); int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, struct timespec *timeout); int etnaviv_gem_cpu_fini(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index bf8fa859e8be..4a29eeadbf1e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -201,7 +201,9 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) obj = vram->object; + mutex_lock(&obj->lock); pages = etnaviv_gem_get_pages(obj); + mutex_unlock(&obj->lock); if (pages) { int j; @@ -213,8 +215,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) iter.hdr->iova = cpu_to_le64(vram->iova); - vaddr = etnaviv_gem_vaddr(&obj->base); - if (vaddr && !IS_ERR(vaddr)) + vaddr = etnaviv_gem_vmap(&obj->base); + if (vaddr) memcpy(iter.data, vaddr, obj->base.size); etnaviv_core_dump_header(&iter, ETDUMP_BUF_BO, iter.data + diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 9f77c3b94cc6..4b519e4309b2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -353,25 +353,39 @@ void etnaviv_gem_put_iova(struct etnaviv_gpu *gpu, struct drm_gem_object *obj) drm_gem_object_unreference_unlocked(obj); } -void *etnaviv_gem_vaddr(struct drm_gem_object *obj) +void *etnaviv_gem_vmap(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); - mutex_lock(&etnaviv_obj->lock); - if (!etnaviv_obj->vaddr) { - struct page **pages = etnaviv_gem_get_pages(etnaviv_obj); - - if (IS_ERR(pages)) - return ERR_CAST(pages); + if (etnaviv_obj->vaddr) + return etnaviv_obj->vaddr; - etnaviv_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT, - VM_MAP, pgprot_writecombine(PAGE_KERNEL)); - } + mutex_lock(&etnaviv_obj->lock); + /* + * Need to check again, as we might have raced with another thread + * while waiting for the mutex. + */ + if (!etnaviv_obj->vaddr) + etnaviv_obj->vaddr = etnaviv_obj->ops->vmap(etnaviv_obj); mutex_unlock(&etnaviv_obj->lock); return etnaviv_obj->vaddr; } +static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) +{ + struct page **pages; + + lockdep_assert_held(&obj->lock); + + pages = etnaviv_gem_get_pages(obj); + if (IS_ERR(pages)) + return NULL; + + return vmap(pages, obj->base.size >> PAGE_SHIFT, + VM_MAP, pgprot_writecombine(PAGE_KERNEL)); +} + static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) { if (op & ETNA_PREP_READ) @@ -522,6 +536,7 @@ static void etnaviv_gem_shmem_release(struct etnaviv_gem_object *etnaviv_obj) static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { .get_pages = etnaviv_gem_shmem_get_pages, .release = etnaviv_gem_shmem_release, + .vmap = etnaviv_gem_vmap_impl, }; void etnaviv_gem_free_object(struct drm_gem_object *obj) @@ -866,6 +881,7 @@ static void etnaviv_gem_userptr_release(struct etnaviv_gem_object *etnaviv_obj) static const struct etnaviv_gem_ops etnaviv_gem_userptr_ops = { .get_pages = etnaviv_gem_userptr_get_pages, .release = etnaviv_gem_userptr_release, + .vmap = etnaviv_gem_vmap_impl, }; int etnaviv_gem_new_userptr(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index a300b4b3d545..ab5df8147a5f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -78,6 +78,7 @@ struct etnaviv_gem_object *to_etnaviv_bo(struct drm_gem_object *obj) struct etnaviv_gem_ops { int (*get_pages)(struct etnaviv_gem_object *); void (*release)(struct etnaviv_gem_object *); + void *(*vmap)(struct etnaviv_gem_object *); }; static inline bool is_active(struct etnaviv_gem_object *etnaviv_obj) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index e94db4f95770..4e67395f5fa1 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -31,7 +31,7 @@ struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj) void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj) { - return etnaviv_gem_vaddr(obj); + return etnaviv_gem_vmap(obj); } void etnaviv_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) @@ -77,9 +77,17 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj) drm_prime_gem_destroy(&etnaviv_obj->base, etnaviv_obj->sgt); } +static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) +{ + lockdep_assert_held(&etnaviv_obj->lock); + + return dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf); +} + static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = { /* .get_pages should never be called */ .release = etnaviv_gem_prime_release, + .vmap = etnaviv_gem_prime_vmap_impl, }; struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 056a72e6ed26..a33162cf4f4c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -72,6 +72,14 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.minor_features3; break; + case ETNAVIV_PARAM_GPU_FEATURES_5: + *value = gpu->identity.minor_features4; + break; + + case ETNAVIV_PARAM_GPU_FEATURES_6: + *value = gpu->identity.minor_features5; + break; + case ETNAVIV_PARAM_GPU_STREAM_COUNT: *value = gpu->identity.stream_count; break; @@ -112,6 +120,10 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.num_constants; break; + case ETNAVIV_PARAM_GPU_NUM_VARYINGS: + *value = gpu->identity.varyings_count; + break; + default: DBG("%s: invalid param: %u", dev_name(gpu->dev), param); return -EINVAL; @@ -120,46 +132,56 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) return 0; } + +#define etnaviv_is_model_rev(gpu, mod, rev) \ + ((gpu)->identity.model == chipModel_##mod && \ + (gpu)->identity.revision == rev) +#define etnaviv_field(val, field) \ + (((val) & field##__MASK) >> field##__SHIFT) + static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) { if (gpu->identity.minor_features0 & chipMinorFeatures0_MORE_MINOR_FEATURES) { - u32 specs[2]; + u32 specs[4]; + unsigned int streams; specs[0] = gpu_read(gpu, VIVS_HI_CHIP_SPECS); specs[1] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_2); - - gpu->identity.stream_count = - (specs[0] & VIVS_HI_CHIP_SPECS_STREAM_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_STREAM_COUNT__SHIFT; - gpu->identity.register_max = - (specs[0] & VIVS_HI_CHIP_SPECS_REGISTER_MAX__MASK) - >> VIVS_HI_CHIP_SPECS_REGISTER_MAX__SHIFT; - gpu->identity.thread_count = - (specs[0] & VIVS_HI_CHIP_SPECS_THREAD_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_THREAD_COUNT__SHIFT; - gpu->identity.vertex_cache_size = - (specs[0] & VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE__SHIFT; - gpu->identity.shader_core_count = - (specs[0] & VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT__SHIFT; - gpu->identity.pixel_pipes = - (specs[0] & VIVS_HI_CHIP_SPECS_PIXEL_PIPES__MASK) - >> VIVS_HI_CHIP_SPECS_PIXEL_PIPES__SHIFT; + specs[2] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_3); + specs[3] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_4); + + gpu->identity.stream_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_STREAM_COUNT); + gpu->identity.register_max = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_REGISTER_MAX); + gpu->identity.thread_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_THREAD_COUNT); + gpu->identity.vertex_cache_size = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE); + gpu->identity.shader_core_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT); + gpu->identity.pixel_pipes = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_PIXEL_PIPES); gpu->identity.vertex_output_buffer_size = - (specs[0] & VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE__SHIFT; - - gpu->identity.buffer_size = - (specs[1] & VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE__SHIFT; - gpu->identity.instruction_count = - (specs[1] & VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT__SHIFT; - gpu->identity.num_constants = - (specs[1] & VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS__MASK) - >> VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS__SHIFT; + etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE); + + gpu->identity.buffer_size = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE); + gpu->identity.instruction_count = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT); + gpu->identity.num_constants = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS); + + gpu->identity.varyings_count = etnaviv_field(specs[2], + VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT); + + /* This overrides the value from older register if non-zero */ + streams = etnaviv_field(specs[3], + VIVS_HI_CHIP_SPECS_4_STREAM_COUNT); + if (streams) + gpu->identity.stream_count = streams; } /* Fill in the stream count if not specified */ @@ -173,7 +195,7 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) /* Convert the register max value */ if (gpu->identity.register_max) gpu->identity.register_max = 1 << gpu->identity.register_max; - else if (gpu->identity.model == 0x0400) + else if (gpu->identity.model == chipModel_GC400) gpu->identity.register_max = 32; else gpu->identity.register_max = 64; @@ -181,10 +203,10 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) /* Convert thread count */ if (gpu->identity.thread_count) gpu->identity.thread_count = 1 << gpu->identity.thread_count; - else if (gpu->identity.model == 0x0400) + else if (gpu->identity.model == chipModel_GC400) gpu->identity.thread_count = 64; - else if (gpu->identity.model == 0x0500 || - gpu->identity.model == 0x0530) + else if (gpu->identity.model == chipModel_GC500 || + gpu->identity.model == chipModel_GC530) gpu->identity.thread_count = 128; else gpu->identity.thread_count = 256; @@ -206,7 +228,7 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) if (gpu->identity.vertex_output_buffer_size) { gpu->identity.vertex_output_buffer_size = 1 << gpu->identity.vertex_output_buffer_size; - } else if (gpu->identity.model == 0x0400) { + } else if (gpu->identity.model == chipModel_GC400) { if (gpu->identity.revision < 0x4000) gpu->identity.vertex_output_buffer_size = 512; else if (gpu->identity.revision < 0x4200) @@ -219,9 +241,8 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) switch (gpu->identity.instruction_count) { case 0: - if ((gpu->identity.model == 0x2000 && - gpu->identity.revision == 0x5108) || - gpu->identity.model == 0x880) + if (etnaviv_is_model_rev(gpu, GC2000, 0x5108) || + gpu->identity.model == chipModel_GC880) gpu->identity.instruction_count = 512; else gpu->identity.instruction_count = 256; @@ -242,6 +263,30 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) if (gpu->identity.num_constants == 0) gpu->identity.num_constants = 168; + + if (gpu->identity.varyings_count == 0) { + if (gpu->identity.minor_features1 & chipMinorFeatures1_HALTI0) + gpu->identity.varyings_count = 12; + else + gpu->identity.varyings_count = 8; + } + + /* + * For some cores, two varyings are consumed for position, so the + * maximum varying count needs to be reduced by one. + */ + if (etnaviv_is_model_rev(gpu, GC5000, 0x5434) || + etnaviv_is_model_rev(gpu, GC4000, 0x5222) || + etnaviv_is_model_rev(gpu, GC4000, 0x5245) || + etnaviv_is_model_rev(gpu, GC4000, 0x5208) || + etnaviv_is_model_rev(gpu, GC3000, 0x5435) || + etnaviv_is_model_rev(gpu, GC2200, 0x5244) || + etnaviv_is_model_rev(gpu, GC2100, 0x5108) || + etnaviv_is_model_rev(gpu, GC2000, 0x5108) || + etnaviv_is_model_rev(gpu, GC1500, 0x5246) || + etnaviv_is_model_rev(gpu, GC880, 0x5107) || + etnaviv_is_model_rev(gpu, GC880, 0x5106)) + gpu->identity.varyings_count -= 1; } static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) @@ -251,12 +296,10 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) chipIdentity = gpu_read(gpu, VIVS_HI_CHIP_IDENTITY); /* Special case for older graphic cores. */ - if (((chipIdentity & VIVS_HI_CHIP_IDENTITY_FAMILY__MASK) - >> VIVS_HI_CHIP_IDENTITY_FAMILY__SHIFT) == 0x01) { - gpu->identity.model = 0x500; /* gc500 */ - gpu->identity.revision = - (chipIdentity & VIVS_HI_CHIP_IDENTITY_REVISION__MASK) - >> VIVS_HI_CHIP_IDENTITY_REVISION__SHIFT; + if (etnaviv_field(chipIdentity, VIVS_HI_CHIP_IDENTITY_FAMILY) == 0x01) { + gpu->identity.model = chipModel_GC500; + gpu->identity.revision = etnaviv_field(chipIdentity, + VIVS_HI_CHIP_IDENTITY_REVISION); } else { gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL); @@ -269,13 +312,12 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) * same. Only for GC400 family. */ if ((gpu->identity.model & 0xff00) == 0x0400 && - gpu->identity.model != 0x0420) { + gpu->identity.model != chipModel_GC420) { gpu->identity.model = gpu->identity.model & 0x0400; } /* Another special case */ - if (gpu->identity.model == 0x300 && - gpu->identity.revision == 0x2201) { + if (etnaviv_is_model_rev(gpu, GC300, 0x2201)) { u32 chipDate = gpu_read(gpu, VIVS_HI_CHIP_DATE); u32 chipTime = gpu_read(gpu, VIVS_HI_CHIP_TIME); @@ -295,11 +337,13 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.features = gpu_read(gpu, VIVS_HI_CHIP_FEATURE); /* Disable fast clear on GC700. */ - if (gpu->identity.model == 0x700) + if (gpu->identity.model == chipModel_GC700) gpu->identity.features &= ~chipFeatures_FAST_CLEAR; - if ((gpu->identity.model == 0x500 && gpu->identity.revision < 2) || - (gpu->identity.model == 0x300 && gpu->identity.revision < 0x2000)) { + if ((gpu->identity.model == chipModel_GC500 && + gpu->identity.revision < 2) || + (gpu->identity.model == chipModel_GC300 && + gpu->identity.revision < 0x2000)) { /* * GC500 rev 1.x and GC300 rev < 2.0 doesn't have these @@ -309,6 +353,8 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.minor_features1 = 0; gpu->identity.minor_features2 = 0; gpu->identity.minor_features3 = 0; + gpu->identity.minor_features4 = 0; + gpu->identity.minor_features5 = 0; } else gpu->identity.minor_features0 = gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_0); @@ -321,6 +367,10 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_2); gpu->identity.minor_features3 = gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_3); + gpu->identity.minor_features4 = + gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_4); + gpu->identity.minor_features5 = + gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_5); } /* GC600 idle register reports zero bits where modules aren't present */ @@ -441,10 +491,9 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) { u16 prefetch; - if (gpu->identity.model == chipModel_GC320 && - gpu_read(gpu, VIVS_HI_CHIP_TIME) != 0x2062400 && - (gpu->identity.revision == 0x5007 || - gpu->identity.revision == 0x5220)) { + if ((etnaviv_is_model_rev(gpu, GC320, 0x5007) || + etnaviv_is_model_rev(gpu, GC320, 0x5220)) && + gpu_read(gpu, VIVS_HI_CHIP_TIME) != 0x2062400) { u32 mc_memory_debug; mc_memory_debug = gpu_read(gpu, VIVS_MC_DEBUG_MEMORY) & ~0xff; @@ -466,7 +515,7 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) VIVS_HI_AXI_CONFIG_ARCACHE(2)); /* GC2000 rev 5108 needs a special bus config */ - if (gpu->identity.model == 0x2000 && gpu->identity.revision == 0x5108) { + if (etnaviv_is_model_rev(gpu, GC2000, 0x5108)) { u32 bus_config = gpu_read(gpu, VIVS_MC_BUS_CONFIG); bus_config &= ~(VIVS_MC_BUS_CONFIG_FE_BUS_CONFIG__MASK | VIVS_MC_BUS_CONFIG_TX_BUS_CONFIG__MASK); @@ -511,8 +560,16 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) if (gpu->identity.model == 0) { dev_err(gpu->dev, "Unknown GPU model\n"); - pm_runtime_put_autosuspend(gpu->dev); - return -ENXIO; + ret = -ENXIO; + goto fail; + } + + /* Exclude VG cores with FE2.0 */ + if (gpu->identity.features & chipFeatures_PIPE_VG && + gpu->identity.features & chipFeatures_FE20) { + dev_info(gpu->dev, "Ignoring GPU with VG and FE2.0\n"); + ret = -ENXIO; + goto fail; } ret = etnaviv_hw_reset(gpu); @@ -539,10 +596,9 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) goto fail; } - /* TODO: we will leak here memory - fix it! */ - gpu->mmu = etnaviv_iommu_new(gpu, iommu, version); if (!gpu->mmu) { + iommu_domain_free(iommu); ret = -ENOMEM; goto fail; } @@ -552,7 +608,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) if (!gpu->buffer) { ret = -ENOMEM; dev_err(gpu->dev, "could not create command buffer\n"); - goto fail; + goto destroy_iommu; } if (gpu->buffer->paddr - gpu->memory_base > 0x80000000) { ret = -EINVAL; @@ -582,6 +638,9 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) free_buffer: etnaviv_gpu_cmdbuf_free(gpu->buffer); gpu->buffer = NULL; +destroy_iommu: + etnaviv_iommu_destroy(gpu->mmu); + gpu->mmu = NULL; fail: pm_runtime_mark_last_busy(gpu->dev); pm_runtime_put_autosuspend(gpu->dev); @@ -642,6 +701,10 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) gpu->identity.minor_features2); seq_printf(m, "\t minor_features3: 0x%08x\n", gpu->identity.minor_features3); + seq_printf(m, "\t minor_features4: 0x%08x\n", + gpu->identity.minor_features4); + seq_printf(m, "\t minor_features5: 0x%08x\n", + gpu->identity.minor_features5); seq_puts(m, "\tspecs\n"); seq_printf(m, "\t stream_count: %d\n", @@ -664,6 +727,8 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) gpu->identity.instruction_count); seq_printf(m, "\t num_constants: %d\n", gpu->identity.num_constants); + seq_printf(m, "\t varyings_count: %d\n", + gpu->identity.varyings_count); seq_printf(m, "\taxi: 0x%08x\n", axi); seq_printf(m, "\tidle: 0x%08x\n", idle); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index c75d50359ab0..f233ac4c7c1c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -46,6 +46,12 @@ struct etnaviv_chip_identity { /* Supported minor feature 3 fields. */ u32 minor_features3; + /* Supported minor feature 4 fields. */ + u32 minor_features4; + + /* Supported minor feature 5 fields. */ + u32 minor_features5; + /* Number of streams supported. */ u32 stream_count; @@ -75,6 +81,9 @@ struct etnaviv_chip_identity { /* Buffer size */ u32 buffer_size; + + /* Number of varyings */ + u8 varyings_count; }; struct etnaviv_event { diff --git a/drivers/gpu/drm/etnaviv/state_hi.xml.h b/drivers/gpu/drm/etnaviv/state_hi.xml.h index 0064f2640396..6a7de5f1454a 100644 --- a/drivers/gpu/drm/etnaviv/state_hi.xml.h +++ b/drivers/gpu/drm/etnaviv/state_hi.xml.h @@ -8,8 +8,8 @@ http://0x04.net/cgit/index.cgi/rules-ng-ng git clone git://0x04.net/rules-ng-ng The rules-ng-ng source files this header was generated from are: -- state_hi.xml ( 23420 bytes, from 2015-03-25 11:47:21) -- common.xml ( 18437 bytes, from 2015-03-25 11:27:41) +- state_hi.xml ( 24309 bytes, from 2015-12-12 09:02:53) +- common.xml ( 18437 bytes, from 2015-12-12 09:02:53) Copyright (C) 2015 */ @@ -182,8 +182,25 @@ Copyright (C) 2015 #define VIVS_HI_CHIP_MINOR_FEATURE_3 0x00000088 +#define VIVS_HI_CHIP_SPECS_3 0x0000008c +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__MASK 0x000001f0 +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__SHIFT 4 +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__MASK) +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__MASK 0x00000007 +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__SHIFT 0 +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__MASK) + #define VIVS_HI_CHIP_MINOR_FEATURE_4 0x00000094 +#define VIVS_HI_CHIP_SPECS_4 0x0000009c +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__MASK 0x0001f000 +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__SHIFT 12 +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__MASK) + +#define VIVS_HI_CHIP_MINOR_FEATURE_5 0x000000a0 + +#define VIVS_HI_CHIP_PRODUCT_ID 0x000000a8 + #define VIVS_PM 0x00000000 #define VIVS_PM_POWER_CONTROLS 0x00000100 @@ -206,6 +223,11 @@ Copyright (C) 2015 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_FE 0x00000001 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_DE 0x00000002 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_PE 0x00000004 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_SH 0x00000008 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_PA 0x00000010 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_SE 0x00000020 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_RA 0x00000040 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_TX 0x00000080 #define VIVS_PM_PULSE_EATER 0x0000010c diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 6bfc46369db1..367a916f364e 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -304,18 +304,10 @@ void dce6_dp_audio_set_dto(struct radeon_device *rdev, unsigned int div = (RREG32(DENTIST_DISPCLK_CNTL) & DENTIST_DPREFCLK_WDIVIDER_MASK) >> DENTIST_DPREFCLK_WDIVIDER_SHIFT; - - if (div < 128 && div >= 96) - div -= 64; - else if (div >= 64) - div = div / 2 - 16; - else if (div >= 8) - div /= 4; - else - div = 0; + div = radeon_audio_decode_dfs_div(div); if (div) - clock = rdev->clock.gpupll_outputfreq * 10 / div; + clock = clock * 100 / div; WREG32(DCE8_DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCE8_DCCG_AUDIO_DTO1_MODULE, clock); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 9953356fe263..3cf04a2f44bb 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -289,6 +289,16 @@ void dce4_dp_audio_set_dto(struct radeon_device *rdev, * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ + if (ASIC_IS_DCE41(rdev)) { + unsigned int div = (RREG32(DCE41_DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = 100 * clock / div; + } + WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCCG_AUDIO_DTO1_MODULE, clock); } diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 4aa5f755572b..13b6029d65cc 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -511,6 +511,11 @@ #define DCCG_AUDIO_DTO1_CNTL 0x05cc # define DCCG_AUDIO_DTO1_USE_512FBR_DTO (1 << 3) +#define DCE41_DENTIST_DISPCLK_CNTL 0x049c +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + /* DCE 4.0 AFMT */ #define HDMI_CONTROL 0x7030 # define HDMI_KEEPOUT_MODE (1 << 0) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 5ae6db98aa4d..78a51b3eda10 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -268,7 +268,7 @@ struct radeon_clock { uint32_t current_dispclk; uint32_t dp_extclk; uint32_t max_pixel_clock; - uint32_t gpupll_outputfreq; + uint32_t vco_freq; }; /* diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 08fc1b5effa8..de9a2ffcf5f7 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -1106,6 +1106,31 @@ union firmware_info { ATOM_FIRMWARE_INFO_V2_2 info_22; }; +union igp_info { + struct _ATOM_INTEGRATED_SYSTEM_INFO info; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; +}; + +static void radeon_atombios_get_dentist_vco_freq(struct radeon_device *rdev) +{ + struct radeon_mode_info *mode_info = &rdev->mode_info; + int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo); + union igp_info *igp_info; + u8 frev, crev; + u16 data_offset; + + if (atom_parse_data_header(mode_info->atom_context, index, NULL, + &frev, &crev, &data_offset)) { + igp_info = (union igp_info *)(mode_info->atom_context->bios + + data_offset); + rdev->clock.vco_freq = + le32_to_cpu(igp_info->info_6.ulDentistVCOFreq); + } +} + bool radeon_atom_get_clock_info(struct drm_device *dev) { struct radeon_device *rdev = dev->dev_private; @@ -1257,12 +1282,18 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) rdev->mode_info.firmware_flags = le16_to_cpu(firmware_info->info.usFirmwareCapability.susAccess); - if (ASIC_IS_DCE8(rdev)) { - rdev->clock.gpupll_outputfreq = + if (ASIC_IS_DCE8(rdev)) + rdev->clock.vco_freq = le32_to_cpu(firmware_info->info_22.ulGPUPLL_OutputFreq); - if (rdev->clock.gpupll_outputfreq == 0) - rdev->clock.gpupll_outputfreq = 360000; /* 3.6 GHz */ - } + else if (ASIC_IS_DCE5(rdev)) + rdev->clock.vco_freq = rdev->clock.current_dispclk; + else if (ASIC_IS_DCE41(rdev)) + radeon_atombios_get_dentist_vco_freq(rdev); + else + rdev->clock.vco_freq = rdev->clock.current_dispclk; + + if (rdev->clock.vco_freq == 0) + rdev->clock.vco_freq = 360000; /* 3.6 GHz */ return true; } @@ -1270,14 +1301,6 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) return false; } -union igp_info { - struct _ATOM_INTEGRATED_SYSTEM_INFO info; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; -}; - bool radeon_atombios_sideport_present(struct radeon_device *rdev) { struct radeon_mode_info *mode_info = &rdev->mode_info; diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 2c02e99b5f95..b214663b370d 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -739,9 +739,6 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector = - radeon_connector->con_priv; if (!dig || !dig->afmt) return; @@ -753,10 +750,7 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, radeon_audio_write_speaker_allocation(encoder); radeon_audio_write_sad_regs(encoder); radeon_audio_write_latency_fields(encoder, mode); - if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) - radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); - else - radeon_audio_set_dto(encoder, dig_connector->dp_clock); + radeon_audio_set_dto(encoder, rdev->clock.vco_freq * 10); radeon_audio_set_audio_packet(encoder); radeon_audio_select_pin(encoder); @@ -781,3 +775,15 @@ void radeon_audio_dpms(struct drm_encoder *encoder, int mode) if (radeon_encoder->audio && radeon_encoder->audio->dpms) radeon_encoder->audio->dpms(encoder, mode == DRM_MODE_DPMS_ON); } + +unsigned int radeon_audio_decode_dfs_div(unsigned int div) +{ + if (div >= 8 && div < 64) + return (div - 8) * 25 + 200; + else if (div >= 64 && div < 96) + return (div - 64) * 50 + 1600; + else if (div >= 96 && div < 128) + return (div - 96) * 100 + 3200; + else + return 0; +} diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h index 059cc3012062..5c70cceaa4a6 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.h +++ b/drivers/gpu/drm/radeon/radeon_audio.h @@ -79,5 +79,6 @@ void radeon_audio_fini(struct radeon_device *rdev); void radeon_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode); void radeon_audio_dpms(struct drm_encoder *encoder, int mode); +unsigned int radeon_audio_decode_dfs_div(unsigned int div); #endif diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b3bb92368ae0..298ea1c453c3 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1670,8 +1670,10 @@ int radeon_modeset_init(struct radeon_device *rdev) /* setup afmt */ radeon_afmt_init(rdev); - radeon_fbdev_init(rdev); - drm_kms_helper_poll_init(rdev->ddev); + if (!list_empty(&rdev->ddev->mode_config.connector_list)) { + radeon_fbdev_init(rdev); + drm_kms_helper_poll_init(rdev->ddev); + } /* do pm late init */ ret = radeon_pm_late_init(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 3dcc5733ff69..e26c963f2e93 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -663,6 +663,7 @@ int radeon_gem_va_ioctl(struct drm_device *dev, void *data, bo_va = radeon_vm_bo_find(&fpriv->vm, rbo); if (!bo_va) { args->operation = RADEON_VA_RESULT_ERROR; + radeon_bo_unreserve(rbo); drm_gem_object_unreference_unlocked(gobj); return -ENOENT; } diff --git a/drivers/gpu/drm/radeon/vce_v1_0.c b/drivers/gpu/drm/radeon/vce_v1_0.c index 07a0d378e122..a01efe39a820 100644 --- a/drivers/gpu/drm/radeon/vce_v1_0.c +++ b/drivers/gpu/drm/radeon/vce_v1_0.c @@ -178,12 +178,12 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) return -EINVAL; } - for (i = 0; i < sign->num; ++i) { - if (sign->val[i].chip_id == chip_id) + for (i = 0; i < le32_to_cpu(sign->num); ++i) { + if (le32_to_cpu(sign->val[i].chip_id) == chip_id) break; } - if (i == sign->num) + if (i == le32_to_cpu(sign->num)) return -EINVAL; data += (256 - 64) / 4; @@ -191,18 +191,18 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) data[1] = sign->val[i].nonce[1]; data[2] = sign->val[i].nonce[2]; data[3] = sign->val[i].nonce[3]; - data[4] = sign->len + 64; + data[4] = cpu_to_le32(le32_to_cpu(sign->len) + 64); memset(&data[5], 0, 44); memcpy(&data[16], &sign[1], rdev->vce_fw->size - sizeof(*sign)); - data += data[4] / 4; + data += le32_to_cpu(data[4]) / 4; data[0] = sign->val[i].sigval[0]; data[1] = sign->val[i].sigval[1]; data[2] = sign->val[i].sigval[2]; data[3] = sign->val[i].sigval[3]; - rdev->vce.keyselect = sign->val[i].keyselect; + rdev->vce.keyselect = le32_to_cpu(sign->val[i].keyselect); return 0; } diff --git a/drivers/gpu/drm/rockchip/Makefile b/drivers/gpu/drm/rockchip/Makefile index d1dc0f7b01db..f6a809afceec 100644 --- a/drivers/gpu/drm/rockchip/Makefile +++ b/drivers/gpu/drm/rockchip/Makefile @@ -2,11 +2,11 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -rockchipdrm-y := rockchip_drm_drv.o rockchip_drm_fb.o rockchip_drm_fbdev.o \ - rockchip_drm_gem.o +rockchipdrm-y := rockchip_drm_drv.o rockchip_drm_fb.o \ + rockchip_drm_gem.o rockchip_drm_vop.o +rockchipdrm-$(CONFIG_DRM_FBDEV_EMULATION) += rockchip_drm_fbdev.o obj-$(CONFIG_ROCKCHIP_DW_HDMI) += dw_hdmi-rockchip.o obj-$(CONFIG_ROCKCHIP_DW_MIPI_DSI) += dw-mipi-dsi.o -obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o rockchip_drm_vop.o \ - rockchip_vop_reg.o +obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o rockchip_vop_reg.o diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c index 7bfe243c6173..f8f8f29fb7c3 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c @@ -461,10 +461,11 @@ static int dw_mipi_dsi_phy_init(struct dw_mipi_dsi *dsi) static int dw_mipi_dsi_get_lane_bps(struct dw_mipi_dsi *dsi) { - unsigned int bpp, i, pre; + unsigned int i, pre; unsigned long mpclk, pllref, tmp; unsigned int m = 1, n = 1, target_mbps = 1000; unsigned int max_mbps = dptdin_map[ARRAY_SIZE(dptdin_map) - 1].max_mbps; + int bpp; bpp = mipi_dsi_pixel_format_to_bpp(dsi->format); if (bpp < 0) { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 8397d1b62ef9..a0d51ccb6ea4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -55,14 +55,12 @@ int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, return arm_iommu_attach_device(dev, mapping); } -EXPORT_SYMBOL_GPL(rockchip_drm_dma_attach_device); void rockchip_drm_dma_detach_device(struct drm_device *drm_dev, struct device *dev) { arm_iommu_detach_device(dev); } -EXPORT_SYMBOL_GPL(rockchip_drm_dma_detach_device); int rockchip_register_crtc_funcs(struct drm_crtc *crtc, const struct rockchip_crtc_funcs *crtc_funcs) @@ -77,7 +75,6 @@ int rockchip_register_crtc_funcs(struct drm_crtc *crtc, return 0; } -EXPORT_SYMBOL_GPL(rockchip_register_crtc_funcs); void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc) { @@ -89,7 +86,6 @@ void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc) priv->crtc_funcs[pipe] = NULL; } -EXPORT_SYMBOL_GPL(rockchip_unregister_crtc_funcs); static struct drm_crtc *rockchip_crtc_from_pipe(struct drm_device *drm, int pipe) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f7844883cb76..3b8f652698f8 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -39,7 +39,6 @@ struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb, return rk_fb->obj[plane]; } -EXPORT_SYMBOL_GPL(rockchip_fb_get_gem_obj); static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb) { @@ -177,8 +176,23 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); } +/* + * We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066 + * have hardware counters for neither vblanks nor scanlines, which results in + * a race where: + * | <-- HW vsync irq and reg take effect + * plane_commit --> | + * get_vblank and wait --> | + * | <-- handle_vblank, vblank->count + 1 + * cleanup_fb --> | + * iommu crash --> | + * | <-- HW vsync irq and reg take effect + * + * This function is equivalent but uses rockchip_crtc_wait_for_update() instead + * of waiting for vblank_count to change. + */ static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +208,10 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue; + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) + continue; + ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue; @@ -241,7 +259,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit) drm_atomic_helper_commit_planes(dev, state, true); - rockchip_atomic_wait_for_complete(state); + rockchip_atomic_wait_for_complete(dev, state); drm_atomic_helper_cleanup_planes(dev, state); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h index 50432e9b5b37..73718c5f5bbf 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h @@ -15,7 +15,18 @@ #ifndef _ROCKCHIP_DRM_FBDEV_H #define _ROCKCHIP_DRM_FBDEV_H +#ifdef CONFIG_DRM_FBDEV_EMULATION int rockchip_drm_fbdev_init(struct drm_device *dev); void rockchip_drm_fbdev_fini(struct drm_device *dev); +#else +static inline int rockchip_drm_fbdev_init(struct drm_device *dev) +{ + return 0; +} + +static inline void rockchip_drm_fbdev_fini(struct drm_device *dev) +{ +} +#endif #endif /* _ROCKCHIP_DRM_FBDEV_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index d908321b94ce..18e07338c6e5 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -234,13 +234,8 @@ int rockchip_gem_dumb_create(struct drm_file *file_priv, /* * align to 64 bytes since Mali requires it. */ - min_pitch = ALIGN(min_pitch, 64); - - if (args->pitch < min_pitch) - args->pitch = min_pitch; - - if (args->size < args->pitch * args->height) - args->size = args->pitch * args->height; + args->pitch = ALIGN(min_pitch, 64); + args->size = args->pitch * args->height; rk_obj = rockchip_gem_create_with_handle(file_priv, dev, args->size, &args->handle); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 46c2a8dfd8aa..fd370548d7d7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -43,8 +43,8 @@ #define REG_SET(x, base, reg, v, mode) \ __REG_SET_##mode(x, base + reg.offset, reg.mask, reg.shift, v) -#define REG_SET_MASK(x, base, reg, v, mode) \ - __REG_SET_##mode(x, base + reg.offset, reg.mask, reg.shift, v) +#define REG_SET_MASK(x, base, reg, mask, v, mode) \ + __REG_SET_##mode(x, base + reg.offset, mask, reg.shift, v) #define VOP_WIN_SET(x, win, name, v) \ REG_SET(x, win->base, win->phy->name, v, RELAXED) @@ -58,16 +58,18 @@ #define VOP_INTR_GET(vop, name) \ vop_read_reg(vop, 0, &vop->data->ctrl->name) -#define VOP_INTR_SET(vop, name, v) \ - REG_SET(vop, 0, vop->data->intr->name, v, NORMAL) +#define VOP_INTR_SET(vop, name, mask, v) \ + REG_SET_MASK(vop, 0, vop->data->intr->name, mask, v, NORMAL) #define VOP_INTR_SET_TYPE(vop, name, type, v) \ do { \ - int i, reg = 0; \ + int i, reg = 0, mask = 0; \ for (i = 0; i < vop->data->intr->nintrs; i++) { \ - if (vop->data->intr->intrs[i] & type) \ + if (vop->data->intr->intrs[i] & type) { \ reg |= (v) << i; \ + mask |= 1 << i; \ + } \ } \ - VOP_INTR_SET(vop, name, reg); \ + VOP_INTR_SET(vop, name, mask, reg); \ } while (0) #define VOP_INTR_GET_TYPE(vop, name, type) \ vop_get_intr_type(vop, &vop->data->intr->name, type) diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index 424d515ffcda..314ff71db978 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -144,19 +144,16 @@ int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused) } #endif /* CONFIG_DEBUG_FS */ -/* - * Asks the firmware to turn on power to the V3D engine. - * - * This may be doable with just the clocks interface, though this - * packet does some other register setup from the firmware, too. - */ int vc4_v3d_set_power(struct vc4_dev *vc4, bool on) { - if (on) - return pm_generic_poweroff(&vc4->v3d->pdev->dev); - else - return pm_generic_resume(&vc4->v3d->pdev->dev); + /* XXX: This interface is needed for GPU reset, and the way to + * do it is to turn our power domain off and back on. We + * can't just reset from within the driver, because the reset + * bits are in the power domain's register area, and get set + * during the poweron process. + */ + return 0; } static void vc4_v3d_init_hw(struct drm_device *dev) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index c49812b80dd0..24fb348a44e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -25,6 +25,7 @@ * **************************************************************************/ #include <linux/module.h> +#include <linux/console.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -1538,6 +1539,12 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static int __init vmwgfx_init(void) { int ret; + +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force()) + return -EINVAL; +#endif + ret = drm_pci_init(&driver, &vmw_pci_driver); if (ret) DRM_ERROR("Failed initializing DRM.\n"); diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index c8487894b312..c43318d3416e 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -932,6 +932,17 @@ MODULE_DEVICE_TABLE(dmi, i8k_dmi_table); static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { { /* + * CPU fan speed going up and down on Dell Studio XPS 8000 + * for unknown reasons. + */ + .ident = "Dell Studio XPS 8000", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8000"), + }, + }, + { + /* * CPU fan speed going up and down on Dell Studio XPS 8100 * for unknown reasons. */ diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c index f77eb971ce95..4f695d8fcafa 100644 --- a/drivers/hwmon/fam15h_power.c +++ b/drivers/hwmon/fam15h_power.c @@ -90,7 +90,15 @@ static ssize_t show_power(struct device *dev, pci_bus_read_config_dword(f4->bus, PCI_DEVFN(PCI_SLOT(f4->devfn), 5), REG_TDP_LIMIT3, &val); - tdp_limit = val >> 16; + /* + * On Carrizo and later platforms, ApmTdpLimit bit field + * is extended to 16:31 from 16:28. + */ + if (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model >= 0x60) + tdp_limit = val >> 16; + else + tdp_limit = (val >> 16) & 0x1fff; + curr_pwr_watts = ((u64)(tdp_limit + data->base_tdp)) << running_avg_range; curr_pwr_watts -= running_avg_capture; diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index ba9732c236c5..10fbd6d841e0 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -874,7 +874,8 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) i2c_set_adapdata(adap, dev); i2c_dw_disable_int(dev); - r = devm_request_irq(dev->dev, dev->irq, i2c_dw_isr, IRQF_SHARED, + r = devm_request_irq(dev->dev, dev->irq, i2c_dw_isr, + IRQF_SHARED | IRQF_COND_SUSPEND, dev_name(dev->dev), dev); if (r) { dev_err(dev->dev, "failure requesting irq %i: %d\n", diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index e04598595073..93f2895383ee 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -137,10 +137,11 @@ static const struct dmi_system_id piix4_dmi_ibm[] = { }; /* SB800 globals */ +static DEFINE_MUTEX(piix4_mutex_sb800); static const char *piix4_main_port_names_sb800[PIIX4_MAX_ADAPTERS] = { - "SDA0", "SDA2", "SDA3", "SDA4" + " port 0", " port 2", " port 3", " port 4" }; -static const char *piix4_aux_port_name_sb800 = "SDA1"; +static const char *piix4_aux_port_name_sb800 = " port 1"; struct i2c_piix4_adapdata { unsigned short smba; @@ -148,7 +149,6 @@ struct i2c_piix4_adapdata { /* SB800 */ bool sb800_main; unsigned short port; - struct mutex *mutex; }; static int piix4_setup(struct pci_dev *PIIX4_dev, @@ -275,10 +275,12 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, else smb_en = (aux) ? 0x28 : 0x2c; + mutex_lock(&piix4_mutex_sb800); outb_p(smb_en, SB800_PIIX4_SMB_IDX); smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); outb_p(smb_en + 1, SB800_PIIX4_SMB_IDX); smba_en_hi = inb_p(SB800_PIIX4_SMB_IDX + 1); + mutex_unlock(&piix4_mutex_sb800); if (!smb_en) { smb_en_status = smba_en_lo & 0x10; @@ -559,7 +561,7 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, u8 port; int retval; - mutex_lock(adapdata->mutex); + mutex_lock(&piix4_mutex_sb800); outb_p(SB800_PIIX4_PORT_IDX, SB800_PIIX4_SMB_IDX); smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); @@ -574,7 +576,7 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1); - mutex_unlock(adapdata->mutex); + mutex_unlock(&piix4_mutex_sb800); return retval; } @@ -625,6 +627,7 @@ static struct i2c_adapter *piix4_main_adapters[PIIX4_MAX_ADAPTERS]; static struct i2c_adapter *piix4_aux_adapter; static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, + bool sb800_main, unsigned short port, const char *name, struct i2c_adapter **padap) { struct i2c_adapter *adap; @@ -639,7 +642,8 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, adap->owner = THIS_MODULE; adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; - adap->algo = &smbus_algorithm; + adap->algo = sb800_main ? &piix4_smbus_algorithm_sb800 + : &smbus_algorithm; adapdata = kzalloc(sizeof(*adapdata), GFP_KERNEL); if (adapdata == NULL) { @@ -649,12 +653,14 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, } adapdata->smba = smba; + adapdata->sb800_main = sb800_main; + adapdata->port = port; /* set up the sysfs linkage to our parent device */ adap->dev.parent = &dev->dev; snprintf(adap->name, sizeof(adap->name), - "SMBus PIIX4 adapter %s at %04x", name, smba); + "SMBus PIIX4 adapter%s at %04x", name, smba); i2c_set_adapdata(adap, adapdata); @@ -673,30 +679,16 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba) { - struct mutex *mutex; struct i2c_piix4_adapdata *adapdata; int port; int retval; - mutex = kzalloc(sizeof(*mutex), GFP_KERNEL); - if (mutex == NULL) - return -ENOMEM; - - mutex_init(mutex); - for (port = 0; port < PIIX4_MAX_ADAPTERS; port++) { - retval = piix4_add_adapter(dev, smba, + retval = piix4_add_adapter(dev, smba, true, port, piix4_main_port_names_sb800[port], &piix4_main_adapters[port]); if (retval < 0) goto error; - - piix4_main_adapters[port]->algo = &piix4_smbus_algorithm_sb800; - - adapdata = i2c_get_adapdata(piix4_main_adapters[port]); - adapdata->sb800_main = true; - adapdata->port = port; - adapdata->mutex = mutex; } return retval; @@ -714,19 +706,20 @@ error: } } - kfree(mutex); - return retval; } static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) { int retval; + bool is_sb800 = false; if ((dev->vendor == PCI_VENDOR_ID_ATI && dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && dev->revision >= 0x40) || dev->vendor == PCI_VENDOR_ID_AMD) { + is_sb800 = true; + if (!request_region(SB800_PIIX4_SMB_IDX, 2, "smba_idx")) { dev_err(&dev->dev, "SMBus base address index region 0x%x already in use!\n", @@ -756,7 +749,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) return retval; /* Try to register main SMBus adapter, give up if we can't */ - retval = piix4_add_adapter(dev, retval, "main", + retval = piix4_add_adapter(dev, retval, false, 0, "", &piix4_main_adapters[0]); if (retval < 0) return retval; @@ -783,7 +776,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) if (retval > 0) { /* Try to add the aux adapter if it exists, * piix4_add_adapter will clean up if this fails */ - piix4_add_adapter(dev, retval, piix4_aux_port_name_sb800, + piix4_add_adapter(dev, retval, false, 0, + is_sb800 ? piix4_aux_port_name_sb800 : "", &piix4_aux_adapter); } @@ -798,10 +792,8 @@ static void piix4_adap_remove(struct i2c_adapter *adap) i2c_del_adapter(adap); if (adapdata->port == 0) { release_region(adapdata->smba, SMBIOSIZE); - if (adapdata->sb800_main) { - kfree(adapdata->mutex); + if (adapdata->sb800_main) release_region(SB800_PIIX4_SMB_IDX, 2); - } } kfree(adapdata); kfree(adap); diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index cb32b593f1c5..36607d52fee0 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return -ENOMEM; rx = adis->buffer; - tx = rx + indio_dev->scan_bytes; + tx = rx + scan_count; spi_message_init(&adis->msg); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 539b0dea8034..e5e223938eec 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2049,7 +2049,7 @@ static void do_attach(struct iommu_dev_data *dev_data, /* Update device table */ set_dte_entry(dev_data->devid, domain, ats); if (alias != dev_data->devid) - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(alias, domain, ats); device_flush_dte(dev_data); } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac7387686ddc..986a53e3eb96 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1489,7 +1489,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) { struct pci_dev *pdev; - if (dev_is_pci(info->dev)) + if (!dev_is_pci(info->dev)) return; pdev = to_pci_dev(info->dev); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 8bbcbfe7695c..381ca5a37a7b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -25,6 +25,7 @@ #include <linux/sizes.h> #include <linux/slab.h> #include <linux/types.h> +#include <linux/dma-mapping.h> #include <asm/barrier.h> diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 715923d5236c..fb50911b3940 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -159,6 +159,7 @@ config TB10X_IRQC config TS4800_IRQ tristate "TS-4800 IRQ controller" select IRQ_DOMAIN + depends on HAS_IOMEM help Support for the TS-4800 FPGA IRQ controller diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index b12a5d58546f..37199b9b2cfa 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -86,7 +86,7 @@ int aic_common_set_priority(int priority, unsigned *val) priority > AT91_AIC_IRQ_MAX_PRIORITY) return -EINVAL; - *val &= AT91_AIC_PRIOR; + *val &= ~AT91_AIC_PRIOR; *val |= priority; return 0; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index e23d1d18f9d6..3447549fcc93 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -875,6 +875,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } alloc_size = (1 << order) * PAGE_SIZE; +retry_alloc_baser: alloc_pages = (alloc_size / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { alloc_pages = GITS_BASER_PAGES_MAX; @@ -938,13 +939,16 @@ retry_baser: * size and retry. If we reach 4K, then * something is horribly wrong... */ + free_pages((unsigned long)base, order); + its->tables[i] = NULL; + switch (psz) { case SZ_16K: psz = SZ_4K; - goto retry_baser; + goto retry_alloc_baser; case SZ_64K: psz = SZ_16K; - goto retry_baser; + goto retry_alloc_baser; } } diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index c22e2d40cb30..efe50845939d 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -241,6 +241,7 @@ static int __init asm9260_of_init(struct device_node *np, writel(0, icoll_priv.intr + i); icoll_add_domain(np, ASM9260_NUM_IRQS); + set_handle_irq(icoll_handle_irq); return 0; } diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c index c71914e8f596..5dc5a760c723 100644 --- a/drivers/irqchip/irq-s3c24xx.c +++ b/drivers/irqchip/irq-s3c24xx.c @@ -605,7 +605,7 @@ err: return ERR_PTR(ret); } -static struct s3c_irq_data init_eint[32] = { +static struct s3c_irq_data __maybe_unused init_eint[32] = { { .type = S3C_IRQTYPE_NONE, }, /* reserved */ { .type = S3C_IRQTYPE_NONE, }, /* reserved */ { .type = S3C_IRQTYPE_NONE, }, /* reserved */ diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 706e3ff67f8b..7ee21ae305ae 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -679,18 +679,6 @@ u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in) return __of_msi_map_rid(dev, &msi_np, rid_in); } -static struct irq_domain *__of_get_msi_domain(struct device_node *np, - enum irq_domain_bus_token token) -{ - struct irq_domain *d; - - d = irq_find_matching_host(np, token); - if (!d) - d = irq_find_host(np); - - return d; -} - /** * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain * @dev: device for which the mapping is to be done. @@ -706,7 +694,7 @@ struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid) struct device_node *np = NULL; __of_msi_map_rid(dev, &np, rid); - return __of_get_msi_domain(np, DOMAIN_BUS_PCI_MSI); + return irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI); } /** @@ -730,7 +718,7 @@ struct irq_domain *of_msi_get_domain(struct device *dev, /* Check for a single msi-parent property */ msi_np = of_parse_phandle(np, "msi-parent", 0); if (msi_np && !of_property_read_bool(msi_np, "#msi-cells")) { - d = __of_get_msi_domain(msi_np, token); + d = irq_find_matching_host(msi_np, token); if (!d) of_node_put(msi_np); return d; @@ -744,7 +732,7 @@ struct irq_domain *of_msi_get_domain(struct device *dev, while (!of_parse_phandle_with_args(np, "msi-parent", "#msi-cells", index, &args)) { - d = __of_get_msi_domain(args.np, token); + d = irq_find_matching_host(args.np, token); if (d) return d; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 5f2fda12e006..fa49f9143b80 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -953,8 +953,10 @@ int acpiphp_enable_slot(struct acpiphp_slot *slot) { pci_lock_rescan_remove(); - if (slot->flags & SLOT_IS_GOING_AWAY) + if (slot->flags & SLOT_IS_GOING_AWAY) { + pci_unlock_rescan_remove(); return -ENODEV; + } /* configure all functions */ if (!(slot->flags & SLOT_ENABLED)) diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index c692dfebd0ba..50597f9522fe 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -139,11 +139,11 @@ static ssize_t chp_measurement_chars_read(struct file *filp, device = container_of(kobj, struct device, kobj); chp = to_channelpath(device); - if (!chp->cmg_chars) + if (chp->cmg == -1) return 0; - return memory_read_from_buffer(buf, count, &off, - chp->cmg_chars, sizeof(struct cmg_chars)); + return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars, + sizeof(chp->cmg_chars)); } static struct bin_attribute chp_measurement_chars_attr = { @@ -416,7 +416,8 @@ static void chp_release(struct device *dev) * chp_update_desc - update channel-path description * @chp - channel-path * - * Update the channel-path description of the specified channel-path. + * Update the channel-path description of the specified channel-path + * including channel measurement related information. * Return zero on success, non-zero otherwise. */ int chp_update_desc(struct channel_path *chp) @@ -428,8 +429,10 @@ int chp_update_desc(struct channel_path *chp) return rc; rc = chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1); + if (rc) + return rc; - return rc; + return chsc_get_channel_measurement_chars(chp); } /** @@ -466,14 +469,6 @@ int chp_new(struct chp_id chpid) ret = -ENODEV; goto out_free; } - /* Get channel-measurement characteristics. */ - if (css_chsc_characteristics.scmc && css_chsc_characteristics.secm) { - ret = chsc_get_channel_measurement_chars(chp); - if (ret) - goto out_free; - } else { - chp->cmg = -1; - } dev_set_name(&chp->dev, "chp%x.%02x", chpid.cssid, chpid.id); /* make it known to the system */ diff --git a/drivers/s390/cio/chp.h b/drivers/s390/cio/chp.h index 4efd5b867cc3..af0232290dc4 100644 --- a/drivers/s390/cio/chp.h +++ b/drivers/s390/cio/chp.h @@ -48,7 +48,7 @@ struct channel_path { /* Channel-measurement related stuff: */ int cmg; int shared; - void *cmg_chars; + struct cmg_chars cmg_chars; }; /* Return channel_path struct for given chpid. */ diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index a831d18596a5..c424c0c7367e 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/device.h> +#include <linux/mutex.h> #include <linux/pci.h> #include <asm/cio.h> @@ -224,8 +225,9 @@ out_unreg: void chsc_chp_offline(struct chp_id chpid) { - char dbf_txt[15]; + struct channel_path *chp = chpid_to_chp(chpid); struct chp_link link; + char dbf_txt[15]; sprintf(dbf_txt, "chpr%x.%02x", chpid.cssid, chpid.id); CIO_TRACE_EVENT(2, dbf_txt); @@ -236,6 +238,11 @@ void chsc_chp_offline(struct chp_id chpid) link.chpid = chpid; /* Wait until previous actions have settled. */ css_wait_for_slow_path(); + + mutex_lock(&chp->lock); + chp_update_desc(chp); + mutex_unlock(&chp->lock); + for_each_subchannel_staged(s390_subchannel_remove_chpid, NULL, &link); } @@ -690,8 +697,9 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow) void chsc_chp_online(struct chp_id chpid) { - char dbf_txt[15]; + struct channel_path *chp = chpid_to_chp(chpid); struct chp_link link; + char dbf_txt[15]; sprintf(dbf_txt, "cadd%x.