diff options
Diffstat (limited to 'arch/arm64')
41 files changed, 543 insertions, 469 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7b071a00425d..b67e6934316f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1549,7 +1549,7 @@ config ARCH_FORCE_MAX_ORDER Don't change if unsure. config UNMAP_KERNEL_AT_EL0 - bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT + bool "Unmap kernel when running in userspace (KPTI)" if EXPERT default y help Speculation attacks against some high-performance processors can diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 9a2d3723cd0f..47ecc4cff9d2 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -200,7 +200,7 @@ endif endif vdso-install-y += arch/arm64/kernel/vdso/vdso.so.dbg -vdso-install-$(CONFIG_COMPAT_VDSO) += arch/arm64/kernel/vdso32/vdso.so.dbg:vdso32.so +vdso-install-$(CONFIG_COMPAT_VDSO) += arch/arm64/kernel/vdso32/vdso32.so.dbg include $(srctree)/scripts/Makefile.defconf diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index 1761f5972443..a5a787371117 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -44,7 +44,7 @@ EFI_ZBOOT_BFD_TARGET := elf64-littleaarch64 EFI_ZBOOT_MACH_TYPE := ARM64 EFI_ZBOOT_FORWARD_CFI := $(CONFIG_ARM64_BTI_KERNEL) -EFI_ZBOOT_OBJCOPY_FLAGS = --add-symbol zboot_code_size=0x$(shell \ +EFI_ZBOOT_OBJCOPY_FLAGS = --add-symbol zboot_code_size=0x$$( \ $(NM) vmlinux|grep _kernel_codesize|cut -d' ' -f1) include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh index 7399d706967a..9b7a09808a3d 100755 --- a/arch/arm64/boot/install.sh +++ b/arch/arm64/boot/install.sh @@ -17,7 +17,8 @@ # $3 - kernel map file # $4 - default install path (blank if root directory) -if [ "$(basename $2)" = "Image.gz" ]; then +if [ "$(basename $2)" = "Image.gz" ] || [ "$(basename $2)" = "vmlinuz.efi" ] +then # Compressed install echo "Installing compressed kernel" base=vmlinuz diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 376a980f2bad..7b1975bf4b90 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -12,7 +12,7 @@ #ifndef __ASM_ASSEMBLER_H #define __ASM_ASSEMBLER_H -#include <asm-generic/export.h> +#include <linux/export.h> #include <asm/alternative.h> #include <asm/asm-bug.h> diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index ceb368d33bf4..06a4670bdb0b 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -58,7 +58,6 @@ static inline unsigned int arch_slab_minalign(void) #define CTR_L1IP(ctr) SYS_FIELD_GET(CTR_EL0, L1Ip, ctr) #define ICACHEF_ALIASING 0 -#define ICACHEF_VPIPT 1 extern unsigned long __icache_flags; /* @@ -70,11 +69,6 @@ static inline int icache_is_aliasing(void) return test_bit(ICACHEF_ALIASING, &__icache_flags); } -static __always_inline int icache_is_vpipt(void) -{ - return test_bit(ICACHEF_VPIPT, &__icache_flags); -} - static inline u32 cache_type_cwg(void) { return SYS_FIELD_GET(CTR_EL0, CWG, read_cpuid_cachetype()); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index f6d416fe49b0..21c824edf8ce 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -617,6 +617,7 @@ static inline bool id_aa64pfr1_mte(u64 pfr1) return val >= ID_AA64PFR1_EL1_MTE_MTE2; } +void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); @@ -819,6 +820,11 @@ static inline bool system_supports_tlb_range(void) return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); } +static inline bool system_supports_lpa2(void) +{ + return cpus_have_final_cap(ARM64_HAS_LPA2); +} + int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index cdf6a35e3994..cda81d009c9b 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -242,14 +242,6 @@ | (\nx << 5) .endm -/* - * Zero the entire ZA array - * ZERO ZA - */ -.macro zero_za - .inst 0xc00800ff -.endm - .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 85d26143faa5..83ddb14b95a5 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -37,27 +37,12 @@ /* - * If KASLR is enabled, then an offset K is added to the kernel address - * space. The bottom 21 bits of this offset are zero to guarantee 2MB - * alignment for PA and VA. - * - * For each pagetable level of the swapper, we know that the shift will - * be larger than 21 (for the 4KB granule case we use section maps thus - * the smallest shift is actually 30) thus there is the possibility that - * KASLR can increase the number of pagetable entries by 1, so we make - * room for this extra entry. - * - * Note KASLR cannot increase the number of required entries for a level - * by more than one because it increments both the virtual start and end - * addresses equally (the extra entry comes from the case where the end - * address is just pushed over a boundary and the start address isn't). + * A relocatable kernel may execute from an address that differs from the one at + * which it was linked. In the worst case, its runtime placement may intersect + * with two adjacent PGDIR entries, which means that an additional page table + * may be needed at each subordinate level. */ - -#ifdef CONFIG_RANDOMIZE_BASE -#define EARLY_KASLR (1) -#else -#define EARLY_KASLR (0) -#endif +#define EXTRA_PAGE __is_defined(CONFIG_RELOCATABLE) #define SPAN_NR_ENTRIES(vstart, vend, shift) \ ((((vend) - 1) >> (shift)) - ((vstart) >> (shift)) + 1) @@ -83,7 +68,7 @@ + EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \ + EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \ + EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */ -#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EARLY_KASLR)) +#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE)) /* the initial ID map may need two extra pages if it needs to be extended */ #if VA_BITS < 48 diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 49e0d4b36bd0..e3e793d0ec30 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -244,13 +244,6 @@ static inline size_t __invalidate_icache_max_range(void) static inline void __invalidate_icache_guest_page(void *va, size_t size) { /* - * VPIPT I-cache maintenance must be done from EL2. See comment in the - * nVHE flavor of __kvm_tlb_flush_vmid_ipa(). - */ - if (icache_is_vpipt() && read_sysreg(CurrentEL) != CurrentEL_EL2) - return; - - /* * Blow the whole I-cache if it is aliasing (i.e. VIPT) or the * invalidation range exceeds our arbitrary limit on invadations by * cache line. diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index d3e354bb8351..10068500d601 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -25,6 +25,8 @@ #define KVM_PGTABLE_MIN_BLOCK_LEVEL 2U #endif +#define kvm_lpa2_is_enabled() false + static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index fde4186cc387..56d1e6f14861 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -182,6 +182,7 @@ #include <linux/types.h> #include <asm/boot.h> #include <asm/bug.h> +#include <asm/sections.h> #if VA_BITS > 48 extern u64 vabits_actual; @@ -193,15 +194,12 @@ extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) -/* the virtual base of the kernel image */ -extern u64 kimage_vaddr; - /* the offset between the kernel virtual and physical mappings */ extern u64 kimage_voffset; static inline unsigned long kaslr_offset(void) { - return kimage_vaddr - KIMAGE_VADDR; + return (u64)&_text - KIMAGE_VADDR; } #ifdef CONFIG_RANDOMIZE_BASE @@ -407,6 +405,5 @@ void dump_mem_limit(void); #define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8) #endif -#include <asm-generic/memory_model.h> #endif /* __ASM_MEMORY_H */ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index e9624f6326dd..483dbfa39c4c 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -71,6 +71,8 @@ extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) +#define lpa2_is_enabled() false + /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index e5bc54522e71..5b0a04810b23 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -167,6 +167,9 @@ struct thread_struct { unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ + + struct user_fpsimd_state kernel_fpsimd_state; + unsigned int kernel_fpsimd_cpu; #ifdef CONFIG_ARM64_PTR_AUTH struct ptrauth_keys_user keys_user; #ifdef CONFIG_ARM64_PTR_AUTH_KERNEL diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h index 6a75d7ecdcaa..8e86c9e70e48 100644 --- a/arch/arm64/include/asm/simd.h +++ b/arch/arm64/include/asm/simd.h @@ -12,8 +12,6 @@ #include <linux/preempt.h> #include <linux/types.h> -DECLARE_PER_CPU(bool, fpsimd_context_busy); - #ifdef CONFIG_KERNEL_MODE_NEON /* @@ -28,17 +26,10 @@ static __must_check inline bool may_use_simd(void) /* * We must make sure that the SVE has been initialized properly * before using the SIMD in kernel. - * fpsimd_context_busy is only set while preemption is disabled, - * and is clear whenever preemption is enabled. Since - * this_cpu_read() is atomic w.r.t. preemption, fpsimd_context_busy - * cannot change under our feet -- if it's set we cannot be - * migrated, and if it's clear we cannot be migrated to a CPU - * where it is set. */ return !WARN_ON(!system_capabilities_finalized()) && system_supports_fpsimd() && - !in_hardirq() && !irqs_disabled() && !in_nmi() && - !this_cpu_read(fpsimd_context_busy); + !in_hardirq() && !irqs_disabled() && !in_nmi(); } #else /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h index 508f734de46e..f63dc654e545 100644 --- a/arch/arm64/include/asm/stacktrace/common.h +++ b/arch/arm64/include/asm/stacktrace/common.h @@ -9,7 +9,6 @@ #ifndef __ASM_STACKTRACE_COMMON_H #define __ASM_STACKTRACE_COMMON_H -#include <linux/kprobes.h> #include <linux/types.h> struct stack_info { @@ -23,12 +22,6 @@ struct stack_info { * @fp: The fp value in the frame record (or the real fp) * @pc: The lr value in the frame record (or the real lr) * - * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance - * associated with the most recently encountered replacement lr - * value. - * - * @task: The task being unwound. - * * @stack: The stack currently being unwound. * @stacks: An array of stacks which can be unwound. * @nr_stacks: The number of stacks in @stacks. @@ -36,10 +29,6 @@ struct stack_info { struct unwind_state { unsigned long fp; unsigned long pc; -#ifdef CONFIG_KRETPROBES - struct llist_node *kr_cur; -#endif - struct task_struct *task; struct stack_info stack; struct stack_info *stacks; @@ -66,14 +55,8 @@ static inline bool stackinfo_on_stack(const struct stack_info *info, return true; } -static inline void unwind_init_common(struct unwind_state *state, - struct task_struct *task) +static inline void unwind_init_common(struct unwind_state *state) { - state->task = task; -#ifdef CONFIG_KRETPROBES - state->kr_cur = NULL; -#endif - state->stack = stackinfo_get_unknown(); } diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h index 25ab83a315a7..44759281d0d4 100644 --- a/arch/arm64/include/asm/stacktrace/nvhe.h +++ b/arch/arm64/include/asm/stacktrace/nvhe.h @@ -31,7 +31,7 @@ static inline void kvm_nvhe_unwind_init(struct unwind_state *state, unsigned long fp, unsigned long pc) { - unwind_init_common(state, NULL); + unwind_init_common(state); state->fp = fp; state->pc = pc; diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b320fb0de56b..c3b19b376c86 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -878,10 +878,12 @@ /* id_aa64mmfr0 */ #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_EL1_TGRAN4_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN 0x0 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_EL1_TGRAN16_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX 0xf #define ARM64_MIN_PARANGE_BITS 32 @@ -889,6 +891,7 @@ #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT 0x0 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE 0x1 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN 0x2 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2 0x3 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX 0x7 #ifdef CONFIG_ARM64_PA_BITS_52 @@ -899,11 +902,13 @@ #if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN16_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 553d1bc559c6..e72a3bf9e563 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -80,6 +80,7 @@ void arch_setup_new_exec(void); #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ #define TIF_SME 27 /* SME in use */ #define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ +#define TIF_KERNEL_FPSTATE 29 /* Task is in a kernel mode FPSIMD section */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 846c563689a8..0150deb332af 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -22,15 +22,15 @@ 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. + * get the tlbi levels in arm64. Default value is TLBI_TTL_UNKNOWN if more than + * one of cleared_* is set or neither is set - this elides the level hinting to + * the hardware. */ static inline int tlb_get_level(struct mmu_gather *tlb) { /* The TTL field is only valid for the leaf entry. */ if (tlb->freed_tables) - return 0; + return TLBI_TTL_UNKNOWN; if (tlb->cleared_ptes && !(tlb->cleared_pmds || tlb->cleared_puds || @@ -47,7 +47,12 @@ static inline int tlb_get_level(struct mmu_gather *tlb) tlb->cleared_p4ds)) return 1; - return 0; + if (tlb->cleared_p4ds && !(tlb->cleared_ptes || + tlb->cleared_pmds || + tlb->cleared_puds)) + return 0; + + return TLBI_TTL_UNKNOWN; } static inline void tlb_flush(struct mmu_gather *tlb) diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index bb2c2833a987..1deb5d789c2e 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -94,19 +94,22 @@ static inline unsigned long get_trans_granule(void) * 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. + * cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform + * a non-hinted invalidation. Any provided level outside the hint range + * will also cause fall-back to 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_TTL_UNKNOWN INT_MAX + #define __tlbi_level(op, addr, level) do { \ u64 arg = addr; \ \ if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) && \ - level) { \ + level >= 0 && level <= 3) { \ u64 ttl = level & 3; \ ttl |= get_trans_granule() << 2; \ arg &= ~TLBI_TTL_MASK; \ @@ -122,28 +125,34 @@ static inline unsigned long get_trans_granule(void) } while (0) /* - * This macro creates a properly formatted VA operand for the TLB RANGE. - * The value bit assignments are: + * 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) + * The address range is determined by below formula: [BADDR, BADDR + (NUM + 1) * + * 2^(5*SCALE + 1) * PAGESIZE) + * + * Note that the first argument, baddr, is pre-shifted; If LPA2 is in use, BADDR + * holds addr[52:16]. Else BADDR holds page number. See for example ARM DDI + * 0487J.a section C5.5.60 "TLBI VAE1IS, TLBI VAE1ISNXS, TLB Invalidate by VA, + * EL1, Inner Shareable". * */ -#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; \ +#define __TLBI_VADDR_RANGE(baddr, asid, scale, num, ttl) \ + ({ \ + unsigned long __ta = (baddr); \ + unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0; \ + __ta &= GENMASK_ULL(36, 0); \ + __ta |= __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. */ @@ -216,12 +225,16 @@ static inline unsigned long get_trans_granule(void) * CPUs, ensuring that any walk-cache entries associated with the * translation are also invalidated. * - * __flush_tlb_range(vma, start, end, stride, last_level) + * __flush_tlb_range(vma, start, end, stride, last_level, tlb_level) * Invalidate the virtual-address range '[start, end)' on all * CPUs for the user address space corresponding to 'vma->mm'. * The invalidation operations are issued at a granularity * determined by 'stride' and only affect any walk-cache entries - * if 'last_level' is equal to false. + * if 'last_level' is equal to false. tlb_level is 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, the value TLBI_TTL_UNKNOWN will + * perform a non-hinted invalidation. * * * Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented @@ -345,34 +358,44 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * @tlb_level: Translation Table level hint, if known * @tlbi_user: If 'true', call an additional __tlbi_user() * (typically for user ASIDs). 