diff options
71 files changed, 1568 insertions, 544 deletions
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index e4ee8b2db604..2baad0bfb09d 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -93,6 +93,11 @@ It exists in the sparse memory mapping model, and it is also somewhat similar to the mem_map variable, both of them are used to translate an address. +MAX_PHYSMEM_BITS +---------------- + +Defines the maximum supported physical address space memory. + page ---- @@ -399,6 +404,17 @@ KERNELPACMASK The mask to extract the Pointer Authentication Code from a kernel virtual address. +TCR_EL1.T1SZ +------------ + +Indicates the size offset of the memory region addressed by TTBR1_EL1. +The region size is 2^(64-T1SZ) bytes. + +TTBR1_EL1 is the table base address register specified by ARMv8-A +architecture which is used to lookup the page-tables for the Virtual +addresses in the higher VA range (refer to ARMv8 ARM document for +more details). + arm === diff --git a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt index 9134e9bcca56..ebd329181c14 100644 --- a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt +++ b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt @@ -28,6 +28,16 @@ Documentation/devicetree/bindings/iommu/iommu.txt. For arm-smmu binding, see: Documentation/devicetree/bindings/iommu/arm,smmu.yaml. +The MSI writes are accompanied by sideband data which is derived from the ICID. +The msi-map property is used to associate the devices with both the ITS +controller and the sideband data which accompanies the writes. + +For generic MSI bindings, see +Documentation/devicetree/bindings/interrupt-controller/msi.txt. + +For GICv3 and GIC ITS bindings, see: +Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml. + Required properties: - compatible @@ -49,11 +59,6 @@ Required properties: region may not be present in some scenarios, such as in the device tree presented to a virtual machine. - - msi-parent - Value type: <phandle> - Definition: Must be present and point to the MSI controller node - handling message interrupts for the MC. - - ranges Value type: <prop-encoded-array> Definition: A standard property. Defines the mapping between the child @@ -119,6 +124,28 @@ Optional properties: associated with the listed IOMMU, with the iommu-specifier (i - icid-base + iommu-base). +- msi-map: Maps an ICID to a GIC ITS and associated msi-specifier + data. + + The property is an arbitrary number of tuples of + (icid-base,gic-its,msi-base,length). + + Any ICID in the interval [icid-base, icid-base + length) is + associated with the listed GIC ITS, with the msi-specifier + (i - icid-base + msi-base). + +Deprecated properties: + + - msi-parent + Value type: <phandle> + Definition: Describes the MSI controller node handling message + interrupts for the MC. When there is no translation + between the ICID and deviceID this property can be used + to describe the MSI controller used by the devices on the + mc-bus. + The use of this property for mc-bus is deprecated. Please + use msi-map. + Example: smmu: iommu@5000000 { @@ -128,13 +155,24 @@ Example: ... }; + gic: interrupt-controller@6000000 { + compatible = "arm,gic-v3"; + ... + } + its: gic-its@6020000 { + compatible = "arm,gic-v3-its"; + msi-controller; + ... + }; + fsl_mc: fsl-mc@80c000000 { compatible = "fsl,qoriq-mc"; reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */ <0x00000000 0x08340000 0 0x40000>; /* MC control reg */ - msi-parent = <&its>; /* define map for ICIDs 23-64 */ iommu-map = <23 &smmu 23 41>; + /* define msi map for ICIDs 23-64 */ + msi-map = <23 &its 23 41>; #address-cells = <3>; #size-cells = <1>; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 66dc41fd49f2..73aee7290cdf 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -118,6 +118,7 @@ config ARM64 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_TIME_NS select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_PCI @@ -1327,6 +1328,8 @@ config SWP_EMULATION ARMv8 obsoletes the use of A32 SWP/SWPB instructions such that they are always undefined. Say Y here to enable software emulation of these instructions for userspace using LDXR/STXR. + This feature can be controlled at runtime with the abi.swp + sysctl which is disabled by default. In some older versions of glibc [<=2.8] SWP is used during futex trylock() operations with the assumption that the code will not @@ -1353,7 +1356,8 @@ config CP15_BARRIER_EMULATION Say Y here to enable software emulation of these instructions for AArch32 userspace code. When this option is enabled, CP15 barrier usage is traced which can help - identify software that needs updating. + identify software that needs updating. This feature can be + controlled at runtime with the abi.cp15_barrier sysctl. If unsure, say Y @@ -1364,7 +1368,8 @@ config SETEND_EMULATION AArch32 EL0, and is deprecated in ARMv8. Say Y here to enable software emulation of the instruction - for AArch32 userspace code. + for AArch32 userspace code. This feature can be controlled + at runtime with the abi.setend sysctl. Note: All the cpus on the system must have mixed endian support at EL0 for this feature to be enabled. If a new CPU - which doesn't support mixed @@ -1596,6 +1601,20 @@ config ARM64_AMU_EXTN correctly reflect reality. Most commonly, the value read will be 0, indicating that the counter is not enabled. +config AS_HAS_ARMV8_4 + def_bool $(cc-option,-Wa$(comma)-march=armv8.4-a) + +config ARM64_TLB_RANGE + bool "Enable support for tlbi range feature" + default y + depends on AS_HAS_ARMV8_4 + help + ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a + range of input addresses. + + The feature introduces new assembly instructions, and they were + support when binutils >= 2.30. + endmenu menu "ARMv8.5 architectural features" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index a0d94d063fa8..4e823b97c92e 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -82,11 +82,18 @@ endif # compiler to generate them and consequently to break the single image contract # we pass it only to the assembler. This option is utilized only in case of non # integrated assemblers. +ifneq ($(CONFIG_AS_HAS_ARMV8_4), y) branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a endif +endif KBUILD_CFLAGS += $(branch-prot-flags-y) +ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) +# make sure to pass the newest target architecture to -march. +KBUILD_CFLAGS += -Wa,-march=armv8.4-a +endif + ifeq ($(CONFIG_SHADOW_CALL_STACK), y) KBUILD_CFLAGS += -ffixed-x18 endif diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 883e8bace3ed..1a33697a8492 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -66,6 +66,7 @@ CONFIG_SCHED_SMT=y CONFIG_NUMA=y CONFIG_SECCOMP=y CONFIG_KEXEC=y +CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_XEN=y CONFIG_COMPAT=y diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index a45366c3909b..bd68e1b7f29f 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -47,20 +47,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); /* ACPI table mapping after acpi_permanent_mmap is set */ -static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, - acpi_size size) -{ - /* For normal memory we already have a cacheable mapping. */ - if (memblock_is_map_memory(phys)) - return (void __iomem *)__phys_to_virt(phys); - - /* - * We should still honor the memory's attribute here because - * crash dump kernel possibly excludes some ACPI (reclaim) - * regions from memblock list. - */ - return __ioremap(phys, size, __acpi_get_mem_attribute(phys)); -} +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); #define acpi_os_ioremap acpi_os_ioremap typedef u64 phys_cpuid_t; diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index d7b3bb0cb180..07b643a70710 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -62,7 +62,9 @@ #define ARM64_HAS_GENERIC_AUTH 52 #define ARM64_HAS_32BIT_EL1 53 #define ARM64_BTI 54 +#define ARM64_HAS_ARMv8_4_TTL 55 +#define ARM64_HAS_TLB_RANGE 56 -#define ARM64_NCAPS 55 +#define ARM64_NCAPS 57 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5d1f4ae42799..ef83d36698ce 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -692,6 +692,12 @@ static inline bool system_supports_bti(void) return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI); } +static inline bool system_supports_tlb_range(void) +{ + return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) && + cpus_have_const_cap(ARM64_HAS_TLB_RANGE); +} + #define ARM64_BP_HARDEN_UNKNOWN -1 #define ARM64_BP_HARDEN_WA_NEEDED 0 #define ARM64_BP_HARDEN_NOT_REQUIRED 1 @@ -774,6 +780,7 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) } u32 get_kvm_ipa_limit(void); +void dump_cpu_features(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 94ba0c5bced2..5abf91e3494c 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -49,6 +49,8 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz); #define set_huge_swap_pte_at set_huge_swap_pte_at +void __init arm64_hugetlb_cma_reserve(void); + #include <asm-generic/hugetlb.h> #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index d683bcbf1e7c..22f73fe09030 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -95,6 +95,7 @@ #define KERNEL_HWCAP_DGH __khwcap2_feature(DGH) #define KERNEL_HWCAP_RNG __khwcap2_feature(RNG) #define KERNEL_HWCAP_BTI __khwcap2_feature(BTI) +/* reserved for KERNEL_HWCAP_MTE __khwcap2_feature(MTE) */ /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 9d4bf58cf7b3..afa722504bfd 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -323,6 +323,7 @@ static inline void *phys_to_virt(phys_addr_t x) __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ }) +void dump_mem_limit(void); #endif /* !ASSEMBLY */ /* diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index b0bd9b55594c..f2d7537d6f83 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -175,7 +175,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp) * take CPU migration into account. */ #define destroy_context(mm) do { } while(0) -void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); +void check_and_switch_context(struct mm_struct *mm); #define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) @@ -214,8 +214,6 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) static inline void __switch_mm(struct mm_struct *next) { - unsigned int cpu = smp_processor_id(); - /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. @@ -225,7 +223,7 @@ static inline void __switch_mm(struct mm_struct *next) return; } - check_and_switch_context(next, cpu); + check_and_switch_context(next); } static inline void diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index e7765b62c712..2c2d7dbe8a02 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -72,6 +72,13 @@ #define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x36 #define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x37 #define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x38 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD 0x39 +#define ARMV8_PMUV3_PERFCTR_OP_RETIRED 0x3A +#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x3B +#define ARMV8_PMUV3_PERFCTR_STALL 0x3C +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND 0x3D +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND 0x3E +#define ARMV8_PMUV3_PERFCTR_STALL_SLOT 0x3F /* Statistical profiling extension microarchitectural events */ #define ARMV8_SPE_PERFCTR_SAMPLE_POP 0x4000 @@ -79,6 +86,26 @@ #define ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE 0x4002 #define ARMV8_SPE_PERFCTR_SAMPLE_COLLISION 0x4003 +/* AMUv1 architecture events */ +#define ARMV8_AMU_PERFCTR_CNT_CYCLES 0x4004 +#define ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM 0x4005 + +/* long-latency read miss events */ +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS 0x4006 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD 0x4009 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS 0x400A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD 0x400B + +/* additional latency from alignment events */ +#define ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT 0x4020 +#define ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT 0x4021 +#define ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT 0x4022 + +/* Armv8.5 Memory Tagging Extension events */ +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED 0x4024 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD 0x4025 +#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR 0x4026 + /* ARMv8 recommended implementation defined event types */ #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x40 #define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x41 diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 9c91a8f93a0e..d400a4d9aee2 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -29,7 +29,7 @@ * Size mapped by an entry at level n ( 0 <= n <= 3) * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits * in the final page. The maximum number of translation levels supported by - * the architecture is 4. Hence, starting at at level n, we have further + * the architecture is 4. Hence, starting at level n, we have further * ((4 - n) - 1) levels of translation excluding the offset within the page. * So, the total number of bits mapped by an entry at level n is : * @@ -82,23 +82,23 @@ * Contiguous page definitions. */ #ifdef CONFIG_ARM64_64K_PAGES -#define CONT_PTE_SHIFT 5 -#define CONT_PMD_SHIFT 5 +#define CONT_PTE_SHIFT (5 + PAGE_SHIFT) +#define CONT_PMD_SHIFT (5 + PMD_SHIFT) #elif defined(CONFIG_ARM64_16K_PAGES) -#define CONT_PTE_SHIFT 7 -#define CONT_PMD_SHIFT 5 +#define CONT_PTE_SHIFT (7 + PAGE_SHIFT) +#define CONT_PMD_SHIFT (5 + PMD_SHIFT) #else -#define CONT_PTE_SHIFT 4 -#define CONT_PMD_SHIFT 4 +#define CONT_PTE_SHIFT (4 + PAGE_SHIFT) +#define CONT_PMD_SHIFT (4 + PMD_SHIFT) #endif -#define CONT_PTES (1 << CONT_PTE_SHIFT) +#define CONT_PTES (1 << (CONT_PTE_SHIFT - PAGE_SHIFT)) #define CONT_PTE_SIZE (CONT_PTES * PAGE_SIZE) #define CONT_PTE_MASK (~(CONT_PTE_SIZE - 1)) -#define CONT_PMDS (1 << CONT_PMD_SHIFT) +#define CONT_PMDS (1 << (CONT_PMD_SHIFT - PMD_SHIFT)) #define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE) #define CONT_PMD_MASK (~(CONT_PMD_SIZE - 1)) -/* the the numerical offset of the PTE within a range of CONT_PTES */ +/* the numerical offset of the PTE within a range of CONT_PTES */ #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1)) /* @@ -178,10 +178,12 @@ #define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */ #define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ #define PTE_S2_XN (_AT(pteval_t, 2) << 53) /* XN[1:0] */ +#define PTE_S2_SW_RESVD (_AT(pteval_t, 15) << 55) /* Reserved for SW */ #define PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[2:1] */ #define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ #define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */ +#define PMD_S2_SW_RESVD (_AT(pmdval_t, 15) << 55) /* Reserved for SW */ #define PUD_S2_RDONLY (_AT(pudval_t, 1) << 6) /* HAP[2:1] */ #define PUD_S2_RDWR (_AT(pudval_t, 3) << 6) /* HAP[2:1] */ @@ -216,6 +218,7 @@ #define TCR_TxSZ(x) (TCR_T0SZ(x) | TCR_T1SZ(x)) #define TCR_TxSZ_WIDTH 6 #define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET) +#define TCR_T1SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET) #define TCR_EPD0_SHIFT 7 #define TCR_EPD0_MASK (UL(1) << TCR_EPD0_SHIFT) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 758e2d1577d0..d5d3fbe73953 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -40,6 +40,16 @@ extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); extern void __pgd_error(const char *file, int line, unsigned long val); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE + +/* Set stride and tlb_level in flush_*_tlb_range */ +#define flush_pmd_tlb_range(vma, addr, end) \ + __flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2) +#define flush_pud_tlb_range(vma, addr, end) \ + __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 953b6a1ce549..966ed30ed5f7 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -27,7 +27,7 @@ * * Some code sections either automatically switch back to PSR.I or explicitly * require to not use priority masking. If bit GIC_PRIO_PSR_I_SET is included - * in the the priority mask, it indicates that PSR.I should be set and + * in the priority mask, it indicates that PSR.I should be set and * interrupt disabling temporarily does not rely on IRQ priorities. */ #define GIC_PRIO_IRQON 0xe0 diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index b767904f28b1..996bf98f0cab 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -256,4 +256,13 @@ stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) return (boundary - 1 < end - 1) ? boundary : end; } +/* + * Level values for the ARMv8.4-TTL extension, mapping PUD/PMD/PTE and + * the architectural page-table level. + */ +#define S2_NO_LEVEL_HINT 0 +#define S2_PUD_LEVEL 1 +#define S2_PMD_LEVEL 2 +#define S2_PTE_LEVEL 3 + #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 463175f80341..554a7e8ecb07 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -421,9 +421,9 @@ */ #define SYS_AMEVCNTR0_EL0(n) SYS_AM_EL0(4 + ((n) >> 3), (n) & 7) -#define SYS_AMEVTYPE0_EL0(n) SYS_AM_EL0(6 + ((n) >> 3), (n) & 7) +#define SYS_AMEVTYPER0_EL0(n) SYS_AM_EL0(6 + ((n) >> 3), (n) & 7) #define SYS_AMEVCNTR1_EL0(n) SYS_AM_EL0(12 + ((n) >> 3), (n) & 7) -#define SYS_AMEVTYPE1_EL0(n) SYS_AM_EL0(14 + ((n) >> 3), (n) & 7) +#define SYS_AMEVTYPER1_EL0(n) SYS_AM_EL0(14 + ((n) >> 3), (n) & 7) /* AMU v1: Fixed (architecturally defined) activity monitors */ #define SYS_AMEVCNTR0_CORE_EL0 SYS_AMEVCNTR0_EL0(0) @@ -617,6 +617,9 @@ #define ID_AA64ISAR0_SHA1_SHIFT 8 #define ID_AA64ISAR0_AES_SHIFT 4 +#define ID_AA64ISAR0_TLB_RANGE_NI 0x0 +#define ID_AA64ISAR0_TLB_RANGE 0x2 + /* id_aa64isar1 */ #define ID_AA64ISAR1_I8MM_SHIFT 52 #define ID_AA64ISAR1_DGH_SHIFT 48 @@ -706,6 +709,9 @@ #define ID_AA64ZFR0_SVEVER_SVE2 0x1 /* id_aa64mmfr0 */ +#define ID_AA64MMFR0_ECV_SHIFT 60 +#define ID_AA64MMFR0_FGT_SHIFT 56 +#define ID_AA64MMFR0_EXS_SHIFT 44 #define ID_AA64MMFR0_TGRAN4_2_SHIFT 40 #define ID_AA64MMFR0_TGRAN64_2_SHIFT 36 #define ID_AA64MMFR0_TGRAN16_2_SHIFT 32 @@ -734,6 +740,10 @@ #endif /* id_aa64mmfr1 */ +#define ID_AA64MMFR1_ETS_SHIFT 36 +#define ID_AA64MMFR1_TWED_SHIFT 32 +#define ID_AA64MMFR1_XNX_SHIFT 28 +#define ID_AA64MMFR1_SPECSEI_SHIFT 24 #define ID_AA64MMFR1_PAN_SHIFT 20 #define ID_AA64MMFR1_LOR_SHIFT 16 #define ID_AA64MMFR1_HPD_SHIFT 12 @@ -746,8 +756,15 @@ /* id_aa64mmfr2 */ #define ID_AA64MMFR2_E0PD_SHIFT 60 +#define ID_AA64MMFR2_EVT_SHIFT 56 +#define ID_AA64MMFR2_BBM_SHIFT 52 +#define ID_AA64MMFR2_TTL_SHIFT 48 #define ID_AA64MMFR2_FWB_SHIFT 40 +#define ID_AA64MMFR2_IDS_SHIFT 36 #define ID_AA64MMFR2_AT_SHIFT 32 +#define ID_AA64MMFR2_ST_SHIFT 28 +#define ID_AA64MMFR2_NV_SHIFT 24 +#define ID_AA64MMFR2_CCIDX_SHIFT 20 #define ID_AA64MMFR2_LVA_SHIFT 16 #define ID_AA64MMFR2_IESB_SHIFT 12 #define ID_AA64MMFR2_LSM_SHIFT 8 @@ -755,6 +772,7 @@ #define ID_AA64MMFR2_CNP_SHIFT 0 /* id_aa64dfr0 */ +#define ID_AA64DFR0_DOUBLELOCK_SHIFT 36 #define ID_AA64DFR0_PMSVER_SHIFT 32 #define ID_AA64DFR0_CTX_CMPS_SHIFT 28 #define ID_AA64DFR0_WRPS_SHIFT 20 @@ -807,18 +825,40 @@ #define ID_ISAR6_DP_SHIFT 4 #define ID_ISAR6_JSCVT_SHIFT 0 +#define ID_MMFR0_INNERSHR_SHIFT 28 +#define ID_MMFR0_FCSE_SHIFT 24 +#define ID_MMFR0_AUXREG_SHIFT 20 +#define ID_MMFR0_TCM_SHIFT 16 +#define ID_MMFR0_SHARELVL_SHIFT 12 +#define ID_MMFR0_OUTERSHR_SHIFT 8 +#define ID_MMFR0_PMSA_SHIFT 4 +#define ID_MMFR0_VMSA_SHIFT 0 + #define ID_MMFR4_EVT_SHIFT 28 #define ID_MMFR4_CCIDX_SHIFT 24 #define ID_MMFR4_LSM_SHIFT 20 #define ID_MMFR4_HPDS_SHIFT 16 #define ID_MMFR4_CNP_SHIFT 12 #define ID_MMFR4_XNX_SHIFT 8 +#define ID_MMFR4_AC2_SHIFT 4 #define ID_MMFR4_SPECSEI_SHIFT 0 #define ID_MMFR5_ETS_SHIFT 0 #define ID_PFR0_DIT_SHIFT 24 #define ID_PFR0_CSV2_SHIFT 16 +#define ID_PFR0_STATE3_SHIFT 12 +#define ID_PFR0_STATE2_SHIFT 8 +#define ID_PFR0_STATE1_SHIFT 4 +#define ID_PFR0_STATE0_SHIFT 0 + +#define ID_DFR0_PERFMON_SHIFT 24 +#define ID_DFR0_MPROFDBG_SHIFT 20 +#define ID_DFR0_MMAPTRC_SHIFT 16 +#define ID_DFR0_COPTRC_SHIFT 12 +#define ID_DFR0_MMAPDBG_SHIFT 8 +#define ID_DFR0_COPSDBG_SHIFT 4 +#define ID_DFR0_COPDBG_SHIFT 0 #define ID_PFR2_SSBS_SHIFT 4 #define ID_PFR2_CSV3_SHIFT 0 @@ -861,6 +901,11 @@ #define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED #endif +#define MVFR2_FPMISC_SHIFT 4 +#define MVFR2_SIMDMISC_SHIFT 0 + +#define DCZID_DZP_SHIFT 4 +#define DCZID_BS_SHIFT 0 /* * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index b76df828e6b7..61c97d3b58c7 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -21,11 +21,37 @@ static void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> +/* + * get the tlbi levels in arm64. Default value is 0 if more than one + * of cleared_* is set or neither is set. + * Arm64 doesn't support p4ds now. + */ +static inline int tlb_get_level(struct mmu_gather *tlb) +{ + if (tlb->cleared_ptes && !(tlb->cleared_pmds || + tlb->cleared_puds || + tlb->cleared_p4ds)) + return 3; + + if (tlb->cleared_pmds && !(tlb->cleared_ptes || + tlb->cleared_puds || + tlb->cleared_p4ds)) + return 2; + + if (tlb->cleared_puds && !(tlb->cleared_ptes || + tlb->cleared_pmds || + tlb->cleared_p4ds)) + return 1; + + return 0; +} + static inline void tlb_flush(struct mmu_gather *tlb) { struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); bool last_level = !tlb->freed_tables; unsigned long stride = tlb_get_unmap_size(tlb); + int tlb_level = tlb_get_level(tlb); /* * If we're tearing down the address space then we only care about @@ -38,7 +64,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) return; } - __flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level); + __flush_tlb_range(&vma, tlb->start, tlb->end, stride, + last_level, tlb_level); } static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index bc3949064725..d493174415db 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -10,6 +10,7 @@ #ifndef __ASSEMBLY__ +#include <linux/bitfield.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <asm/cputype.h> @@ -60,6 +61,102 @@ }) /* + * Get translation granule of the system, which is decided by + * PAGE_SIZE. Used by TTL. + * - 4KB : 1 + * - 16KB : 2 + * - 64KB : 3 + */ +#define TLBI_TTL_TG_4K 1 +#define TLBI_TTL_TG_16K 2 +#define TLBI_TTL_TG_64K 3 + +static inline unsigned long get_trans_granule(void) +{ + switch (PAGE_SIZE) { + case SZ_4K: + return TLBI_TTL_TG_4K; + case SZ_16K: + return TLBI_TTL_TG_16K; + case SZ_64K: + return TLBI_TTL_TG_64K; + default: + return 0; + } +} + +/* + * Level-based TLBI operations. + * + * When ARMv8.4-TTL exists, TLBI operations take an additional hint for + * the level at which the invalidation must take place. If the level is + * wrong, no invalidation may take place. In the case where the level + * cannot be easily determined, a 0 value for the level parameter will + * perform a non-hinted invalidation. + * + * For Stage-2 invalidation, use the level values provided to that effect + * in asm/stage2_pgtable.h. + */ +#define TLBI_TTL_MASK GENMASK_ULL(47, 44) + +#define __tlbi_level(op, addr, level) do { \ + u64 arg = addr; \ + \ + if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) && \ + level) { \ + u64 ttl = level & 3; \ + ttl |= get_trans_granule() << 2; \ + arg &= ~TLBI_TTL_MASK; \ + arg |= FIELD_PREP(TLBI_TTL_MASK, ttl); \ + } \ + \ + __tlbi(op, arg); \ +} while(0) + +#define __tlbi_user_level(op, arg, level) do { \ + if (arm64_kernel_unmapped_at_el0()) \ + __tlbi_level(op, (arg | USER_ASID_FLAG), level); \ +} while (0) + +/* + * This macro creates a properly formatted VA operand for the TLB RANGE. + * The value bit assignments are: + * + * +----------+------+-------+-------+-------+----------------------+ + * | ASID | TG | SCALE | NUM | TTL | BADDR | + * +-----------------+-------+-------+-------+----------------------+ + * |63 48|47 46|45 44|43 39|38 37|36 0| + * + * The address range is determined by below formula: + * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE) + * + */ +#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl) \ + ({ \ + unsigned long __ta = (addr) >> PAGE_SHIFT; \ + __ta &= GENMASK_ULL(36, 0); \ + __ta |= (unsigned long)(ttl) << 37; \ + __ta |= (unsigned long)(num) << 39; \ + __ta |= (unsigned long)(scale) << 44; \ + __ta |= get_trans_granule() << 46; \ + __ta |= (unsigned long)(asid) << 48; \ + __ta; \ + }) + +/* These macros are used by the TLBI RANGE feature. */ +#define __TLBI_RANGE_PAGES(num, scale) \ + ((unsigned long)((num) + 1) << (5 * (scale) + 1)) +#define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3) + +/* + * Generate 'num' values from -1 to 30 with -1 rejected by the + * __flush_tlb_range() loop below. + */ +#define TLBI_RANGE_MASK GENMASK_ULL(4, 0) +#define __TLBI_RANGE_NUM(pages, scale) \ + ((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1) + +/* * TLB Invalidation * ================ * @@ -179,34 +276,83 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, - unsigned long stride, bool last_level) + unsigned long stride, bool last_level, + int tlb_level) { + int num = 0; + int scale = 0; unsigned long asid = ASID(vma->vm_mm); unsigned long addr; + unsigned long pages; start = round_down(start, stride); end = round_up(end, stride); + pages = (end - start) >> PAGE_SHIFT; - if ((end - start) >= (MAX_TLBI_OPS * stride)) { + /* + * When not uses TLB range ops, we can handle up to + * (MAX_TLBI_OPS - 1) pages; + * When uses TLB range ops, we can handle up to + * (MAX_TLBI_RANGE_PAGES - 1) pages. + */ + if ((!system_supports_tlb_range() && + (end - start) >= (MAX_TLBI_OPS * stride)) || + pages >= MAX_TLBI_RANGE_PAGES) { flush_tlb_mm(vma->vm_mm); return; } - /* Convert the stride into units of 4k */ - stride >>= 12; + dsb(ishst); - start = __TLBI_VADDR(start, asid); - end = __TLBI_VADDR(end, asid); + /* + * When the CPU does not support TLB range operations, flush the TLB + * entries one by one at the granularity of 'stride'. If the the TLB + * range ops are supported, then: + * + * 1. If 'pages' is odd, flush the first page through non-range + * operations; + * + * 2. For remaining pages: the minimum range granularity is decided + * by 'scale', so multiple range TLBI operations may be required. + * Start from scale = 0, flush the corresponding number of pages + * ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it + * until no pages left. + * + * Note that certain ranges can be represented by either num = 31 and + * scale or num = 0 and scale + 1. The loop below favours the latter + * since num is limited to 30 by the __TLBI_RANGE_NUM() macro. + */ + while (pages > 0) { + if (!system_supports_tlb_range() || + pages % 2 == 1) { + addr = __TLBI_VADDR(start, asid); + if (last_level) { + __tlbi_level(vale1is, addr, tlb_level); + __tlbi_user_level(vale1is, addr, tlb_level); + } else { + __tlbi_level(vae1is, addr, tlb_level); + __tlbi_user_level(vae1is, addr, tlb_level); + } + start += stride; + pages -= stride >> PAGE_SHIFT; + continue; + } - dsb(ishst); - for (addr = start; addr < end; addr += stride) { - if (last_level) { - __tlbi(vale1is, addr); - __tlbi_user(vale1is, addr); - } else { - __tlbi(vae1is, addr); - __tlbi_user(vae1is, addr); + num = __TLBI_RANGE_NUM(pages, scale); + if (num >= 0) { + addr = __TLBI_VADDR_RANGE(start, asid, scale, + num, tlb_level); + if (last_level) { + __tlbi(rvale1is, addr); + __tlbi_user(rvale1is, addr); + } else { + __tlbi(rvae1is, addr); + __tlbi_user(rvae1is, addr); + } + start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; + pages -= __TLBI_RANGE_PAGES(num, scale); } + scale++; } dsb(ish); } @@ -217,8 +363,9 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, /* * We cannot use leaf-only invalidation here, since we may be invalidating * table entries as part of collapsing hugepages or moving page tables. + * Set the tlb_level to 0 because we can not get enough information here. */ - __flush_tlb_range(vma, start, end, PAGE_SIZE, false); + __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0); } static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h index 07468428fd29..f99dcb94b438 100644 --- a/arch/arm64/include/asm/vdso.h +++ b/arch/arm64/include/asm/vdso.h @@ -12,6 +12,8 @@ */ #define VDSO_LBASE 0x0 +#define __VVAR_PAGES 2 + #ifndef __ASSEMBLY__ #include <generated/vdso-offsets.h> diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index bcf7649999a4..d0cbb04bfc10 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -153,6 +153,18 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return ret; } +#ifdef CONFIG_TIME_NS +static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +{ + const struct vdso_data *ret; + + /* See __arch_get_vdso_data(). */ + asm volatile("mov %0, %1" : "=r"(ret) : "r"(_timens_data)); + + return ret; +} +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 127fa63893e2..9c29ad3049f8 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -97,6 +97,14 @@ const struct vdso_data *__arch_get_vdso_data(void) return _vdso_data; } +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(void) +{ + return _timens_data; +} +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 2d6ba1c2592e..912162f73529 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -74,5 +74,6 @@ #define HWCAP2_DGH (1 << 15) #define HWCAP2_RNG (1 << 16) #define HWCAP2_BTI (1 << 17) +/* reserved for HWCAP2_MTE (1 << 18) */ #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 8b0ebce92427..0c796c795dbe 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -179,7 +179,7 @@ struct sve_context { * The same convention applies when returning from a signal: a caller * will need to remove or resize the sve_context block if it wants to * make the SVE registers live when they were previously non-live or - * vice-versa. This may require the the caller to allocate fresh + * vice-versa. This may require the caller to allocate fresh * memory and/or move other context blocks in the signal frame. * * Changing the vector length during signal return is not permitted: diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a7586a4db142..455966401102 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -261,6 +261,81 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) return __pgprot(PROT_DEVICE_nGnRnE); } +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + efi_memory_desc_t *md, *region = NULL; + pgprot_t prot; + + if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP))) + return NULL; + + for_each_efi_memory_desc(md) { + u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + + if (phys < md->phys_addr || phys >= end) + continue; + + if (phys + size > end) { + pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n"); + return NULL; + } + region = md; + break; + } + + /* + * It is fine for AML to remap regions that are not represented in the + * EFI memory map at all, as it only describes normal memory, and MMIO + * regions that require a virtual mapping to make them accessible to + * the EFI runtime services. + */ + prot = __pgprot(PROT_DEVICE_nGnRnE); + if (region) { + switch (region->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); + return NULL; + + case EFI_RUNTIME_SERVICES_CODE: + /* + * This would be unusual, but not problematic per se, + * as long as we take care not to create a writable + * mapping for executable code. + */ + prot = PAGE_KERNEL_RO; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + /* + * ACPI reclaim memory is used to pass firmware tables + * and other data that is intended for consumption by + * the OS only, which may decide it wants to reclaim + * that memory and use it for something else. We never + * do that, but we usually add it to the linear map + * anyway, in which case we should use the existing + * mapping. + */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__phys_to_virt(phys); + /* fall through */ + + default: + if (region->attribute & EFI_MEMORY_WB) + prot = PAGE_KERNEL; + else if (region->attribute & EFI_MEMORY_WT) + prot = __pgprot(PROT_NORMAL_WT); + else if (region->attribute & EFI_MEMORY_WC) + prot = __pgprot(PROT_NORMAL_NC); + } + } + return __ioremap(phys, size, prot); +} + /* * Claim Synchronous External Aborts as a firmware first notification. * diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 9f63053a63a9..3c8aaa146843 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -119,25 +119,12 @@ static inline void finalize_system_capabilities(void) static_branch_enable(&arm64_const_caps_ready); } -static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p) +void dump_cpu_features(void) { /* file-wide pr_fmt adds "CPU features: " prefix */ pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps); - return 0; } -static struct notifier_block cpu_hwcaps_notifier = { - .notifier_call = dump_cpu_hwcaps -}; - -static int __init register_cpu_hwcaps_dumper(void) -{ - atomic_notifier_chain_register(&panic_notifier_list, - &cpu_hwcaps_notifier); - return 0; -} -__initcall(register_cpu_hwcaps_dumper); - DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcap_keys); @@ -269,6 +256,9 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EXS_SHIFT, 4, 0), /* * Page size not being supported at Stage-2 is not fatal. You * just give up KVM if PAGE_SIZE isn't supported there. Go fix @@ -312,6 +302,10 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_XNX_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_SPECSEI_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0), @@ -323,8 +317,15 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EVT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_BBM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_TTL_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IDS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_ST_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_NV_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CCIDX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0), @@ -345,7 +346,7 @@ static const struct arm64_ftr_bits ftr_ctr[] = { * make use of *minLine. * If we have differing I-cache policies, report it as the weakest - VIPT. */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT), /* L1Ip */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, CTR_L1IP_SHIFT, 2, ICACHE_POLICY_VIPT), /* L1Ip */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IMINLINE_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -356,19 +357,19 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = { }; static const struct arm64_ftr_bits ftr_id_mmfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0xf), /* InnerShr */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), /* FCSE */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), /* TCM */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* ShareLvl */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0xf), /* OuterShr */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* PMSA */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* VMSA */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_INNERSHR_SHIFT, 4, 0xf), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_FCSE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_AUXREG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_TCM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_SHARELVL_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_OUTERSHR_SHIFT, 4, 0xf), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_PMSA_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_VMSA_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 36, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_DOUBLELOCK_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), @@ -384,14 +385,14 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { }; static const struct arm64_ftr_bits ftr_mvfr2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* FPMisc */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* SIMDMisc */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_dczid[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */ - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */ + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, DCZID_DZP_SHIFT, 1, 1), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, DCZID_BS_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -423,7 +424,8 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_HPDS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CNP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_XNX_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* ac2 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_AC2_SHIFT, 4, 0), + /* * SpecSEI = 1 indicates that the PE might generate an SError on an * external abort on speculative read. It is safe to assume that an @@ -465,10 +467,10 @@ static const struct arm64_ftr_bits ftr_id_isar6[] = { static const struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_DIT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_CSV2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* State3 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), /* State2 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), /* State1 */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* State0 */ + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE0_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -492,13 +494,13 @@ static const struct arm64_ftr_bits ftr_id_pfr2[] = { static const struct arm64_ftr_bits ftr_id_dfr0[] = { /* [31:28] TraceFilt */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_PERFMON_SHIFT, 4, 0xf), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPDBG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPSDBG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPDBG_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -697,11 +699,52 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, static void __init sort_ftr_regs(void) { - int i; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(arm64_ftr_regs); i++) { + const struct arm64_ftr_reg *ftr_reg = arm64_ftr_regs[i].reg; + const struct arm64_ftr_bits *ftr_bits = ftr_reg->ftr_bits; + unsigned int j = 0; + + /* + * Features here must be sorted in descending order with respect + * to their shift values and should not overlap with each other. + */ + for (; ftr_bits->width != 0; ftr_bits++, j++) { + unsigned int width = ftr_reg->ftr_bits[j].width; + unsigned int shift = ftr_reg->ftr_bits[j].shift; + unsigned int prev_shift; + + WARN((shift + width) > 64, + "%s has invalid feature at shift %d\n", + ftr_reg->name, shift); + + /* + * Skip the first feature. There is nothing to + * compare against for now. + */ + if (j == 0) + continue; + + prev_shift = ftr_reg->ftr_bits[j - 1].shift; + WARN((shift + width) > prev_shift, + "%s has feature overlap at shift %d\n", + ftr_reg->name, shift); + } - /* Check that the array is sorted so that we can do the binary search */ - for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++) + /* + * Skip the first register. There is nothing to + * compare against for now. + */ + if (i == 0) + continue; + /* + * Registers here must be sorted in ascending order with respect + * to sys_id for subsequent binary search in get_arm64_ftr_reg() + * to work correctly. + */ BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id); + } } /* @@ -1882,6 +1925,26 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .cpu_enable = cpu_has_fwb, }, + { + .desc = "ARMv8.4 Translation Table Level", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_HAS_ARMv8_4_TTL, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64MMFR2_TTL_SHIFT, + .min_field_value = 1, + .matches = has_cpuid_feature, + }, + { + .desc = "TLB range maintenance instructions", + .capability = ARM64_HAS_TLB_RANGE, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64ISAR0_EL1, + .field_pos = ID_AA64ISAR0_TLB_SHIFT, + .sign = FTR_UNSIGNED, + .min_field_value = ID_AA64ISAR0_TLB_RANGE, + }, #ifdef CONFIG_ARM64_HW_AFDBM { /* diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 86637466daa8..393c6fb1f1cb 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -93,6 +93,7 @@ static const char *const hwcap_str[] = { "dgh", "rng", "bti", + /* reserved for "mte" */ NULL }; diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c index 1f646b07e3e9..314391a156ee 100644 --- a/arch/arm64/kernel/crash_core.c +++ b/arch/arm64/kernel/crash_core.c @@ -7,6 +7,14 @@ #include <linux/crash_core.h> #include <asm/cpufeature.h> #include <asm/memory.h> +#include <asm/pgtable-hwdef.h> + +static inline u64 get_tcr_el1_t1sz(void); + +static inline u64 get_tcr_el1_t1sz(void) +{ + return (read_sysreg(tcr_el1) & TCR_T1SZ_MASK) >> TCR_T1SZ_OFFSET; +} void arch_crash_save_vmcoreinfo(void) { @@ -16,6 +24,8 @@ void arch_crash_save_vmcoreinfo(void) kimage_voffset); vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", PHYS_OFFSET); + vmcoreinfo_append_str("NUMBER(TCR_EL1_T1SZ)=0x%llx\n", + get_tcr_el1_t1sz()); vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); vmcoreinfo_append_str("NUMBER(KERNELPACMASK)=0x%llx\n", system_supports_address_auth() ? diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b668aad3b762..945b46a1990d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -210,28 +210,9 @@ alternative_cb_end add x29, sp, #S_STACKFRAME #ifdef CONFIG_ARM64_SW_TTBR0_PAN - /* - * Set the TTBR0 PAN bit in SPSR. When the exception is taken from - * EL0, there is no need to check the state of TTBR0_EL1 since - * accesses are always enabled. - * Note that the meaning of this bit differs from the ARMv8.1 PAN - * feature as all TTBR0_EL1 accesses are disabled, not just those to - * user mappings. - */ -alternative_if ARM64_HAS_PAN - b 1f // skip TTBR0 PAN +alternative_if_not ARM64_HAS_PAN + bl __swpan_entry_el\el alternative_else_nop_endif - - .if \el != 0 - mrs x21, ttbr0_el1 - tst x21, #TTBR_ASID_MASK // Check for the reserved ASID - orr x23, x23, #PSR_PAN_BIT // Set the emulated PAN in the saved SPSR - b.eq 1f // TTBR0 access already disabled - and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR - .endif - - __uaccess_ttbr0_disable x21 -1: #endif stp x22, x23, [sp, #S_PC] @@ -285,34 +266,9 @@ alternative_else_nop_endif .endif #ifdef CONFIG_ARM64_SW_TTBR0_PAN - /* - * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR - * PAN bit checking. - */ -alternative_if ARM64_HAS_PAN - b 2f // skip TTBR0 PAN +alternative_if_not ARM64_HAS_PAN + bl __swpan_exit_el\el alternative_else_nop_endif - - .if \el != 0 - tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set - .endif - - __uaccess_ttbr0_enable x0, x1 - - .if \el == 0 - /* - * Enable errata workarounds only if returning to user. The only - * workaround currently required for TTBR0_EL1 changes are for the - * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache - * corruption). - */ - bl post_ttbr_update_workaround - .endif -1: - .if \el != 0 - and x22, x22, #~PSR_PAN_BIT // ARMv8.0 CPUs do not understand this bit - .endif -2: #endif .if \el == 0 @@ -392,6 +348,49 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 sb .endm +#ifdef CONFIG_ARM64_SW_TTBR0_PAN + /* + * Set the TTBR0 PAN bit in SPSR. When the exception is taken from + * EL0, there is no need to check the state of TTBR0_EL1 since + * accesses are always enabled. + * Note that the meaning of this bit differs from the ARMv8.1 PAN + * feature as all TTBR0_EL1 accesses are disabled, not just those to + * user mappings. + */ +SYM_CODE_START_LOCAL(__swpan_entry_el1) + mrs x21, ttbr0_el1 + tst x21, #TTBR_ASID_MASK // Check for the reserved ASID + orr x23, x23, #PSR_PAN_BIT // Set the emulated PAN in the saved SPSR + b.eq 1f // TTBR0 access already disabled + and x23, x23, #~PSR_PAN_BIT // Clear the emulated PAN in the saved SPSR +SYM_INNER_LABEL(__swpan_entry_el0, SYM_L_LOCAL) + __uaccess_ttbr0_disable x21 +1: ret +SYM_CODE_END(__swpan_entry_el1) + + /* + * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR + * PAN bit checking. + */ +SYM_CODE_START_LOCAL(__swpan_exit_el1) + tbnz x22, #22, 1f // Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set + __uaccess_ttbr0_enable x0, x1 +1: and x22, x22, #~PSR_PAN_BIT // ARMv8.0 CPUs do not understand this bit + ret +SYM_CODE_END(__swpan_exit_el1) + +SYM_CODE_START_LOCAL(__swpan_exit_el0) + __uaccess_ttbr0_enable x0, x1 + /* + * Enable errata workarounds only if returning to user. The only + * workaround currently required for TTBR0_EL1 changes are for the + * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache + * corruption). + */ + b post_ttbr_update_workaround +SYM_CODE_END(__swpan_exit_el0) +#endif + .macro irq_stack_entry mov x19, sp // preserve the original sp #ifdef CONFIG_SHADOW_CALL_STACK diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 65b08a74aec6..0ce3a28e3347 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -253,6 +253,40 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, return ret; } +static bool branch_rela_needs_plt(Elf64_Sym *syms, Elf64_Rela *rela, + Elf64_Word dstidx) +{ + + Elf64_Sym *s = syms + ELF64_R_SYM(rela->r_info); + + if (s->st_shndx == dstidx) + return false; + + return ELF64_R_TYPE(rela->r_info) == R_AARCH64_JUMP26 || + ELF64_R_TYPE(rela->r_info) == R_AARCH64_CALL26; +} + +/* Group branch PLT relas at the front end of the array. */ +static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela, + int numrels, Elf64_Word dstidx) +{ + int i = 0, j = numrels - 1; + + if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + return 0; + + while (i < j) { + if (branch_rela_needs_plt(syms, &rela[i], dstidx)) + i++; + else if (branch_rela_needs_plt(syms, &rela[j], dstidx)) + swap(rela[i], rela[j]); + else + j--; + } + + return i; +} + int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { @@ -290,7 +324,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, for (i = 0; i < ehdr->e_shnum; i++) { Elf64_Rela *rels = (void *)ehdr + sechdrs[i].sh_offset; - int numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela); + int nents, numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela); Elf64_Shdr *dstsec = sechdrs + sechdrs[i].sh_info; if (sechdrs[i].sh_type != SHT_RELA) @@ -300,8 +334,14 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (!(dstsec->sh_flags & SHF_EXECINSTR)) continue; - /* sort by type, symbol index and addend */ - sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL); + /* + * sort branch relocations requiring a PLT by type, symbol index + * and addend + */ + nents = partition_branch_plt_relas(syms, rels, numrels, + sechdrs[i].sh_info); + if (nents) + sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL); if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) core_plts += count_plts(syms, rels, numrels, diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 4d7879484cec..462f9a9cc44b 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -13,12 +13,15 @@ #include <asm/sysreg.h> #include <asm/virt.h> +#include <clocksource/arm_arch_timer.h> + #include <linux/acpi.h> #include <linux/clocksource.h> #include <linux/kvm_host.h> #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> +#include <linux/sched_clock.h> #include <linux/smp.h> /* ARMv8 Cortex-A53 specific event types. */ @@ -155,7 +158,7 @@ armv8pmu_events_sysfs_show(struct device *dev, pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - return sprintf(page, "event=0x%03llx\n", pmu_attr->id); + return sprintf(page, "event=0x%04llx\n", pmu_attr->id); } #define ARMV8_EVENT_ATTR(name, config) \ @@ -222,10 +225,29 @@ static struct attribute *armv8_pmuv3_event_attrs[] = { ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), + ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD), + ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED), + ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC), + ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL), + ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND), + ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND), + ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT), ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), + ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES), + ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM), + ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS), + ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD), + ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS), + ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD), + ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT), + ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT), + ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT), + ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED), + ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD), + ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR), NULL, }; @@ -244,10 +266,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj, test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) return attr->mode; - pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; - if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && - test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap)) - return attr->mode; + if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) { + u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; + + if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS && + test_bit(id, cpu_pmu->pmceid_ext_bitmap)) + return attr->mode; + } return 0; } @@ -1165,28 +1190,54 @@ device_initcall(armv8_pmu_driver_init) void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { - u32 freq; - u32 shift; + struct clock_read_data *rd; + unsigned int seq; + u64 ns; - /* - * Internal timekeeping for enabled/running/stopped times - * is always computed with the sched_clock. - */ - freq = arch_timer_get_rate(); - userpg->cap_user_time = 1; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_time_short = 0; + + do { + rd = sched_clock_read_begin(&seq); + + if (rd->read_sched_clock != arch_timer_read_counter) + return; + + userpg->time_mult = rd->mult; + userpg->time_shift = rd->shift; + userpg->time_zero = rd->epoch_ns; + userpg->time_cycles = rd->epoch_cyc; + userpg->time_mask = rd->sched_clock_mask; + + /* + * Subtract the cycle base, such that software that + * doesn't know about cap_user_time_short still 'works' + * assuming no wraps. + */ + ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift); + userpg->time_zero -= ns; + + } while (sched_clock_read_retry(seq)); + + userpg->time_offset = userpg->time_zero - now; - clocks_calc_mult_shift(&userpg->time_mult, &shift, freq, - NSEC_PER_SEC, 0); /* * time_shift is not expected to be greater than 31 due to * the original published conversion algorithm shifting a * 32-bit value (now specifies a 64-bit value) - refer * perf_event_mmap_page documentation in perf_event.h. */ - if (shift == 32) { - shift = 31; + if (userpg->time_shift == 32) { + userpg->time_shift = 31; userpg->time_mult >>= 1; } - userpg->time_shift = (u16)shift; - userpg->time_offset = -now; + + /* + * Internal timekeeping for enabled/running/stopped times + * is always computed with the sched_clock. + */ + userpg->cap_user_time = 1; + userpg->cap_user_time_zero = 1; + userpg->cap_user_time_short = 1; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 93b3844cf442..c793276ec7ad 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -400,11 +400,7 @@ static int __init topology_init(void) } subsys_initcall(topology_init); -/* - * Dump out kernel offset information on panic. - */ -static int dump_kernel_offset(struct notifier_block *self, unsigned long v, - void *p) +static void dump_kernel_offset(void) { const unsigned long offset = kaslr_offset(); @@ -415,17 +411,25 @@ static int dump_kernel_offset(struct notifier_block *self, unsigned long v, } else { pr_emerg("Kernel Offset: disabled\n"); } +} + +static int arm64_panic_block_dump(struct notifier_block *self, + unsigned long v, void *p) +{ + dump_kernel_offset(); + dump_cpu_features(); + dump_mem_limit(); return 0; } -static struct notifier_block kernel_offset_notifier = { - .notifier_call = dump_kernel_offset +static struct notifier_block arm64_panic_block = { + .notifier_call = arm64_panic_block_dump }; -static int __init register_kernel_offset_dumper(void) +static int __init register_arm64_panic_block(void) { atomic_notifier_chain_register(&panic_notifier_list, - &kernel_offset_notifier); + &arm64_panic_block); return 0; } -__initcall(register_kernel_offset_dumper); +device_initcall(register_arm64_panic_block); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 139679c745bf..2dd8e3b8b94b 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -199,12 +199,12 @@ static noinline void __save_stack_trace(struct task_struct *tsk, put_task_stack(tsk); } -EXPORT_SYMBOL_GPL(save_stack_trace_tsk); void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { __save_stack_trace(tsk, trace, 1); } +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); void save_stack_trace(struct stack_trace *trace) { diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 47f651df781c..13ebd5ca2070 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -855,7 +855,7 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs) pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", tsk_stk, tsk_stk + THREAD_SIZE); pr_emerg("IRQ stack: [0x%016lx..0x%016lx]\n", - irq_stk, irq_stk + THREAD_SIZE); + irq_stk, irq_stk + IRQ_STACK_SIZE); pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n", ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index e546df0efefb..d4202a32abc9 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/signal.h> #include <linux/slab.h> +#include <linux/time_namespace.h> #include <linux/timekeeper_internal.h> #include <linux/vmalloc.h> #include <vdso/datapage.h> @@ -40,6 +41,12 @@ enum vdso_abi { #endif /* CONFIG_COMPAT_VDSO */ }; +enum vvar_pages { + VVAR_DATA_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, + VVAR_NR_PAGES, +}; + struct vdso_abi_info { const char *name; const char *vdso_code_start; @@ -107,25 +114,122 @@ static int __vdso_init(enum vdso_abi abi) vdso_info[abi].vdso_code_start) >> PAGE_SHIFT; - /* Allocate the vDSO pagelist, plus a page for the data. */ - vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages + 1, + vdso_pagelist = kcalloc(vdso_info[abi].vdso_pages, sizeof(struct page *), GFP_KERNEL); if (vdso_pagelist == NULL) return -ENOMEM; - /* Grab the vDSO data page. */ - vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data)); - - /* Grab the vDSO code pages. */ pfn = sym_to_pfn(vdso_info[abi].vdso_code_start); for (i = 0; i < vdso_info[abi].vdso_pages; i++) - vdso_pagelist[i + 1] = pfn_to_page(pfn + i); + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info[abi].cm->pages = vdso_pagelist; + + return 0; +} + +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a task + * changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + mmap_read_lock(mm); + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; - vdso_info[abi].dm->pages = &vdso_pagelist[0]; - vdso_info[abi].cm->pages = &vdso_pagelist[1]; + if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm)) + zap_page_range(vma, vma->vm_start, size); +#ifdef CONFIG_COMPAT_VDSO + if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm)) + zap_page_range(vma, vma->vm_start, size); +#endif + } + + mmap_read_unlock(mm); + return 0; +} + +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops. + * For more details check_vma_flags() and __access_remote_vm() + */ + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} +#else +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct page *timens_page = find_timens_vvar_page(vma); + unsigned long pfn; + + switch (vmf->pgoff) { + case VVAR_DATA_PAGE_OFFSET: + if (timens_page) + pfn = page_to_pfn(timens_page); + else + pfn = sym_to_pfn(vdso_data); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and + * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + +static int vvar_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + unsigned long new_size = new_vma->vm_end - new_vma->vm_start; + + if (new_size != VVAR_NR_PAGES * PAGE_SIZE) + return -EINVAL; return 0; } @@ -139,9 +243,11 @@ static int __setup_additional_pages(enum vdso_abi abi, unsigned long gp_flags = 0; void *ret; + BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + vdso_text_len = vdso_info[abi].vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ - vdso_mapping_len = vdso_text_len + PAGE_SIZE; + vdso_mapping_len = vdso_text_len + VVAR_NR_PAGES * PAGE_SIZE; vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { @@ -149,8 +255,8 @@ static int __setup_additional_pages(enum vdso_abi abi, goto up_fail; } - ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE, - VM_READ|VM_MAYREAD, + ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE, + VM_READ|VM_MAYREAD|VM_PFNMAP, vdso_info[abi].dm); if (IS_ERR(ret)) goto up_fail; @@ -158,7 +264,7 @@ static int __setup_additional_pages(enum vdso_abi abi, if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti()) gp_flags = VM_ARM64_BTI; - vdso_base += PAGE_SIZE; + vdso_base += VVAR_NR_PAGES * PAGE_SIZE; mm->context.vdso = (void *)vdso_base; ret = _install_special_mapping(mm, vdso_base, vdso_text_len, VM_READ|VM_EXEC|gp_flags| @@ -206,6 +312,8 @@ static struct vm_special_mapping aarch32_vdso_maps[] = { #ifdef CONFIG_COMPAT_VDSO [AA32_MAP_VVAR] = { .name = "[vvar]", + .fault = vvar_fault, + .mremap = vvar_mremap, }, [AA32_MAP_VDSO] = { .name = "[vdso]", @@ -371,6 +479,8 @@ enum aarch64_map { static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = { [AA64_MAP_VVAR] = { .name = "[vvar]", + .fault = vvar_fault, + .mremap = vvar_mremap, }, [AA64_MAP_VDSO] = { .name = "[vdso]", diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 7ad2d3a0cd48..d808ad31e01f 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -17,7 +17,10 @@ OUTPUT_ARCH(aarch64) SECTIONS { - PROVIDE(_vdso_data = . - PAGE_SIZE); + PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = VDSO_LBASE + SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index 337d03522048..3348ce5ea306 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -17,7 +17,10 @@ OUTPUT_ARCH(arm) SECTIONS { - PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE); + PROVIDE_HIDDEN(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); +#ifdef CONFIG_TIME_NS + PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE); +#endif . = VDSO_LBASE + SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index baf5ce9225ce..d3196671c590 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1024,9 +1024,9 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, /* Macro to expand the AMU counter and type registers*/ #define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } -#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu } +#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu } #define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } -#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu } +#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu } static bool trap_ptrauth(struct kvm_vcpu *vcpu, struct sys_reg_params *p, @@ -1629,22 +1629,22 @@ static const struct sys_reg_desc sys_reg_descs[] = { AMU_AMEVCNTR0_EL0(13), AMU_AMEVCNTR0_EL0(14), AMU_AMEVCNTR0_EL0(15), - AMU_AMEVTYPE0_EL0(0), - AMU_AMEVTYPE0_EL0(1), - AMU_AMEVTYPE0_EL0(2), - AMU_AMEVTYPE0_EL0(3), - AMU_AMEVTYPE0_EL0(4), - AMU_AMEVTYPE0_EL0(5), - AMU_AMEVTYPE0_EL0(6), - AMU_AMEVTYPE0_EL0(7), - AMU_AMEVTYPE0_EL0(8), - AMU_AMEVTYPE0_EL0(9), - AMU_AMEVTYPE0_EL0(10), - AMU_AMEVTYPE0_EL0(11), - AMU_AMEVTYPE0_EL0(12), - AMU_AMEVTYPE0_EL0(13), - AMU_AMEVTYPE0_EL0(14), - AMU_AMEVTYPE0_EL0(15), + AMU_AMEVTYPER0_EL0(0), + AMU_AMEVTYPER0_EL0(1), + AMU_AMEVTYPER0_EL0(2), + AMU_AMEVTYPER0_EL0(3), + AMU_AMEVTYPER0_EL0(4), + AMU_AMEVTYPER0_EL0(5), + AMU_AMEVTYPER0_EL0(6), + AMU_AMEVTYPER0_EL0(7), + AMU_AMEVTYPER0_EL0(8), + AMU_AMEVTYPER0_EL0(9), + AMU_AMEVTYPER0_EL0(10), + AMU_AMEVTYPER0_EL0(11), + AMU_AMEVTYPER0_EL0(12), + AMU_AMEVTYPER0_EL0(13), + AMU_AMEVTYPER0_EL0(14), + AMU_AMEVTYPER0_EL0(15), AMU_AMEVCNTR1_EL0(0), AMU_AMEVCNTR1_EL0(1), AMU_AMEVCNTR1_EL0(2), @@ -1661,22 +1661,22 @@ static const struct sys_reg_desc sys_reg_descs[] = { AMU_AMEVCNTR1_EL0(13), AMU_AMEVCNTR1_EL0(14), AMU_AMEVCNTR1_EL0(15), - AMU_AMEVTYPE1_EL0(0), - AMU_AMEVTYPE1_EL0(1), - AMU_AMEVTYPE1_EL0(2), - AMU_AMEVTYPE1_EL0(3), - AMU_AMEVTYPE1_EL0(4), - AMU_AMEVTYPE1_EL0(5), - AMU_AMEVTYPE1_EL0(6), - AMU_AMEVTYPE1_EL0(7), - AMU_AMEVTYPE1_EL0(8), - AMU_AMEVTYPE1_EL0(9), - AMU_AMEVTYPE1_EL0(10), - AMU_AMEVTYPE1_EL0(11), - AMU_AMEVTYPE1_EL0(12), - AMU_AMEVTYPE1_EL0(13), - AMU_AMEVTYPE1_EL0(14), - AMU_AMEVTYPE1_EL0(15), + AMU_AMEVTYPER1_EL0(0), + AMU_AMEVTYPER1_EL0(1), + AMU_AMEVTYPER1_EL0(2), + AMU_AMEVTYPER1_EL0(3), + AMU_AMEVTYPER1_EL0(4), + AMU_AMEVTYPER1_EL0(5), + AMU_AMEVTYPER1_EL0(6), + AMU_AMEVTYPER1_EL0(7), + AMU_AMEVTYPER1_EL0(8), + AMU_AMEVTYPER1_EL0(9), + AMU_AMEVTYPER1_EL0(10), + AMU_AMEVTYPER1_EL0(11), + AMU_AMEVTYPER1_EL0(12), + AMU_AMEVTYPER1_EL0(13), + AMU_AMEVTYPER1_EL0(14), + AMU_AMEVTYPER1_EL0(15), { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index d702d60e64da..a206655a39a5 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -198,9 +198,10 @@ set_asid: return idx2asid(asid) | generation; } -void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) +void check_and_switch_context(struct mm_struct *mm) { unsigned long flags; + unsigned int cpu; u64 asid, old_active_asid; if (system_supports_cnp()) @@ -222,9 +223,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) * relaxed xchg in flush_context will treat us as reserved * because atomic RmWs are totally ordered for a given location. */ - old_active_asid = atomic64_read(&per_cpu(active_asids, cpu)); + old_active_asid = atomic64_read(this_cpu_ptr(&active_asids)); if (old_active_asid && asid_gen_match(asid) && - atomic64_cmpxchg_relaxed(&per_cpu(active_asids, cpu), + atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_asids), old_active_asid, asid)) goto switch_mm_fastpath; @@ -236,10 +237,11 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) atomic64_set(&mm->context.id, asid); } + cpu = smp_processor_id(); if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) local_flush_tlb_all(); - atomic64_set(&per_cpu(active_asids, cpu), asid); + atomic64_set(this_cpu_ptr(&active_asids), asid); raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); switch_mm_fastpath: diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 0a52ce46f020..aa421bf4956e 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -19,6 +19,44 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> +/* + * HugeTLB Support Matrix + * + * --------------------------------------------------- + * | Page Size | CONT PTE | PMD | CONT PMD | PUD | + * --------------------------------------------------- + * | 4K | 64K | 2M | 32M | 1G | + * | 16K | 2M | 32M | 1G | | + * | 64K | 2M | 512M | 16G | | + * --------------------------------------------------- + */ + +/* + * Reserve CMA areas for the largest supported gigantic + * huge page when requested. Any other smaller gigantic + * huge pages could still be served from those areas. + */ +#ifdef CONFIG_CMA +void __init arm64_hugetlb_cma_reserve(void) +{ + int order; + +#ifdef CONFIG_ARM64_4K_PAGES + order = PUD_SHIFT - PAGE_SHIFT; +#else + order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT; +#endif + /* + * HugeTLB CMA reservation is required for gigantic + * huge pages which could not be allocated via the + * page allocator. Just warn if there is any change + * breaking this assumption. + */ + WARN_ON(order <= MAX_ORDER); + hugetlb_cma_reserve(order); +} +#endif /* CONFIG_CMA */ + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { @@ -457,9 +495,9 @@ static int __init hugetlbpage_init(void) #ifdef CONFIG_ARM64_4K_PAGES hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); #endif - hugetlb_add_hstate((CONT_PMD_SHIFT + PMD_SHIFT) - PAGE_SHIFT); + hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); - hugetlb_add_hstate((CONT_PTE_SHIFT + PAGE_SHIFT) - PAGE_SHIFT); + hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT); return 0; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 1e93cfc7c47a..f8c19c6c8e71 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -425,8 +425,8 @@ void __init bootmem_init(void) * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ -#ifdef CONFIG_ARM64_4K_PAGES - hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) + arm64_hugetlb_cma_reserve(); #endif /* @@ -563,27 +563,11 @@ void free_initmem(void) unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -/* - * Dump out memory limit information on panic. - */ -static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p) +void dump_mem_limit(void) { if (memory_limit != PHYS_ADDR_MAX) { pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); } else { pr_emerg("Memory Limit: none\n"); } - return 0; -} - -static struct notifier_block mem_limit_notifier = { - .notifier_call = dump_mem_limit, -}; - -static int __init register_mem_limit_dumper(void) -{ - atomic_notifier_chain_register(&panic_notifier_list, - &mem_limit_notifier); - return 0; } -__initcall(register_mem_limit_dumper); diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 28a6b387e80e..ec782e4a0fe4 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -264,15 +264,31 @@ static acpi_status iort_match_node_callback(struct acpi_iort_node *node, if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL }; - struct acpi_device *adev = to_acpi_device_node(dev->fwnode); + struct acpi_device *adev; struct acpi_iort_named_component *ncomp; + struct device *nc_dev = dev; + + /* + * Walk the device tree to find a device with an + * ACPI companion; there is no point in scanning + * IORT for a device matching a named component if + * the device does not have an ACPI companion to + * start with. + */ + do { + adev = ACPI_COMPANION(nc_dev); + if (adev) + break; + + nc_dev = nc_dev->parent; + } while (nc_dev); if (!adev) goto out; status = acpi_get_name(adev->handle, ACPI_FULL_PATHNAME, &buf); if (ACPI_FAILURE(status)) { - dev_warn(dev, "Can't get device full path name\n"); + dev_warn(nc_dev, "Can't get device full path name\n"); goto out; } @@ -534,7 +550,6 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev) node = iort_get_iort_node(dev->fwnode); if (node) return node; - /* * if not, then it should be a platform device defined in * DSDT/SSDT (with Named Component node in IORT) @@ -543,32 +558,29 @@ static struct acpi_iort_node *iort_find_dev_node(struct device *dev) iort_match_node_callback, dev); } - /* Find a PCI root bus */ pbus = to_pci_dev(dev)->bus; - while (!pci_is_root_bus(pbus)) - pbus = pbus->parent; return iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX, iort_match_node_callback, &pbus->dev); } /** - * iort_msi_map_rid() - Map a MSI requester ID for a device + * iort_msi_map_id() - Map a MSI input ID for a device * @dev: The device for which the mapping is to be done. - * @req_id: The device requester ID. + * @input_id: The device input ID. * - * Returns: mapped MSI RID on success, input requester ID otherwise + * Returns: mapped MSI ID on success, input ID otherwise */ -u32 iort_msi_map_rid(struct device *dev, u32 req_id) +u32 iort_msi_map_id(struct device *dev, u32 input_id) { struct acpi_iort_node *node; u32 dev_id; node = iort_find_dev_node(dev); if (!node) - return req_id; + return input_id; - iort_node_map_id(node, req_id, &dev_id, IORT_MSI_TYPE); + iort_node_map_id(node, input_id, &dev_id, IORT_MSI_TYPE); return dev_id; } @@ -625,13 +637,13 @@ static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base) /** * iort_dev_find_its_id() - Find the ITS identifier for a device * @dev: The device. - * @req_id: Device's requester ID + * @id: Device's ID * @idx: Index of the ITS identifier list. * @its_id: ITS identifier. * * Returns: 0 on success, appropriate error value otherwise */ -static int iort_dev_find_its_id(struct device *dev, u32 req_id, +static int iort_dev_find_its_id(struct device *dev, u32 id, unsigned int idx, int *its_id) { struct acpi_iort_its_group *its; @@ -641,7 +653,7 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id, if (!node) return -ENXIO; - node = iort_node_map_id(node, req_id, NULL, IORT_MSI_TYPE); + node = iort_node_map_id(node, id, NULL, IORT_MSI_TYPE); if (!node) return -ENXIO; @@ -664,19 +676,20 @@ static int iort_dev_find_its_id(struct device *dev, u32 req_id, * * Returns: the MSI domain for this device, NULL otherwise */ -struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id) +struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, + enum irq_domain_bus_token bus_token) { struct fwnode_handle *handle; int its_id; - if (iort_dev_find_its_id(dev, req_id, 0, &its_id)) + if (iort_dev_find_its_id(dev, id, 0, &its_id)) return NULL; handle = iort_find_domain_token(its_id); if (!handle) return NULL; - return irq_find_matching_fwnode(handle, DOMAIN_BUS_PCI_MSI); + return irq_find_matching_fwnode(handle, bus_token); } static void iort_set_device_domain(struct device *dev, @@ -965,19 +978,54 @@ static void iort_named_component_init(struct device *dev, nc->node_flags); } +static int iort_nc_iommu_map(struct device *dev, struct acpi_iort_node *node) +{ + struct acpi_iort_node *parent; + int err = -ENODEV, i = 0; + u32 streamid = 0; + + do { + + parent = iort_node_map_platform_id(node, &streamid, + IORT_IOMMU_TYPE, + i++); + + if (parent) + err = iort_iommu_xlate(dev, parent, streamid); + } while (parent && !err); + + return err; +} + +static int iort_nc_iommu_map_id(struct device *dev, + struct acpi_iort_node *node, + const u32 *in_id) +{ + struct acpi_iort_node *parent; + u32 streamid; + + parent = iort_node_map_id(node, *in_id, &streamid, IORT_IOMMU_TYPE); + if (parent) + return iort_iommu_xlate(dev, parent, streamid); + + return -ENODEV; +} + + /** - * iort_iommu_configure - Set-up IOMMU configuration for a device. + * iort_iommu_configure_id - Set-up IOMMU configuration for a device. * * @dev: device to configure + * @id_in: optional input id const value pointer * * Returns: iommu_ops pointer on configuration success * NULL on configuration failure */ -const struct iommu_ops *iort_iommu_configure(struct device *dev) +const struct iommu_ops *iort_iommu_configure_id(struct device *dev, + const u32 *id_in) { - struct acpi_iort_node *node, *parent; + struct acpi_iort_node *node; const struct iommu_ops *ops; - u32 streamid = 0; int err = -ENODEV; /* @@ -1006,21 +1054,13 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) if (fwspec && iort_pci_rc_supports_ats(node)) fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; } else { - int i = 0; - node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT, iort_match_node_callback, dev); if (!node) return NULL; - do { - parent = iort_node_map_platform_id(node, &streamid, - IORT_IOMMU_TYPE, - i++); - - if (parent) - err = iort_iommu_xlate(dev, parent, streamid); - } while (parent && !err); + err = id_in ? iort_nc_iommu_map_id(dev, node, id_in) : + iort_nc_iommu_map(dev, node); if (!err) iort_named_component_init(dev, node); @@ -1045,6 +1085,7 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) return ops; } + #else static inline const struct iommu_ops *iort_fwspec_iommu_ops(struct device *dev) { return NULL; } @@ -1053,7 +1094,8 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops, { return 0; } int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) { return 0; } -const struct iommu_ops *iort_iommu_configure(struct device *dev) +const struct iommu_ops *iort_iommu_configure_id(struct device *dev, + const u32 *input_id) { return NULL; } #endif diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 8777faced51a..2142f1554761 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1457,8 +1457,10 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, * acpi_dma_configure - Set-up DMA configuration for the device. * @dev: The pointer to the device * @attr: device dma attributes + * @input_id: input device id const value pointer */ -int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) +int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, + const u32 *input_id) { const struct iommu_ops *iommu; u64 dma_addr = 0, size = 0; @@ -1470,7 +1472,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) iort_dma_setup(dev, &dma_addr, &size); - iommu = iort_iommu_configure(dev); + iommu = iort_iommu_configure_id(dev, input_id); if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; @@ -1479,7 +1481,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) return 0; } -EXPORT_SYMBOL_GPL(acpi_dma_configure); +EXPORT_SYMBOL_GPL(acpi_dma_configure_id); static void acpi_init_coherency(struct acpi_device *adev) { diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index c8b1c3842c1a..189bff2115a8 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -592,6 +592,7 @@ static int dprc_probe(struct fsl_mc_device *mc_dev) bool mc_io_created = false; bool msi_domain_set = false; u16 major_ver, minor_ver; + struct irq_domain *mc_msi_domain; if (!is_fsl_mc_bus_dprc(mc_dev)) return -EINVAL; @@ -621,31 +622,15 @@ static int dprc_probe(struct fsl_mc_device *mc_dev) return error; mc_io_created = true; + } - /* - * Inherit parent MSI domain: - */ - dev_set_msi_domain(&mc_dev->dev, - dev_get_msi_domain(parent_dev)); - msi_domain_set = true; + mc_msi_domain = fsl_mc_find_msi_domain(&mc_dev->dev); + if (!mc_msi_domain) { + dev_warn(&mc_dev->dev, + "WARNING: MC bus without interrupt support\n"); } else { - /* - * This is a root DPRC - */ - struct irq_domain *mc_msi_domain; - - if (dev_is_fsl_mc(parent_dev)) - return -EINVAL; - - error = fsl_mc_find_msi_domain(parent_dev, - &mc_msi_domain); - if (error < 0) { - dev_warn(&mc_dev->dev, - "WARNING: MC bus without interrupt support\n"); - } else { - dev_set_msi_domain(&mc_dev->dev, mc_msi_domain); - msi_domain_set = true; - } + dev_set_msi_domain(&mc_dev->dev, mc_msi_domain); + msi_domain_set = true; } error = dprc_open(mc_dev->mc_io, 0, mc_dev->obj_desc.id, diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 40526da5c6a6..324d49d6df89 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -18,6 +18,8 @@ #include <linux/bitops.h> #include <linux/msi.h> #include <linux/dma-mapping.h> +#include <linux/acpi.h> +#include <linux/iommu.h> #include "fsl-mc-private.h" @@ -38,6 +40,7 @@ struct fsl_mc { struct fsl_mc_device *root_mc_bus_dev; u8 num_translation_ranges; struct fsl_mc_addr_translation_range *translation_ranges; + void *fsl_mc_regs; }; /** @@ -56,6 +59,10 @@ struct fsl_mc_addr_translation_range { phys_addr_t start_phys_addr; }; +#define FSL_MC_FAPR 0x28 +#define MC_FAPR_PL BIT(18) +#define MC_FAPR_BMT BIT(17) + /** * fsl_mc_bus_match - device to driver matching callback * @dev: the fsl-mc device to match against @@ -118,11 +125,16 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env) static int fsl_mc_dma_configure(struct device *dev) { struct device *dma_dev = dev; + struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); + u32 input_id = mc_dev->icid; while (dev_is_fsl_mc(dma_dev)) dma_dev = dma_dev->parent; - return of_dma_configure(dev, dma_dev->of_node, 0); + if (dev_of_node(dma_dev)) + return of_dma_configure_id(dev, dma_dev->of_node, 0, &input_id); + + return acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id); } static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, @@ -368,8 +380,8 @@ EXPORT_SYMBOL_GPL(fsl_mc_get_version); /** * fsl_mc_get_root_dprc - function to traverse to the root dprc */ -static void fsl_mc_get_root_dprc(struct device *dev, - struct device **root_dprc_dev) +void fsl_mc_get_root_dprc(struct device *dev, + struct device **root_dprc_dev) { if (!dev) { *root_dprc_dev = NULL; @@ -863,8 +875,11 @@ static int fsl_mc_bus_probe(struct platform_device *pdev) struct fsl_mc_io *mc_io = NULL; int container_id; phys_addr_t mc_portal_phys_addr; - u32 mc_portal_size; - struct resource res; + u32 mc_portal_size, mc_stream_id; + struct resource *plat_res; + + if (!iommu_present(&fsl_mc_bus_type)) + return -EPROBE_DEFER; mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL); if (!mc) @@ -872,19 +887,33 @@ static int fsl_mc_bus_probe(struct platform_device *pdev) platform_set_drvdata(pdev, mc); + plat_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + mc->fsl_mc_regs = devm_ioremap_resource(&pdev->dev, plat_res); + if (IS_ERR(mc->fsl_mc_regs)) + return PTR_ERR(mc->fsl_mc_regs); + + if (IS_ENABLED(CONFIG_ACPI) && !dev_of_node(&pdev->dev)) { + mc_stream_id = readl(mc->fsl_mc_regs + FSL_MC_FAPR); + /* + * HW ORs the PL and BMT bit, places the result in bit 15 of + * the StreamID and ORs in the ICID. Calculate it accordingly. + */ + mc_stream_id = (mc_stream_id & 0xffff) | + ((mc_stream_id & (MC_FAPR_PL | MC_FAPR_BMT)) ? + 0x4000 : 0); + error = acpi_dma_configure_id(&pdev->dev, DEV_DMA_COHERENT, + &mc_stream_id); + if (error) + dev_warn(&pdev->dev, "failed to configure dma: %d.\n", + error); + } + /* * Get physical address of MC portal for the root DPRC: */ - error = of_address_to_resource(pdev->dev.of_node, 0, &res); - if (error < 0) { - dev_err(&pdev->dev, - "of_address_to_resource() failed for %pOF\n", - pdev->dev.of_node); - return error; - } - - mc_portal_phys_addr = res.start; - mc_portal_size = resource_size(&res); + plat_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + mc_portal_phys_addr = plat_res->start; + mc_portal_size = resource_size(plat_res); error = fsl_create_mc_io(&pdev->dev, mc_portal_phys_addr, mc_portal_size, NULL, FSL_MC_IO_ATOMIC_CONTEXT_PORTAL, &mc_io); @@ -901,11 +930,13 @@ static int fsl_mc_bus_probe(struct platform_device *pdev) dev_info(&pdev->dev, "MC firmware version: %u.%u.%u\n", mc_version.major, mc_version.minor, mc_version.revision); - error = get_mc_addr_translation_ranges(&pdev->dev, - &mc->translation_ranges, - &mc->num_translation_ranges); - if (error < 0) - goto error_cleanup_mc_io; + if (dev_of_node(&pdev->dev)) { + error = get_mc_addr_translation_ranges(&pdev->dev, + &mc->translation_ranges, + &mc->num_translation_ranges); + if (error < 0) + goto error_cleanup_mc_io; + } error = dprc_get_container_id(mc_io, 0, &container_id); if (error < 0) { @@ -932,6 +963,7 @@ static int fsl_mc_bus_probe(struct platform_device *pdev) goto error_cleanup_mc_io; mc->root_mc_bus_dev = mc_bus_dev; + mc_bus_dev->dev.fwnode = pdev->dev.fwnode; return 0; error_cleanup_mc_io: @@ -965,11 +997,18 @@ static const struct of_device_id fsl_mc_bus_match_table[] = { MODULE_DEVICE_TABLE(of, fsl_mc_bus_match_table); +static const struct acpi_device_id fsl_mc_bus_acpi_match_table[] = { + {"NXP0008", 0 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, fsl_mc_bus_acpi_match_table); + static struct platform_driver fsl_mc_bus_driver = { .driver = { .name = "fsl_mc_bus", .pm = NULL, .of_match_table = fsl_mc_bus_match_table, + .acpi_match_table = fsl_mc_bus_acpi_match_table, }, .probe = fsl_mc_bus_probe, .remove = fsl_mc_bus_remove, diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 8b9c66d7c4ff..8edadf05cbb7 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -13,6 +13,7 @@ #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/msi.h> +#include <linux/acpi_iort.h> #include "fsl-mc-private.h" @@ -177,23 +178,36 @@ struct irq_domain *fsl_mc_msi_create_irq_domain(struct fwnode_handle *fwnode, return domain; } -int fsl_mc_find_msi_domain(struct device *mc_platform_dev, - struct irq_domain **mc_msi_domain) +struct irq_domain *fsl_mc_find_msi_domain(struct device *dev) { + struct device *root_dprc_dev; + struct device *bus_dev; struct irq_domain *msi_domain; - struct device_node *mc_of_node = mc_platform_dev->of_node; + struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); - msi_domain = of_msi_get_domain(mc_platform_dev, mc_of_node, - DOMAIN_BUS_FSL_MC_MSI); - if (!msi_domain) { - pr_err("Unable to find fsl-mc MSI domain for %pOF\n", - mc_of_node); + fsl_mc_get_root_dprc(dev, &root_dprc_dev); + bus_dev = root_dprc_dev->parent; + + if (bus_dev->of_node) { + msi_domain = of_msi_map_get_device_domain(dev, + mc_dev->icid, + DOMAIN_BUS_FSL_MC_MSI); - return -ENOENT; + /* + * if the msi-map property is missing assume that all the + * child containers inherit the domain from the parent + */ + if (!msi_domain) + + msi_domain = of_msi_get_domain(bus_dev, + bus_dev->of_node, + DOMAIN_BUS_FSL_MC_MSI); + } else { + msi_domain = iort_get_device_domain(dev, mc_dev->icid, + DOMAIN_BUS_FSL_MC_MSI); } - *mc_msi_domain = msi_domain; - return 0; + return msi_domain; } static void fsl_mc_msi_free_descs(struct device *dev) diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h index 21ca8c756ee7..7a46a12eb747 100644 --- a/drivers/bus/fsl-mc/fsl-mc-private.h +++ b/drivers/bus/fsl-mc/fsl-mc-private.h @@ -595,8 +595,7 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, void fsl_mc_msi_domain_free_irqs(struct device *dev); -int fsl_mc_find_msi_domain(struct device *mc_platform_dev, - struct irq_domain **mc_msi_domain); +struct irq_domain *fsl_mc_find_msi_domain(struct device *dev); int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus, unsigned int irq_count); @@ -613,6 +612,9 @@ void fsl_destroy_mc_io(struct fsl_mc_io *mc_io); bool fsl_mc_is_root_dprc(struct device *dev); +void fsl_mc_get_root_dprc(struct device *dev, + struct device **root_dprc_dev); + struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc, struct fsl_mc_device *mc_bus_dev); diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 20738aacac89..e505b9130a1c 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -118,46 +118,66 @@ static int of_iommu_xlate(struct device *dev, return ret; } -struct of_pci_iommu_alias_info { - struct device *dev; - struct device_node *np; -}; - -static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) +static int of_iommu_configure_dev_id(struct device_node *master_np, + struct device *dev, + const u32 *id) { - struct of_pci_iommu_alias_info *info = data; struct of_phandle_args iommu_spec = { .args_count = 1 }; int err; - err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask", - &iommu_spec.np, iommu_spec.args); + err = of_map_id(master_np, *id, "iommu-map", + "iommu-map-mask", &iommu_spec.np, + iommu_spec.args); if (err) return err == -ENODEV ? NO_IOMMU : err; - err = of_iommu_xlate(info->dev, &iommu_spec); + err = of_iommu_xlate(dev, &iommu_spec); of_node_put(iommu_spec.np); return err; } -static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev, - struct device_node *master_np) +static int of_iommu_configure_dev(struct device_node *master_np, + struct device *dev) { - struct of_phandle_args iommu_spec = { .args_count = 1 }; - int err; - - err = of_map_rid(master_np, mc_dev->icid, "iommu-map", - "iommu-map-mask", &iommu_spec.np, - iommu_spec.args); - if (err) - return err == -ENODEV ? NO_IOMMU : err; + struct of_phandle_args iommu_spec; + int err = NO_IOMMU, idx = 0; + + while (!of_parse_phandle_with_args(master_np, "iommus", + "#iommu-cells", + idx, &iommu_spec)) { + err = of_iommu_xlate(dev, &iommu_spec); + of_node_put(iommu_spec.np); + idx++; + if (err) + break; + } - err = of_iommu_xlate(&mc_dev->dev, &iommu_spec); - of_node_put(iommu_spec.np); return err; } +struct of_pci_iommu_alias_info { + struct device *dev; + struct device_node *np; +}; + +static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) +{ + struct of_pci_iommu_alias_info *info = data; + u32 input_id = alias; + + return of_iommu_configure_dev_id(info->np, info->dev, &input_id); +} + +static int of_iommu_configure_device(struct device_node *master_np, + struct device *dev, const u32 *id) +{ + return (id) ? of_iommu_configure_dev_id(master_np, dev, id) : + of_iommu_configure_dev(master_np, dev); +} + const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np) + struct device_node *master_np, + const u32 *id) { const struct iommu_ops *ops = NULL; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); @@ -188,21 +208,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, pci_request_acs(); err = pci_for_each_dma_alias(to_pci_dev(dev), of_pci_iommu_init, &info); - } else if (dev_is_fsl_mc(dev)) { - err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np); } else { - struct of_phandle_args iommu_spec; - int idx = 0; - - while (!of_parse_phandle_with_args(master_np, "iommus", - "#iommu-cells", - idx, &iommu_spec)) { - err = of_iommu_xlate(dev, &iommu_spec); - of_node_put(iommu_spec.np); - idx++; - if (err) - break; - } + err = of_iommu_configure_device(master_np, dev, id); fwspec = dev_iommu_fwspec_get(dev); if (!err && fwspec) diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c index 606efa64adff..634263dfd7b5 100644 --- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c @@ -7,6 +7,8 @@ * */ +#include <linux/acpi.h> +#include <linux/acpi_iort.h> #include <linux/of_device.h> #include <linux/of_address.h> #include <linux/irq.h> @@ -23,6 +25,19 @@ static struct irq_chip its_msi_irq_chip = { .irq_set_affinity = msi_domain_set_affinity }; +static u32 fsl_mc_msi_domain_get_msi_id(struct irq_domain *domain, + struct fsl_mc_device *mc_dev) +{ + struct device_node *of_node; + u32 out_id; + + of_node = irq_domain_get_of_node(domain); + out_id = of_node ? of_msi_map_id(&mc_dev->dev, of_node, mc_dev->icid) : + iort_msi_map_id(&mc_dev->dev, mc_dev->icid); + + return out_id; +} + static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain, struct device *dev, int nvec, msi_alloc_info_t *info) @@ -43,7 +58,8 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain, * NOTE: This device id corresponds to the IOMMU stream ID * associated with the DPRC object (ICID). */ - info->scratchpad[0].ul = mc_bus_dev->icid; + info->scratchpad[0].ul = fsl_mc_msi_domain_get_msi_id(msi_domain, + mc_bus_dev); msi_info = msi_get_domain_info(msi_domain->parent); /* Allocate at least 32 MSIs, and always as a power of 2 */ @@ -66,12 +82,71 @@ static const struct of_device_id its_device_id[] = { {}, }; -static int __init its_fsl_mc_msi_init(void) +static void __init its_fsl_mc_msi_init_one(struct fwnode_handle *handle, + const char *name) { - struct device_node *np; struct irq_domain *parent; struct irq_domain *mc_msi_domain; + parent = irq_find_matching_fwnode(handle, DOMAIN_BUS_NEXUS); + if (!parent || !msi_get_domain_info(parent)) { + pr_err("%s: unable to locate ITS domain\n", name); + return; + } + + mc_msi_domain = fsl_mc_msi_create_irq_domain(handle, + &its_fsl_mc_msi_domain_info, + parent); + if (!mc_msi_domain) { + pr_err("%s: unable to create fsl-mc domain\n", name); + return; + } + + pr_info("fsl-mc MSI: %s domain created\n", name); +} + +#ifdef CONFIG_ACPI +static int __init +its_fsl_mc_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_generic_translator *its_entry; + struct fwnode_handle *dom_handle; + const char *node_name; + int err = 0; + + its_entry = (struct acpi_madt_generic_translator *)header; + node_name = kasprintf(GFP_KERNEL, "ITS@0x%lx", + (long)its_entry->base_address); + + dom_handle = iort_find_domain_token(its_entry->translation_id); + if (!dom_handle) { + pr_err("%s: Unable to locate ITS domain handle\n", node_name); + err = -ENXIO; + goto out; + } + + its_fsl_mc_msi_init_one(dom_handle, node_name); + +out: + kfree(node_name); + return err; +} + + +static void __init its_fsl_mc_acpi_msi_init(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR, + its_fsl_mc_msi_parse_madt, 0); +} +#else +static inline void its_fsl_mc_acpi_msi_init(void) { } +#endif + +static void __init its_fsl_mc_of_msi_init(void) +{ + struct device_node *np; + for (np = of_find_matching_node(NULL, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { if (!of_device_is_available(np)) @@ -79,23 +154,15 @@ static int __init its_fsl_mc_msi_init(void) if (!of_property_read_bool(np, "msi-controller")) continue; - parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS); - if (!parent || !msi_get_domain_info(parent)) { - pr_err("%pOF: unable to locate ITS domain\n", np); - continue; - } - - mc_msi_domain = fsl_mc_msi_create_irq_domain( - of_node_to_fwnode(np), - &its_fsl_mc_msi_domain_info, - parent); - if (!mc_msi_domain) { - pr_err("%pOF: unable to create fsl-mc domain\n", np); - continue; - } - - pr_info("fsl-mc MSI: %pOF domain created\n", np); + its_fsl_mc_msi_init_one(of_node_to_fwnode(np), + np->full_name); } +} + +static int __init its_fsl_mc_msi_init(void) +{ + its_fsl_mc_of_msi_init(); + its_fsl_mc_acpi_msi_init(); return 0; } diff --git a/drivers/of/base.c b/drivers/of/base.c index ae03b1218b06..ea44fea99813 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -2201,15 +2201,15 @@ int of_find_last_cache_level(unsigned int cpu) } /** - * of_map_rid - Translate a requester ID through a downstream mapping. + * of_map_id - Translate an ID through a downstream mapping. * @np: root complex device node. - * @rid: device requester ID to map. + * @id: device ID to map. * @map_name: property name of the map to use. * @map_mask_name: optional property name of the mask to use. * @target: optional pointer to a target device node. * @id_out: optional pointer to receive the translated ID. * - * Given a device requester ID, look up the appropriate implementation-defined + * Given a device ID, look up the appropriate implementation-defined * platform ID and/or the target device which receives transactions on that * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or * @id_out may be NULL if only the other is required. If @target points to @@ -2219,11 +2219,11 @@ int of_find_last_cache_level(unsigned int cpu) * * Return: 0 on success or a standard error code on failure. */ -int of_map_rid(struct device_node *np, u32 rid, +int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) { - u32 map_mask, masked_rid; + u32 map_mask, masked_id; int map_len; const __be32 *map = NULL; @@ -2235,7 +2235,7 @@ int of_map_rid(struct device_node *np, u32 rid, if (target) return -ENODEV; /* Otherwise, no map implies no translation */ - *id_out = rid; + *id_out = id; return 0; } @@ -2255,22 +2255,22 @@ int of_map_rid(struct device_node *np, u32 rid, if (map_mask_name) of_property_read_u32(np, map_mask_name, &map_mask); - masked_rid = map_mask & rid; + masked_id = map_mask & id; for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) { struct device_node *phandle_node; - u32 rid_base = be32_to_cpup(map + 0); + u32 id_base = be32_to_cpup(map + 0); u32 phandle = be32_to_cpup(map + 1); u32 out_base = be32_to_cpup(map + 2); - u32 rid_len = be32_to_cpup(map + 3); + u32 id_len = be32_to_cpup(map + 3); - if (rid_base & ~map_mask) { - pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n", + if (id_base & ~map_mask) { + pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores id-base (0x%x)\n", np, map_name, map_name, - map_mask, rid_base); + map_mask, id_base); return -EFAULT; } - if (masked_rid < rid_base || masked_rid >= rid_base + rid_len) + if (masked_id < id_base || masked_id >= id_base + id_len) continue; phandle_node = of_find_node_by_phandle(phandle); @@ -2288,20 +2288,20 @@ int of_map_rid(struct device_node *np, u32 rid, } if (id_out) - *id_out = masked_rid - rid_base + out_base; + *id_out = masked_id - id_base + out_base; - pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n", - np, map_name, map_mask, rid_base, out_base, - rid_len, rid, masked_rid - rid_base + out_base); + pr_debug("%pOF: %s, using mask %08x, id-base: %08x, out-base: %08x, length: %08x, id: %08x -> %08x\n", + np, map_name, map_mask, id_base, out_base, + id_len, id, masked_id - id_base + out_base); return 0; } - pr_info("%pOF: no %s translation for rid 0x%x on %pOF\n", np, map_name, - rid, target && *target ? *target : NULL); + pr_info("%pOF: no %s translation for id 0x%x on %pOF\n", np, map_name, + id, target && *target ? *target : NULL); /* Bypasses translation */ if (id_out) - *id_out = rid; + *id_out = id; return 0; } -EXPORT_SYMBOL_GPL(of_map_rid); +EXPORT_SYMBOL_GPL(of_map_id); diff --git a/drivers/of/device.c b/drivers/of/device.c index 27203bfd0b22..b439c1e05434 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -78,6 +78,7 @@ int of_device_add(struct platform_device *ofdev) * @np: Pointer to OF node having DMA configuration * @force_dma: Whether device is to be set up by of_dma_configure() even if * DMA capability is not explicitly described by firmware. + * @id: Optional const pointer value input id * * Try to get devices's DMA configuration from DT and update it * accordingly. @@ -86,7 +87,8 @@ int of_device_add(struct platform_device *ofdev) * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events * to fix up DMA configuration. */ -int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) +int of_dma_configure_id(struct device *dev, struct device_node *np, + bool force_dma, const u32 *id) { u64 dma_addr, paddr, size = 0; int ret; @@ -160,7 +162,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); - iommu = of_iommu_configure(dev, np); + iommu = of_iommu_configure(dev, np, id); if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; @@ -171,7 +173,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) return 0; } -EXPORT_SYMBOL_GPL(of_dma_configure); +EXPORT_SYMBOL_GPL(of_dma_configure_id); int of_device_register(struct platform_device *pdev) { diff --git a/drivers/of/irq.c b/drivers/of/irq.c index a296eaf52a5b..25d17b8a1a1a 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -576,55 +576,57 @@ err: } } -static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, - u32 rid_in) +static u32 __of_msi_map_id(struct device *dev, struct device_node **np, + u32 id_in) { struct device *parent_dev; - u32 rid_out = rid_in; + u32 id_out = id_in; /* * Walk up the device parent links looking for one with a * "msi-map" property. */ for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) - if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map", - "msi-map-mask", np, &rid_out)) + if (!of_map_id(parent_dev->of_node, id_in, "msi-map", + "msi-map-mask", np, &id_out)) break; - return rid_out; + return id_out; } /** - * of_msi_map_rid - Map a MSI requester ID for a device. + * of_msi_map_id - Map a MSI ID for a device. * @dev: device for which the mapping is to be done. * @msi_np: device node of the expected msi controller. - * @rid_in: unmapped MSI requester ID for the device. + * @id_in: unmapped MSI ID for the device. * * Walk up the device hierarchy looking for devices with a "msi-map" - * property. If found, apply the mapping to @rid_in. + * property. If found, apply the mapping to @id_in. * - * Returns the mapped MSI requester ID. + * Returns the mapped MSI ID. */ -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in) +u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in) { - return __of_msi_map_rid(dev, &msi_np, rid_in); + return __of_msi_map_id(dev, &msi_np, id_in); } /** * 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. - * @rid: Requester ID for the device. + * @id: Device ID. + * @bus_token: Bus token * * Walk up the device hierarchy looking for devices with a "msi-map" * property. * * Returns: the MSI domain for this device (or NULL on failure) */ -struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid) +struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id, + u32 bus_token) { struct device_node *np = NULL; - __of_msi_map_rid(dev, &np, rid); - return irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI); + __of_msi_map_id(dev, &np, id); + return irq_find_matching_host(np, bus_token); } /** diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 6b43a5455c7a..19aeadb22f11 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1535,8 +1535,8 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev) pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); of_node = irq_domain_get_of_node(domain); - rid = of_node ? of_msi_map_rid(&pdev->dev, of_node, rid) : - iort_msi_map_rid(&pdev->dev, rid); + rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) : + iort_msi_map_id(&pdev->dev, rid); return rid; } @@ -1556,9 +1556,10 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) u32 rid = pci_dev_id(pdev); pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); - dom = of_msi_map_get_device_domain(&pdev->dev, rid); + dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI); if (!dom) - dom = iort_get_device_domain(&pdev->dev, rid); + dom = iort_get_device_domain(&pdev->dev, rid, + DOMAIN_BUS_PCI_MSI); return dom; } #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 48e28ef93a70..2d09f3e47d12 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -755,8 +755,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; - res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0); - smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0); + smmu_pmu->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res_0); if (IS_ERR(smmu_pmu->reg_base)) return PTR_ERR(smmu_pmu->reg_base); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 5afb6ceb284f..a3abcc4b7d9f 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -588,8 +588,13 @@ bool acpi_dma_supported(struct acpi_device *adev); enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, u64 *size); -int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr); - +int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, + const u32 *input_id); +static inline int acpi_dma_configure(struct device *dev, + enum dev_dma_attr attr) +{ + return acpi_dma_configure_id(dev, attr, NULL); +} struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children); int acpi_is_root_bridge(acpi_handle); diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 3f1649a8cf55..ef75ec86f865 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -512,6 +512,38 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm } #endif +/* + * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, + * and set corresponding cleared_*. + */ +static inline void tlb_flush_pte_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + __tlb_adjust_range(tlb, address, size); + tlb->cleared_ptes = 1; +} + +static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + __tlb_adjust_range(tlb, address, size); + tlb->cleared_pmds = 1; +} + +static inline void tlb_flush_pud_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + __tlb_adjust_range(tlb, address, size); + tlb->cleared_puds = 1; +} + +static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + __tlb_adjust_range(tlb, address, size); + tlb->cleared_p4ds = 1; +} + #ifndef __tlb_remove_tlb_entry #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #endif @@ -525,19 +557,17 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ - __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - tlb->cleared_ptes = 1; \ + tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - __tlb_adjust_range(tlb, address, _sz); \ if (_sz == PMD_SIZE) \ - tlb->cleared_pmds = 1; \ + tlb_flush_pmd_range(tlb, address, _sz); \ else if (_sz == PUD_SIZE) \ - tlb->cleared_puds = 1; \ + tlb_flush_pud_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) @@ -551,8 +581,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ - __tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE); \ - tlb->cleared_pmds = 1; \ + tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) @@ -566,8 +595,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ - __tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE); \ - tlb->cleared_puds = 1; \ + tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) @@ -592,9 +620,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ - __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ - tlb->cleared_pmds = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif @@ -602,9 +629,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ - __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ - tlb->cleared_puds = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif @@ -612,9 +638,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ - __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ - tlb->cleared_p4ds = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d661cd0ee64d..6d2c47489d90 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -905,6 +905,13 @@ static inline int acpi_dma_configure(struct device *dev, return 0; } +static inline int acpi_dma_configure_id(struct device *dev, + enum dev_dma_attr attr, + const u32 *input_id) +{ + return 0; +} + #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 8e7e2ec37f1b..20a32120bb88 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -28,27 +28,29 @@ void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT void acpi_iort_init(void); -u32 iort_msi_map_rid(struct device *dev, u32 req_id); -struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +u32 iort_msi_map_id(struct device *dev, u32 id); +struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, + enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); -const struct iommu_ops *iort_iommu_configure(struct device *dev); +const struct iommu_ops *iort_iommu_configure_id(struct device *dev, + const u32 *id_in); int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); #else static inline void acpi_iort_init(void) { } -static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) -{ return req_id; } -static inline struct irq_domain *iort_get_device_domain(struct device *dev, - u32 req_id) +static inline u32 iort_msi_map_id(struct device *dev, u32 id) +{ return id; } +static inline struct irq_domain *iort_get_device_domain( + struct device *dev, u32 id, enum irq_domain_bus_token bus_token) { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size) { } -static inline const struct iommu_ops *iort_iommu_configure( - struct device *dev) +static inline const struct iommu_ops *iort_iommu_configure_id( + struct device *dev, const u32 *id_in) { return NULL; } static inline int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 56d6a5c6e353..efcbde731f03 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -81,6 +81,28 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 + #ifndef __ASSEMBLY__ #include <linux/linkage.h> @@ -332,15 +354,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) /* - * Return codes defined in ARM DEN 0070A - * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C - */ -#define SMCCC_RET_SUCCESS 0 -#define SMCCC_RET_NOT_SUPPORTED -1 -#define SMCCC_RET_NOT_REQUIRED -2 -#define SMCCC_RET_INVALID_PARAMETER -3 - -/* * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. * Used when the SMCCC conduit is not defined. The empty asm statement * avoids compiler warnings about unused variables. @@ -385,18 +398,5 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, method; \ }) -/* Paravirtualised time calls (defined by ARM DEN0057A) */ -#define ARM_SMCCC_HV_PV_TIME_FEATURES \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ - ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_STANDARD_HYP, \ - 0x20) - -#define ARM_SMCCC_HV_PV_TIME_ST \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ - ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_STANDARD_HYP, \ - 0x21) - #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/of.h b/include/linux/of.h index c669c0a4732f..60abe3f636ad 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -554,7 +554,7 @@ bool of_console_check(struct device_node *dn, char *name, int index); extern int of_cpu_node_to_id(struct device_node *np); -int of_map_rid(struct device_node *np, u32 rid, +int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -978,7 +978,7 @@ static inline int of_cpu_node_to_id(struct device_node *np) return -ENODEV; } -static inline int of_map_rid(struct device_node *np, u32 rid, +static inline int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) { diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8d31e39dd564..07ca187fc5e4 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -55,9 +55,15 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return of_node_get(cpu_dev->of_node); } -int of_dma_configure(struct device *dev, +int of_dma_configure_id(struct device *dev, struct device_node *np, - bool force_dma); + bool force_dma, const u32 *id); +static inline int of_dma_configure(struct device *dev, + struct device_node *np, + bool force_dma) +{ + return of_dma_configure_id(dev, np, force_dma, NULL); +} #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, @@ -106,6 +112,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) return NULL; } +static inline int of_dma_configure_id(struct device *dev, + struct device_node *np, + bool force_dma) +{ + return 0; +} static inline int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index f3d40dd7bb66..16f4b3e87f20 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -13,7 +13,8 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix, size_t *size); extern const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np); + struct device_node *master_np, + const u32 *id); #else @@ -25,7 +26,8 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix, } static inline const struct iommu_ops *of_iommu_configure(struct device *dev, - struct device_node *master_np) + struct device_node *master_np, + const u32 *id) { return NULL; } diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 1214cabb2247..e8b78139f78c 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -52,9 +52,10 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token); extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, - u32 rid); + u32 id, + u32 bus_token); extern void of_msi_configure(struct device *dev, struct device_node *np); -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); +u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -85,17 +86,17 @@ static inline struct irq_domain *of_msi_get_domain(struct device *dev, return NULL; } static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev, - u32 rid) + u32 id, u32 bus_token) { return NULL; } static inline void of_msi_configure(struct device *dev, struct device_node *np) { } -static inline u32 of_msi_map_rid(struct device *dev, - struct device_node *msi_np, u32 rid_in) +static inline u32 of_msi_map_id(struct device *dev, + struct device_node *msi_np, u32 id_in) { - return rid_in; + return id_in; } #endif diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 0bb04a96a6d4..528718e4ed52 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -6,6 +6,34 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK +/** + * struct clock_read_data - data required to read from sched_clock() + * + * @epoch_ns: sched_clock() value at last update + * @epoch_cyc: Clock cycle value at last update. + * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit + * clocks. + * @read_sched_clock: Current clock source (or dummy source when suspended). + * @mult: Multipler for scaled math conversion. + * @shift: Shift value for scaled math conversion. + * + * Care must be taken when updating this structure; it is read by + * some very hot code paths. It occupies <=40 bytes and, when combined + * with the seqcount used to synchronize access, comfortably fits into + * a 64 byte cache line. + */ +struct clock_read_data { + u64 epoch_ns; + u64 epoch_cyc; + u64 sched_clock_mask; + u64 (*read_sched_clock)(void); + u32 mult; + u32 shift; +}; + +extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq); +extern int sched_clock_read_retry(unsigned int seq); + extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..21a1edd08cbe 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -532,9 +532,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -593,13 +594,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h index 7955c56d6b3c..ee810cae4e1e 100644 --- a/include/vdso/datapage.h +++ b/include/vdso/datapage.h @@ -109,6 +109,7 @@ struct vdso_data { * relocation, and this is what we need. */ extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden"))); +extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden"))); /* * The generic vDSO implementation requires that gettimeofday.h diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 9f1557b98468..18175687133a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -413,6 +413,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); #endif VMCOREINFO_STRUCT_SIZE(page); VMCOREINFO_STRUCT_SIZE(pglist_data); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index fa3f800d7d76..0deaf4b79fb4 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -20,31 +20,6 @@ #include "timekeeping.h" /** - * struct clock_read_data - data required to read from sched_clock() - * - * @epoch_ns: sched_clock() value at last update - * @epoch_cyc: Clock cycle value at last update. - * @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit - * clocks. - * @read_sched_clock: Current clock source (or dummy source when suspended). - * @mult: Multipler for scaled math conversion. - * @shift: Shift value for scaled math conversion. - * - * Care must be taken when updating this structure; it is read by - * some very hot code paths. It occupies <=40 bytes and, when combined - * with the seqcount used to synchronize access, comfortably fits into - * a 64 byte cache line. - */ -struct clock_read_data { - u64 epoch_ns; - u64 epoch_cyc; - u64 sched_clock_mask; - u64 (*read_sched_clock)(void); - u32 mult; - u32 shift; -}; - -/** * struct clock_data - all data needed for sched_clock() (including * registration of a new clock source) * @@ -93,6 +68,17 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) return (cyc * mult) >> shift; } +struct clock_read_data *sched_clock_read_begin(unsigned int *seq) +{ + *seq = raw_read_seqcount_latch(&cd.seq); + return cd.read_data + (*seq & 1); +} + +int sched_clock_read_retry(unsigned int seq) +{ + return read_seqcount_retry(&cd.seq, seq); +} + unsigned long long notrace sched_clock(void) { u64 cyc, res; @@ -100,13 +86,12 @@ unsigned long long notrace sched_clock(void) struct clock_read_data *rd; do { - seq = raw_read_seqcount(&cd.seq); - rd = cd.read_data + (seq & 1); + rd = sched_clock_read_begin(&seq); cyc = (rd->read_sched_clock() - rd->epoch_cyc) & rd->sched_clock_mask; res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); - } while (read_seqcount_retry(&cd.seq, seq)); + } while (sched_clock_read_retry(seq)); return res; } diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 7225107a9aaf..e59022b3f125 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -434,6 +434,11 @@ static int arm_is_fake_mcount(Elf32_Rel const *rp) return 1; } +static int arm64_is_fake_mcount(Elf64_Rel const *rp) +{ + return ELF64_R_TYPE(w(rp->r_info)) != R_AARCH64_CALL26; +} + /* 64-bit EM_MIPS has weird ELF64_Rela.r_info. * http://techpubs.sgi.com/library/manuals/4000/007-4658-001/pdf/007-4658-001.pdf * We interpret Table 29 Relocation Operation (Elf64_Rel, Elf64_Rela) [p.40] @@ -547,6 +552,7 @@ static int do_file(char const *const fname) make_nop = make_nop_arm64; rel_type_nop = R_AARCH64_NONE; ideal_nop = ideal_nop4_arm64; + is_fake_mcount64 = arm64_is_fake_mcount; break; case EM_IA_64: reltype = R_IA64_IMM64; break; case EM_MIPS: /* reltype: e_class */ break; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..21a1edd08cbe 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -532,9 +532,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -593,13 +594,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. |