%02x", chpid.cssid, chpid.id); CIO_TRACE_EVENT(2, dbf_txt); @@ -701,6 +709,11 @@ void chsc_chp_online(struct chp_id chpid) link.chpid = chpid; /* Wait until previous actions have settled. */ css_wait_for_slow_path(); + + mutex_lock(&chp->lock); + chp_update_desc(chp); + mutex_unlock(&chp->lock); + for_each_subchannel_staged(__s390_process_res_acc, NULL, &link); css_schedule_reprobe(); @@ -967,22 +980,19 @@ static void chsc_initialize_cmg_chars(struct channel_path *chp, u8 cmcv, struct cmg_chars *chars) { - struct cmg_chars *cmg_chars; int i, mask; - cmg_chars = chp->cmg_chars; for (i = 0; i < NR_MEASUREMENT_CHARS; i++) { mask = 0x80 >> (i + 3); if (cmcv & mask) - cmg_chars->values[i] = chars->values[i]; + chp->cmg_chars.values[i] = chars->values[i]; else - cmg_chars->values[i] = 0; + chp->cmg_chars.values[i] = 0; } } int chsc_get_channel_measurement_chars(struct channel_path *chp) { - struct cmg_chars *cmg_chars; int ccode, ret; struct { @@ -1006,10 +1016,11 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp) u32 data[NR_MEASUREMENT_CHARS]; } __attribute__ ((packed)) *scmc_area; - chp->cmg_chars = NULL; - cmg_chars = kmalloc(sizeof(*cmg_chars), GFP_KERNEL); - if (!cmg_chars) - return -ENOMEM; + chp->shared = -1; + chp->cmg = -1; + + if (!css_chsc_characteristics.scmc || !css_chsc_characteristics.secm) + return 0; spin_lock_irq(&chsc_page_lock); memset(chsc_page, 0, PAGE_SIZE); @@ -1031,25 +1042,19 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp) scmc_area->response.code); goto out; } - if (scmc_area->not_valid) { - chp->cmg = -1; - chp->shared = -1; + if (scmc_area->not_valid) goto out; - } + chp->cmg = scmc_area->cmg; chp->shared = scmc_area->shared; if (chp->cmg != 2 && chp->cmg != 3) { /* No cmg-dependent data. */ goto out; } - chp->cmg_chars = cmg_chars; chsc_initialize_cmg_chars(chp, scmc_area->cmcv, (struct cmg_chars *) &scmc_area->data); out: spin_unlock_irq(&chsc_page_lock); - if (!chp->cmg_chars) - kfree(cmg_chars); - return ret; } diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index 7b23f43c7b08..de1b6c1d172c 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -112,9 +112,10 @@ static inline int convert_error(struct zcrypt_device *zdev, atomic_set(&zcrypt_rescan_req, 1); zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; case REP82_ERROR_TRANSPORT_FAIL: case REP82_ERROR_MACHINE_FAILURE: @@ -123,16 +124,18 @@ static inline int convert_error(struct zcrypt_device *zdev, atomic_set(&zcrypt_rescan_req, 1); zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; default: zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 74edf2934e7c..eedfaa2cf715 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -336,9 +336,10 @@ static int convert_type80(struct zcrypt_device *zdev, /* The result is too short, the CEX2A card may not do that.. */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, t80h->code); + AP_QID_DEVICE(zdev->ap_dev->qid), + zdev->online, t80h->code); return -EAGAIN; /* repeat the request on a different device. */ } @@ -368,9 +369,9 @@ static int convert_response(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 9a2dd472c1cc..21959719daef 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -572,9 +572,9 @@ static int convert_type86_ica(struct zcrypt_device *zdev, return -EINVAL; zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, msg->hdr.reply_code); return -EAGAIN; /* repeat the request on a different device. */ } @@ -715,9 +715,9 @@ static int convert_response_ica(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -747,9 +747,9 @@ static int convert_response_xcrb(struct zcrypt_device *zdev, xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -773,9 +773,9 @@ static int convert_response_ep11_xcrb(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -800,9 +800,9 @@ static int convert_response_rng(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig index 37a0c7156087..b67661836c9f 100644 --- a/drivers/scsi/hisi_sas/Kconfig +++ b/drivers/scsi/hisi_sas/Kconfig @@ -1,5 +1,7 @@ config SCSI_HISI_SAS tristate "HiSilicon SAS" + depends on HAS_DMA + depends on ARM64 || COMPILE_TEST select SCSI_SAS_LIBSAS select BLK_DEV_INTEGRITY help diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4e08d1cd704d..bb669d32ccd0 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2893,7 +2893,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) rw_max = q->limits.io_opt = - logical_to_sectors(sdp, sdkp->opt_xfer_blocks); + sdkp->opt_xfer_blocks * sdp->sector_size; else rw_max = BLK_DEF_MAX_SECTORS; @@ -3268,8 +3268,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; - if (!sdkp) - return 0; /* this can happen */ + if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ + return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); @@ -3308,6 +3308,9 @@ static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + if (!sdkp->device->manage_start_stop) return 0; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8bd54a64efd6..64c867405ad4 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -144,6 +144,9 @@ static int sr_runtime_suspend(struct device *dev) { struct scsi_cd *cd = dev_get_drvdata(dev); + if (!cd) /* E.g.: runtime suspend following sr_remove() */ + return 0; + if (cd->media_present) return -EBUSY; else @@ -985,6 +988,7 @@ static int sr_remove(struct device *dev) scsi_autopm_get_device(cd->device); del_gendisk(cd->disk); + dev_set_drvdata(dev, NULL); mutex_lock(&sr_ref_mutex); kref_put(&cd->kref, sr_kref_release); diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index 79ac19246548..70b8f4fabfad 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -825,8 +825,7 @@ static void lcd_write_cmd_s(int cmd) lcd_send_serial(0x1F); /* R/W=W, RS=0 */ lcd_send_serial(cmd & 0x0F); lcd_send_serial((cmd >> 4) & 0x0F); - /* the shortest command takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest command takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -837,8 +836,7 @@ static void lcd_write_data_s(int data) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(data & 0x0F); lcd_send_serial((data >> 4) & 0x0F); - /* the shortest data takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest data takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -848,20 +846,19 @@ static void lcd_write_cmd_p8(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, cmd); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_CLR; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(120, 500); /* the shortest command takes at least 120 us */ + udelay(120); /* the shortest command takes at least 120 us */ spin_unlock_irq(&pprt_lock); } @@ -871,20 +868,19 @@ static void lcd_write_data_p8(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_SET; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(45, 100); /* the shortest data takes at least 45 us */ + udelay(45); /* the shortest data takes at least 45 us */ spin_unlock_irq(&pprt_lock); } @@ -894,7 +890,7 @@ static void lcd_write_cmd_tilcd(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the control port */ w_ctr(pprt, cmd); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -904,7 +900,7 @@ static void lcd_write_data_tilcd(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -947,7 +943,7 @@ static void lcd_clear_fast_s(void) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(' ' & 0x0F); lcd_send_serial((' ' >> 4) & 0x0F); - usleep_range(40, 100); /* the shortest data takes at least 40 us */ + udelay(40); /* the shortest data takes at least 40 us */ } spin_unlock_irq(&pprt_lock); @@ -971,7 +967,7 @@ static void lcd_clear_fast_p8(void) w_dtr(pprt, ' '); /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); bits.e = BIT_SET; bits.rs = BIT_SET; @@ -979,13 +975,13 @@ static void lcd_clear_fast_p8(void) set_ctrl_bits(); /* maintain the strobe during 40 us */ - usleep_range(40, 100); + udelay(40); bits.e = BIT_CLR; set_ctrl_bits(); /* the shortest data takes at least 45 us */ - usleep_range(45, 100); + udelay(45); } spin_unlock_irq(&pprt_lock); @@ -1007,7 +1003,7 @@ static void lcd_clear_fast_tilcd(void) for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) { /* present the data to the data port */ w_dtr(pprt, ' '); - usleep_range(60, 120); + udelay(60); } spin_unlock_irq(&pprt_lock); diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 63c59bc89b04..30cf973f326d 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -264,8 +264,9 @@ static struct notifier_block vt_notifier_block = { .notifier_call = vt_notifier_call, }; -static unsigned char get_attributes(u16 *pos) +static unsigned char get_attributes(struct vc_data *vc, u16 *pos) { + pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1); return (u_char) (scr_readw(pos) >> 8); } @@ -275,7 +276,7 @@ static void speakup_date(struct vc_data *vc) spk_y = spk_cy = vc->vc_y; spk_pos = spk_cp = vc->vc_pos; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) spk_pos); + spk_attr = get_attributes(vc, (u_short *)spk_pos); } static void bleep(u_short val) @@ -469,8 +470,12 @@ static u16 get_char(struct vc_data *vc, u16 *pos, u_char *attribs) u16 ch = ' '; if (vc && pos) { - u16 w = scr_readw(pos); - u16 c = w & 0xff; + u16 w; + u16 c; + + pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1); + w = scr_readw(pos); + c = w & 0xff; if (w & vc->vc_hi_font_mask) c |= 0x100; @@ -746,7 +751,7 @@ static int get_line(struct vc_data *vc) u_char tmp2; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) spk_pos); + spk_attr = get_attributes(vc, (u_short *)spk_pos); for (i = 0; i < vc->vc_cols; i++) { buf[i] = (u_char) get_char(vc, (u_short *) tmp, &tmp2); tmp += 2; @@ -811,7 +816,7 @@ static int say_from_to(struct vc_data *vc, u_long from, u_long to, u_short saved_punc_mask = spk_punc_mask; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) from); + spk_attr = get_attributes(vc, (u_short *)from); while (from < to) { buf[i++] = (char)get_char(vc, (u_short *) from, &tmp); from += 2; @@ -886,7 +891,7 @@ static int get_sentence_buf(struct vc_data *vc, int read_punc) sentmarks[bn][0] = &sentbuf[bn][0]; i = 0; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) start); + spk_attr = get_attributes(vc, (u_short *)start); while (start < end) { sentbuf[bn][i] = (char)get_char(vc, (u_short *) start, &tmp); @@ -1585,7 +1590,7 @@ static int count_highlight_color(struct vc_data *vc) u16 *ptr; for (ptr = start; ptr < end; ptr++) { - ch = get_attributes(ptr); + ch = get_attributes(vc, ptr); bg = (ch & 0x70) >> 4; speakup_console[vc_num]->ht.bgcount[bg]++; } diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index aa5ab6c80ed4..41ef099b7aa6 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -142,7 +142,9 @@ static void __speakup_paste_selection(struct work_struct *work) struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); - ld = tty_ldisc_ref_wait(tty); + ld = tty_ldisc_ref(tty); + if (!ld) + goto tty_unref; tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); @@ -162,6 +164,7 @@ static void __speakup_paste_selection(struct work_struct *work) tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); +tty_unref: tty_kref_put(tty); } diff --git a/drivers/staging/speakup/serialio.c b/drivers/staging/speakup/serialio.c index 3b5835b28128..a5bbb338f275 100644 --- a/drivers/staging/speakup/serialio.c +++ b/drivers/staging/speakup/serialio.c @@ -6,6 +6,11 @@ #include "spk_priv.h" #include "serialio.h" +#include <linux/serial_core.h> +/* WARNING: Do not change this to <linux/serial.h> without testing that + * SERIAL_PORT_DFNS does get defined to the appropriate value. */ +#include <asm/serial.h> + #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif @@ -23,9 +28,15 @@ const struct old_serial_port *spk_serial_init(int index) int baud = 9600, quot = 0; unsigned int cval = 0; int cflag = CREAD | HUPCL | CLOCAL | B9600 | CS8; - const struct old_serial_port *ser = rs_table + index; + const struct old_serial_port *ser; int err; + if (index >= ARRAY_SIZE(rs_table)) { + pr_info("no port info for ttyS%d\n", index); + return NULL; + } + ser = rs_table + index; + /* Divisor, bytesize and parity */ quot = ser->baud_base / baud; cval = cflag & (CSIZE | CSTOPB); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d9a5fc28fef4..b280abaad91b 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -269,16 +269,13 @@ static void n_tty_check_throttle(struct tty_struct *tty) static void n_tty_check_unthrottle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY && - tty->link->ldisc->ops->write_wakeup == n_tty_write_wakeup) { + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { if (chars_in_buffer(tty) > TTY_THRESHOLD_UNTHROTTLE) return; if (!tty->count) return; n_tty_kick_worker(tty); - n_tty_write_wakeup(tty->link); - if (waitqueue_active(&tty->link->write_wait)) - wake_up_interruptible_poll(&tty->link->write_wait, POLLOUT); + tty_wakeup(tty->link); return; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 4097f3f65b3b..e71ec78fc11e 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1379,6 +1379,9 @@ ce4100_serial_setup(struct serial_private *priv, #define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a #define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c +#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3 +#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4 + #define BYT_PRV_CLK 0x800 #define BYT_PRV_CLK_EN (1 << 0) #define BYT_PRV_CLK_M_VAL_SHIFT 1 @@ -1461,11 +1464,13 @@ byt_serial_setup(struct serial_private *priv, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_BYT_UART1: case PCI_DEVICE_ID_INTEL_BSW_UART1: + case PCI_DEVICE_ID_INTEL_BDW_UART1: rx_param->src_id = 3; tx_param->dst_id = 2; break; case PCI_DEVICE_ID_INTEL_BYT_UART2: case PCI_DEVICE_ID_INTEL_BSW_UART2: + case PCI_DEVICE_ID_INTEL_BDW_UART2: rx_param->src_id = 5; tx_param->dst_id = 4; break; @@ -2062,6 +2067,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART1, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, /* * ITE */ @@ -5506,6 +5525,16 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, pbn_byt }, + /* Intel Broadwell */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + /* * Intel Quark x1000 */ diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 892c92354745..5cec01c75691 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1463,13 +1463,13 @@ static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; - if (!tty->count) - return -EIO; - if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) return -EIO; + if (!tty->count) + return -EAGAIN; + if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; @@ -2065,7 +2065,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); - tty_lock(tty); + retval = tty_lock_interruptible(tty); + if (retval) { + if (retval == -EINTR) + retval = -ERESTARTSYS; + goto err_unref; + } /* safe to drop the kref from tty_driver_lookup_tty() */ tty_kref_put(tty); retval = tty_reopen(tty); @@ -2083,7 +2088,11 @@ retry_open: if (IS_ERR(tty)) { retval = PTR_ERR(tty); - goto err_file; + if (retval != -EAGAIN || signal_pending(current)) + goto err_file; + tty_free_file(filp); + schedule(); + goto retry_open; } tty_add_file(tty, filp); @@ -2152,6 +2161,7 @@ retry_open: return 0; err_unlock: mutex_unlock(&tty_mutex); +err_unref: /* after locks to avoid deadlock */ if (!IS_ERR_OR_NULL(driver)) tty_driver_kref_put(driver); @@ -2649,6 +2659,28 @@ static int tiocsetd(struct tty_struct *tty, int __user *p) } /** + * tiocgetd - get line discipline + * @tty: tty device + * @p: pointer to user data + * + * Retrieves the line discipline id directly from the ldisc. + * + * Locking: waits for ldisc reference (in case the line discipline + * is changing or the tty is being hungup) + */ + +static int tiocgetd(struct tty_struct *tty, int __user *p) +{ + struct tty_ldisc *ld; + int ret; + + ld = tty_ldisc_ref_wait(tty); + ret = put_user(ld->ops->num, p); + tty_ldisc_deref(ld); + return ret; +} + +/** * send_break - performed time break * @tty: device to break on * @duration: timeout in mS @@ -2874,7 +2906,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case TIOCGSID: return tiocgsid(tty, real_tty, p); case TIOCGETD: - return put_user(tty->ldisc->ops->num, (int __user *)p); + return tiocgetd(tty, p); case TIOCSETD: return tiocsetd(tty, p); case TIOCVHANGUP: diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index 77703a391207..d2f3c4cd697f 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -19,6 +19,14 @@ void __lockfunc tty_lock(struct tty_struct *tty) } EXPORT_SYMBOL(tty_lock); +int tty_lock_interruptible(struct tty_struct *tty) +{ + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) + return -EIO; + tty_kref_get(tty); + return mutex_lock_interruptible(&tty->legacy_mutex); +} + void __lockfunc tty_unlock(struct tty_struct *tty) { if (WARN(tty->magic != TTY_MAGIC, "U Bad %p\n", tty)) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e7cbc44eef57..bd51bdd0a7bf 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4250,6 +4250,7 @@ unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed) { return screenpos(vc, 2 * w_offset, viewed); } +EXPORT_SYMBOL_GPL(screen_pos); void getconsxy(struct vc_data *vc, unsigned char *p) { diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 82f25cc1c460..ecca316386f5 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -123,8 +123,8 @@ struct iommu_group *vfio_iommu_group_get(struct device *dev) /* * With noiommu enabled, an IOMMU group will be created for a device * that doesn't already have one and doesn't have an iommu_ops on their - * bus. We use iommu_present() again in the main code to detect these - * fake groups. + * bus. We set iommudata simply to be able to identify these groups + * as special use and for reclamation later. */ if (group || !noiommu || iommu_present(dev->bus)) return group; @@ -134,6 +134,7 @@ struct iommu_group *vfio_iommu_group_get(struct device *dev) return NULL; iommu_group_set_name(group, "vfio-noiommu"); + iommu_group_set_iommudata(group, &noiommu, NULL); ret = iommu_group_add_device(group, dev); iommu_group_put(group); if (ret) @@ -158,7 +159,7 @@ EXPORT_SYMBOL_GPL(vfio_iommu_group_get); void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) { #ifdef CONFIG_VFIO_NOIOMMU - if (!iommu_present(dev->bus)) + if (iommu_group_get_iommudata(group) == &noiommu) iommu_group_remove_device(dev); #endif @@ -190,16 +191,10 @@ static long vfio_noiommu_ioctl(void *iommu_data, return -ENOTTY; } -static int vfio_iommu_present(struct device *dev, void *unused) -{ - return iommu_present(dev->bus) ? 1 : 0; -} - static int vfio_noiommu_attach_group(void *iommu_data, struct iommu_group *iommu_group) { - return iommu_group_for_each_dev(iommu_group, NULL, - vfio_iommu_present) ? -EINVAL : 0; + return iommu_group_get_iommudata(iommu_group) == &noiommu ? 0 : -EINVAL; } static void vfio_noiommu_detach_group(void *iommu_data, @@ -323,8 +318,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, - bool iommu_present) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) { struct vfio_group *group, *tmp; struct device *dev; @@ -342,7 +336,9 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; - group->noiommu = !iommu_present; +#ifdef CONFIG_VFIO_NOIOMMU + group->noiommu = (iommu_group_get_iommudata(iommu_group) == &noiommu); +#endif group->nb.notifier_call = vfio_iommu_group_notifier; @@ -767,7 +763,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group, iommu_present(dev->bus)); + group = vfio_create_group(iommu_group); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 36205c27c4d0..f6bed86c17f9 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -545,6 +545,7 @@ err_enable_device: static void virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct device *dev = get_device(&vp_dev->vdev.dev); unregister_virtio_device(&vp_dev->vdev); @@ -554,6 +555,7 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) virtio_pci_modern_remove(vp_dev); pci_disable_device(pci_dev); + put_device(dev); } static struct pci_driver virtio_pci_driver = { diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index 945fc4327201..4ac2ca8a7656 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -242,7 +242,7 @@ static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); } -static struct cleancache_ops tmem_cleancache_ops = { +static const struct cleancache_ops tmem_cleancache_ops = { .put_page = tmem_cleancache_put_page, .get_page = tmem_cleancache_get_page, .invalidate_page = tmem_cleancache_flush_page, diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 88d9af3d4581..5fb60ea7eee2 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, list_add_tail(&work->ordered_list, &wq->ordered_list); spin_unlock_irqrestore(&wq->list_lock, flags); } - queue_work(wq->normal_wq, &work->normal_work); trace_btrfs_work_queued(work); + queue_work(wq->normal_wq, &work->normal_work); } void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dd08e29f5117..4545e2e2ad45 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -182,6 +182,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" }, { .id = 0, .name_stem = "tree" }, }; @@ -1787,7 +1788,6 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; - set_freezable(); do { again = 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 393e36bd5845..53dbeaf6ce94 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -153,6 +153,20 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) static unsigned long *alloc_bitmap(u32 bitmap_size) { + void *mem; + + /* + * The allocation size varies, observed numbers were < 4K up to 16K. + * Using vmalloc unconditionally would be too heavy, we'll try + * contiguous allocations first. + */ + if (bitmap_size <= PAGE_SIZE) + return kzalloc(bitmap_size, GFP_NOFS); + + mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN); + if (mem) + return mem; + return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); } @@ -289,7 +303,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; @@ -438,7 +452,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e28f3d4691af..5f06eb1f4384 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7116,21 +7116,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, if (ret) return ERR_PTR(ret); - em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, - ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - return em; - } - + /* + * Create the ordered extent before the extent map. This is to avoid + * races with the fast fsync path that would lead to it logging file + * extent items that point to disk extents that were not yet written to. + * The fast fsync path collects ordered extents into a local list and + * then collects all the new extent maps, so we must create the ordered + * extent first and make sure the fast fsync path collects any new + * ordered extents after collecting new extent maps as well. + * The fsync path simply can not rely on inode_dio_wait() because it + * causes deadlock with AIO. + */ ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, ins.offset, ins.offset, 0); if (ret) { btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - free_extent_map(em); return ERR_PTR(ret); } + em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, + ins.offset, ins.offset, ins.offset, 0); + if (IS_ERR(em)) { + struct btrfs_ordered_extent *oe; + + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); + oe = btrfs_lookup_ordered_extent(inode, start); + ASSERT(oe); + if (WARN_ON(!oe)) + return em; + set_bit(BTRFS_ORDERED_IOERR, &oe->flags); + set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags); + btrfs_remove_ordered_extent(inode, oe); + /* Once for our lookup and once for the ordered extents tree. */ + btrfs_put_ordered_extent(oe); + btrfs_put_ordered_extent(oe); + } return em; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fd1c4d982463..2bd0011450df 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid) root_objectid == BTRFS_TREE_LOG_OBJECTID || root_objectid == BTRFS_CSUM_TREE_OBJECTID || root_objectid == BTRFS_UUID_TREE_OBJECTID || - root_objectid == BTRFS_QUOTA_TREE_OBJECTID) + root_objectid == BTRFS_QUOTA_TREE_OBJECTID || + root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) return 1; return 0; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index e0ac85949067..539e7b5e3f86 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); +BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(mixed_backref), @@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(raid56), BTRFS_FEAT_ATTR_PTR(skinny_metadata), BTRFS_FEAT_ATTR_PTR(no_holes), + BTRFS_FEAT_ATTR_PTR(free_space_tree), NULL }; @@ -780,6 +782,39 @@ failure: return error; } + +/* + * Change per-fs features in /sys/fs/btrfs/UUID/features to match current + * values in superblock. Call after any changes to incompat/compat_ro flags + */ +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set) +{ + struct btrfs_fs_devices *fs_devs; + struct kobject *fsid_kobj; + u64 features; + int ret; + + if (!fs_info) + return; + + features = get_features(fs_info, set); + ASSERT(bit & supported_feature_masks[set]); + + fs_devs = fs_info->fs_devices; + fsid_kobj = &fs_devs->fsid_kobj; + + if (!fsid_kobj->state_initialized) + return; + + /* + * FIXME: this is too heavy to update just one value, ideally we'd like + * to use sysfs_update_group but some refactoring is needed first. + */ + sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group); + ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); +} + static int btrfs_init_debugfs(void) { #ifdef CONFIG_DEBUG_FS diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 9c09522125a6..d7da1a4c2f6c 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = { \ #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature) #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \ - BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature) + BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature) #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature) @@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, struct kobject *parent); int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs); void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs); +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set); + #endif /* _BTRFS_SYSFS_H_ */ diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index b1d920b30070..0e1e61a7ec23 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -82,18 +82,18 @@ void btrfs_destroy_test_fs(void) struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void) { struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info), - GFP_NOFS); + GFP_KERNEL); if (!fs_info) return fs_info; fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->fs_devices) { kfree(fs_info); return NULL; } fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->super_copy) { kfree(fs_info->fs_devices); kfree(fs_info); @@ -180,11 +180,11 @@ btrfs_alloc_dummy_block_group(unsigned long length) { struct btrfs_block_group_cache *cache; - cache = kzalloc(sizeof(*cache), GFP_NOFS); + cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (!cache) return NULL; cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), - GFP_NOFS); + GFP_KERNEL); if (!cache->free_space_ctl) { kfree(cache); return NULL; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index e29fa297e053..669b58201e36 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -94,7 +94,7 @@ static int test_find_delalloc(void) * test. */ for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) { - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL); if (!page) { test_msg("Failed to allocate test page\n"); ret = -ENOMEM; @@ -113,7 +113,7 @@ static int test_find_delalloc(void) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL); start = 0; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -144,7 +144,7 @@ static int test_find_delalloc(void) test_msg("Couldn't find the locked page\n"); goto out_bits; } - set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -199,7 +199,7 @@ static int test_find_delalloc(void) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -262,7 +262,7 @@ static int test_find_delalloc(void) } ret = 0; out_bits: - clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS); + clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL); out: if (locked_page) page_cache_release(locked_page); @@ -360,7 +360,7 @@ static int test_eb_bitmaps(void) test_msg("Running extent buffer bitmap tests\n"); - bitmap = kmalloc(len, GFP_NOFS); + bitmap = kmalloc(len, GFP_KERNEL); if (!bitmap) { test_msg("Couldn't allocate test bitmap\n"); return -ENOMEM; diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 5de55fdd28bc..e2d3da02deee 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -974,7 +974,7 @@ static int test_extent_accounting(void) (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095, EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1045,7 +1045,7 @@ static int test_extent_accounting(void) BTRFS_MAX_EXTENT_SIZE+8191, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1079,7 +1079,7 @@ static int test_extent_accounting(void) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1096,7 +1096,7 @@ out: clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); iput(inode); btrfs_free_dummy_root(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 323e12cc9d2f..978c3a810893 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4127,7 +4127,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_path *path, struct list_head *logged_list, - struct btrfs_log_ctx *ctx) + struct btrfs_log_ctx *ctx, + const u64 start, + const u64 end) { struct extent_map *em, *n; struct list_head extents; @@ -4166,7 +4168,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - + /* + * Collect any new ordered extents within the range. This is to + * prevent logging file extent items without waiting for the disk + * location they point to being written. We do this only to deal + * with races against concurrent lockless direct IO writes. + */ + btrfs_get_logged_extents(inode, logged_list, start, end); process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); @@ -4701,7 +4709,7 @@ log_extents: goto out_unlock; } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, - &logged_list, ctx); + &logged_list, ctx, start, end); if (ret) { err = ret; goto out_unlock; diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c6eb..053818dd6c18 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 89d008dc08e2..fe5efada9d68 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async); +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc); + void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state); diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index bda5ec0b4b4d..fccf7f44139d 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -37,7 +37,7 @@ struct cleancache_ops { void (*invalidate_fs)(int); }; -extern int cleancache_register_ops(struct cleancache_ops *ops); +extern int cleancache_register_ops(const struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(struct super_block *); extern int __cleancache_get_page(struct page *); @@ -48,14 +48,14 @@ extern void __cleancache_invalidate_fs(struct super_block *); #ifdef CONFIG_CLEANCACHE #define cleancache_enabled (1) -static inline bool cleancache_fs_enabled(struct page *page) -{ - return page->mapping->host->i_sb->cleancache_poolid >= 0; -} static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) { return mapping->host->i_sb->cleancache_poolid >= 0; } +static inline bool cleancache_fs_enabled(struct page *page) +{ + return cleancache_fs_enabled_mapping(page->mapping); +} #else #define cleancache_enabled (0) #define cleancache_fs_enabled(_page) (0) @@ -89,11 +89,9 @@ static inline void cleancache_init_shared_fs(struct super_block *sb) static inline int cleancache_get_page(struct page *page) { - int ret = -1; - if (cleancache_enabled && cleancache_fs_enabled(page)) - ret = __cleancache_get_page(page); - return ret; + return __cleancache_get_page(page); + return -1; } static inline void cleancache_put_page(struct page *page) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0639dcc98195..81de7123959d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -165,7 +165,6 @@ struct ftrace_ops { ftrace_func_t saved_func; int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE - int nr_trampolines; struct ftrace_ops_hash local_hash; struct ftrace_ops_hash *func_hash; struct ftrace_ops_hash old_hash; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 76dd4f0da5ca..2ead22dd74a0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -87,7 +87,8 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @start_pid: timer statistics field to store the pid of the task which + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which * started the timer * @start_site: timer statistics field to store the site where the timer * was started @@ -101,7 +102,8 @@ struct hrtimer { ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; - unsigned long state; + u8 state; + u8 is_rel; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -321,6 +323,27 @@ static inline void clock_was_set_delayed(void) { } #endif +static inline ktime_t +__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) +{ + ktime_t rem = ktime_sub(timer->node.expires, now); + + /* + * Adjust relative timers for the extra we added in + * hrtimer_start_range_ns() to prevent short timeouts. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) + rem.tv64 -= hrtimer_resolution; + return rem; +} + +static inline ktime_t +hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) +{ + return __hrtimer_expires_remaining_adjusted(timer, + timer->base->get_time()); +} + extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); @@ -390,7 +413,12 @@ static inline void hrtimer_restart(struct hrtimer *timer) } /* Query timers: */ -extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); +extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + return __hrtimer_get_remaining(timer, false); +} extern u64 hrtimer_get_next_event(void); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f28dff313b07..a5c539fa5d2b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -133,8 +133,9 @@ struct iommu_dm_region { /** * struct iommu_ops - iommu ops and capabilities - * @domain_init: init iommu domain - * @domain_destroy: destroy iommu domain + * @capable: check capability + * @domain_alloc: allocate iommu domain + * @domain_free: free iommu domain * @attach_dev: attach device to an iommu domain * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain @@ -144,8 +145,15 @@ struct iommu_dm_region { * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping + * @device_group: find iommu group for a particular device * @domain_get_attr: Query domain attributes * @domain_set_attr: Change domain attributes + * @get_dm_regions: Request list of direct mapping requirements for a device + * @put_dm_regions: Free list of direct mapping requirements for a device + * @domain_window_enable: Configure and enable a particular window for a domain + * @domain_window_disable: Disable a particular window for a domain + * @domain_set_windows: Set the number of windows for a domain + * @domain_get_windows: Return the number of windows for a domain * @of_xlate: add OF master IDs to iommu grouping * @pgsize_bitmap: bitmap of supported page sizes * @priv: per-instance data private to the iommu driver @@ -182,9 +190,9 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - /* Set the numer of window per domain */ + /* Set the number of windows per domain */ int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); - /* Get the numer of window per domain */ + /* Get the number of windows per domain */ u32 (*domain_get_windows)(struct iommu_domain *domain); #ifdef CONFIG_OF_IOMMU diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index f64622ad02c1..04579d9fbce4 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -70,6 +70,7 @@ struct irq_fwspec { */ enum irq_domain_bus_token { DOMAIN_BUS_ANY = 0, + DOMAIN_BUS_WIRED, DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f9828a48f16a..b35a61a481fa 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -634,9 +634,6 @@ struct perf_event_context { int nr_cgroups; /* cgroup evts */ void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; - - struct delayed_work orphans_remove; - bool orphans_remove_sched; }; /* @@ -729,7 +726,7 @@ extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); -extern struct perf_event *perf_event_get(unsigned int fd); +extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); @@ -1044,7 +1041,7 @@ extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); -extern int __perf_event_disable(void *info); +extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_task_tick(void); #else /* !CONFIG_PERF_EVENTS: */ static inline void * @@ -1070,7 +1067,7 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } -static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index e7a018eaf3a2..017fced60242 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -1,10 +1,13 @@ #ifndef __LINUX_SWIOTLB_H #define __LINUX_SWIOTLB_H +#include <linux/dma-direction.h> +#include <linux/init.h> #include <linux/types.h> struct device; struct dma_attrs; +struct page; struct scatterlist; extern int swiotlb_force; diff --git a/include/linux/tty.h b/include/linux/tty.h index 2fd8708ea888..d9fb4b043f56 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -649,6 +649,7 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(struct tty_struct *tty); +extern int tty_lock_interruptible(struct tty_struct *tty); extern void __lockfunc tty_unlock(struct tty_struct *tty); extern void __lockfunc tty_lock_slave(struct tty_struct *tty); extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); diff --git a/include/trace/events/fence.h b/include/trace/events/fence.h index 98feb1b82896..d6dfa05ba322 100644 --- a/include/trace/events/fence.h +++ b/include/trace/events/fence.h @@ -17,7 +17,7 @@ TRACE_EVENT(fence_annotate_wait_on, TP_STRUCT__entry( __string(driver, fence->ops->get_driver_name(fence)) - __string(timeline, fence->ops->get_driver_name(fence)) + __string(timeline, fence->ops->get_timeline_name(fence)) __field(unsigned int, context) __field(unsigned int, seqno) diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index 4cc989ad6851..f95e1c43c3fb 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -48,6 +48,8 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_FEATURES_2 0x05 #define ETNAVIV_PARAM_GPU_FEATURES_3 0x06 #define ETNAVIV_PARAM_GPU_FEATURES_4 0x07 +#define ETNAVIV_PARAM_GPU_FEATURES_5 0x08 +#define ETNAVIV_PARAM_GPU_FEATURES_6 0x09 #define ETNAVIV_PARAM_GPU_STREAM_COUNT 0x10 #define ETNAVIV_PARAM_GPU_REGISTER_MAX 0x11 @@ -59,6 +61,7 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_BUFFER_SIZE 0x17 #define ETNAVIV_PARAM_GPU_INSTRUCTION_COUNT 0x18 #define ETNAVIV_PARAM_GPU_NUM_CONSTANTS 0x19 +#define ETNAVIV_PARAM_GPU_NUM_VARYINGS 0x1a #define ETNA_MAX_PIPES 4 diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b0799bced518..89ebbc4d1164 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) { struct perf_event *event; const struct perf_event_attr *attr; + struct file *file; - event = perf_event_get(fd); - if (IS_ERR(event)) - return event; + file = perf_event_get(fd); + if (IS_ERR(file)) + return file; + + event = file->private_data; attr = perf_event_attrs(event); if (IS_ERR(attr)) @@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) goto err; if (attr->type == PERF_TYPE_RAW) - return event; + return file; if (attr->type == PERF_TYPE_HARDWARE) - return event; + return file; if (attr->type == PERF_TYPE_SOFTWARE && attr->config == PERF_COUNT_SW_BPF_OUTPUT) - return event; + return file; err: - perf_event_release_kernel(event); + fput(file); return ERR_PTR(-EINVAL); } static void perf_event_fd_array_put_ptr(void *ptr) { - struct perf_event *event = ptr; - - perf_event_release_kernel(event); + fput((struct file *)ptr); } static const struct bpf_map_ops perf_event_array_ops = { diff --git a/kernel/events/core.c b/kernel/events/core.c index 06ae52e99ac2..5946460b2425 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -49,8 +49,6 @@ #include <asm/irq_regs.h> -static struct workqueue_struct *perf_wq; - typedef int (*remote_function_f)(void *); struct remote_function_call { @@ -126,44 +124,181 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info) return data.ret; } -static void event_function_call(struct perf_event *event, - int (*active)(void *), - void (*inactive)(void *), - void *data) +static inline struct perf_cpu_context * +__get_cpu_context(struct perf_event_context *ctx) +{ + return this_cpu_ptr(ctx->pmu->pmu_cpu_context); +} + +static void perf_ctx_lock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx) + raw_spin_lock(&ctx->lock); +} + +static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (ctx) + raw_spin_unlock(&ctx->lock); + raw_spin_unlock(&cpuctx->ctx.lock); +} + +#define TASK_TOMBSTONE ((void *)-1L) + +static bool is_kernel_event(struct perf_event *event) +{ + return READ_ONCE(event->owner) == TASK_TOMBSTONE; +} + +/* + * On task ctx scheduling... + * + * When !ctx->nr_events a task context will not be scheduled. This means + * we can disable the scheduler hooks (for performance) without leaving + * pending task ctx state. + * + * This however results in two special cases: + * + * - removing the last event from a task ctx; this is relatively straight + * forward and is done in __perf_remove_from_context. + * + * - adding the first event to a task ctx; this is tricky because we cannot + * rely on ctx->is_active and therefore cannot use event_function_call(). + * See perf_install_in_context(). + * + * This is because we need a ctx->lock serialized variable (ctx->is_active) + * to reliably determine if a particular task/context is scheduled in. The + * task_curr() use in task_function_call() is racy in that a remote context + * switch is not a single atomic operation. + * + * As is, the situation is 'safe' because we set rq->curr before we do the + * actual context switch. This means that task_curr() will fail early, but + * we'll continue spinning on ctx->is_active until we've passed + * perf_event_task_sched_out(). + * + * Without this ctx->lock serialized variable we could have race where we find + * the task (and hence the context) would not be active while in fact they are. + * + * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. + */ + +typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *, + struct perf_event_context *, void *); + +struct event_function_struct { + struct perf_event *event; + event_f func; + void *data; +}; + +static int event_function(void *info) +{ + struct event_function_struct *efs = info; + struct perf_event *event = efs->event; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + int ret = 0; + + WARN_ON_ONCE(!irqs_disabled()); + + perf_ctx_lock(cpuctx, task_ctx); + /* + * Since we do the IPI call without holding ctx->lock things can have + * changed, double check we hit the task we set out to hit. + */ + if (ctx->task) { + if (ctx->task != current) { + ret = -EAGAIN; + goto unlock; + } + + /* + * We only use event_function_call() on established contexts, + * and event_function() is only ever called when active (or + * rather, we'll have bailed in task_function_call() or the + * above ctx->task != current test), therefore we must have + * ctx->is_active here. + */ + WARN_ON_ONCE(!ctx->is_active); + /* + * And since we have ctx->is_active, cpuctx->task_ctx must + * match. + */ + WARN_ON_ONCE(task_ctx != ctx); + } else { + WARN_ON_ONCE(&cpuctx->ctx != ctx); + } + + efs->func(event, cpuctx, ctx, efs->data); +unlock: + perf_ctx_unlock(cpuctx, task_ctx); + + return ret; +} + +static void event_function_local(struct perf_event *event, event_f func, void *data) +{ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + int ret = event_function(&efs); + WARN_ON_ONCE(ret); +} + +static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; + struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + if (!event->parent) { + /* + * If this is a !child event, we must hold ctx::mutex to + * stabilize the the event->ctx relation. See + * perf_event_ctx_lock(). + */ + lockdep_assert_held(&ctx->mutex); + } if (!task) { - cpu_function_call(event->cpu, active, data); + cpu_function_call(event->cpu, event_function, &efs); return; } again: - if (!task_function_call(task, active, data)) + if (task == TASK_TOMBSTONE) + return; + + if (!task_function_call(task, event_function, &efs)) return; raw_spin_lock_irq(&ctx->lock); - if (ctx->is_active) { - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; - raw_spin_unlock_irq(&ctx->lock); - goto again; + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + if (task != TASK_TOMBSTONE) { + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + func(event, NULL, ctx, data); } - inactive(data); raw_spin_unlock_irq(&ctx->lock); } -#define EVENT_OWNER_KERNEL ((void *) -1) - -static bool is_kernel_event(struct perf_event *event) -{ - return event->owner == EVENT_OWNER_KERNEL; -} - #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -368,28 +503,6 @@ static inline u64 perf_event_clock(struct perf_event *event) return event->clock(); } -static inline struct perf_cpu_context * -__get_cpu_context(struct perf_event_context *ctx) -{ - return this_cpu_ptr(ctx->pmu->pmu_cpu_context); -} - -static void perf_ctx_lock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - raw_spin_lock(&cpuctx->ctx.lock); - if (ctx) - raw_spin_lock(&ctx->lock); -} - -static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (ctx) - raw_spin_unlock(&ctx->lock); - raw_spin_unlock(&cpuctx->ctx.lock); -} - #ifdef CONFIG_CGROUP_PERF static inline bool @@ -579,13 +692,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* - * next is NULL when called from perf_event_enable_on_exec() - * that will systematically cause a cgroup_switch() - */ - if (next) - cgrp2 = perf_cgroup_from_task(next, NULL); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -611,8 +718,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* prev can never be NULL */ cgrp2 = perf_cgroup_from_task(prev, NULL); /* @@ -917,7 +1022,7 @@ static void put_ctx(struct perf_event_context *ctx) if (atomic_dec_and_test(&ctx->refcount)) { if (ctx->parent_ctx) put_ctx(ctx->parent_ctx); - if (ctx->task) + if (ctx->task && ctx->task != TASK_TOMBSTONE) put_task_struct(ctx->task); call_rcu(&ctx->rcu_head, free_ctx); } @@ -934,9 +1039,8 @@ static void put_ctx(struct perf_event_context *ctx) * perf_event_context::mutex nests and those are: * * - perf_event_exit_task_context() [ child , 0 ] - * __perf_event_exit_task() - * sync_child_event() - * put_event() [ parent, 1 ] + * perf_event_exit_event() + * put_event() [ parent, 1 ] * * - perf_event_init_context() [ parent, 0 ] * inherit_task_group() @@ -979,8 +1083,8 @@ static void put_ctx(struct perf_event_context *ctx) * Lock order: * task_struct::perf_event_mutex * perf_event_context::mutex - * perf_event_context::lock * perf_event::child_mutex; + * perf_event_context::lock * perf_event::mmap_mutex * mmap_sem */ @@ -1078,6 +1182,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. + * * This has to cope with with the fact that until it is locked, * the context could get moved to another task. */ @@ -1118,9 +1223,12 @@ retry: goto retry; } - if (!atomic_inc_not_zero(&ctx->refcount)) { + if (ctx->task == TASK_TOMBSTONE || + !atomic_inc_not_zero(&ctx->refcount)) { raw_spin_unlock(&ctx->lock); ctx = NULL; + } else { + WARN_ON_ONCE(ctx->task != task); } } rcu_read_unlock(); @@ -1246,6 +1354,8 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); event->attach_state |= PERF_ATTACH_CONTEXT; @@ -1448,11 +1558,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) { ctx->nr_cgroups--; + /* + * Because cgroup events are always per-cpu events, this will + * always be called from the right CPU. + */ cpuctx = __get_cpu_context(ctx); /* - * if there are no more cgroup events - * then cler cgrp to avoid stale pointer - * in update_cgrp_time_from_cpuctx() + * If there are no more cgroup events then clear cgrp to avoid + * stale pointer in update_cgrp_time_from_cpuctx(). */ if (!ctx->nr_cgroups) cpuctx->cgrp = NULL; @@ -1530,45 +1643,11 @@ out: perf_event__header_size(tmp); } -/* - * User event without the task. - */ static bool is_orphaned_event(struct perf_event *event) { - return event && !is_kernel_event(event) && !event->owner; + return event->state == PERF_EVENT_STATE_EXIT; } -/* - * Event has a parent but parent's task finished and it's - * alive only because of children holding refference. - */ -static bool is_orphaned_child(struct perf_event *event) -{ - return is_orphaned_event(event->parent); -} - -static void orphans_remove_work(struct work_struct *work); - -static void schedule_orphans_remove(struct perf_event_context *ctx) -{ - if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) - return; - - if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { - get_ctx(ctx); - ctx->orphans_remove_sched = true; - } -} - -static int __init perf_workqueue_init(void) -{ - perf_wq = create_singlethread_workqueue("perf"); - WARN(!perf_wq, "failed to create perf workqueue\n"); - return perf_wq ? 0 : -1; -} - -core_initcall(perf_workqueue_init); - static inline int pmu_filter_match(struct perf_event *event) { struct pmu *pmu = event->pmu; @@ -1629,9 +1708,6 @@ event_sched_out(struct perf_event *event, if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - perf_pmu_enable(event->pmu); } @@ -1655,21 +1731,8 @@ group_sched_out(struct perf_event *group_event, cpuctx->exclusive = 0; } -struct remove_event { - struct perf_event *event; - bool detach_group; -}; - -static void ___perf_remove_from_context(void *info) -{ - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - - if (re->detach_group) - perf_group_detach(event); - list_del_event(event, ctx); -} +#define DETACH_GROUP 0x01UL +#define DETACH_STATE 0x02UL /* * Cross CPU call to remove a performance event @@ -1677,33 +1740,33 @@ static void ___perf_remove_from_context(void *info) * We disable the event on the hardware level first. After that we * remove it from the context list. */ -static int __perf_remove_from_context(void *info) +static void +__perf_remove_from_context(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + unsigned long flags = (unsigned long)info; - raw_spin_lock(&ctx->lock); event_sched_out(event, cpuctx, ctx); - if (re->detach_group) + if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (!ctx->nr_events && cpuctx->task_ctx == ctx) { + if (flags & DETACH_STATE) + event->state = PERF_EVENT_STATE_EXIT; + + if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; - cpuctx->task_ctx = NULL; + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + cpuctx->task_ctx = NULL; + } } - raw_spin_unlock(&ctx->lock); - - return 0; } /* * Remove the event from a task's (or a CPU's) list of events. * - * CPU events are removed with a smp call. For task events we only - * call when the task is on a CPU. - * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This is OK when called from perf_release since @@ -1711,73 +1774,32 @@ static int __perf_remove_from_context(void *info) * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ -static void perf_remove_from_context(struct perf_event *event, bool detach_group) +static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { - struct perf_event_context *ctx = event->ctx; - struct remove_event re = { - .event = event, - .detach_group = detach_group, - }; + lockdep_assert_held(&event->ctx->mutex); - lockdep_assert_held(&ctx->mutex); - - event_function_call(event, __perf_remove_from_context, - ___perf_remove_from_context, &re); + event_function_call(event, __perf_remove_from_context, (void *)flags); } /* * Cross CPU call to disable a performance event */ -int __perf_event_disable(void *info) -{ - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - - /* - * If this is a per-task event, need to check whether this - * event's task is the current task on this cpu. - * - * Can trigger due to concurrent perf_event_context_sched_out() - * flipping contexts around. - */ - if (ctx->task && cpuctx->task_ctx != ctx) - return -EINVAL; - - raw_spin_lock(&ctx->lock); - - /* - * If the event is on, turn it off. - * If it is in error state, leave it in error state. - */ - if (event->state >= PERF_EVENT_STATE_INACTIVE) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - update_group_times(event); - if (event == event->group_leader) - group_sched_out(event, cpuctx, ctx); - else - event_sched_out(event, cpuctx, ctx); - event->state = PERF_EVENT_STATE_OFF; - } - - raw_spin_unlock(&ctx->lock); - - return 0; -} - -void ___perf_event_disable(void *info) +static void __perf_event_disable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; + if (event->state < PERF_EVENT_STATE_INACTIVE) + return; - /* - * Since we have the lock this context can't be scheduled - * in, so we can change the state safely. - */ - if (event->state == PERF_EVENT_STATE_INACTIVE) { - update_group_times(event); - event->state = PERF_EVENT_STATE_OFF; - } + update_context_time(ctx); + update_cgrp_time_from_event(event); + update_group_times(event); + if (event == event->group_leader) + group_sched_out(event, cpuctx, ctx); + else + event_sched_out(event, cpuctx, ctx); + event->state = PERF_EVENT_STATE_OFF; } /* @@ -1788,7 +1810,8 @@ void ___perf_event_disable(void *info) * remains valid. This condition is satisifed when called through * perf_event_for_each_child or perf_event_for_each because they * hold the top-level event's child_mutex, so any descendant that - * goes to exit will block in sync_child_event. + * goes to exit will block in perf_event_exit_event(). + * * When called from perf_pending_event it's OK because event->ctx * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. @@ -1804,8 +1827,12 @@ static void _perf_event_disable(struct perf_event *event) } raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_disable, - ___perf_event_disable, event); + event_function_call(event, __perf_event_disable, NULL); +} + +void perf_event_disable_local(struct perf_event *event) +{ + event_function_local(event, __perf_event_disable, NULL); } /* @@ -1918,9 +1945,6 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - out: perf_pmu_enable(event->pmu); @@ -2039,7 +2063,8 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_event_context *ctx); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, @@ -2058,16 +2083,15 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); } -static void ___perf_install_in_context(void *info) +static void ctx_resched(struct perf_cpu_context *cpuctx, + struct perf_event_context *task_ctx) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - - /* - * Since the task isn't running, its safe to add the event, us holding - * the ctx->lock ensures the task won't get scheduled in. - */ - add_event_to_ctx(event, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + if (task_ctx) + task_ctx_sched_out(cpuctx, task_ctx); + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + perf_event_sched_in(cpuctx, task_ctx, current); + perf_pmu_enable(cpuctx->ctx.pmu); } /* @@ -2077,55 +2101,31 @@ static void ___perf_install_in_context(void *info) */ static int __perf_install_in_context(void *info) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; + struct perf_event_context *ctx = info; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - struct task_struct *task = current; - - perf_ctx_lock(cpuctx, task_ctx); - perf_pmu_disable(cpuctx->ctx.pmu); - - /* - * If there was an active task_ctx schedule it out. - */ - if (task_ctx) - task_ctx_sched_out(task_ctx); - /* - * If the context we're installing events in is not the - * active task_ctx, flip them. - */ - if (ctx->task && task_ctx != ctx) { - if (task_ctx) - raw_spin_unlock(&task_ctx->lock); + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx->task) { raw_spin_lock(&ctx->lock); + /* + * If we hit the 'wrong' task, we've since scheduled and + * everything should be sorted, nothing to do! + */ task_ctx = ctx; - } + if (ctx->task != current) + goto unlock; - if (task_ctx) { - cpuctx->task_ctx = task_ctx; - task = task_ctx->task; + /* + * If task_ctx is set, it had better be to us. + */ + WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx); + } else if (task_ctx) { + raw_spin_lock(&task_ctx->lock); } - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - - update_context_time(ctx); - /* - * update cgrp time only if current cgrp - * matches event->cgrp. Must be done before - * calling add_event_to_ctx() - */ - update_cgrp_time_from_event(event); - - add_event_to_ctx(event, ctx); - - /* - * Schedule everything back in - */ - perf_event_sched_in(cpuctx, task_ctx, task); - - perf_pmu_enable(cpuctx->ctx.pmu); + ctx_resched(cpuctx, task_ctx); +unlock: perf_ctx_unlock(cpuctx, task_ctx); return 0; @@ -2133,27 +2133,54 @@ static int __perf_install_in_context(void *info) /* * Attach a performance event to a context - * - * First we add the event to the list with the hardware enable bit - * in event->hw_config cleared. - * - * If the event is attached to a task which is on a CPU we use a smp - * call to enable it in the task context. The task might have been - * scheduled away, but we check this in the smp call again. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { + struct task_struct *task = NULL; + lockdep_assert_held(&ctx->mutex); event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; - event_function_call(event, __perf_install_in_context, - ___perf_install_in_context, event); + /* + * Installing events is tricky because we cannot rely on ctx->is_active + * to be set in case this is the nr_events 0 -> 1 transition. + * + * So what we do is we add the event to the list here, which will allow + * a future context switch to DTRT and then send a racy IPI. If the IPI + * fails to hit the right task, this means a context switch must have + * happened and that will have taken care of business. + */ + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + /* + * Worse, we cannot even rely on the ctx actually existing anymore. If + * between find_get_context() and perf_install_in_context() the task + * went through perf_event_exit_task() its dead and we should not be + * adding new events. + */ + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; + } + update_context_time(ctx); + /* + * Update cgrp time only if current cgrp matches event->cgrp. + * Must be done before calling add_event_to_ctx(). + */ + update_cgrp_time_from_event(event); + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); + + if (task) + task_function_call(task, __perf_install_in_context, ctx); + else + cpu_function_call(cpu, __perf_install_in_context, ctx); } /* @@ -2180,43 +2207,30 @@ static void __perf_event_mark_enabled(struct perf_event *event) /* * Cross CPU call to enable a performance event */ -static int __perf_event_enable(void *info) +static void __perf_event_enable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; struct perf_event *leader = event->group_leader; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - int err; + struct perf_event_context *task_ctx; - /* - * There's a time window between 'ctx->is_active' check - * in perf_event_enable function and this place having: - * - IRQs on - * - ctx->lock unlocked - * - * where the task could be killed and 'ctx' deactivated - * by perf_event_exit_task. - */ - if (!ctx->is_active) - return -EINVAL; + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state <= PERF_EVENT_STATE_ERROR) + return; - raw_spin_lock(&ctx->lock); update_context_time(ctx); - - if (event->state >= PERF_EVENT_STATE_INACTIVE) - goto unlock; - - /* - * set current task's cgroup time reference point - */ - perf_cgroup_set_timestamp(current, ctx); - __perf_event_mark_enabled(event); + if (!ctx->is_active) + return; + if (!event_filter_match(event)) { - if (is_cgroup_event(event)) + if (is_cgroup_event(event)) { + perf_cgroup_set_timestamp(current, ctx); // XXX ? perf_cgroup_defer_enabled(event); - goto unlock; + } + return; } /* @@ -2224,41 +2238,13 @@ static int __perf_event_enable(void *info) * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) - goto unlock; - - if (!group_can_go_on(event, cpuctx, 1)) { - err = -EEXIST; - } else { - if (event == leader) - err = group_sched_in(event, cpuctx, ctx); - else - err = event_sched_in(event, cpuctx, ctx); - } - - if (err) { - /* - * If this event can't go on and it's part of a - * group, then the whole group has to come off. - */ - if (leader != event) { - group_sched_out(leader, cpuctx, ctx); - perf_mux_hrtimer_restart(cpuctx); - } - if (leader->attr.pinned) { - update_group_times(leader); - leader->state = PERF_EVENT_STATE_ERROR; - } - } + return; -unlock: - raw_spin_unlock(&ctx->lock); + task_ctx = cpuctx->task_ctx; + if (ctx->task) + WARN_ON_ONCE(task_ctx != ctx); - return 0; -} - -void ___perf_event_enable(void *info) -{ - __perf_event_mark_enabled((struct perf_event *)info); + ctx_resched(cpuctx, task_ctx); } /* @@ -2275,7 +2261,8 @@ static void _perf_event_enable(struct perf_event *event) struct perf_event_context *ctx = event->ctx; raw_spin_lock_irq(&ctx->lock); - if (event->state >= PERF_EVENT_STATE_INACTIVE) { + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state < PERF_EVENT_STATE_ERROR) { raw_spin_unlock_irq(&ctx->lock); return; } @@ -2291,8 +2278,7 @@ static void _perf_event_enable(struct perf_event *event) event->state = PERF_EVENT_STATE_OFF; raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_enable, - ___perf_event_enable, event); + event_function_call(event, __perf_event_enable, NULL); } /* @@ -2342,12 +2328,27 @@ static void ctx_sched_out(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type) { - struct perf_event *event; int is_active = ctx->is_active; + struct perf_event *event; - ctx->is_active &= ~event_type; - if (likely(!ctx->nr_events)) + lockdep_assert_held(&ctx->lock); + + if (likely(!ctx->nr_events)) { + /* + * See __perf_remove_from_context(). + */ + WARN_ON_ONCE(ctx->is_active); + if (ctx->task) + WARN_ON_ONCE(cpuctx->task_ctx); return; + } + + ctx->is_active &= ~event_type; + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; + } update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx); @@ -2518,17 +2519,21 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, raw_spin_lock(&ctx->lock); raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { - /* - * XXX do we need a memory barrier of sorts - * wrt to rcu_dereference() of perf_event_ctxp - */ - task->perf_event_ctxp[ctxn] = next_ctx; - next->perf_event_ctxp[ctxn] = ctx; - ctx->task = next; - next_ctx->task = task; + WRITE_ONCE(ctx->task, next); + WRITE_ONCE(next_ctx->task, task); swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + /* + * RCU_INIT_POINTER here is safe because we've not + * modified the ctx and the above modification of + * ctx->task and ctx->task_ctx_data are immaterial + * since those values are always verified under + * ctx->lock which we're now holding. + */ + RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], next_ctx); + RCU_INIT_POINTER(next->perf_event_ctxp[ctxn], ctx); + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); @@ -2541,8 +2546,7 @@ unlock: if (do_switch) { raw_spin_lock(&ctx->lock); - ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; + task_ctx_sched_out(cpuctx, ctx); raw_spin_unlock(&ctx->lock); } } @@ -2637,10 +2641,9 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_event_context *ctx) +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - if (!cpuctx->task_ctx) return; @@ -2648,7 +2651,6 @@ static void task_ctx_sched_out(struct perf_event_context *ctx) return; ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; } /* @@ -2725,13 +2727,22 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type, struct task_struct *task) { - u64 now; int is_active = ctx->is_active; + u64 now; + + lockdep_assert_held(&ctx->lock); - ctx->is_active |= event_type; if (likely(!ctx->nr_events)) return; + ctx->is_active |= event_type; + if (ctx->task) { + if (!is_active) + cpuctx->task_ctx = ctx; + else + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + } + now = perf_clock(); ctx->timestamp = now; perf_cgroup_set_timestamp(task, ctx); @@ -2773,12 +2784,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * cpu flexible, task flexible. */ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - - if (ctx->nr_events) - cpuctx->task_ctx = ctx; - - perf_event_sched_in(cpuctx, cpuctx->task_ctx, task); - + perf_event_sched_in(cpuctx, ctx, task); perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); } @@ -2800,6 +2806,16 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; + /* + * If cgroup events exist on this CPU, then we need to check if we have + * to switch in PMU state; cgroup event are system-wide mode only. + * + * Since cgroup events are CPU events, we must schedule these in before + * we schedule in the task events. + */ + if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) + perf_cgroup_sched_in(prev, task); + for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -2807,13 +2823,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, perf_event_context_sched_in(ctx, task); } - /* - * if cgroup events exist on this CPU, then we need - * to check if we have to switch in PMU state. - * cgroup event are system-wide mode only - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); if (atomic_read(&nr_switch_events)) perf_event_switch(task, prev, true); @@ -3099,46 +3108,30 @@ static int event_enable_on_exec(struct perf_event *event, static void perf_event_enable_on_exec(int ctxn) { struct perf_event_context *ctx, *clone_ctx = NULL; + struct perf_cpu_context *cpuctx; struct perf_event *event; unsigned long flags; int enabled = 0; - int ret; local_irq_save(flags); ctx = current->perf_event_ctxp[ctxn]; if (!ctx || !ctx->nr_events) goto out; - /* - * We must ctxsw out cgroup events to avoid conflict - * when invoking perf_task_event_sched_in() later on - * in this function. Otherwise we end up trying to - * ctxswin cgroup events which are already scheduled - * in. - */ - perf_cgroup_sched_out(current, NULL); - - raw_spin_lock(&ctx->lock); - task_ctx_sched_out(ctx); - - list_for_each_entry(event, &ctx->event_list, event_entry) { - ret = event_enable_on_exec(event, ctx); - if (ret) - enabled = 1; - } + cpuctx = __get_cpu_context(ctx); + perf_ctx_lock(cpuctx, ctx); + list_for_each_entry(event, &ctx->event_list, event_entry) + enabled |= event_enable_on_exec(event, ctx); /* - * Unclone this context if we enabled any event. + * Unclone and reschedule this context if we enabled any event. */ - if (enabled) + if (enabled) { clone_ctx = unclone_ctx(ctx); + ctx_resched(cpuctx, ctx); + } + perf_ctx_unlock(cpuctx, ctx); - raw_spin_unlock(&ctx->lock); - - /* - * Also calls ctxswin for cgroup events, if any: - */ - perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); @@ -3334,7 +3327,6 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); atomic_set(&ctx->refcount, 1); - INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); } static struct perf_event_context * @@ -3521,11 +3513,13 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) static void unaccount_event(struct perf_event *event) { + bool dec = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) @@ -3535,12 +3529,15 @@ static void unaccount_event(struct perf_event *event) if (event->attr.freq) atomic_dec(&nr_freq_events); if (event->attr.context_switch) { - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; atomic_dec(&nr_switch_events); } if (is_cgroup_event(event)) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (has_branch_stack(event)) + dec = true; + + if (dec) static_key_slow_dec_deferred(&perf_sched_events); unaccount_event_cpu(event, event->cpu); @@ -3556,7 +3553,7 @@ static void unaccount_event(struct perf_event *event) * 3) two matching events on the same context. * * The former two cases are handled in the allocation path (perf_event_alloc(), - * __free_event()), the latter -- before the first perf_install_in_context(). + * _free_event()), the latter -- before the first perf_install_in_context(). */ static int exclusive_event_init(struct perf_event *event) { @@ -3631,29 +3628,6 @@ static bool exclusive_event_installable(struct perf_event *event, return true; } -static void __free_event(struct perf_event *event) -{ - if (!event->parent) { - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - put_callchain_buffers(); - } - - perf_event_free_bpf_prog(event); - - if (event->destroy) - event->destroy(event); - - if (event->ctx) - put_ctx(event->ctx); - - if (event->pmu) { - exclusive_event_destroy(event); - module_put(event->pmu->module); - } - - call_rcu(&event->rcu_head, free_event_rcu); -} - static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending); @@ -3675,7 +3649,25 @@ static void _free_event(struct perf_event *event) if (is_cgroup_event(event)) perf_detach_cgroup(event); - __free_event(event); + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + put_callchain_buffers(); + } + + perf_event_free_bpf_prog(event); + + if (event->destroy) + event->destroy(event); + + if (event->ctx) + put_ctx(event->ctx); + + if (event->pmu) { + exclusive_event_destroy(event); + module_put(event->pmu->module); + } + + call_rcu(&event->rcu_head, free_event_rcu); } /* @@ -3702,14 +3694,13 @@ static void perf_remove_from_owner(struct perf_event *event) struct task_struct *owner; rcu_read_lock(); - owner = ACCESS_ONCE(event->owner); /* - * Matches the smp_wmb() in perf_event_exit_task(). If we observe - * !owner it means the list deletion is complete and we can indeed - * free this event, otherwise we need to serialize on + * Matches the smp_store_release() in perf_event_exit_task(). If we + * observe !owner it means the list deletion is complete and we can + * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ - smp_read_barrier_depends(); + owner = lockless_dereference(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last @@ -3737,8 +3728,10 @@ static void perf_remove_from_owner(struct perf_event *event) * ensured they're done, and we can proceed with freeing the * event. */ - if (event->owner) + if (event->owner) { list_del_init(&event->owner_entry); + smp_store_release(&event->owner, NULL); + } mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } @@ -3746,36 +3739,98 @@ static void perf_remove_from_owner(struct perf_event *event) static void put_event(struct perf_event *event) { - struct perf_event_context *ctx; - if (!atomic_long_dec_and_test(&event->refcount)) return; + _free_event(event); +} + +/* + * Kill an event dead; while event:refcount will preserve the event + * object, it will not preserve its functionality. Once the last 'user' + * gives up the object, we'll destroy the thing. + */ +int perf_event_release_kernel(struct perf_event *event) +{ + struct perf_event_context *ctx; + struct perf_event *child, *tmp; + if (!is_kernel_event(event)) perf_remove_from_owner(event); + ctx = perf_event_ctx_lock(event); + WARN_ON_ONCE(ctx->parent_ctx); + perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE); + perf_event_ctx_unlock(event, ctx); + /* - * There are two ways this annotation is useful: + * At this point we must have event->state == PERF_EVENT_STATE_EXIT, + * either from the above perf_remove_from_context() or through + * perf_event_exit_event(). * - * 1) there is a lock recursion from perf_event_exit_task - * see the comment there. + * Therefore, anybody acquiring event->child_mutex after the below + * loop _must_ also see this, most importantly inherit_event() which + * will avoid placing more children on the list. * - * 2) there is a lock-inversion with mmap_sem through - * perf_read_group(), which takes faults while - * holding ctx->mutex, however this is called after - * the last filedesc died, so there is no possibility - * to trigger the AB-BA case. + * Thus this guarantees that we will in fact observe and kill _ALL_ + * child events. */ - ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); - WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, true); - perf_event_ctx_unlock(event, ctx); + WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT); - _free_event(event); -} +again: + mutex_lock(&event->child_mutex); + list_for_each_entry(child, &event->child_list, child_list) { -int perf_event_release_kernel(struct perf_event *event) -{ + /* + * Cannot change, child events are not migrated, see the + * comment with perf_event_ctx_lock_nested(). + */ + ctx = lockless_dereference(child->ctx); + /* + * Since child_mutex nests inside ctx::mutex, we must jump + * through hoops. We start by grabbing a reference on the ctx. + * + * Since the event cannot get freed while we hold the + * child_mutex, the context must also exist and have a !0 + * reference count. + */ + get_ctx(ctx); + + /* + * Now that we have a ctx ref, we can drop child_mutex, and + * acquire ctx::mutex without fear of it going away. Then we + * can re-acquire child_mutex. + */ + mutex_unlock(&event->child_mutex); + mutex_lock(&ctx->mutex); + mutex_lock(&event->child_mutex); + + /* + * Now that we hold ctx::mutex and child_mutex, revalidate our + * state, if child is still the first entry, it didn't get freed + * and we can continue doing so. + */ + tmp = list_first_entry_or_null(&event->child_list, + struct perf_event, child_list); + if (tmp == child) { + perf_remove_from_context(child, DETACH_GROUP); + list_del(&child->child_list); + free_event(child); + /* + * This matches the refcount bump in inherit_event(); + * this can't be the last reference. + */ + put_event(event); + } + + mutex_unlock(&event->child_mutex); + mutex_unlock(&ctx->mutex); + put_ctx(ctx); + goto again; + } + mutex_unlock(&event->child_mutex); + + /* Must be the last reference */ put_event(event); return 0; } @@ -3786,46 +3841,10 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel); */ static int perf_release(struct inode *inode, struct file *file) { - put_event(file->private_data); + perf_event_release_kernel(file->private_data); return 0; } -/* - * Remove all orphanes events from the context. - */ -static void orphans_remove_work(struct work_struct *work) -{ - struct perf_event_context *ctx; - struct perf_event *event, *tmp; - - ctx = container_of(work, struct perf_event_context, - orphans_remove.work); - - mutex_lock(&ctx->mutex); - list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { - struct perf_event *parent_event = event->parent; - - if (!is_orphaned_child(event)) - continue; - - perf_remove_from_context(event, true); - - mutex_lock(&parent_event->child_mutex); - list_del_init(&event->child_list); - mutex_unlock(&parent_event->child_mutex); - - free_event(event); - put_event(parent_event); - } - - raw_spin_lock_irq(&ctx->lock); - ctx->orphans_remove_sched = false; - raw_spin_unlock_irq(&ctx->lock); - mutex_unlock(&ctx->mutex); - - put_ctx(ctx); -} - u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -4054,7 +4073,7 @@ static void _perf_event_reset(struct perf_event *event) /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block - * in sync_child_event if it goes to exit, thus satisfying the + * in perf_event_exit_event() if it goes to exit, thus satisfying the * task existence requirements of perf_event_enable/disable. */ static void perf_event_for_each_child(struct perf_event *event, @@ -4086,36 +4105,14 @@ static void perf_event_for_each(struct perf_event *event, perf_event_for_each_child(sibling, func); } -struct period_event { - struct perf_event *event; - u64 value; -}; - -static void ___perf_event_period(void *info) -{ - struct period_event *pe = info; - struct perf_event *event = pe->event; - u64 value = pe->value; - - if (event->attr.freq) { - event->attr.sample_freq = value; - } else { - event->attr.sample_period = value; - event->hw.sample_period = value; - } - - local64_set(&event->hw.period_left, 0); -} - -static int __perf_event_period(void *info) +static void __perf_event_period(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct period_event *pe = info; - struct perf_event *event = pe->event; - struct perf_event_context *ctx = event->ctx; - u64 value = pe->value; + u64 value = *((u64 *)info); bool active; - raw_spin_lock(&ctx->lock); if (event->attr.freq) { event->attr.sample_freq = value; } else { @@ -4135,14 +4132,10 @@ static int __perf_event_period(void *info) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } - raw_spin_unlock(&ctx->lock); - - return 0; } static int perf_event_period(struct perf_event *event, u64 __user *arg) { - struct period_event pe = { .event = event, }; u64 value; if (!is_sampling_event(event)) @@ -4157,10 +4150,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; - pe.value = value; - - event_function_call(event, __perf_event_period, - ___perf_event_period, &pe); + event_function_call(event, __perf_event_period, &value); return 0; } @@ -4932,7 +4922,7 @@ static void perf_pending_event(struct irq_work *entry) if (event->pending_disable) { event->pending_disable = 0; - __perf_event_disable(event); + perf_event_disable_local(event); } if (event->pending_wakeup) { @@ -7753,11 +7743,13 @@ static void account_event_cpu(struct perf_event *event, int cpu) static void account_event(struct perf_event *event) { + bool inc = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) @@ -7770,11 +7762,14 @@ static void account_event(struct perf_event *event) } if (event->attr.context_switch) { atomic_inc(&nr_switch_events); - static_key_slow_inc(&perf_sched_events.key); + inc = true; } if (has_branch_stack(event)) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (is_cgroup_event(event)) + inc = true; + + if (inc) static_key_slow_inc(&perf_sched_events.key); account_event_cpu(event, event->cpu); @@ -8422,11 +8417,11 @@ SYSCALL_DEFINE5(perf_event_open, * See perf_event_ctx_lock() for comments on the details * of swizzling perf_event::ctx. */ - perf_remove_from_context(group_leader, false); + perf_remove_from_context(group_leader, 0); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_remove_from_context(sibling, false); + perf_remove_from_context(sibling, 0); put_ctx(gctx); } @@ -8479,6 +8474,8 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__header_size(event); perf_event__id_header_size(event); + event->owner = current; + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); @@ -8488,8 +8485,6 @@ SYSCALL_DEFINE5(perf_event_open, put_online_cpus(); - event->owner = current; - mutex_lock(¤t->perf_event_mutex); list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); @@ -8556,7 +8551,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, } /* Mark owner so we could distinguish it from user events. */ - event->owner = EVENT_OWNER_KERNEL; + event->owner = TASK_TOMBSTONE; account_event(event); @@ -8606,7 +8601,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex); list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) { - perf_remove_from_context(event, false); + perf_remove_from_context(event, 0); unaccount_event_cpu(event, src_cpu); put_ctx(src_ctx); list_add(&event->migrate_entry, &events); @@ -8673,33 +8668,15 @@ static void sync_child_event(struct perf_event *child_event, &parent_event->child_total_time_enabled); atomic64_add(child_event->total_time_running, &parent_event->child_total_time_running); - - /* - * Remove this event from the parent's list - */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); - list_del_init(&child_event->child_list); - mutex_unlock(&parent_event->child_mutex); - - /* - * Make sure user/parent get notified, that we just - * lost one event. - */ - perf_event_wakeup(parent_event); - - /* - * Release the parent event, if this was the last - * reference to it. - */ - put_event(parent_event); } static void -__perf_event_exit_task(struct perf_event *child_event, - struct perf_event_context *child_ctx, - struct task_struct *child) +perf_event_exit_event(struct perf_event *child_event, + struct perf_event_context *child_ctx, + struct task_struct *child) { + struct perf_event *parent_event = child_event->parent; + /* * Do not destroy the 'original' grouping; because of the context * switch optimization the original events could've ended up in a @@ -8712,57 +8689,86 @@ __perf_event_exit_task(struct perf_event *child_event, * Do destroy all inherited groups, we don't care about those * and being thorough is better. */ - perf_remove_from_context(child_event, !!child_event->parent); + raw_spin_lock_irq(&child_ctx->lock); + WARN_ON_ONCE(child_ctx->is_active); + + if (parent_event) + perf_group_detach(child_event); + list_del_event(child_event, child_ctx); + child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */ + raw_spin_unlock_irq(&child_ctx->lock); /* - * It can happen that the parent exits first, and has events - * that are still around due to the child reference. These - * events need to be zapped. + * Parent events are governed by their filedesc, retain them. */ - if (child_event->parent) { - sync_child_event(child_event, child); - free_event(child_event); - } else { - child_event->state = PERF_EVENT_STATE_EXIT; + if (!parent_event) { perf_event_wakeup(child_event); + return; } + /* + * Child events can be cleaned up. + */ + + sync_child_event(child_event, child); + + /* + * Remove this event from the parent's list + */ + WARN_ON_ONCE(parent_event->ctx->parent_ctx); + mutex_lock(&parent_event->child_mutex); + list_del_init(&child_event->child_list); + mutex_unlock(&parent_event->child_mutex); + + /* + * Kick perf_poll() for is_event_hup(). + */ + perf_event_wakeup(parent_event); + free_event(child_event); + put_event(parent_event); } static void perf_event_exit_task_context(struct task_struct *child, int ctxn) { - struct perf_event *child_event, *next; struct perf_event_context *child_ctx, *clone_ctx = NULL; - unsigned long flags; + struct perf_event *child_event, *next; + + WARN_ON_ONCE(child != current); - if (likely(!child->perf_event_ctxp[ctxn])) + child_ctx = perf_pin_task_context(child, ctxn); + if (!child_ctx) return; - local_irq_save(flags); /* - * We can't reschedule here because interrupts are disabled, - * and either child is current or it is a task that can't be - * scheduled, so we are now safe from rescheduling changing - * our context. + * In order to reduce the amount of tricky in ctx tear-down, we hold + * ctx::mutex over the entire thing. This serializes against almost + * everything that wants to access the ctx. + * + * The exception is sys_perf_event_open() / + * perf_event_create_kernel_count() which does find_get_context() + * without ctx::mutex (it cannot because of the move_group double mutex + * lock thing). See the comments in perf_install_in_context(). */ - child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); + mutex_lock(&child_ctx->mutex); /* - * Take the context lock here so that if find_get_context is - * reading child->perf_event_ctxp, we wait until it has - * incremented the context's refcount before we do put_ctx below. + * In a single ctx::lock section, de-schedule the events and detach the + * context from the task such that we cannot ever get it scheduled back + * in. */ - raw_spin_lock(&child_ctx->lock); - task_ctx_sched_out(child_ctx); - child->perf_event_ctxp[ctxn] = NULL; + raw_spin_lock_irq(&child_ctx->lock); + task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx); /* - * If this context is a clone; unclone it so it can't get - * swapped to another process while we're removing all - * the events from it. + * Now that the context is inactive, destroy the task <-> ctx relation + * and mark the context dead. */ + RCU_INIT_POINTER(child->perf_event_ctxp[ctxn], NULL); + put_ctx(child_ctx); /* cannot be last */ + WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); + put_task_struct(current); /* cannot be last */ + clone_ctx = unclone_ctx(child_ctx); - update_context_time(child_ctx); - raw_spin_unlock_irqrestore(&child_ctx->lock, flags); + raw_spin_unlock_irq(&child_ctx->lock); if (clone_ctx) put_ctx(clone_ctx); @@ -8774,20 +8780,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) */ perf_event_task(child, child_ctx, 0); - /* - * We can recurse on the same lock type through: - * - * __perf_event_exit_task() - * sync_child_event() - * put_event() - * mutex_lock(&ctx->mutex) - * - * But since its the parent context it won't be the same instance. - */ - mutex_lock(&child_ctx->mutex); - list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) - __perf_event_exit_task(child_event, child_ctx, child); + perf_event_exit_event(child_event, child_ctx, child); mutex_unlock(&child_ctx->mutex); @@ -8812,8 +8806,7 @@ void perf_event_exit_task(struct task_struct *child) * the owner, closes a race against perf_release() where * we need to serialize on the owner->perf_event_mutex. */ - smp_wmb(); - event->owner = NULL; + smp_store_release(&event->owner, NULL); } mutex_unlock(&child->perf_event_mutex); @@ -8896,21 +8889,20 @@ void perf_event_delayed_put(struct task_struct *task) WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); } -struct perf_event *perf_event_get(unsigned int fd) +struct file *perf_event_get(unsigned int fd) { - int err; - struct fd f; - struct perf_event *event; + struct file *file; - err = perf_fget_light(fd, &f); - if (err) - return ERR_PTR(err); + file = fget_raw(fd); + if (!file) + return ERR_PTR(-EBADF); - event = f.file->private_data; - atomic_long_inc(&event->refcount); - fdput(f); + if (file->f_op != &perf_fops) { + fput(file); + return ERR_PTR(-EBADF); + } - return event; + return file; } const struct perf_event_attr *perf_event_attrs(struct perf_event *event) @@ -8953,8 +8945,16 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; + /* + * is_orphaned_event() and list_add_tail(&parent_event->child_list) + * must be under the same lock in order to serialize against + * perf_event_release_kernel(), such that either we must observe + * is_orphaned_event() or they will observe us on the child_list. + */ + mutex_lock(&parent_event->child_mutex); if (is_orphaned_event(parent_event) || !atomic_long_inc_not_zero(&parent_event->refcount)) { + mutex_unlock(&parent_event->child_mutex); free_event(child_event); return NULL; } @@ -9002,8 +9002,6 @@ inherit_event(struct perf_event *parent_event, /* * Link this into the parent event's child list */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); list_add_tail(&child_event->child_list, &parent_event->child_list); mutex_unlock(&parent_event->child_mutex); @@ -9221,13 +9219,14 @@ static void perf_event_init_cpu(int cpu) #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE static void __perf_event_exit_context(void *__info) { - struct remove_event re = { .detach_group = true }; struct perf_event_context *ctx = __info; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event *event; - rcu_read_lock(); - list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) - __perf_remove_from_context(&re); - rcu_read_unlock(); + raw_spin_lock(&ctx->lock); + list_for_each_entry(event, &ctx->event_list, event_entry) + __perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP); + raw_spin_unlock(&ctx->lock); } static void perf_event_exit_cpu_context(int cpu) diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 92ce5f4ccc26..3f8cb1e14588 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -444,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att * current task. */ if (irqs_disabled() && bp->ctx && bp->ctx->task == current) - __perf_event_disable(bp); + perf_event_disable_local(bp); else perf_event_disable(bp); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index adfdc0536117..1faad2cfdb9e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -459,6 +459,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx) __free_page(page); } +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + if (rb->aux_nr_pages) { + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; + } +} + int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, pgoff_t pgoff, int nr_pages, long watermark, int flags) { @@ -547,30 +566,11 @@ out: if (!ret) rb->aux_pgoff = pgoff; else - rb_free_aux(rb); + __rb_free_aux(rb); return ret; } -static void __rb_free_aux(struct ring_buffer *rb) -{ - int pg; - - if (rb->aux_priv) { - rb->free_aux(rb->aux_priv); - rb->free_aux = NULL; - rb->aux_priv = NULL; - } - - if (rb->aux_nr_pages) { - for (pg = 0; pg < rb->aux_nr_pages; pg++) - rb_free_aux_page(rb, pg); - - kfree(rb->aux_pages); - rb->aux_nr_pages = 0; - } -} - void rb_free_aux(struct ring_buffer *rb) { if (atomic_dec_and_test(&rb->aux_refcount)) diff --git a/kernel/futex.c b/kernel/futex.c index 0773f2b23b10..5d6ce6413ef1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1191,7 +1191,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, if (pi_state->owner != current) return -EINVAL; - raw_spin_lock(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* @@ -1217,22 +1217,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, else if (curval != uval) ret = -EINVAL; if (ret) { - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } - raw_spin_lock_irq(&pi_state->owner->pi_lock); + raw_spin_lock(&pi_state->owner->pi_lock); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + raw_spin_unlock(&pi_state->owner->pi_lock); - raw_spin_lock_irq(&new_owner->pi_lock); + raw_spin_lock(&new_owner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &new_owner->pi_state_list); pi_state->owner = new_owner; - raw_spin_unlock_irq(&new_owner->pi_lock); + raw_spin_unlock(&new_owner->pi_lock); - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); @@ -2127,11 +2127,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * we returned due to timeout or signal without taking the * rt_mutex. Too late. */ - raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); owner = rt_mutex_owner(&q->pi_state->pi_mutex); if (!owner) owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); ret = fixup_pi_state_owner(uaddr, q, owner); goto out; } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a302cf9a2126..57bff7857e87 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) unsigned int flags = 0, irq = desc->irq_data.irq; struct irqaction *action = desc->action; - do { + /* action might have become NULL since we dropped the lock */ + while (action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval |= res; action = action->next; - } while (action); + } add_interrupt_randomness(irq, flags); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 6e655f7acd3b..3e56d2f03e24 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -575,10 +575,15 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) unsigned int type = IRQ_TYPE_NONE; int virq; - if (fwspec->fwnode) - domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY); - else + if (fwspec->fwnode) { + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_WIRED); + if (!domain) + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_ANY); + } else { domain = irq_default_domain; + } if (!domain) { pr_warn("no irq domain found for %s !\n", diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 8251e75dd9c0..3e746607abe5 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -99,13 +99,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) * 2) Drop lock->wait_lock * 3) Try to unlock the lock with cmpxchg */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { struct task_struct *owner = rt_mutex_owner(lock); clear_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* * If a new waiter comes in between the unlock and the cmpxchg * we have two situations: @@ -147,11 +148,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) /* * Simple slow path only version: lock->owner is protected by lock->wait_lock. */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { lock->owner = NULL; - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return true; } #endif @@ -433,7 +435,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, int ret = 0, depth = 0; struct rt_mutex *lock; bool detect_deadlock; - unsigned long flags; bool requeue = true; detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); @@ -476,7 +477,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * [1] Task cannot go away as we did a get_task() before ! */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock_irq(&task->pi_lock); /* * [2] Get the waiter on which @task is blocked on. @@ -560,7 +561,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * operations. */ if (!raw_spin_trylock(&lock->wait_lock)) { - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); cpu_relax(); goto retry; } @@ -591,7 +592,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * No requeue[7] here. Just release @task [8] */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -599,14 +600,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * If there is no owner of the lock, end of chain. */ if (!rt_mutex_owner(lock)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* * No requeue [11] here. We just do deadlock detection. @@ -621,8 +622,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* If owner is not blocked, end of chain. */ if (!next_lock) @@ -643,7 +644,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, rt_mutex_enqueue(lock, waiter); /* [8] Release the task */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -661,14 +662,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, */ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) wake_up_process(rt_mutex_top_waiter(lock)->task); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. the owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* [11] requeue the pi waiters if necessary */ if (waiter == rt_mutex_top_waiter(lock)) { @@ -722,8 +723,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop the locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* * Make the actual exit decisions [12], based on the stored @@ -746,7 +747,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto again; out_unlock_pi: - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); out_put_task: put_task_struct(task); @@ -756,7 +757,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * Try to take an rt-mutex * - * Must be called with lock->wait_lock held. + * Must be called with lock->wait_lock held and interrupts disabled * * @lock: The lock to be acquired. * @task: The task which wants to acquire the lock @@ -766,8 +767,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) { - unsigned long flags; - /* * Before testing whether we can acquire @lock, we set the * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all @@ -852,7 +851,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * case, but conditionals are more expensive than a redundant * store. */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); task->pi_blocked_on = NULL; /* * Finish the lock acquisition. @task is the new owner. If @@ -861,7 +860,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); takeit: /* We got the lock. */ @@ -883,7 +882,7 @@ takeit: * * Prepare waiter and propagate pi chain * - * This must be called with lock->wait_lock held. + * This must be called with lock->wait_lock held and interrupts disabled */ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -894,7 +893,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *top_waiter = waiter; struct rt_mutex *next_lock; int chain_walk = 0, res; - unsigned long flags; /* * Early deadlock detection. We really don't want the task to @@ -908,7 +906,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (owner == task) return -EDEADLK; - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; @@ -921,12 +919,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, task->pi_blocked_on = waiter; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); if (!owner) return 0; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); if (waiter == rt_mutex_top_waiter(lock)) { rt_mutex_dequeue_pi(owner, top_waiter); rt_mutex_enqueue_pi(owner, waiter); @@ -941,7 +939,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Even if full deadlock detection is on, if the owner is not * blocked itself, we can avoid finding this out in the chain @@ -957,12 +955,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); return res; } @@ -971,15 +969,14 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * Remove the top waiter from the current tasks pi waiter tree and * queue it up. * - * Called with lock->wait_lock held. + * Called with lock->wait_lock held and interrupts disabled. */ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); waiter = rt_mutex_top_waiter(lock); @@ -1001,7 +998,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, */ lock->owner = (void *) RT_MUTEX_HAS_WAITERS; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); wake_q_add(wake_q, waiter->task); } @@ -1009,7 +1006,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, /* * Remove a waiter from a lock and give up * - * Must be called with lock->wait_lock held and + * Must be called with lock->wait_lock held and interrupts disabled. I must * have just failed to try_to_take_rt_mutex(). */ static void remove_waiter(struct rt_mutex *lock, @@ -1018,12 +1015,11 @@ static void remove_waiter(struct rt_mutex *lock, bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex *next_lock; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); rt_mutex_dequeue(lock, waiter); current->pi_blocked_on = NULL; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); /* * Only update priority if the waiter was the highest priority @@ -1032,7 +1028,7 @@ static void remove_waiter(struct rt_mutex *lock, if (!owner || !is_top_waiter) return; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); rt_mutex_dequeue_pi(owner, waiter); @@ -1044,7 +1040,7 @@ static void remove_waiter(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Don't walk the chain, if the owner task is not blocked @@ -1056,12 +1052,12 @@ static void remove_waiter(struct rt_mutex *lock, /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, next_lock, NULL, current); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); } /* @@ -1097,11 +1093,11 @@ void rt_mutex_adjust_pi(struct task_struct *task) * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE - * or TASK_UNINTERRUPTIBLE) + * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter * - * lock->wait_lock must be held by the caller. + * Must be called with lock->wait_lock held and interrupts disabled */ static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, @@ -1129,13 +1125,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, break; } - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); schedule(); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(state); } @@ -1172,17 +1168,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk) { struct rt_mutex_waiter waiter; + unsigned long flags; int ret = 0; debug_rt_mutex_init_waiter(&waiter); RB_CLEAR_NODE(&waiter.pi_tree_entry); RB_CLEAR_NODE(&waiter.tree_entry); - raw_spin_lock(&lock->wait_lock); + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can + * be called in early boot if the cmpxchg() fast path is disabled + * (debug, no architecture support). In this case we will acquire the + * rtmutex with lock->wait_lock held. But we cannot unconditionally + * enable interrupts in that early boot case. So we need to use the + * irqsave/restore variants. + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return 0; } @@ -1211,7 +1216,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* Remove pending timer: */ if (unlikely(timeout)) @@ -1227,6 +1232,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) { + unsigned long flags; int ret; /* @@ -1238,10 +1244,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) return 0; /* - * The mutex has currently no owner. Lock the wait lock and - * try to acquire the lock. + * The mutex has currently no owner. Lock the wait lock and try to + * acquire the lock. We use irqsave here to support early boot calls. */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); ret = try_to_take_rt_mutex(lock, current, NULL); @@ -1251,7 +1257,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return ret; } @@ -1263,7 +1269,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, struct wake_q_head *wake_q) { - raw_spin_lock(&lock->wait_lock); + unsigned long flags; + + /* irqsave required to support early boot calls */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); debug_rt_mutex_unlock(lock); @@ -1302,10 +1311,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ while (!rt_mutex_has_waiters(lock)) { /* Drops lock->wait_lock ! */ - if (unlock_rt_mutex_safe(lock) == true) + if (unlock_rt_mutex_safe(lock, flags) == true) return false; /* Relock the rtmutex and try again */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); } /* @@ -1316,7 +1325,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ mark_wakeup_next_waiter(wake_q, lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* check PI boosting */ return true; @@ -1596,10 +1605,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); if (try_to_take_rt_mutex(lock, task, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 1; } @@ -1620,7 +1629,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (unlikely(ret)) remove_waiter(lock, waiter); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); @@ -1668,7 +1677,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(TASK_INTERRUPTIBLE); @@ -1684,7 +1693,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return ret; } diff --git a/kernel/pid.c b/kernel/pid.c index f4ad91b746f1..4d73a834c7e6 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -588,7 +588,7 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - /* Veryify no one has done anything silly */ + /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); /* bump default and minimum pid_max based on number of cpus */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 02e8dfaa1ce2..68d3ebc12601 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -235,7 +235,7 @@ config PM_TRACE_RTC config APM_EMULATION tristate "Advanced Power Management Emulation" - depends on PM && SYS_SUPPORTS_APM_EMULATION + depends on SYS_SUPPORTS_APM_EMULATION help APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 63d3a24e081a..9503d590e5ef 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6840,7 +6840,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1926606ece80..56b7d4b83947 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1220,8 +1220,6 @@ static void task_numa_assign(struct task_numa_env *env, { if (env->best_task) put_task_struct(env->best_task); - if (p) - get_task_struct(p); env->best_task = p; env->best_imp = imp; @@ -1289,20 +1287,30 @@ static void task_numa_compare(struct task_numa_env *env, long imp = env->p->numa_group ? groupimp : taskimp; long moveimp = imp; int dist = env->dist; + bool assigned = false; rcu_read_lock(); raw_spin_lock_irq(&dst_rq->lock); cur = dst_rq->curr; /* - * No need to move the exiting task, and this ensures that ->curr - * wasn't reaped and thus get_task_struct() in task_numa_assign() - * is safe under RCU read lock. - * Note that rcu_read_lock() itself can't protect from the final - * put_task_struct() after the last schedule(). + * No need to move the exiting task or idle task. */ if ((cur->flags & PF_EXITING) || is_idle_task(cur)) cur = NULL; + else { + /* + * The task_struct must be protected here to protect the + * p->numa_faults access in the task_weight since the + * numa_faults could already be freed in the following path: + * finish_task_switch() + * --> put_task_struct() + * --> __put_task_struct() + * --> task_numa_free() + */ + get_task_struct(cur); + } + raw_spin_unlock_irq(&dst_rq->lock); /* @@ -1386,6 +1394,7 @@ balance: */ if (!load_too_imbalanced(src_load, dst_load, env)) { imp = moveimp - 1; + put_task_struct(cur); cur = NULL; goto assign; } @@ -1411,9 +1420,16 @@ balance: env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); assign: + assigned = true; task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); + /* + * The dst_rq->curr isn't assigned. The protection for task_struct is + * finished. + */ + if (cur && !assigned) + put_task_struct(cur); } static void task_numa_find_cpu(struct task_numa_env *env, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index de0e786b2667..544a7133cbd1 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -162,7 +162,7 @@ static void cpuidle_idle_call(void) */ if (idle_should_freeze()) { entered_state = cpuidle_enter_freeze(drv, dev); - if (entered_state >= 0) { + if (entered_state > 0) { local_irq_enable(); goto exit_idle; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 580ac2d4024f..15a1795bbba1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void) put_seccomp_filter(thread); smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); + + /* + * Don't let an unprivileged task work around + * the no_new_privs restriction by creating + * a thread that sets it up, enters seccomp, + * then dies. + */ + if (task_no_new_privs(caller)) + task_set_no_new_privs(thread); + /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ - if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) { - /* - * Don't let an unprivileged task work around - * the no_new_privs restriction by creating - * a thread that sets it up, enters seccomp, - * then dies. - */ - if (task_no_new_privs(caller)) - task_set_no_new_privs(thread); - + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); - } } } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 435b8850dd80..fa909f9fd559 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer, */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - unsigned long newstate, int reprogram) + u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - unsigned int state = timer->state; + u8 state = timer->state; timer->state = newstate; if (!