'flase' for IPA instructions + * @lpa2: If 'true', the lpa2 scheme is used as set out below * * When the CPU does not support TLB range operations, flush the TLB * entries one by one at the granularity of 'stride'. If the TLB * range ops are supported, then: * - * 1. If 'pages' is odd, flush the first page through non-range - * operations; + * 1. If FEAT_LPA2 is in use, the start address of a range operation must be + * 64KB aligned, so flush pages one by one until the alignment is reached + * using the non-range operations. This step is skipped if LPA2 is not in + * use. + * + * 2. The minimum range granularity is decided by 'scale', so multiple range + * TLBI operations may be required. Start from scale = 3, flush the largest + * possible number of pages ((num+1)*2^(5*scale+1)) that fit into the + * requested range, then decrement scale and continue until one or zero pages + * are left. We must start from highest scale to ensure 64KB start alignment + * is maintained in the LPA2 case. * - * 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. + * 3. If there is 1 page remaining, flush it through non-range operations. Range + * operations can only span an even number of pages. We save this for last to + * ensure 64KB start alignment is maintained for the LPA2 case. * * 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. */ #define __flush_tlb_range_op(op, start, pages, stride, \ - asid, tlb_level, tlbi_user) \ + asid, tlb_level, tlbi_user, lpa2) \ do { \ int num = 0; \ - int scale = 0; \ + int scale = 3; \ + int shift = lpa2 ? 16 : PAGE_SHIFT; \ unsigned long addr; \ \ while (pages > 0) { \ if (!system_supports_tlb_range() || \ - pages % 2 == 1) { \ + pages == 1 || \ + (lpa2 && start != ALIGN(start, SZ_64K))) { \ addr = __TLBI_VADDR(start, asid); \ __tlbi_level(op, addr, tlb_level); \ if (tlbi_user) \ @@ -384,20 +407,20 @@ do { \ \ num = __TLBI_RANGE_NUM(pages, scale); \ if (num >= 0) { \ - addr = __TLBI_VADDR_RANGE(start, asid, scale, \ - num, tlb_level); \ + addr = __TLBI_VADDR_RANGE(start >> shift, asid, \ + scale, num, tlb_level); \ __tlbi(r##op, addr); \ if (tlbi_user) \ __tlbi_user(r##op, addr); \ start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \ pages -= __TLBI_RANGE_PAGES(num, scale); \ } \ - scale++; \ + scale--; \ } \ } while (0) #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \ - __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false) + __flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled()); static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -427,9 +450,11 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, asid = ASID(vma->vm_mm); if (last_level) - __flush_tlb_range_op(vale1is, start, pages, stride, asid, tlb_level, true); + __flush_tlb_range_op(vale1is, start, pages, stride, asid, + tlb_level, true, lpa2_is_enabled()); else - __flush_tlb_range_op(vae1is, start, pages, stride, asid, tlb_level, true); + __flush_tlb_range_op(vae1is, start, pages, stride, asid, + tlb_level, true, lpa2_is_enabled()); dsb(ish); mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); @@ -441,9 +466,10 @@ 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. + * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough + * information here. */ - __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0); + __flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN); } static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 646591c67e7a..73b10e64b9df 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1081,25 +1081,6 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); - - /* - * Initialize the indirect array of CPU capabilities pointers before we - * handle the boot CPU below. - */ - init_cpucap_indirect_list(); - - /* - * Detect broken pseudo-NMI. Must be called _before_ the call to - * setup_boot_cpu_capabilities() since it interacts with - * can_use_gic_priorities(). - */ - detect_system_supports_pseudo_nmi(); - - /* - * Detect and enable early CPU capabilities based on the boot CPU, - * after we have initialised the CPU feature infrastructure. - */ - setup_boot_cpu_capabilities(); } static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new) @@ -1584,16 +1565,6 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, return has_sre; } -static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int __unused) -{ - u32 midr = read_cpuid_id(); - - /* Cavium ThunderX pass 1.x and 2.x */ - return midr_is_cpu_model_range(midr, MIDR_THUNDERX, - MIDR_CPU_VAR_REV(0, 0), - MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK)); -} - static bool has_cache_idc(const struct arm64_cpu_capabilities *entry, int scope) { @@ -1768,6 +1739,39 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, return !meltdown_safe; } +#if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2) +static bool has_lpa2_at_stage1(u64 mmfr0) +{ + unsigned int tgran; + + tgran = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + return tgran == ID_AA64MMFR0_EL1_TGRAN_LPA2; +} + +static bool has_lpa2_at_stage2(u64 mmfr0) +{ + unsigned int tgran; + + tgran = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_TGRAN_2_SHIFT); + return tgran == ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2; +} + +static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 mmfr0; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + return has_lpa2_at_stage1(mmfr0) && has_lpa2_at_stage2(mmfr0); +} +#else +static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope) +{ + return false; +} +#endif + #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 #define KPTI_NG_TEMP_VA (-(1UL << PMD_SHIFT)) @@ -2322,12 +2326,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }, #endif /* CONFIG_ARM64_LSE_ATOMICS */ { - .desc = "Software prefetching using PRFM", - .capability = ARM64_HAS_NO_HW_PREFETCH, - .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, - .matches = has_no_hw_prefetch, - }, - { .desc = "Virtualization Host Extensions", .capability = ARM64_HAS_VIRT_HOST_EXTN, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, @@ -2731,6 +2729,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP) }, + { + .desc = "52-bit Virtual Addressing for KVM (LPA2)", + .capability = ARM64_HAS_LPA2, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_lpa2, + }, {}, }; @@ -3271,14 +3275,6 @@ void check_local_cpu_capabilities(void) verify_local_cpu_capabilities(); } -static void __init setup_boot_cpu_capabilities(void) -{ - /* Detect capabilities with either SCOPE_BOOT_CPU or SCOPE_LOCAL_CPU */ - update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU); - /* Enable the SCOPE_BOOT_CPU capabilities alone right away */ - enable_cpu_capabilities(SCOPE_BOOT_CPU); -} - bool this_cpu_has_cap(unsigned int n) { if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { @@ -3334,37 +3330,52 @@ unsigned long cpu_get_elf_hwcap2(void) return elf_hwcap[1]; } -void __init setup_system_features(void) +static void __init setup_boot_cpu_capabilities(void) { - int i; /* - * The system-wide safe feature feature register values have been - * finalized. Finalize and log the available system capabilities. + * The boot CPU's feature register values have been recorded. Detect + * boot cpucaps and local cpucaps for the boot CPU, then enable and + * patch alternatives for the available boot cpucaps. */ - update_cpu_capabilities(SCOPE_SYSTEM); - if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && - !cpus_have_cap(ARM64_HAS_PAN)) - pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); + update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU); + enable_cpu_capabilities(SCOPE_BOOT_CPU); + apply_boot_alternatives(); +} +void __init setup_boot_cpu_features(void) +{ /* - * Enable all the available capabilities which have not been enabled - * already. + * Initialize the indirect array of CPU capabilities pointers before we + * handle the boot CPU. */ - enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU); + init_cpucap_indirect_list(); - kpti_install_ng_mappings(); + /* + * Detect broken pseudo-NMI. Must be called _before_ the call to + * setup_boot_cpu_capabilities() since it interacts with + * can_use_gic_priorities(). + */ + detect_system_supports_pseudo_nmi(); - sve_setup(); - sme_setup(); + setup_boot_cpu_capabilities(); +} +static void __init setup_system_capabilities(void) +{ /* - * Check for sane CTR_EL0.CWG value. + * The system-wide safe feature register values have been finalized. + * Detect, enable, and patch alternatives for the available system + * cpucaps. */ - if (!cache_type_cwg()) - pr_warn("No Cache Writeback Granule information, assuming %d\n", - ARCH_DMA_MINALIGN); + update_cpu_capabilities(SCOPE_SYSTEM); + enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU); + apply_alternatives_all(); - for (i = 0; i < ARM64_NCAPS; i++) { + /* + * Log any cpucaps with a cpumask as these aren't logged by + * update_cpu_capabilities(). + */ + for (int i = 0; i < ARM64_NCAPS; i++) { const struct arm64_cpu_capabilities *caps = cpucap_ptrs[i]; if (caps && caps->cpus && caps->desc && @@ -3372,6 +3383,29 @@ void __init setup_system_features(void) pr_info("detected: %s on CPU%*pbl\n", caps->desc, cpumask_pr_args(caps->cpus)); } + + /* + * TTBR0 PAN doesn't have its own cpucap, so log it manually. + */ + if (system_uses_ttbr0_pan()) + pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); +} + +void __init setup_system_features(void) +{ + setup_system_capabilities(); + + kpti_install_ng_mappings(); + + sve_setup(); + sme_setup(); + + /* + * Check for sane CTR_EL0.CWG value. + */ + if (!cache_type_cwg()) + pr_warn("No Cache Writeback Granule information, assuming %d\n", + ARCH_DMA_MINALIGN); } void __init setup_user_features(void) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index a257da7b56fe..47043c0d95ec 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -36,8 +36,6 @@ static struct cpuinfo_arm64 boot_cpu_data; static inline const char *icache_policy_str(int l1ip) { switch (l1ip) { - case CTR_EL0_L1Ip_VPIPT: - return "VPIPT"; case CTR_EL0_L1Ip_VIPT: return "VIPT"; case CTR_EL0_L1Ip_PIPT: @@ -388,9 +386,6 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) switch (l1ip) { case CTR_EL0_L1Ip_PIPT: break; - case CTR_EL0_L1Ip_VPIPT: - set_bit(ICACHEF_VPIPT, &__icache_flags); - break; case CTR_EL0_L1Ip_VIPT: default: /* Assume aliasing */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1559c706d32d..505f389be3e0 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -85,13 +85,13 @@ * softirq kicks in. Upon vcpu_put(), KVM will save the vcpu FP state and * flag the register state as invalid. * - * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may - * save the task's FPSIMD context back to task_struct from softirq context. - * To prevent this from racing with the manipulation of the task's FPSIMD state - * from task context and thereby corrupting the state, it is necessary to - * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE - * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to - * run but prevent them to use FPSIMD. + * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may be + * called from softirq context, which will save the task's FPSIMD context back + * to task_struct. To prevent this from racing with the manipulation of the + * task's FPSIMD state from task context and thereby corrupting the state, it + * is necessary to protect any manipulation of a task's fpsimd_state or + * TIF_FOREIGN_FPSTATE flag with get_cpu_fpsimd_context(), which will suspend + * softirq servicing entirely until put_cpu_fpsimd_context() is called. * * For a certain task, the sequence may look something like this: * - the task gets scheduled in; if both the task's fpsimd_cpu field @@ -209,27 +209,14 @@ static inline void sme_free(struct task_struct *t) { } #endif -DEFINE_PER_CPU(bool, fpsimd_context_busy); -EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); - static void fpsimd_bind_task_to_cpu(void); -static void __get_cpu_fpsimd_context(void) -{ - bool busy = __this_cpu_xchg(fpsimd_context_busy, true); - - WARN_ON(busy); -} - /* * Claim ownership of the CPU FPSIMD context for use by the calling context. * * The caller may freely manipulate the FPSIMD context metadata until * put_cpu_fpsimd_context() is called. * - * The double-underscore version must only be called if you know the task - * can't be preempted. - * * On RT kernels local_bh_disable() is not sufficient because it only * serializes soft interrupt related sections via a local lock, but stays * preemptible. Disabling preemption is the right choice here as bottom @@ -242,14 +229,6 @@ static void get_cpu_fpsimd_context(void) local_bh_disable(); else preempt_disable(); - __get_cpu_fpsimd_context(); -} - -static void __put_cpu_fpsimd_context(void) -{ - bool busy = __this_cpu_xchg(fpsimd_context_busy, false); - - WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */ } /* @@ -261,18 +240,12 @@ static void __put_cpu_fpsimd_context(void) */ static void put_cpu_fpsimd_context(void) { - __put_cpu_fpsimd_context(); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_bh_enable(); else preempt_enable(); } -static bool have_cpu_fpsimd_context(void) -{ - return !preemptible() && __this_cpu_read(fpsimd_context_busy); -} - unsigned int task_get_vl(const struct task_struct *task, enum vec_type type) { return task->thread.vl[type]; @@ -383,7 +356,8 @@ static void task_fpsimd_load(void) bool restore_ffr; WARN_ON(!system_supports_fpsimd()); - WARN_ON(!have_cpu_fpsimd_context()); + WARN_ON(preemptible()); + WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { @@ -406,7 +380,7 @@ static void task_fpsimd_load(void) default: /* * This indicates either a bug in - * fpsimd_save() or memory corruption, we + * fpsimd_save_user_state() or memory corruption, we * should always record an explicit format * when we save. We always at least have the * memory allocated for FPSMID registers so @@ -457,7 +431,7 @@ static void task_fpsimd_load(void) * than via current, if we are saving KVM state then it will have * ensured that the type of registers to save is set in last->to_save. */ -static void fpsimd_save(void) +static void fpsimd_save_user_state(void) { struct cpu_fp_state const *last = this_cpu_ptr(&fpsimd_last_state); @@ -467,7 +441,7 @@ static void fpsimd_save(void) unsigned int vl; WARN_ON(!system_supports_fpsimd()); - WARN_ON(!have_cpu_fpsimd_context()); + WARN_ON(preemptible()); if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; @@ -888,7 +862,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, if (task == current) { get_cpu_fpsimd_context(); - fpsimd_save(); + fpsimd_save_user_state(); } fpsimd_flush_task_state(task); @@ -1171,7 +1145,7 @@ void __init sve_setup(void) unsigned long b; int max_bit; - if (!cpus_have_cap(ARM64_SVE)) + if (!system_supports_sve()) return; /* @@ -1301,7 +1275,7 @@ void __init sme_setup(void) struct vl_info *info = &vl_info[ARM64_VEC_SME]; int min_bit, max_bit; - if (!cpus_have_cap(ARM64_SME)) + if (!system_supports_sme()) return; /* @@ -1500,6 +1474,34 @@ void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs) current); } +static void fpsimd_load_kernel_state(struct task_struct *task) +{ + struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); + + /* + * Elide the load if this CPU holds the most recent kernel mode + * FPSIMD context of the current task. + */ + if (last->st == &task->thread.kernel_fpsimd_state && + task->thread.kernel_fpsimd_cpu == smp_processor_id()) + return; + + fpsimd_load_state(&task->thread.kernel_fpsimd_state); +} + +static void fpsimd_save_kernel_state(struct task_struct *task) +{ + struct cpu_fp_state cpu_fp_state = { + .st = &task->thread.kernel_fpsimd_state, + .to_save = FP_STATE_FPSIMD, + }; + + fpsimd_save_state(&task->thread.kernel_fpsimd_state); + fpsimd_bind_state_to_cpu(&cpu_fp_state); + + task->thread.kernel_fpsimd_cpu = smp_processor_id(); +} + void fpsimd_thread_switch(struct task_struct *next) { bool wrong_task, wrong_cpu; @@ -1507,24 +1509,31 @@ void fpsimd_thread_switch(struct task_struct *next) if (!system_supports_fpsimd()) return; - __get_cpu_fpsimd_context(); + WARN_ON_ONCE(!irqs_disabled()); /* Save unsaved fpsimd state, if any: */ - fpsimd_save(); - - /* - * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's - * state. For kernel threads, FPSIMD registers are never loaded - * and wrong_task and wrong_cpu will always be true. - */ - wrong_task = __this_cpu_read(fpsimd_last_state.st) != - &next->thread.uw.fpsimd_state; - wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); + if (test_thread_flag(TIF_KERNEL_FPSTATE)) + fpsimd_save_kernel_state(current); + else + fpsimd_save_user_state(); - update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, - wrong_task || wrong_cpu); + if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { + fpsimd_load_kernel_state(next); + set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); + } else { + /* + * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's + * state. For kernel threads, FPSIMD registers are never + * loaded with user mode FPSIMD state and so wrong_task and + * wrong_cpu will always be true. + */ + wrong_task = __this_cpu_read(fpsimd_last_state.st) != + &next->thread.uw.fpsimd_state; + wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); - __put_cpu_fpsimd_context(); + update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, + wrong_task || wrong_cpu); + } } static void fpsimd_flush_thread_vl(enum vec_type type) @@ -1614,7 +1623,7 @@ void fpsimd_preserve_current_state(void) return; get_cpu_fpsimd_context(); - fpsimd_save(); + fpsimd_save_user_state(); put_cpu_fpsimd_context(); } @@ -1826,13 +1835,15 @@ static void fpsimd_flush_cpu_state(void) */ void fpsimd_save_and_flush_cpu_state(void) { + unsigned long flags; + if (!system_supports_fpsimd()) return; WARN_ON(preemptible()); - __get_cpu_fpsimd_context(); - fpsimd_save(); + local_irq_save(flags); + fpsimd_save_user_state(); fpsimd_flush_cpu_state(); - __put_cpu_fpsimd_context(); + local_irq_restore(flags); } #ifdef CONFIG_KERNEL_MODE_NEON @@ -1864,10 +1875,37 @@ void kernel_neon_begin(void) get_cpu_fpsimd_context(); /* Save unsaved fpsimd state, if any: */ - fpsimd_save(); + if (test_thread_flag(TIF_KERNEL_FPSTATE)) { + BUG_ON(IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()); + fpsimd_save_kernel_state(current); + } else { + fpsimd_save_user_state(); + + /* + * Set the thread flag so that the kernel mode FPSIMD state + * will be context switched along with the rest of the task + * state. + * + * On non-PREEMPT_RT, softirqs may interrupt task level kernel + * mode FPSIMD, but the task will not be preemptible so setting + * TIF_KERNEL_FPSTATE for those would be both wrong (as it + * would mark the task context FPSIMD state as requiring a + * context switch) and unnecessary. + * + * On PREEMPT_RT, softirqs are serviced from a separate thread, + * which is scheduled as usual, and this guarantees that these + * softirqs are not interrupting use of the FPSIMD in kernel + * mode in task context. So in this case, setting the flag here + * is always appropriate. + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) || !in_serving_softirq()) + set_thread_flag(TIF_KERNEL_FPSTATE); + } /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); + + put_cpu_fpsimd_context(); } EXPORT_SYMBOL_GPL(kernel_neon_begin); @@ -1885,7 +1923,16 @@ void kernel_neon_end(void) if (!system_supports_fpsimd()) return; - put_cpu_fpsimd_context(); + /* + * If we are returning from a nested use of kernel mode FPSIMD, restore + * the task context kernel mode FPSIMD state. This can only happen when + * running in softirq context on non-PREEMPT_RT. + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && in_serving_softirq() && + test_thread_flag(TIF_KERNEL_FPSTATE)) + fpsimd_load_kernel_state(current); + else + clear_thread_flag(TIF_KERNEL_FPSTATE); } EXPORT_SYMBOL_GPL(kernel_neon_end); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7b236994f0e1..cab7f91949d8 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -482,7 +482,7 @@ SYM_FUNC_START_LOCAL(__primary_switched) str_l x21, __fdt_pointer, x5 // Save FDT pointer - ldr_l x4, kimage_vaddr // Save the offset between + adrp x4, _text // Save the offset between sub x4, x4, x0 // the kernel virtual and str_l x4, kimage_voffset, x5 // physical mappings diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 3addc09f8746..e30fd9e32ef3 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -21,14 +21,25 @@ static u64 __boot_status __initdata; +// temporary __prel64 related definitions +// to be removed when this code is moved under pi/ + +#define __prel64_initconst __initconst + +#define PREL64(type, name) union { type *name; } + +#define prel64_pointer(__d) (__d) + +typedef bool filter_t(u64 val); + struct ftr_set_desc { char name[FTR_DESC_NAME_LEN]; - struct arm64_ftr_override *override; + PREL64(struct arm64_ftr_override, override); struct { char name[FTR_DESC_FIELD_LEN]; u8 shift; u8 width; - bool (*filter)(u64 val); + PREL64(filter_t, filter); } fields[]; }; @@ -46,7 +57,7 @@ static bool __init mmfr1_vh_filter(u64 val) val == 0); } -static const struct ftr_set_desc mmfr1 __initconst = { +static const struct ftr_set_desc mmfr1 __prel64_initconst = { .name = "id_aa64mmfr1", .override = &id_aa64mmfr1_override, .fields = { @@ -70,7 +81,7 @@ static bool __init pfr0_sve_filter(u64 val) return true; } -static const struct ftr_set_desc pfr0 __initconst = { +static const struct ftr_set_desc pfr0 __prel64_initconst = { .name = "id_aa64pfr0", .override = &id_aa64pfr0_override, .fields = { @@ -94,7 +105,7 @@ static bool __init pfr1_sme_filter(u64 val) return true; } -static const struct ftr_set_desc pfr1 __initconst = { +static const struct ftr_set_desc pfr1 __prel64_initconst = { .name = "id_aa64pfr1", .override = &id_aa64pfr1_override, .fields = { @@ -105,7 +116,7 @@ static const struct ftr_set_desc pfr1 __initconst = { }, }; -static const struct ftr_set_desc isar1 __initconst = { +static const struct ftr_set_desc isar1 __prel64_initconst = { .name = "id_aa64isar1", .override = &id_aa64isar1_override, .fields = { @@ -117,7 +128,7 @@ static const struct ftr_set_desc isar1 __initconst = { }, }; -static const struct ftr_set_desc isar2 __initconst = { +static const struct ftr_set_desc isar2 __prel64_initconst = { .name = "id_aa64isar2", .override = &id_aa64isar2_override, .fields = { @@ -128,7 +139,7 @@ static const struct ftr_set_desc isar2 __initconst = { }, }; -static const struct ftr_set_desc smfr0 __initconst = { +static const struct ftr_set_desc smfr0 __prel64_initconst = { .name = "id_aa64smfr0", .override = &id_aa64smfr0_override, .fields = { @@ -149,7 +160,7 @@ static bool __init hvhe_filter(u64 val) ID_AA64MMFR1_EL1_VH_SHIFT)); } -static const struct ftr_set_desc sw_features __initconst = { +static const struct ftr_set_desc sw_features __prel64_initconst = { .name = "arm64_sw", .override = &arm64_sw_feature_override, .fields = { @@ -159,22 +170,23 @@ static const struct ftr_set_desc sw_features __initconst = { }, }; -static const struct ftr_set_desc * const regs[] __initconst = { - &mmfr1, - &pfr0, - &pfr1, - &isar1, - &isar2, - &smfr0, - &sw_features, +static const +PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { + { &mmfr1 }, + { &pfr0 }, + { &pfr1 }, + { &isar1 }, + { &isar2 }, + { &smfr0 }, + { &sw_features }, }; static const struct { char alias[FTR_ALIAS_NAME_LEN]; char feature[FTR_ALIAS_OPTION_LEN]; } aliases[] __initconst = { - { "kvm-arm.mode=nvhe", "id_aa64mmfr1.vh=0" }, - { "kvm-arm.mode=protected", "id_aa64mmfr1.vh=0" }, + { "kvm_arm.mode=nvhe", "id_aa64mmfr1.vh=0" }, + { "kvm_arm.mode=protected", "id_aa64mmfr1.vh=0" }, { "arm64.nosve", "id_aa64pfr0.sve=0" }, { "arm64.nosme", "id_aa64pfr1.sme=0" }, { "arm64.nobti", "id_aa64pfr1.bt=0" }, @@ -187,45 +199,61 @@ static const struct { { "nokaslr", "arm64_sw.nokaslr=1" }, }; -static int __init parse_nokaslr(char *unused) +static int __init parse_hexdigit(const char *p, u64 *v) { - /* nokaslr param handling is done by early cpufeature code */ + // skip "0x" if it comes next + if (p[0] == '0' && tolower(p[1]) == 'x') + p += 2; + + // check whether the RHS is a single hex digit + if (!isxdigit(p[0]) || (p[1] && !isspace(p[1]))) + return -EINVAL; + + *v = tolower(*p) - (isdigit(*p) ? '0' : 'a' - 10); return 0; } -early_param("nokaslr", parse_nokaslr); -static int __init find_field(const char *cmdline, +static int __init find_field(const char *cmdline, char *opt, int len, const struct ftr_set_desc *reg, int f, u64 *v) { - char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2]; - int len; + int flen = strlen(reg->fields[f].name); - len = snprintf(opt, ARRAY_SIZE(opt), "%s.%s=", - reg->name, reg->fields[f].name); + // append '<fieldname>=' to obtain '<name>.<fieldname>=' + memcpy(opt + len, reg->fields[f].name, flen); + len += flen; + opt[len++] = '='; - if (!parameqn(cmdline, opt, len)) + if (memcmp(cmdline, opt, len)) return -1; - return kstrtou64(cmdline + len, 0, v); + return parse_hexdigit(cmdline + len, v); } static void __init match_options(const char *cmdline) { + char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2]; int i; for (i = 0; i < ARRAY_SIZE(regs); i++) { + const struct ftr_set_desc *reg = prel64_pointer(regs[i].reg); + struct arm64_ftr_override *override; + int len = strlen(reg->name); int f; - if (!regs[i]->override) - continue; + override = prel64_pointer(reg->override); - for (f = 0; strlen(regs[i]->fields[f].name); f++) { - u64 shift = regs[i]->fields[f].shift; - u64 width = regs[i]->fields[f].width ?: 4; + // set opt[] to '<name>.' + memcpy(opt, reg->name, len); + opt[len++] = '.'; + + for (f = 0; reg->fields[f].name[0] != '\0'; f++) { + u64 shift = reg->fields[f].shift; + u64 width = reg->fields[f].width ?: 4; u64 mask = GENMASK_ULL(shift + width - 1, shift); + bool (*filter)(u64 val); u64 v; - if (find_field(cmdline, regs[i], f, &v)) + if (find_field(cmdline, opt, len, reg, f, &v)) continue; /* @@ -233,16 +261,16 @@ static void __init match_options(const char *cmdline) * it by setting the value to the all-ones while * clearing the mask... Yes, this is fragile. */ - if (regs[i]->fields[f].filter && - !regs[i]->fields[f].filter(v)) { - regs[i]->override->val |= mask; - regs[i]->override->mask &= ~mask; + filter = prel64_pointer(reg->fields[f].filter); + if (filter && !filter(v)) { + override->val |= mask; + override->mask &= ~mask; continue; } - regs[i]->override->val &= ~mask; - regs[i]->override->val |= (v << shift) & mask; - regs[i]->override->mask |= mask; + override->val &= ~mask; + override->val |= (v << shift) & mask; + override->mask |= mask; return; } @@ -258,23 +286,29 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) cmdline = skip_spaces(cmdline); - for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++); - if (!len) + /* terminate on "--" appearing on the command line by itself */ + if (cmdline[0] == '-' && cmdline[1] == '-' && isspace(cmdline[2])) return; - len = min(len, ARRAY_SIZE(buf) - 1); - memcpy(buf, cmdline, len); - buf[len] = '\0'; - - if (strcmp(buf, "--") == 0) + for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++) { + if (len >= sizeof(buf) - 1) + break; + if (cmdline[len] == '-') + buf[len] = '_'; + else + buf[len] = cmdline[len]; + } + if (!len) return; + buf[len] = 0; + cmdline += len; match_options(buf); for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++) - if (parameq(buf, aliases[i].alias)) + if (!memcmp(buf, aliases[i].alias, len + 1)) __parse_cmdline(aliases[i].feature, false); } while (1); } @@ -316,13 +350,16 @@ void init_feature_override(u64 boot_status); asmlinkage void __init init_feature_override(u64 boot_status) { + struct arm64_ftr_override *override; + const struct ftr_set_desc *reg; int i; for (i = 0; i < ARRAY_SIZE(regs); i++) { - if (regs[i]->override) { - regs[i]->override->val = 0; - regs[i]->override->mask = 0; - } + reg = prel64_pointer(regs[i].reg); + override = prel64_pointer(reg->override); + + override->val = 0; + override->mask = 0; } __boot_status = boot_status; @@ -330,9 +367,9 @@ asmlinkage void __init init_feature_override(u64 boot_status) parse_cmdline(); for (i = 0; i < ARRAY_SIZE(regs); i++) { - if (regs[i]->override) - dcache_clean_inval_poc((unsigned long)regs[i]->override, - (unsigned long)regs[i]->override + - sizeof(*regs[i]->override)); + reg = prel64_pointer(regs[i].reg); + override = prel64_pointer(reg->override); + dcache_clean_inval_poc((unsigned long)override, + (unsigned long)(override + 1)); } } diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 6ad5c6ef5329..85087e2df564 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> +#include <asm/numa.h> #include <asm/softirq_stack.h> #include <asm/stacktrace.h> #include <asm/vmap_stack.h> @@ -47,17 +48,17 @@ static void init_irq_scs(void) for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = - scs_alloc(cpu_to_node(cpu)); + scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK -static void init_irq_stacks(void) +static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { - p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 94a269cd1f07..12c7f3c8ba76 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -36,3 +36,10 @@ void __init kaslr_init(void) pr_info("KASLR enabled\n"); __kaslr_is_enabled = true; } + +static int __init parse_nokaslr(char *unused) +{ + /* nokaslr param handling is done by early cpufeature code */ + return 0; +} +early_param("nokaslr", parse_nokaslr); diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 4c0ea3cd4ea4..c844a0546d7f 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -3,6 +3,7 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \ + $(DISABLE_LATENT_ENTROPY_PLUGIN) \ $(call cc-option,-mbranch-protection=none) \ -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ -include $(srctree)/include/linux/hidden.h \ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index defbab84e9e5..4ced34f62dab 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -439,9 +439,8 @@ static void __init hyp_mode_check(void) void __init smp_cpus_done(unsigned int max_cpus) { pr_info("SMP: Total of %d processors activated.