(state & HRTIMER_STATE_ENQUEUED)) @@ -930,7 +930,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state = timer->state; + u8 state = timer->state; int reprogram; /* @@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest return 0; } +static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ +#ifdef CONFIG_TIME_LOW_RES + /* + * CONFIG_TIME_LOW_RES indicates that the system has no way to return + * granular time values. For relative timers we add hrtimer_resolution + * (i.e. one jiffie) to prevent short timeouts. + */ + timer->is_rel = mode & HRTIMER_MODE_REL; + if (timer->is_rel) + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); +#endif + return tim; +} + /** * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added @@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ remove_hrtimer(timer, base, true); - if (mode & HRTIMER_MODE_REL) { + if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); - /* - * CONFIG_TIME_LOW_RES is a temporary way for architectures - * to signal that they simply return xtime in - * do_gettimeoffset(). In this case we want to round up by - * resolution when starting a relative timer, to avoid short - * timeouts. This will go away with the GTOD framework. - */ -#ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); -#endif - } + + tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); @@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read + * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); - rem = hrtimer_expires_remaining(timer); + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) + rem = hrtimer_expires_remaining_adjusted(timer); + else + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } -EXPORT_SYMBOL_GPL(hrtimer_get_remaining); +EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** @@ -1220,6 +1231,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, fn = timer->function; /* + * Clear the 'is relative' flag for the TIME_LOW_RES case. If the + * timer is restarted with a period then it becomes an absolute + * timer. If its not restarted it does not matter. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES)) + timer->is_rel = false; + + /* * Because we run timers from hardirq context, there is no chance * they get migrated to another cpu, therefore its safe to unlock * the timer base. diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467573..1d5c7204ddc9 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 36f2ca09aa5e..6df8927c58a5 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -685,8 +685,18 @@ int ntp_validate_timex(struct timex *txc) if (!capable(CAP_SYS_TIME)) return -EPERM; - if (!timeval_inject_offset_valid(&txc->time)) - return -EINVAL; + if (txc->modes & ADJ_NANO) { + struct timespec ts; + + ts.tv_sec = txc->time.tv_sec; + ts.tv_nsec = txc->time.tv_usec; + if (!timespec_inject_offset_valid(&ts)) + return -EINVAL; + + } else { + if (!timeval_inject_offset_valid(&txc->time)) + return -EINVAL; + } } /* diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9fa47..f2826c35e918 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9d7a053545f5..0b17424349eb 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -36,16 +36,17 @@ */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); -/* - * The time, when the last jiffy update happened. Protected by jiffies_lock. - */ -static ktime_t last_jiffies_update; - struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +/* + * The time, when the last jiffy update happened. Protected by jiffies_lock. + */ +static ktime_t last_jiffies_update; + /* * Must be called with interrupts disabled ! */ @@ -151,6 +152,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } +#endif #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; @@ -993,9 +995,9 @@ static void tick_nohz_switch_to_nohz(void) /* Get the next period */ next = tick_init_jiffy_update(); - hrtimer_forward_now(&ts->sched_timer, tick_period); hrtimer_set_expires(&ts->sched_timer, next); - tick_program_event(next, 1); + hrtimer_forward_now(&ts->sched_timer, tick_period); + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f75e35b60149..ba7d8b288bb3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); - SEQ_printf(m, ", S:%02lx", timer->state); + SEQ_printf(m, ", S:%02x", timer->state); #ifdef CONFIG_TIMER_STATS SEQ_printf(m, ", "); print_name_offset(m, timer->start_site); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 45dd798bcd37..326a75e884db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -191,14 +191,17 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); struct perf_event *event; + struct file *file; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (!event) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + /* make sure event is local and doesn't have pmu::count */ if (event->oncpu != smp_processor_id() || event->pmu->count) @@ -228,6 +231,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) void *data = (void *) (long) r4; struct perf_sample_data sample_data; struct perf_event *event; + struct file *file; struct perf_raw_record raw = { .size = size, .data = data, @@ -236,10 +240,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (unlikely(!event)) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87fb9801bd9e..d9293402ee68 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1751,7 +1751,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, regs); + ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 547f7f923dbc..519b5a10fd70 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -21,7 +21,7 @@ #define ODEBUG_HASH_BITS 14 #define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS) -#define ODEBUG_POOL_SIZE 512 +#define ODEBUG_POOL_SIZE 1024 #define ODEBUG_POOL_MIN_LEVEL 256 #define ODEBUG_CHUNK_SHIFT PAGE_SHIFT diff --git a/mm/cleancache.c b/mm/cleancache.c index 8fc50811119b..ba5d8f3e6d68 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -22,7 +22,7 @@ * cleancache_ops is set by cleancache_register_ops to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops *cleancache_ops __read_mostly; +static const struct cleancache_ops *cleancache_ops __read_mostly; /* * Counters available via /sys/kernel/debug/cleancache (if debugfs is @@ -49,7 +49,7 @@ static void cleancache_register_ops_sb(struct super_block *sb, void *unused) /* * Register operations for cleancache. Returns 0 on success. */ -int cleancache_register_ops(struct cleancache_ops *ops) +int cleancache_register_ops(const struct cleancache_ops *ops) { if (cmpxchg(&cleancache_ops, NULL, ops)) return -EBUSY; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index e080746e1a6b..48958d3cec9e 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -594,7 +594,8 @@ static int ignore_undef_symbol(struct elf_info *info, const char *symname) if (strncmp(symname, "_restgpr0_", sizeof("_restgpr0_") - 1) == 0 || strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0 || strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 || - strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0) + strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0 || + strcmp(symname, ".TOC.") == 0) return 1; /* Do not ignore this symbol */ return 0; diff --git a/security/keys/key.c b/security/keys/key.c index 07a87311055c..09ef276c4bdc 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -430,7 +430,8 @@ static int __key_instantiate_and_link(struct key *key, /* and link it into the destination keyring */ if (keyring) { - set_bit(KEY_FLAG_KEEP, &key->flags); + if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) + set_bit(KEY_FLAG_KEEP, &key->flags); __key_link(key, _edit); } diff --git a/sound/core/Kconfig b/sound/core/Kconfig index e3e949126a56..a2a1e24becc6 100644 --- a/sound/core/Kconfig +++ b/sound/core/Kconfig @@ -97,11 +97,11 @@ config SND_PCM_TIMER bool "PCM timer interface" if EXPERT default y help - If you disable this option, pcm timer will be inavailable, so - those stubs used pcm timer (e.g. dmix, dsnoop & co) may work + If you disable this option, pcm timer will be unavailable, so + those stubs that use pcm timer (e.g. dmix, dsnoop & co) may work incorrectlly. - For some embedded device, we may disable it to reduce memory + For some embedded devices, we may disable it to reduce memory footprint, about 20KB on x86_64 platform. config SND_SEQUENCER_OSS diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 18b8dc45bb8f..7fac3cae8abd 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -46,6 +46,13 @@ #include <sound/compress_offload.h> #include <sound/compress_driver.h> +/* struct snd_compr_codec_caps overflows the ioctl bit size for some + * architectures, so we need to disable the relevant ioctls. + */ +#if _IOC_SIZEBITS < 14 +#define COMPR_CODEC_CAPS_OVERFLOW +#endif + /* TODO: * - add substream support for multiple devices in case of * SND_DYNAMIC_MINORS is not used @@ -440,6 +447,7 @@ out: return retval; } +#ifndef COMPR_CODEC_CAPS_OVERFLOW static int snd_compr_get_codec_caps(struct snd_compr_stream *stream, unsigned long arg) { @@ -463,6 +471,7 @@ out: kfree(caps); return retval; } +#endif /* !COMPR_CODEC_CAPS_OVERFLOW */ /* revisit this with snd_pcm_preallocate_xxx */ static int snd_compr_allocate_buffer(struct snd_compr_stream *stream, @@ -801,9 +810,11 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): retval = snd_compr_get_caps(stream, arg); break; +#ifndef COMPR_CODEC_CAPS_OVERFLOW case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): retval = snd_compr_get_codec_caps(stream, arg); break; +#endif case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): retval = snd_compr_set_params(stream, arg); break; diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index b1221b29728e..6779e82b46dd 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -202,7 +202,7 @@ snd_seq_oss_open(struct file *file, int level) dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { - pr_err("ALSA: seq_oss: too many applications\n"); + pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 0f3b38184fe5..b16dbef04174 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -308,7 +308,7 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) struct seq_oss_synth *rec; struct seq_oss_synthinfo *info; - if (snd_BUG_ON(dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) + if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 75b74850c005..bde33308f0d6 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver."); module_param(fake_buffer, bool, 0444); MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations."); #ifdef CONFIG_HIGH_RES_TIMERS -module_param(hrtimer, bool, 0644); +module_param(hrtimer, bool, 0444); MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source."); #endif diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 926e5dcbb66a..5022c9b97ddf 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -47,14 +47,16 @@ static const unsigned int bridgeco_freq_table[] = { [6] = 0x07, }; -static unsigned int -get_formation_index(unsigned int rate) +static int +get_formation_index(unsigned int rate, unsigned int *index) { unsigned int i; for (i = 0; i < ARRAY_SIZE(snd_bebob_rate_table); i++) { - if (snd_bebob_rate_table[i] == rate) - return i; + if (snd_bebob_rate_table[i] == rate) { + *index = i; + return 0; + } } return -EINVAL; } @@ -425,7 +427,9 @@ make_both_connections(struct snd_bebob *bebob, unsigned int rate) goto end; /* confirm params for both streams */ - index = get_formation_index(rate); + err = get_formation_index(rate, &index); + if (err < 0) + goto end; pcm_channels = bebob->tx_stream_formations[index].pcm; midi_channels = bebob->tx_stream_formations[index].midi; err = amdtp_am824_set_parameters(&bebob->tx_stream, rate, diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig index 0216475fc759..37adcc6cbe6b 100644 --- a/sound/isa/Kconfig +++ b/sound/isa/Kconfig @@ -3,6 +3,7 @@ config SND_WSS_LIB tristate select SND_PCM + select SND_TIMER config SND_SB_COMMON tristate @@ -42,6 +43,7 @@ config SND_AD1816A select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Analog Devices SoundPort AD1816A or compatible sound chips. @@ -209,6 +211,7 @@ config SND_GUSCLASSIC tristate "Gravis UltraSound Classic" select SND_RAWMIDI select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Classic soundcards. @@ -221,6 +224,7 @@ config SND_GUSEXTREME select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Extreme soundcards. diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 656ce39bddbc..8f6594a7d37f 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -155,6 +155,7 @@ config SND_AZT3328 select SND_PCM select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y here to include support for Aztech AZF3328 (PCI168) @@ -463,6 +464,7 @@ config SND_EMU10K1 select SND_HWDEP select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y to include support for Sound Blaster PCI 512, Live!, @@ -889,6 +891,7 @@ config SND_YMFPCI select SND_OPL3_LIB select SND_MPU401_UART select SND_AC97_CODEC + select SND_TIMER help Say Y here to include support for Yamaha PCI audio chips - YMF724, YMF724F, YMF740, YMF740C, YMF744, YMF754. diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 256e6cda218f..4045dca3d699 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -90,6 +90,8 @@ enum { #define NVIDIA_HDA_ENABLE_COHBIT 0x01 /* Defines for Intel SCH HDA snoop control */ +#define INTEL_HDA_CGCTL 0x48 +#define INTEL_HDA_CGCTL_MISCBDCGE (0x1 << 6) #define INTEL_SCH_HDA_DEVC 0x78 #define INTEL_SCH_HDA_DEVC_NOSNOOP (0x1<<11) @@ -534,10 +536,21 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; + u32 val; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } azx_init_chip(chip, full_reset); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val | INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 426a29a1c19b..1f52b55d77c9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -3653,6 +3653,7 @@ HDA_CODEC_ENTRY(0x10de0070, "GPU 70 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0071, "GPU 71 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0072, "GPU 72 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de007d, "GPU 7d HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de0083, "GPU 83 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), diff --git a/sound/sparc/Kconfig b/sound/sparc/Kconfig index d75deba5617d..dfcd38647606 100644 --- a/sound/sparc/Kconfig +++ b/sound/sparc/Kconfig @@ -22,6 +22,7 @@ config SND_SUN_AMD7930 config SND_SUN_CS4231 tristate "Sun CS4231" select SND_PCM + select SND_TIMER help Say Y here to include support for CS4231 sound device on Sun. diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 23ea6d800c4c..a75d9ce7d77a 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1205,8 +1205,12 @@ void snd_usb_set_interface_quirk(struct usb_device *dev) * "Playback Design" products need a 50ms delay after setting the * USB interface. */ - if (le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) + switch (le16_to_cpu(dev->descriptor.idVendor)) { + case 0x23ba: /* Playback Design */ + case 0x0644: /* TEAC Corp. */ mdelay(50); + break; + } } void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, @@ -1221,6 +1225,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + /* + * "TEAC Corp." products need a 20ms delay after each + * class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x0644) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + mdelay(20); + /* Marantz/Denon devices with USB DAC functionality need a delay * after each class compliant request */ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0a22407e1d7d..5d34815c7ccb 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -77,6 +77,9 @@ include config/utilities.mak # Define NO_AUXTRACE if you do not want AUX area tracing support # # Define NO_LIBBPF if you do not want BPF support +# +# Define FEATURES_DUMP to provide features detection dump file +# and bypass the feature detection # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -166,6 +169,15 @@ ifeq ($(config),1) include config/Makefile endif +# The FEATURE_DUMP_EXPORT holds location of the actual +# FEATURE_DUMP file to be used to bypass feature detection +# (for bpf or any other subproject) +ifeq ($(FEATURES_DUMP),) +FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP) +else +FEATURE_DUMP_EXPORT := $(FEATURES_DUMP) +endif + export prefix bindir sharedir sysconfdir DESTDIR # sparse is architecture-neutral, which means that we need to tell it @@ -436,7 +448,7 @@ $(LIBAPI)-clean: $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null $(LIBBPF): fixdep FORCE - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP) + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) @@ -611,6 +623,17 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(python-clean) # +# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY) +# file if defined, with no further action. +feature-dump: +ifdef FEATURE_DUMP_COPY + @cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY) + @echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)" +else + @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP" +endif + +# # Trick: if ../../.git does not exist - we are building out of tree for example, # then force version regeneration: # diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 3e89ba825f6b..7f064eb37158 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -17,7 +17,7 @@ static pid_t spawn(void) if (pid) return pid; - while(1); + while(1) sleep(5); return 0; } diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index e5959c136a19..511141b102e8 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -181,7 +181,11 @@ LDFLAGS += -Wl,-z,noexecstack EXTLIBS = -lpthread -lrt -lm -ldl +ifeq ($(FEATURES_DUMP),) include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif ifeq ($(feature-stackprotector-all), 1) CFLAGS += -fstack-protector-all diff --git a/tools/perf/tests/make b/tools/perf/tests/make index df38decc48c3..f918015512af 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -5,7 +5,7 @@ ifeq ($(MAKECMDGOALS),) # no target specified, trigger the whole suite all: @echo "Testing Makefile"; $(MAKE) -sf tests/make MK=Makefile - @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf + @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf SET_PARALLEL=1 SET_O=1 else # run only specific test over 'Makefile' %: @@ -13,6 +13,26 @@ else endif else PERF := . +PERF_O := $(PERF) +O_OPT := + +ifneq ($(O),) + FULL_O := $(shell readlink -f $(O) || echo $(O)) + PERF_O := $(FULL_O) + ifeq ($(SET_O),1) + O_OPT := 'O=$(FULL_O)' + endif + K_O_OPT := 'O=$(FULL_O)' +endif + +PARALLEL_OPT= +ifeq ($(SET_PARALLEL),1) + cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null) + ifeq ($(cores),0) + cores := 1 + endif + PARALLEL_OPT="-j$(cores)" +endif # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -156,11 +176,11 @@ test_make_doc := $(test_ok) test_make_help_O := $(test_ok) test_make_doc_O := $(test_ok) -test_make_python_perf_so := test -f $(PERF)/python/perf.so +test_make_python_perf_so := test -f $(PERF_O)/python/perf.so -test_make_perf_o := test -f $(PERF)/perf.o -test_make_util_map_o := test -f $(PERF)/util/map.o -test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o +test_make_perf_o := test -f $(PERF_O)/perf.o +test_make_util_map_o := test -f $(PERF_O)/util/map.o +test_make_util_pmu_bison_o := test -f $(PERF_O)/util/pmu-bison.o define test_dest_files for file in $(1); do \ @@ -227,7 +247,7 @@ test_make_perf_o_O := test -f $$TMP_O/perf.o test_make_util_map_o_O := test -f $$TMP_O/util/map.o test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o -test_default = test -x $(PERF)/perf +test_default = test -x $(PERF_O)/perf test = $(if $(test_$1),$(test_$1),$(test_default)) test_default_O = test -x $$TMP_O/perf @@ -247,12 +267,12 @@ endif MAKEFLAGS := --no-print-directory -clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null) +clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null) $(run): $(call clean) @TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \ + cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)" >> $@ 2>&1; \ @@ -263,7 +283,7 @@ $(run_O): $(call clean) @TMP_O=$$(mktemp -d); \ TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ + cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)" >> $@ 2>&1; \ @@ -276,17 +296,22 @@ tarpkg: ( eval $$cmd ) >> $@ 2>&1 && \ rm -f $@ +KERNEL_O := ../.. +ifneq ($(O),) + KERNEL_O := $(O) +endif + make_kernelsrc: - @echo "- make -C <kernelsrc> tools/perf" + @echo "- make -C <kernelsrc> $(PARALLEL_OPT) $(K_O_OPT) tools/perf" $(call clean); \ - (make -C ../.. tools/perf) > $@ 2>&1 && \ - test -x perf && rm -f $@ || (cat $@ ; false) + (make -C ../.. $(PARALLEL_OPT) $(K_O_OPT) tools/perf) > $@ 2>&1 && \ + test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) make_kernelsrc_tools: - @echo "- make -C <kernelsrc>/tools perf" + @echo "- make -C <kernelsrc>/tools $(PARALLEL_OPT) $(K_O_OPT) perf" $(call clean); \ - (make -C ../../tools perf) > $@ 2>&1 && \ - test -x perf && rm -f $@ || (cat $@ ; false) + (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \ + test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools @echo OK diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d4d7cc27252f..718bd46d47fa 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser, nd = browser->curr_hot; break; case K_UNTAB: - if (nd != NULL) + if (nd != NULL) { nd = rb_next(nd); if (nd == NULL) nd = rb_first(&browser->entries); - else + } else nd = browser->curr_hot; break; case K_F1: diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c226303e3da0..68a7612019dc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -131,6 +131,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen); } if (h->mem_info->iaddr.sym) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d5636ba94b20..40b7a0d0905b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1149,7 +1149,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, machine = machines__find(machines, pid); if (!machine) - machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2f901d15e063..2b58edccd56f 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -310,7 +310,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, int i, ret; aggr->val = aggr->ena = aggr->run = 0; - init_stats(ps->res_stats); if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3b2de6eb3376..ab02209a7cf3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1466,7 +1466,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0) + if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); /* diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index e86d937cc22c..60fe3c569bd9 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -45,7 +45,17 @@ static inline int ksft_exit_fail(void) } #endif -#define NSEC_PER_SEC 1000000000L +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + +#define ADJ_SETOFFSET 0x0100 + +#include <sys/syscall.h> +static int clock_adjtime(clockid_t id, struct timex *tx) +{ + return syscall(__NR_clock_adjtime, id, tx); +} + /* clear NTP time_status & time_state */ int clear_time_state(void) @@ -193,10 +203,137 @@ out: } +int set_offset(long long offset, int use_nano) +{ + struct timex tmx = {}; + int ret; + + tmx.modes = ADJ_SETOFFSET; + if (use_nano) { + tmx.modes |= ADJ_NANO; + + tmx.time.tv_sec = offset / NSEC_PER_SEC; + tmx.time.tv_usec = offset % NSEC_PER_SEC; + + if (offset < 0 && tmx.time.tv_usec) { + tmx.time.tv_sec -= 1; + tmx.time.tv_usec += NSEC_PER_SEC; + } + } else { + tmx.time.tv_sec = offset / USEC_PER_SEC; + tmx.time.tv_usec = offset % USEC_PER_SEC; + + if (offset < 0 && tmx.time.tv_usec) { + tmx.time.tv_sec -= 1; + tmx.time.tv_usec += USEC_PER_SEC; + } + } + + ret = clock_adjtime(CLOCK_REALTIME, &tmx); + if (ret < 0) { + printf("(sec: %ld usec: %ld) ", tmx.time.tv_sec, tmx.time.tv_usec); + printf("[FAIL]\n"); + return -1; + } + return 0; +} + +int set_bad_offset(long sec, long usec, int use_nano) +{ + struct timex tmx = {}; + int ret; + + tmx.modes = ADJ_SETOFFSET; + if (use_nano) + tmx.modes |= ADJ_NANO; + + tmx.time.tv_sec = sec; + tmx.time.tv_usec = usec; + ret = clock_adjtime(CLOCK_REALTIME, &tmx); + if (ret >= 0) { + printf("Invalid (sec: %ld usec: %ld) did not fail! ", tmx.time.tv_sec, tmx.time.tv_usec); + printf("[FAIL]\n"); + return -1; + } + return 0; +} + +int validate_set_offset(void) +{ + printf("Testing ADJ_SETOFFSET... "); + + /* Test valid values */ + if (set_offset(NSEC_PER_SEC - 1, 1)) + return -1; + + if (set_offset(-NSEC_PER_SEC + 1, 1)) + return -1; + + if (set_offset(-NSEC_PER_SEC - 1, 1)) + return -1; + + if (set_offset(5 * NSEC_PER_SEC, 1)) + return -1; + + if (set_offset(-5 * NSEC_PER_SEC, 1)) + return -1; + + if (set_offset(5 * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1)) + return -1; + + if (set_offset(-5 * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1)) + return -1; + + if (set_offset(USEC_PER_SEC - 1, 0)) + return -1; + + if (set_offset(-USEC_PER_SEC + 1, 0)) + return -1; + + if (set_offset(-USEC_PER_SEC - 1, 0)) + return -1; + + if (set_offset(5 * USEC_PER_SEC, 0)) + return -1; + + if (set_offset(-5 * USEC_PER_SEC, 0)) + return -1; + + if (set_offset(5 * USEC_PER_SEC + USEC_PER_SEC / 2, 0)) + return -1; + + if (set_offset(-5 * USEC_PER_SEC - USEC_PER_SEC / 2, 0)) + return -1; + + /* Test invalid values */ + if (set_bad_offset(0, -1, 1)) + return -1; + if (set_bad_offset(0, -1, 0)) + return -1; + if (set_bad_offset(0, 2 * NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, 2 * USEC_PER_SEC, 0)) + return -1; + if (set_bad_offset(0, NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, USEC_PER_SEC, 0)) + return -1; + if (set_bad_offset(0, -NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, -USEC_PER_SEC, 0)) + return -1; + + printf("[OK]\n"); + return 0; +} + int main(int argc, char **argv) { if (validate_freq()) return ksft_exit_fail(); + if (validate_set_offset()) + return ksft_exit_fail(); + return ksft_exit_pass(); } diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 26b7926bda88..ba34f9e96efd 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -1,15 +1,19 @@ #if defined(__i386__) || defined(__x86_64__) #define barrier() asm volatile("" ::: "memory") -#define mb() __sync_synchronize() - -#define smp_mb() mb() -# define dma_rmb() barrier() -# define dma_wmb() barrier() -# define smp_rmb() barrier() -# define smp_wmb() barrier() +#define virt_mb() __sync_synchronize() +#define virt_rmb() barrier() +#define virt_wmb() barrier() +/* Atomic store should be enough, but gcc generates worse code in that case. */ +#define virt_store_mb(var, value) do { \ + typeof(var) virt_store_mb_value = (value); \ + __atomic_exchange(&(var), &virt_store_mb_value, &virt_store_mb_value, \ + __ATOMIC_SEQ_CST); \ + barrier(); \ +} while (0); /* Weak barriers should be used. If not - it's a bug */ -# define rmb() abort() -# define wmb() abort() +# define mb() abort() +# define rmb() abort() +# define wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h new file mode 100644 index 000000000000..845960e1cbf2 --- /dev/null +++ b/tools/virtio/linux/compiler.h @@ -0,0 +1,9 @@ +#ifndef LINUX_COMPILER_H +#define LINUX_COMPILER_H + +#define WRITE_ONCE(var, val) \ + (*((volatile typeof(val) *)(&(var))) = (val)) + +#define READ_ONCE(var) (*((volatile typeof(val) *)(&(var)))) + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 4db7d5691ba7..033849948215 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -8,6 +8,7 @@ #include <assert.h> #include <stdarg.h> +#include <linux/compiler.h> #include <linux/types.h> #include <linux/printk.h> #include <linux/bug.h> diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile new file mode 100644 index 000000000000..feaa64ac4630 --- /dev/null +++ b/tools/virtio/ringtest/Makefile @@ -0,0 +1,22 @@ +all: + +all: ring virtio_ring_0_9 virtio_ring_poll + +CFLAGS += -Wall +CFLAGS += -pthread -O2 -ggdb +LDFLAGS += -pthread -O2 -ggdb + +main.o: main.c main.h +ring.o: ring.c main.h +virtio_ring_0_9.o: virtio_ring_0_9.c main.h +virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h +ring: ring.o main.o +virtio_ring_0_9: virtio_ring_0_9.o main.o +virtio_ring_poll: virtio_ring_poll.o main.o +clean: + -rm main.o + -rm ring.o ring + -rm virtio_ring_0_9.o virtio_ring_0_9 + -rm virtio_ring_poll.o virtio_ring_poll + +.PHONY: all clean diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README new file mode 100644 index 000000000000..34e94c46104f --- /dev/null +++ b/tools/virtio/ringtest/README @@ -0,0 +1,2 @@ +Partial implementation of various ring layouts, useful to tune virtio design. +Uses shared memory heavily. diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c new file mode 100644 index 000000000000..3a5ff438bd62 --- /dev/null +++ b/tools/virtio/ringtest/main.c @@ -0,0 +1,366 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Command line processing and common functions for ring benchmarking. + */ +#define _GNU_SOURCE +#include <getopt.h> +#include <pthread.h> +#include <assert.h> +#include <sched.h> +#include "main.h" +#include <sys/eventfd.