\n", num_online_cpus()); - setup_system_features(); hyp_mode_check(); - apply_alternatives_all(); + setup_system_features(); setup_user_features(); mark_linear_text_alias_ro(); } @@ -454,14 +453,9 @@ void __init smp_prepare_boot_cpu(void) * freed shortly, so we must move over to the runtime per-cpu area. */ set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - cpuinfo_store_boot_cpu(); - /* - * We now know enough about the boot CPU to apply the - * alternatives that cannot wait until interrupt handling - * and/or scheduling is enabled. - */ - apply_boot_alternatives(); + cpuinfo_store_boot_cpu(); + setup_boot_cpu_features(); /* Conditionally switch to GIC PMR for interrupt masking */ if (system_uses_irq_prio_masking()) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 17f66a74c745..7f88028a00c0 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -8,6 +8,7 @@ #include <linux/efi.h> #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> @@ -19,6 +20,31 @@ #include <asm/stacktrace.h> /* + * Kernel unwind state + * + * @common: Common unwind state. + * @task: The task being unwound. + * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance + * associated with the most recently encountered replacement lr + * value. + */ +struct kunwind_state { + struct unwind_state common; + struct task_struct *task; +#ifdef CONFIG_KRETPROBES + struct llist_node *kr_cur; +#endif +}; + +static __always_inline void +kunwind_init(struct kunwind_state *state, + struct task_struct *task) +{ + unwind_init_common(&state->common); + state->task = task; +} + +/* * Start an unwind from a pt_regs. * * The unwind will begin at the PC within the regs. @@ -26,13 +52,13 @@ * The regs must be on a stack currently owned by the calling task. */ static __always_inline void -unwind_init_from_regs(struct unwind_state *state, - struct pt_regs *regs) +kunwind_init_from_regs(struct kunwind_state *state, + struct pt_regs *regs) { - unwind_init_common(state, current); + kunwind_init(state, current); - state->fp = regs->regs[29]; - state->pc = regs->pc; + state->common.fp = regs->regs[29]; + state->common.pc = regs->pc; } /* @@ -44,12 +70,12 @@ unwind_init_from_regs(struct unwind_state *state, * The function which invokes this must be noinline. */ static __always_inline void -unwind_init_from_caller(struct unwind_state *state) +kunwind_init_from_caller(struct kunwind_state *state) { - unwind_init_common(state, current); + kunwind_init(state, current); - state->fp = (unsigned long)__builtin_frame_address(1); - state->pc = (unsigned long)__builtin_return_address(0); + state->common.fp = (unsigned long)__builtin_frame_address(1); + state->common.pc = (unsigned long)__builtin_return_address(0); } /* @@ -63,35 +89,38 @@ unwind_init_from_caller(struct unwind_state *state) * call this for the current task. */ static __always_inline void -unwind_init_from_task(struct unwind_state *state, - struct task_struct *task) +kunwind_init_from_task(struct kunwind_state *state, + struct task_struct *task) { - unwind_init_common(state, task); + kunwind_init(state, task); - state->fp = thread_saved_fp(task); - state->pc = thread_saved_pc(task); + state->common.fp = thread_saved_fp(task); + state->common.pc = thread_saved_pc(task); } static __always_inline int -unwind_recover_return_address(struct unwind_state *state) +kunwind_recover_return_address(struct kunwind_state *state) { #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (state->task->ret_stack && - (state->pc == (unsigned long)return_to_handler)) { + (state->common.pc == (unsigned long)return_to_handler)) { unsigned long orig_pc; - orig_pc = ftrace_graph_ret_addr(state->task, NULL, state->pc, - (void *)state->fp); - if (WARN_ON_ONCE(state->pc == orig_pc)) + orig_pc = ftrace_graph_ret_addr(state->task, NULL, + state->common.pc, + (void *)state->common.fp); + if (WARN_ON_ONCE(state->common.pc == orig_pc)) return -EINVAL; - state->pc = orig_pc; + state->common.pc = orig_pc; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_KRETPROBES - if (is_kretprobe_trampoline(state->pc)) { - state->pc = kretprobe_find_ret_addr(state->task, - (void *)state->fp, - &state->kr_cur); + if (is_kretprobe_trampoline(state->common.pc)) { + unsigned long orig_pc; + orig_pc = kretprobe_find_ret_addr(state->task, + (void *)state->common.fp, + &state->kr_cur); + state->common.pc = orig_pc; } #endif /* CONFIG_KRETPROBES */ @@ -106,38 +135,40 @@ unwind_recover_return_address(struct unwind_state *state) * and the location (but not the fp value) of B. */ static __always_inline int -unwind_next(struct unwind_state *state) +kunwind_next(struct kunwind_state *state) { struct task_struct *tsk = state->task; - unsigned long fp = state->fp; + unsigned long fp = state->common.fp; int err; /* Final frame; nothing to unwind */ if (fp == (unsigned long)task_pt_regs(tsk)->stackframe) return -ENOENT; - err = unwind_next_frame_record(state); + err = unwind_next_frame_record(&state->common); if (err) return err; - state->pc = ptrauth_strip_kernel_insn_pac(state->pc); + state->common.pc = ptrauth_strip_kernel_insn_pac(state->common.pc); - return unwind_recover_return_address(state); + return kunwind_recover_return_address(state); } +typedef bool (*kunwind_consume_fn)(const struct kunwind_state *state, void *cookie); + static __always_inline void -unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry, - void *cookie) +do_kunwind(struct kunwind_state *state, kunwind_consume_fn consume_state, + void *cookie) { - if (unwind_recover_return_address(state)) + if (kunwind_recover_return_address(state)) return; while (1) { int ret; - if (!consume_entry(cookie, state->pc)) + if (!consume_state(state, cookie)) break; - ret = unwind_next(state); + ret = kunwind_next(state); if (ret < 0) break; } @@ -172,9 +203,10 @@ unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry, : stackinfo_get_unknown(); \ }) -noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, - void *cookie, struct task_struct *task, - struct pt_regs *regs) +static __always_inline void +kunwind_stack_walk(kunwind_consume_fn consume_state, + void *cookie, struct task_struct *task, + struct pt_regs *regs) { struct stack_info stacks[] = { stackinfo_get_task(task), @@ -190,22 +222,48 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, STACKINFO_EFI, #endif }; - struct unwind_state state = { - .stacks = stacks, - .nr_stacks = ARRAY_SIZE(stacks), + struct kunwind_state state = { + .common = { + .stacks = stacks, + .nr_stacks = ARRAY_SIZE(stacks), + }, }; if (regs) { if (task != current) return; - unwind_init_from_regs(&state, regs); + kunwind_init_from_regs(&state, regs); } else if (task == current) { - unwind_init_from_caller(&state); + kunwind_init_from_caller(&state); } else { - unwind_init_from_task(&state, task); + kunwind_init_from_task(&state, task); } - unwind(&state, consume_entry, cookie); + do_kunwind(&state, consume_state, cookie); +} + +struct kunwind_consume_entry_data { + stack_trace_consume_fn consume_entry; + void *cookie; +}; + +static bool +arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie) +{ + struct kunwind_consume_entry_data *data = cookie; + return data->consume_entry(data->cookie, state->common.pc); +} + +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task, + struct pt_regs *regs) +{ + struct kunwind_consume_entry_data data = { + .consume_entry = consume_entry, + .cookie = cookie, + }; + + kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs); } static bool dump_backtrace_entry(void *arg, unsigned long where) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 1f911a76c5af..2266fcdff78a 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -118,7 +118,7 @@ endif VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os # Build rules -targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw +targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso32.so.dbg vdso.so.raw c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso)) c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday)) asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso)) @@ -127,15 +127,15 @@ obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) targets += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) -include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE +include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE $(call if_changed,vdsosym) # Strip rule for vdso.so $(obj)/vdso.so: OBJCOPYFLAGS := -S -$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE +$(obj)/vdso.so: $(obj)/vdso32.so.dbg FORCE $(call if_changed,objcopy) -$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE +$(obj)/vdso32.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE $(call if_changed,vdsomunge) # Link rule for the .so file, .lds has to be first diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 9d23a51d7f75..b29f15418c0a 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -12,7 +12,7 @@ #include <nvhe/pkvm.h> #include <nvhe/trap_handler.h> -/* Used by icache_is_vpipt(). */ +/* Used by icache_is_aliasing(). */ unsigned long __icache_flags; /* Used by kvm_get_vttbr(). */ diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 1b265713d6be..a60fb13e2192 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -105,28 +105,6 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, dsb(ish); isb(); - /* - * If the host is running at EL1 and we have a VPIPT I-cache, - * then we must perform I-cache maintenance at EL2 in order for - * it to have an effect on the guest. Since the guest cannot hit - * I-cache lines allocated with a different VMID, we don't need - * to worry about junk out of guest reset (we nuke the I-cache on - * VMID rollover), but we do need to be careful when remapping - * executable pages for the same guest. This can happen when KSM - * takes a CoW fault on an executable page, copies the page into - * a page that was previously mapped in the guest and then needs - * to invalidate the guest view of the I-cache for that page - * from EL1. To solve this, we invalidate the entire I-cache when - * unmapping a page from a guest if we have a VPIPT I-cache but - * the host is running at EL1. As above, we could do better if - * we had the VA. - * - * The moral of this story is: if you have a VPIPT I-cache, then - * you should be running with VHE enabled. - */ - if (icache_is_vpipt()) - icache_inval_all_pou(); - __tlb_switch_to_host(&cxt); } @@ -157,28 +135,6 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu, dsb(nsh); isb(); - /* - * If the host is running at EL1 and we have a VPIPT I-cache, - * then we must perform I-cache maintenance at EL2 in order for - * it to have an effect on the guest. Since the guest cannot hit - * I-cache lines allocated with a different VMID, we don't need - * to worry about junk out of guest reset (we nuke the I-cache on - * VMID rollover), but we do need to be careful when remapping - * executable pages for the same guest. This can happen when KSM - * takes a CoW fault on an executable page, copies the page into - * a page that was previously mapped in the guest and then needs - * to invalidate the guest view of the I-cache for that page - * from EL1. To solve this, we invalidate the entire I-cache when - * unmapping a page from a guest if we have a VPIPT I-cache but - * the host is running at EL1. As above, we could do better if - * we had the VA. - * - * The moral of this story is: if you have a VPIPT I-cache, then - * you should be running with VHE enabled. - */ - if (icache_is_vpipt()) - icache_inval_all_pou(); - __tlb_switch_to_host(&cxt); } @@ -205,10 +161,6 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, dsb(ish); isb(); - /* See the comment in __kvm_tlb_flush_vmid_ipa() */ - if (icache_is_vpipt()) - icache_inval_all_pou(); - __tlb_switch_to_host(&cxt); } @@ -246,18 +198,5 @@ void __kvm_flush_vm_context(void) /* Same remark as in __tlb_switch_to_guest() */ dsb(ish); __tlbi(alle1is); - - /* - * VIPT and PIPT caches are not affected by VMID, so no maintenance - * is necessary across a VMID rollover. - * - * VPIPT caches constrain lookup and maintenance to the active VMID, - * so we need to invalidate lines with a stale VMID to avoid an ABA - * race after multiple rollovers. - * - */ - if (icache_is_vpipt()) - asm volatile("ic ialluis"); - dsb(ish); } diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index b636b4111dbf..b32e2940df7d 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -216,18 +216,5 @@ void __kvm_flush_vm_context(void) { dsb(ishst); __tlbi(alle1is); - - /* - * VIPT and PIPT caches are not affected by VMID, so no maintenance - * is necessary across a VMID rollover. - * - * VPIPT caches constrain lookup and maintenance to the active VMID, - * so we need to invalidate lines with a stale VMID to avoid an ABA - * race after multiple rollovers. - * - */ - if (icache_is_vpipt()) - asm volatile("ic ialluis"); - dsb(ish); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index fe99b3dab6ce..3d9467ff73bc 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -267,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) { - u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT; + u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu)); - val &= ARMV8_PMU_PMCR_N_MASK; if (val == 0) return BIT(ARMV8_PMU_CYCLE_IDX); else @@ -1136,8 +1135,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void) */ u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu) { - u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) & - ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); + u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0); - return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT); + return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 4735e1b37fb3..ff45d688bd7d 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -877,7 +877,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx) u64 pmcr, val; pmcr = kvm_vcpu_read_pmcr(vcpu); - val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; + val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr); if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) { kvm_inject_undefined(vcpu); return false; @@ -1143,7 +1143,7 @@ static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { - u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK; + u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val); struct kvm *kvm = vcpu->kvm; mutex_lock(&kvm->arch.config_lock); diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S index c336d2ffdec5..6a56d7cf309d 100644 --- a/arch/arm64/lib/copy_page.S +++ b/arch/arm64/lib/copy_page.S @@ -18,13 +18,6 @@ * x1 - src */ SYM_FUNC_START(__pi_copy_page) -alternative_if ARM64_HAS_NO_HW_PREFETCH - // Prefetch three cache lines ahead. - prfm pldl1strm, [x1, #128] - prfm pldl1strm, [x1, #256] - prfm pldl1strm, [x1, #384] -alternative_else_nop_endif - ldp x2, x3, [x1] ldp x4, x5, [x1, #16] ldp x6, x7, [x1, #32] @@ -39,10 +32,6 @@ alternative_else_nop_endif 1: tst x0, #(PAGE_SIZE - 1) -alternative_if ARM64_HAS_NO_HW_PREFETCH - prfm pldl1strm, [x1, #384] -alternative_else_nop_endif - stnp x2, x3, [x0, #-256] ldp x2, x3, [x1] stnp x4, x5, [x0, #16 - 256] diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 15f6347d23b6..1ac7467d34c9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -52,9 +52,6 @@ u64 vabits_actual __ro_after_init = VA_BITS_MIN; EXPORT_SYMBOL(vabits_actual); #endif -u64 kimage_vaddr __ro_after_init = (u64)&_text; -EXPORT_SYMBOL(kimage_vaddr); - u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -674,6 +671,9 @@ static int __init map_entry_trampoline(void) { int i; + if (!arm64_kernel_unmapped_at_el0()) + return 0; + pgprot_t prot = kernel_exec_prot(); phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index b98c38288a9d..1e07d74d7a6c 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -37,10 +37,10 @@ HAS_GIC_PRIO_MASKING HAS_GIC_PRIO_RELAXED_SYNC HAS_HCX HAS_LDAPR +HAS_LPA2 HAS_LSE_ATOMICS HAS_MOPS HAS_NESTED_VIRT -HAS_NO_HW_PREFETCH HAS_PAN HAS_S1PIE HAS_RAS_EXTN diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 5ceaa1d3630e..4c9b67934367 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2165,9 +2165,10 @@ Field 27:24 CWG Field 23:20 ERG Field 19:16 DminLine Enum 15:14 L1Ip - 0b00 VPIPT + # This was named as VPIPT in the ARM but now documented as reserved + 0b00 RESERVED_VPIPT # This is named as AIVIVT in the ARM but documented as reserved - 0b01 RESERVED + 0b01 RESERVED_AIVIVT 0b10 VIPT 0b11 PIPT EndEnum |