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <limits.h> + +int runcycles = 10000000; +int max_outstanding = INT_MAX; +int batch = 1; + +bool do_sleep = false; +bool do_relax = false; +bool do_exit = true; + +unsigned ring_size = 256; + +static int kickfd = -1; +static int callfd = -1; + +void notify(int fd) +{ + unsigned long long v = 1; + int r; + + vmexit(); + r = write(fd, &v, sizeof v); + assert(r == sizeof v); + vmentry(); +} + +void wait_for_notify(int fd) +{ + unsigned long long v = 1; + int r; + + vmexit(); + r = read(fd, &v, sizeof v); + assert(r == sizeof v); + vmentry(); +} + +void kick(void) +{ + notify(kickfd); +} + +void wait_for_kick(void) +{ + wait_for_notify(kickfd); +} + +void call(void) +{ + notify(callfd); +} + +void wait_for_call(void) +{ + wait_for_notify(callfd); +} + +void set_affinity(const char *arg) +{ + cpu_set_t cpuset; + int ret; + pthread_t self; + long int cpu; + char *endptr; + + if (!arg) + return; + + cpu = strtol(arg, &endptr, 0); + assert(!*endptr); + + assert(cpu >= 0 || cpu < CPU_SETSIZE); + + self = pthread_self(); + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + + ret = pthread_setaffinity_np(self, sizeof(cpu_set_t), &cpuset); + assert(!ret); +} + +static void run_guest(void) +{ + int completed_before; + int completed = 0; + int started = 0; + int bufs = runcycles; + int spurious = 0; + int r; + unsigned len; + void *buf; + int tokick = batch; + + for (;;) { + if (do_sleep) + disable_call(); + completed_before = completed; + do { + if (started < bufs && + started - completed < max_outstanding) { + r = add_inbuf(0, NULL, "Hello, world!"); + if (__builtin_expect(r == 0, true)) { + ++started; + if (!--tokick) { + tokick = batch; + if (do_sleep) + kick_available(); + } + + } + } else + r = -1; + + /* Flush out completed bufs if any */ + if (get_buf(&len, &buf)) { + ++completed; + if (__builtin_expect(completed == bufs, false)) + return; + r = 0; + } + } while (r == 0); + if (completed == completed_before) + ++spurious; + assert(completed <= bufs); + assert(started <= bufs); + if (do_sleep) { + if (enable_call()) + wait_for_call(); + } else { + poll_used(); + } + } +} + +static void run_host(void) +{ + int completed_before; + int completed = 0; + int spurious = 0; + int bufs = runcycles; + unsigned len; + void *buf; + + for (;;) { + if (do_sleep) { + if (enable_kick()) + wait_for_kick(); + } else { + poll_avail(); + } + if (do_sleep) + disable_kick(); + completed_before = completed; + while (__builtin_expect(use_buf(&len, &buf), true)) { + if (do_sleep) + call_used(); + ++completed; + if (__builtin_expect(completed == bufs, false)) + return; + } + if (completed == completed_before) + ++spurious; + assert(completed <= bufs); + if (completed == bufs) + break; + } +} + +void *start_guest(void *arg) +{ + set_affinity(arg); + run_guest(); + pthread_exit(NULL); +} + +void *start_host(void *arg) +{ + set_affinity(arg); + run_host(); + pthread_exit(NULL); +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "help", + .has_arg = no_argument, + .val = 'h', + }, + { + .name = "host-affinity", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "guest-affinity", + .has_arg = required_argument, + .val = 'G', + }, + { + .name = "ring-size", + .has_arg = required_argument, + .val = 'R', + }, + { + .name = "run-cycles", + .has_arg = required_argument, + .val = 'C', + }, + { + .name = "outstanding", + .has_arg = required_argument, + .val = 'o', + }, + { + .name = "batch", + .has_arg = required_argument, + .val = 'b', + }, + { + .name = "sleep", + .has_arg = no_argument, + .val = 's', + }, + { + .name = "relax", + .has_arg = no_argument, + .val = 'x', + }, + { + .name = "exit", + .has_arg = no_argument, + .val = 'e', + }, + { + } +}; + +static void help(void) +{ + fprintf(stderr, "Usage: <test> [--help]" + " [--host-affinity H]" + " [--guest-affinity G]" + " [--ring-size R (default: %d)]" + " [--run-cycles C (default: %d)]" + " [--batch b]" + " [--outstanding o]" + " [--sleep]" + " [--relax]" + " [--exit]" + "\n", + ring_size, + runcycles); +} + +int main(int argc, char **argv) +{ + int ret; + pthread_t host, guest; + void *tret; + char *host_arg = NULL; + char *guest_arg = NULL; + char *endptr; + long int c; + + kickfd = eventfd(0, 0); + assert(kickfd >= 0); + callfd = eventfd(0, 0); + assert(callfd >= 0); + + for (;;) { + int o = getopt_long(argc, argv, optstring, longopts, NULL); + switch (o) { + case -1: + goto done; + case '?': + help(); + exit(2); + case 'H': + host_arg = optarg; + break; + case 'G': + guest_arg = optarg; + break; + case 'R': + ring_size = strtol(optarg, &endptr, 0); + assert(ring_size && !(ring_size & (ring_size - 1))); + assert(!*endptr); + break; + case 'C': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + runcycles = c; + break; + case 'o': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + max_outstanding = c; + break; + case 'b': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + batch = c; + break; + case 's': + do_sleep = true; + break; + case 'x': + do_relax = true; + break; + case 'e': + do_exit = true; + break; + default: + help(); + exit(4); + break; + } + } + + /* does nothing here, used to make sure all smp APIs compile */ + smp_acquire(); + smp_release(); + smp_mb(); +done: + + if (batch > max_outstanding) + batch = max_outstanding; + + if (optind < argc) { + help(); + exit(4); + } + alloc_ring(); + + ret = pthread_create(&host, NULL, start_host, host_arg); + assert(!ret); + ret = pthread_create(&guest, NULL, start_guest, guest_arg); + assert(!ret); + + ret = pthread_join(guest, &tret); + assert(!ret); + ret = pthread_join(host, &tret); + assert(!ret); + return 0; +} diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h new file mode 100644 index 000000000000..16917acb0ade --- /dev/null +++ b/tools/virtio/ringtest/main.h @@ -0,0 +1,119 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Common macros and functions for ring benchmarking. + */ +#ifndef MAIN_H +#define MAIN_H + +#include <stdbool.h> + +extern bool do_exit; + +#if defined(__x86_64__) || defined(__i386__) +#include "x86intrin.h" + +static inline void wait_cycles(unsigned long long cycles) +{ + unsigned long long t; + + t = __rdtsc(); + while (__rdtsc() - t < cycles) {} +} + +#define VMEXIT_CYCLES 500 +#define VMENTRY_CYCLES 500 + +#else +static inline void wait_cycles(unsigned long long cycles) +{ + _Exit(5); +} +#define VMEXIT_CYCLES 0 +#define VMENTRY_CYCLES 0 +#endif + +static inline void vmexit(void) +{ + if (!do_exit) + return; + + wait_cycles(VMEXIT_CYCLES); +} +static inline void vmentry(void) +{ + if (!do_exit) + return; + + wait_cycles(VMENTRY_CYCLES); +} + +/* implemented by ring */ +void alloc_ring(void); +/* guest side */ +int add_inbuf(unsigned, void *, void *); +void *get_buf(unsigned *, void **); +void disable_call(); +bool enable_call(); +void kick_available(); +void poll_used(); +/* host side */ +void disable_kick(); +bool enable_kick(); +bool use_buf(unsigned *, void **); +void call_used(); +void poll_avail(); + +/* implemented by main */ +extern bool do_sleep; +void kick(void); +void wait_for_kick(void); +void call(void); +void wait_for_call(void); + +extern unsigned ring_size; + +/* Compiler barrier - similar to what Linux uses */ +#define barrier() asm volatile("" ::: "memory") + +/* Is there a portable way to do this? */ +#if defined(__x86_64__) || defined(__i386__) +#define cpu_relax() asm ("rep; nop" ::: "memory") +#else +#define cpu_relax() assert(0) +#endif + +extern bool do_relax; + +static inline void busy_wait(void) +{ + if (do_relax) + cpu_relax(); + else + /* prevent compiler from removing busy loops */ + barrier(); +} + +/* + * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized + * with other __ATOMIC_SEQ_CST calls. + */ +#define smp_mb() __sync_synchronize() + +/* + * This abuses the atomic builtins for thread fences, and + * adds a compiler barrier. + */ +#define smp_release() do { \ + barrier(); \ + __atomic_thread_fence(__ATOMIC_RELEASE); \ +} while (0) + +#define smp_acquire() do { \ + __atomic_thread_fence(__ATOMIC_ACQUIRE); \ + barrier(); \ +} while (0) + +#endif diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c new file mode 100644 index 000000000000..c25c8d248b6b --- /dev/null +++ b/tools/virtio/ringtest/ring.c @@ -0,0 +1,272 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Simple descriptor-based ring. virtio 0.9 compatible event index is used for + * signalling, unconditionally. + */ +#define _GNU_SOURCE +#include "main.h" +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +/* Next - Where next entry will be written. + * Prev - "Next" value when event triggered previously. + * Event - Peer requested event after writing this entry. + */ +static inline bool need_event(unsigned short event, + unsigned short next, + unsigned short prev) +{ + return (unsigned short)(next - event - 1) < (unsigned short)(next - prev); +} + +/* Design: + * Guest adds descriptors with unique index values and DESC_HW in flags. + * Host overwrites used descriptors with correct len, index, and DESC_HW clear. + * Flags are always set last. + */ +#define DESC_HW 0x1 + +struct desc { + unsigned short flags; + unsigned short index; + unsigned len; + unsigned long long addr; +}; + +/* how much padding is needed to avoid false cache sharing */ +#define HOST_GUEST_PADDING 0x80 + +/* Mostly read */ +struct event { + unsigned short kick_index; + unsigned char reserved0[HOST_GUEST_PADDING - 2]; + unsigned short call_index; + unsigned char reserved1[HOST_GUEST_PADDING - 2]; +}; + +struct data { + void *buf; /* descriptor is writeable, we can't get buf from there */ + void *data; +} *data; + +struct desc *ring; +struct event *event; + +struct guest { + unsigned avail_idx; + unsigned last_used_idx; + unsigned num_free; + unsigned kicked_avail_idx; + unsigned char reserved[HOST_GUEST_PADDING - 12]; +} guest; + +struct host { + /* we do not need to track last avail index + * unless we have more than one in flight. + */ + unsigned used_idx; + unsigned called_used_idx; + unsigned char reserved[HOST_GUEST_PADDING - 4]; +} host; + +/* implemented by ring */ +void alloc_ring(void) +{ + int ret; + int i; + + ret = posix_memalign((void **)&ring, 0x1000, ring_size * sizeof *ring); + if (ret) { + perror("Unable to allocate ring buffer.\n"); + exit(3); + } + event = malloc(sizeof *event); + if (!event) { + perror("Unable to allocate event buffer.\n"); + exit(3); + } + memset(event, 0, sizeof *event); + guest.avail_idx = 0; + guest.kicked_avail_idx = -1; + guest.last_used_idx = 0; + host.used_idx = 0; + host.called_used_idx = -1; + for (i = 0; i < ring_size; ++i) { + struct desc desc = { + .index = i, + }; + ring[i] = desc; + } + guest.num_free = ring_size; + data = malloc(ring_size * sizeof *data); + if (!data) { + perror("Unable to allocate data buffer.\n"); + exit(3); + } + memset(data, 0, ring_size * sizeof *data); +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + unsigned head, index; + + if (!guest.num_free) + return -1; + + guest.num_free--; + head = (ring_size - 1) & (guest.avail_idx++); + + /* Start with a write. On MESI architectures this helps + * avoid a shared state with consumer that is polling this descriptor. + */ + ring[head].addr = (unsigned long)(void*)buf; + ring[head].len = len; + /* read below might bypass write above. That is OK because it's just an + * optimization. If this happens, we will get the cache line in a + * shared state which is unfortunate, but probably not worth it to + * add an explicit full barrier to avoid this. + */ + barrier(); + index = ring[head].index; + data[index].buf = buf; + data[index].data = datap; + /* Barrier A (for pairing) */ + smp_release(); + ring[head].flags = DESC_HW; + + return 0; +} + +void *get_buf(unsigned *lenp, void **bufp) +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + unsigned index; + void *datap; + + if (ring[head].flags & DESC_HW) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + *lenp = ring[head].len; + index = ring[head].index & (ring_size - 1); + datap = data[index].data; + *bufp = data[index].buf; + data[index].buf = NULL; + data[index].data = NULL; + guest.num_free++; + guest.last_used_idx++; + return datap; +} + +void poll_used(void) +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + + while (ring[head].flags & DESC_HW) + busy_wait(); +} + +void disable_call() +{ + /* Doing nothing to disable calls might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_call() +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + + event->call_index = guest.last_used_idx; + /* Flush call index write */ + /* Barrier D (for pairing) */ + smp_mb(); + return ring[head].flags & DESC_HW; +} + +void kick_available(void) +{ + /* Flush in previous flags write */ + /* Barrier C (for pairing) */ + smp_mb(); + if (!need_event(event->kick_index, + guest.avail_idx, + guest.kicked_avail_idx)) + return; + + guest.kicked_avail_idx = guest.avail_idx; + kick(); +} + +/* host side */ +void disable_kick() +{ + /* Doing nothing to disable kicks might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_kick() +{ + unsigned head = (ring_size - 1) & host.used_idx; + + event->kick_index = host.used_idx; + /* Barrier C (for pairing) */ + smp_mb(); + return !(ring[head].flags & DESC_HW); +} + +void poll_avail(void) +{ + unsigned head = (ring_size - 1) & host.used_idx; + + while (!(ring[head].flags & DESC_HW)) + busy_wait(); +} + +bool use_buf(unsigned *lenp, void **bufp) +{ + unsigned head = (ring_size - 1) & host.used_idx; + + if (!(ring[head].flags & DESC_HW)) + return false; + + /* make sure length read below is not speculated */ + /* Barrier A (for pairing) */ + smp_acquire(); + + /* simple in-order completion: we don't need + * to touch index at all. This also means we + * can just modify the descriptor in-place. + */ + ring[head].len--; + /* Make sure len is valid before flags. + * Note: alternative is to write len and flags in one access - + * possible on 64 bit architectures but wmb is free on Intel anyway + * so I have no way to test whether it's a gain. + */ + /* Barrier B (for pairing) */ + smp_release(); + ring[head].flags = 0; + host.used_idx++; + return true; +} + +void call_used(void) +{ + /* Flush in previous flags write */ + /* Barrier D (for pairing) */ + smp_mb(); + if (!need_event(event->call_index, + host.used_idx, + host.called_used_idx)) + return; + + host.called_used_idx = host.used_idx; + call(); +} diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh new file mode 100755 index 000000000000..52b0f71ffa8d --- /dev/null +++ b/tools/virtio/ringtest/run-on-all.sh @@ -0,0 +1,24 @@ +#!/bin/sh + +#use last CPU for host. Why not the first? +#many devices tend to use cpu0 by default so +#it tends to be busier +HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1) + +#run command on all cpus +for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n); +do + #Don't run guest and host on same CPU + #It actually works ok if using signalling + if + (echo "$@" | grep -e "--sleep" > /dev/null) || \ + test $HOST_AFFINITY '!=' $cpu + then + echo "GUEST AFFINITY $cpu" + "$@" --host-affinity $HOST_AFFINITY --guest-affinity $cpu + fi +done +echo "NO GUEST AFFINITY" +"$@" --host-affinity $HOST_AFFINITY +echo "NO AFFINITY" +"$@" diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c new file mode 100644 index 000000000000..47c9a1a18d36 --- /dev/null +++ b/tools/virtio/ringtest/virtio_ring_0_9.c @@ -0,0 +1,316 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Partial implementation of virtio 0.9. event index is used for signalling, + * unconditionally. Design roughly follows linux kernel implementation in order + * to be able to judge its performance. + */ +#define _GNU_SOURCE +#include "main.h" +#include <stdlib.h> +#include <stdio.h> +#include <assert.h> +#include <string.h> +#include <linux/virtio_ring.h> + +struct data { + void *data; +} *data; + +struct vring ring; + +/* enabling the below activates experimental ring polling code + * (which skips index reads on consumer in favor of looking at + * high bits of ring id ^ 0x8000). + */ +/* #ifdef RING_POLL */ + +/* how much padding is needed to avoid false cache sharing */ +#define HOST_GUEST_PADDING 0x80 + +struct guest { + unsigned short avail_idx; + unsigned short last_used_idx; + unsigned short num_free; + unsigned short kicked_avail_idx; + unsigned short free_head; + unsigned char reserved[HOST_GUEST_PADDING - 10]; +} guest; + +struct host { + /* we do not need to track last avail index + * unless we have more than one in flight. + */ + unsigned short used_idx; + unsigned short called_used_idx; + unsigned char reserved[HOST_GUEST_PADDING - 4]; +} host; + +/* implemented by ring */ +void alloc_ring(void) +{ + int ret; + int i; + void *p; + + ret = posix_memalign(&p, 0x1000, vring_size(ring_size, 0x1000)); + if (ret) { + perror("Unable to allocate ring buffer.\n"); + exit(3); + } + memset(p, 0, vring_size(ring_size, 0x1000)); + vring_init(&ring, ring_size, p, 0x1000); + + guest.avail_idx = 0; + guest.kicked_avail_idx = -1; + guest.last_used_idx = 0; + /* Put everything in free lists. */ + guest.free_head = 0; + for (i = 0; i < ring_size - 1; i++) + ring.desc[i].next = i + 1; + host.used_idx = 0; + host.called_used_idx = -1; + guest.num_free = ring_size; + data = malloc(ring_size * sizeof *data); + if (!data) { + perror("Unable to allocate data buffer.\n"); + exit(3); + } + memset(data, 0, ring_size * sizeof *data); +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + unsigned head, avail; + struct vring_desc *desc; + + if (!guest.num_free) + return -1; + + head = guest.free_head; + guest.num_free--; + + desc = ring.desc; + desc[head].flags = VRING_DESC_F_NEXT; + desc[head].addr = (unsigned long)(void *)buf; + desc[head].len = len; + /* We do it like this to simulate the way + * we'd have to flip it if we had multiple + * descriptors. + */ + desc[head].flags &= ~VRING_DESC_F_NEXT; + guest.free_head = desc[head].next; + + data[head].data = datap; + +#ifdef RING_POLL + /* Barrier A (for pairing) */ + smp_release(); + avail = guest.avail_idx++; + ring.avail->ring[avail & (ring_size - 1)] = + (head | (avail & ~(ring_size - 1))) ^ 0x8000; +#else + avail = (ring_size - 1) & (guest.avail_idx++); + ring.avail->ring[avail] = head; + /* Barrier A (for pairing) */ + smp_release(); +#endif + ring.avail->idx = guest.avail_idx; + return 0; +} + +void *get_buf(unsigned *lenp, void **bufp) +{ + unsigned head; + unsigned index; + void *datap; + +#ifdef RING_POLL + head = (ring_size - 1) & guest.last_used_idx; + index = ring.used->ring[head].id; + if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1)) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + index &= ring_size - 1; +#else + if (ring.used->idx == guest.last_used_idx) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + head = (ring_size - 1) & guest.last_used_idx; + index = ring.used->ring[head].id; +#endif + *lenp = ring.used->ring[head].len; + datap = data[index].data; + *bufp = (void*)(unsigned long)ring.desc[index].addr; + data[index].data = NULL; + ring.desc[index].next = guest.free_head; + guest.free_head = index; + guest.num_free++; + guest.last_used_idx++; + return datap; +} + +void poll_used(void) +{ +#ifdef RING_POLL + unsigned head = (ring_size - 1) & guest.last_used_idx; + + for (;;) { + unsigned index = ring.used->ring[head].id; + + if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1)) + busy_wait(); + else + break; + } +#else + unsigned head = guest.last_used_idx; + + while (ring.used->idx == head) + busy_wait(); +#endif +} + +void disable_call() +{ + /* Doing nothing to disable calls might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_call() +{ + unsigned short last_used_idx; + + vring_used_event(&ring) = (last_used_idx = guest.last_used_idx); + /* Flush call index write */ + /* Barrier D (for pairing) */ + smp_mb(); +#ifdef RING_POLL + { + unsigned short head = last_used_idx & (ring_size - 1); + unsigned index = ring.used->ring[head].id; + + return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1); + } +#else + return ring.used->idx == last_used_idx; +#endif +} + +void kick_available(void) +{ + /* Flush in previous flags write */ + /* Barrier C (for pairing) */ + smp_mb(); + if (!vring_need_event(vring_avail_event(&ring), + guest.avail_idx, + guest.kicked_avail_idx)) + return; + + guest.kicked_avail_idx = guest.avail_idx; + kick(); +} + +/* host side */ +void disable_kick() +{ + /* Doing nothing to disable kicks might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_kick() +{ + unsigned head = host.used_idx; + + vring_avail_event(&ring) = head; + /* Barrier C (for pairing) */ + smp_mb(); +#ifdef RING_POLL + { + unsigned index = ring.avail->ring[head & (ring_size - 1)]; + + return (index ^ head ^ 0x8000) & ~(ring_size - 1); + } +#else + return head == ring.avail->idx; +#endif +} + +void poll_avail(void) +{ + unsigned head = host.used_idx; +#ifdef RING_POLL + for (;;) { + unsigned index = ring.avail->ring[head & (ring_size - 1)]; + if ((index ^ head ^ 0x8000) & ~(ring_size - 1)) + busy_wait(); + else + break; + } +#else + while (ring.avail->idx == head) + busy_wait(); +#endif +} + +bool use_buf(unsigned *lenp, void **bufp) +{ + unsigned used_idx = host.used_idx; + struct vring_desc *desc; + unsigned head; + +#ifdef RING_POLL + head = ring.avail->ring[used_idx & (ring_size - 1)]; + if ((used_idx ^ head ^ 0x8000) & ~(ring_size - 1)) + return false; + /* Barrier A (for pairing) */ + smp_acquire(); + + used_idx &= ring_size - 1; + desc = &ring.desc[head & (ring_size - 1)]; +#else + if (used_idx == ring.avail->idx) + return false; + + /* Barrier A (for pairing) */ + smp_acquire(); + + used_idx &= ring_size - 1; + head = ring.avail->ring[used_idx]; + desc = &ring.desc[head]; +#endif + + *lenp = desc->len; + *bufp = (void *)(unsigned long)desc->addr; + + /* now update used ring */ + ring.used->ring[used_idx].id = head; + ring.used->ring[used_idx].len = desc->len - 1; + /* Barrier B (for pairing) */ + smp_release(); + host.used_idx++; + ring.used->idx = host.used_idx; + + return true; +} + +void call_used(void) +{ + /* Flush in previous flags write */ + /* Barrier D (for pairing) */ + smp_mb(); + if (!vring_need_event(vring_used_event(&ring), + host.used_idx, + host.called_used_idx)) + return; + + host.called_used_idx = host.used_idx; + call(); +} diff --git a/tools/virtio/ringtest/virtio_ring_poll.c b/tools/virtio/ringtest/virtio_ring_poll.c new file mode 100644 index 000000000000..84fc2c557aaa --- /dev/null +++ b/tools/virtio/ringtest/virtio_ring_poll.c @@ -0,0 +1,2 @@ +#define RING_POLL 1 +#include "virtio_ring_0_9.c" |