diff options
Diffstat (limited to 'arch/arm64')
55 files changed, 445 insertions, 310 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2511b30d0f6..b10515c0200b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -78,6 +78,7 @@ config ARM64 select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION select ARCH_KEEP_MEMBLOCK + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_GNU_PROPERTY select ARCH_USE_MEMTEST @@ -96,6 +97,7 @@ config ARM64 select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_SUPPORTS_PAGE_TABLE_CHECK select ARCH_SUPPORTS_PER_VMA_LOCK + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT @@ -348,9 +350,6 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y -config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE - def_bool y - config SMP def_bool y @@ -1461,60 +1460,28 @@ config PARAVIRT_TIME_ACCOUNTING If in doubt, say N here. -config KEXEC - depends on PM_SLEEP_SMP - select KEXEC_CORE - bool "kexec system call" - help - kexec is a system call that implements the ability to shutdown your - current kernel, and to start another kernel. It is like a reboot - but it is independent of the system firmware. And like a reboot - you can start any kernel with it, not just Linux. +config ARCH_SUPPORTS_KEXEC + def_bool PM_SLEEP_SMP -config KEXEC_FILE - bool "kexec file based system call" - select KEXEC_CORE - select HAVE_IMA_KEXEC if IMA - help - This is new version of kexec system call. This system call is - file based and takes file descriptors as system call argument - for kernel and initramfs as opposed to list of segments as - accepted by previous system call. +config ARCH_SUPPORTS_KEXEC_FILE + def_bool y -config KEXEC_SIG - bool "Verify kernel signature during kexec_file_load() syscall" +config ARCH_SELECTS_KEXEC_FILE + def_bool y depends on KEXEC_FILE - help - Select this option to verify a signature with loaded kernel - image. If configured, any attempt of loading a image without - valid signature will fail. - - In addition to that option, you need to enable signature - verification for the corresponding kernel image type being - loaded in order for this to work. + select HAVE_IMA_KEXEC if IMA -config KEXEC_IMAGE_VERIFY_SIG - bool "Enable Image signature verification support" - default y - depends on KEXEC_SIG - depends on EFI && SIGNED_PE_FILE_VERIFICATION - help - Enable Image signature verification support. +config ARCH_SUPPORTS_KEXEC_SIG + def_bool y -comment "Support for PE file signature verification disabled" - depends on KEXEC_SIG - depends on !EFI || !SIGNED_PE_FILE_VERIFICATION +config ARCH_SUPPORTS_KEXEC_IMAGE_VERIFY_SIG + def_bool y -config CRASH_DUMP - bool "Build kdump crash kernel" - help - Generate crash dump after being started by kexec. This should - be normally only set in special crash dump kernels which are - loaded in the main kernel with kexec-tools into a specially - reserved region and then later executed after a crash by - kdump/kexec. +config ARCH_DEFAULT_KEXEC_IMAGE_VERIFY_SIG + def_bool y - For more details see Documentation/admin-guide/kdump/kdump.rst +config ARCH_SUPPORTS_CRASH_DUMP + def_bool y config TRANS_TABLE def_bool y @@ -1793,9 +1760,6 @@ config ARM64_PAN The feature is detected at runtime, and will remain as a 'nop' instruction if the cpu does not implement the feature. -config AS_HAS_LDAPR - def_bool $(as-instr,.arch_extension rcpc) - config AS_HAS_LSE_ATOMICS def_bool $(as-instr,.arch_extension lse) @@ -1933,6 +1897,9 @@ config AS_HAS_ARMV8_3 config AS_HAS_CFI_NEGATE_RA_STATE def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) +config AS_HAS_LDAPR + def_bool $(as-instr,.arch_extension rcpc) + endmenu # "ARMv8.3 architectural features" menu "ARMv8.4 architectural features" diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index 4818e204c2ac..fbe64dce66e0 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -81,11 +81,6 @@ aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o -CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS - -$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE - $(call if_changed_rule,cc_o_c) - quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $(<) void $(@) diff --git a/arch/arm64/crypto/aes-glue-ce.c b/arch/arm64/crypto/aes-glue-ce.c new file mode 100644 index 000000000000..7d309ceeddf3 --- /dev/null +++ b/arch/arm64/crypto/aes-glue-ce.c @@ -0,0 +1,2 @@ +#define USE_V8_CRYPTO_EXTENSIONS +#include "aes-glue.c" diff --git a/arch/arm64/crypto/aes-glue-neon.c b/arch/arm64/crypto/aes-glue-neon.c new file mode 100644 index 000000000000..8ba046321064 --- /dev/null +++ b/arch/arm64/crypto/aes-glue-neon.c @@ -0,0 +1 @@ +#include "aes-glue.c" diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index bd68e1b7f29f..4d537d56eb84 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -42,6 +42,9 @@ #define ACPI_MADT_GICC_SPE (offsetof(struct acpi_madt_generic_interrupt, \ spe_interrupt) + sizeof(u16)) +#define ACPI_MADT_GICC_TRBE (offsetof(struct acpi_madt_generic_interrupt, \ + trbe_interrupt) + sizeof(u16)) + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 37185e978aeb..d115451ed263 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -114,7 +114,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define copy_to_user_page copy_to_user_page /* - * flush_dcache_page is used when the kernel has written to the page + * flush_dcache_folio is used when the kernel has written to the page * cache page at virtual address page->virtual. * * If this page isn't mapped (ie, page_mapping == NULL), or it might @@ -127,6 +127,8 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +void flush_dcache_folio(struct folio *); +#define flush_dcache_folio flush_dcache_folio static __always_inline void icache_inval_all_pou(void) { diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 4cf2cb053bc8..f482b994c608 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -30,28 +30,16 @@ int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool has_bti); -#define arch_efi_call_virt_setup() \ -({ \ - efi_virtmap_load(); \ - __efi_fpsimd_begin(); \ - raw_spin_lock(&efi_rt_lock); \ -}) - #undef arch_efi_call_virt #define arch_efi_call_virt(p, f, args...) \ __efi_rt_asm_wrapper((p)->f, #f, args) -#define arch_efi_call_virt_teardown() \ -({ \ - raw_spin_unlock(&efi_rt_lock); \ - __efi_fpsimd_end(); \ - efi_virtmap_unload(); \ -}) - -extern raw_spinlock_t efi_rt_lock; extern u64 *efi_rt_stack_top; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); + /* * efi_rt_stack_top[-1] contains the value the stack pointer had before * switching to the EFI runtime stack. diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 6a4a1ab8eb23..f43a38ac1779 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -10,6 +10,7 @@ #ifndef __ASM_HUGETLB_H #define __ASM_HUGETLB_H +#include <asm/cacheflush.h> #include <asm/page.h> #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION @@ -60,4 +61,19 @@ extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #include <asm-generic/hugetlb.h> +#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE +static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) +{ + unsigned long stride = huge_page_size(hstate_vma(vma)); + + if (stride == PMD_SIZE) + __flush_tlb_range(vma, start, end, stride, false, 2); + else if (stride == PUD_SIZE) + __flush_tlb_range(vma, start, end, stride, false, 1); + else + __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0); +} + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 692b1ec663b2..521267478d18 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -138,6 +138,7 @@ #define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16) #define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16) #define KERNEL_HWCAP_MOPS __khwcap2_feature(MOPS) +#define KERNEL_HWCAP_HBC __khwcap2_feature(HBC) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 139a88e4e852..db1aeacd4cd9 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -186,6 +186,8 @@ enum aarch64_insn_ldst_type { AARCH64_INSN_LDST_LOAD_ACQ_EX, AARCH64_INSN_LDST_STORE_EX, AARCH64_INSN_LDST_STORE_REL_EX, + AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET, + AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET, }; enum aarch64_insn_adsb_type { @@ -324,6 +326,7 @@ __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(store_imm, 0x3FC00000, 0x39000000) __AARCH64_INSN_FUNCS(load_imm, 0x3FC00000, 0x39400000) +__AARCH64_INSN_FUNCS(signed_load_imm, 0X3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(store_pre, 0x3FE00C00, 0x38000C00) __AARCH64_INSN_FUNCS(load_pre, 0x3FE00C00, 0x38400C00) __AARCH64_INSN_FUNCS(store_post, 0x3FE00C00, 0x38000400) @@ -337,6 +340,7 @@ __AARCH64_INSN_FUNCS(ldset, 0x3F20FC00, 0x38203000) __AARCH64_INSN_FUNCS(swp, 0x3F20FC00, 0x38208000) __AARCH64_INSN_FUNCS(cas, 0x3FA07C00, 0x08A07C00) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) +__AARCH64_INSN_FUNCS(signed_ldr_reg, 0X3FE0FC00, 0x38A0E800) __AARCH64_INSN_FUNCS(ldr_imm, 0x3FC00000, 0x39400000) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 51d92abf945e..3b694511b98f 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -139,8 +139,7 @@ extern void __memset_io(volatile void __iomem *, int, size_t); * I/O memory mapping functions. */ -bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot); -#define ioremap_allowed ioremap_allowed +#define ioremap_prot ioremap_prot #define _PAGE_IOREMAP PROT_DEVICE_nGnRE diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 577773870b66..85d26143faa5 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -118,31 +118,4 @@ #define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) #endif -/* - * To make optimal use of block mappings when laying out the linear - * mapping, round down the base of physical memory to a size that can - * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE - * (64k granule), or a multiple that can be mapped using contiguous bits - * in the page tables: 32 * PMD_SIZE (16k granule) - */ -#if defined(CONFIG_ARM64_4K_PAGES) -#define ARM64_MEMSTART_SHIFT PUD_SHIFT -#elif defined(CONFIG_ARM64_16K_PAGES) -#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT -#else -#define ARM64_MEMSTART_SHIFT PMD_SHIFT -#endif - -/* - * sparsemem vmemmap imposes an additional requirement on the alignment of - * memstart_addr, due to the fact that the base of the vmemmap region - * has a direct correspondence, and needs to appear sufficiently aligned - * in the virtual address space. - */ -#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS -#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) -#else -#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) -#endif - #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 4384eaa0aeb7..94b68850cb9f 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -64,7 +64,6 @@ extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); -extern void init_mem_pgprot(void); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index c028afb1cd0b..4cedbaa16f41 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -90,7 +90,7 @@ static inline bool try_page_mte_tagging(struct page *page) } void mte_zero_clear_page_tags(void *addr); -void mte_sync_tags(pte_t old_pte, pte_t pte); +void mte_sync_tags(pte_t pte); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); @@ -122,7 +122,7 @@ static inline bool try_page_mte_tagging(struct page *page) static inline void mte_zero_clear_page_tags(void *addr) { } -static inline void mte_sync_tags(pte_t old_pte, pte_t pte) +static inline void mte_sync_tags(pte_t pte) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 0bd18de9fd97..432932ad087f 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -103,6 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) +#define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) @@ -120,7 +121,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) -#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) +#define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) @@ -212,7 +213,7 @@ static inline pte_t pte_wrprotect(pte_t pte) * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); @@ -337,30 +338,29 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, * don't expose tags (instruction fetches don't check tags). */ if (system_supports_mte() && pte_access_permitted(pte, false) && - !pte_special(pte)) { - pte_t old_pte = READ_ONCE(*ptep); - /* - * We only need to synchronise if the new PTE has tags enabled - * or if swapping in (in which case another mapping may have - * set tags in the past even if this PTE isn't tagged). - * (!pte_none() && !pte_present()) is an open coded version of - * is_swap_pte() - */ - if (pte_tagged(pte) || (!pte_none(old_pte) && !pte_present(old_pte))) - mte_sync_tags(old_pte, pte); - } + !pte_special(pte) && pte_tagged(pte)) + mte_sync_tags(pte); __check_safe_pte_update(mm, ptep, pte); set_pte(ptep, pte); } -static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, unsigned int nr) { - page_table_check_pte_set(mm, addr, ptep, pte); - return __set_pte_at(mm, addr, ptep, pte); + page_table_check_ptes_set(mm, ptep, pte, nr); + + for (;;) { + __set_pte_at(mm, addr, ptep, pte); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + pte_val(pte) += PAGE_SIZE; + } } +#define set_ptes set_ptes /* * Huge pte definitions. @@ -534,14 +534,14 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(mm, addr, pmdp, pmd); + page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - page_table_check_pud_set(mm, addr, pudp, pud); + page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); } @@ -823,7 +823,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } @@ -938,7 +939,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); - page_table_check_pte_clear(mm, address, pte); + page_table_check_pte_clear(mm, pte); return pte; } @@ -950,7 +951,7 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); - page_table_check_pmd_clear(mm, address, pmd); + page_table_check_pmd_clear(mm, pmd); return pmd; } @@ -986,7 +987,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { - page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif @@ -1059,8 +1060,9 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) /* * On AArch64, the cache coherency is handled via the set_pte_at() function. */ -static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + unsigned int nr) { /* * We don't do anything here, so there's a very small chance of @@ -1069,6 +1071,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, */ } +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #ifdef CONFIG_ARM64_PA_BITS_52 diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index 4292d9bafb9d..484cb6972e99 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -17,6 +17,9 @@ #include <asm/virt.h> +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + extern unsigned long sdei_exit_mode; /* Software Delegated Exception entry point from firmware*/ @@ -29,6 +32,9 @@ asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num, unsigned long pc, unsigned long pstate); +/* Abort a running handler. Context is discarded. */ +void __sdei_handler_abort(void); + /* * The above entry point does the minimum to call C code. This function does * anything else, before calling the driver. diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b481935e9314..16464bf9a8aa 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -803,15 +803,21 @@ /* * For registers without architectural names, or simply unsupported by * GAS. + * + * __check_r forces warnings to be generated by the compiler when + * evaluating r which wouldn't normally happen due to being passed to + * the assembler via __stringify(r). */ #define read_sysreg_s(r) ({ \ u64 __val; \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \ __val; \ }) #define write_sysreg_s(v, r) do { \ u64 __val = (u64)(v); \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \ } while (0) diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index c995d1f4594f..2c29239d05c3 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -75,18 +75,20 @@ static inline void tlb_flush(struct mmu_gather *tlb) static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { - pgtable_pte_page_dtor(pte); - tlb_remove_table(tlb, pte); + struct ptdesc *ptdesc = page_ptdesc(pte); + + pagetable_pte_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr) { - struct page *page = virt_to_page(pmdp); + struct ptdesc *ptdesc = virt_to_ptdesc(pmdp); - pgtable_pmd_page_dtor(page); - tlb_remove_table(tlb, page); + pagetable_pmd_dtor(ptdesc); + tlb_remove_ptdesc(tlb, ptdesc); } #endif @@ -94,7 +96,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, unsigned long addr) { - tlb_remove_table(tlb, virt_to_page(pudp)); + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pudp)); } #endif diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h new file mode 100644 index 000000000000..fedb0b87b8db --- /dev/null +++ b/arch/arm64/include/asm/tlbbatch.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_ARM64_TLBBATCH_H +#define _ARCH_ARM64_TLBBATCH_H + +struct arch_tlbflush_unmap_batch { + /* + * For arm64, HW can do tlb shootdown, so we don't + * need to record cpumask for sending IPI + */ +}; + +#endif /* _ARCH_ARM64_TLBBATCH_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 412a3b9a3c25..55b50e1d4a84 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -13,6 +13,7 @@ #include <linux/bitfield.h> #include <linux/mm_types.h> #include <linux/sched.h> +#include <linux/mmu_notifier.h> #include <asm/cputype.h> #include <asm/mmu.h> @@ -252,17 +253,26 @@ static inline void flush_tlb_mm(struct mm_struct *mm) __tlbi(aside1is, asid); __tlbi_user(aside1is, asid); dsb(ish); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } -static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, - unsigned long uaddr) +static inline void __flush_tlb_page_nosync(struct mm_struct *mm, + unsigned long uaddr) { unsigned long addr; dsb(ishst); - addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); + addr = __TLBI_VADDR(uaddr, ASID(mm)); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, uaddr & PAGE_MASK, + (uaddr & PAGE_MASK) + PAGE_SIZE); +} + +static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, + unsigned long uaddr) +{ + return __flush_tlb_page_nosync(vma->vm_mm, uaddr); } static inline void flush_tlb_page(struct vm_area_struct *vma, @@ -272,6 +282,53 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, dsb(ish); } +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ +#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI + /* + * TLB flush deferral is not required on systems which are affected by + * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation + * will have two consecutive TLBI instructions with a dsb(ish) in between + * defeating the purpose (i.e save overall 'dsb ish' cost). + */ + if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI))) + return false; +#endif + return true; +} + +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, + unsigned long uaddr) +{ + __flush_tlb_page_nosync(mm, uaddr); +} + +/* + * If mprotect/munmap/etc occurs during TLB batched flushing, we need to + * synchronise all the TLBI issued with a DSB to avoid the race mentioned in + * flush_tlb_batched_pending(). + */ +static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) +{ + dsb(ish); +} + +/* + * To support TLB batched flush for multiple pages unmapping, we only send + * the TLBI for each page in arch_tlbbatch_add_pending() and wait for the + * completion at the end in arch_tlbbatch_flush(). Since we've already issued + * TLBI for each page so only a DSB is needed to synchronise its effect on the + * other CPUs. + * + * This will save the time waiting on DSB comparing issuing a TLBI;DSB sequence + * for each page. + */ +static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + dsb(ish); +} + /* * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. @@ -358,6 +415,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, scale++; } dsb(ish); + mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, start, end); } static inline void flush_tlb_range(struct vm_area_struct *vma, diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 64a514f90131..bd77253b62e0 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 452 +#define __NR_compat_syscalls 453 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index d952a28463e0..78b68311ec81 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -909,6 +909,8 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index a2cac4305b1e..53026f45a509 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -103,5 +103,6 @@ #define HWCAP2_SME_B16B16 (1UL << 41) #define HWCAP2_SME_F16F16 (1UL << 42) #define HWCAP2_MOPS (1UL << 43) +#define HWCAP2_HBC (1UL << 44) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 1febd412b4d2..e459cfd33711 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -569,7 +569,7 @@ static void __init register_insn_emulation(struct insn_emulation *insn) sysctl->extra2 = &insn->max; sysctl->proc_handler = emulation_proc_handler; - register_sysctl("abi", sysctl); + register_sysctl_sz("abi", sysctl, 1); } } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f9d456fe132d..a5f533f63b60 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -222,7 +222,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), @@ -2708,12 +2708,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Enhanced Virtualization Traps", .capability = ARM64_HAS_EVT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_EVT_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64MMFR2_EL1_EVT_IMP, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP) }, {}, }; @@ -2844,6 +2840,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS), + HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index d1f68599c29f..f372295207fb 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -9,8 +9,6 @@ #include <linux/acpi.h> #include <linux/cpuidle.h> #include <linux/cpu_pm.h> -#include <linux/of.h> -#include <linux/of_device.h> #include <linux/psci.h> #ifdef CONFIG_ACPI_PROCESSOR_IDLE diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 58622dc85917..98fda8500535 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -126,6 +126,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_B16B16] = "smeb16b16", [KERNEL_HWCAP_SME_F16F16] = "smef16f16", [KERNEL_HWCAP_MOPS] = "mops", + [KERNEL_HWCAP_HBC] = "hbc", }; #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3afbe503b066..2b478ca356b0 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -159,7 +159,21 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) return s; } -DEFINE_RAW_SPINLOCK(efi_rt_lock); +static DEFINE_RAW_SPINLOCK(efi_rt_lock); + +void arch_efi_call_virt_setup(void) +{ + efi_virtmap_load(); + __efi_fpsimd_begin(); + raw_spin_lock(&efi_rt_lock); +} + +void arch_efi_call_virt_teardown(void) +{ + raw_spin_unlock(&efi_rt_lock); + __efi_fpsimd_end(); + efi_virtmap_unload(); +} asmlinkage u64 *efi_rt_stack_top __ro_after_init; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 6b2e0c367702..0fc94207e69a 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -355,6 +355,35 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +/* + * As per the ABI exit SME streaming mode and clear the SVE state not + * shared with FPSIMD on syscall entry. + */ +static inline void fp_user_discard(void) +{ + /* + * If SME is active then exit streaming mode. If ZA is active + * then flush the SVE registers but leave userspace access to + * both SVE and SME enabled, otherwise disable SME for the + * task and fall through to disabling SVE too. This means + * that after a syscall we never have any streaming mode + * register state to track, if this changes the KVM code will + * need updating. + */ + if (system_supports_sme()) + sme_smstop_sm(); + + if (!system_supports_sve()) + return; + + if (test_thread_flag(TIF_SVE)) { + unsigned int sve_vq_minus_one; + + sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_flush_live(true, sve_vq_minus_one); + } +} + UNHANDLED(el1t, 64, sync) UNHANDLED(el1t, 64, irq) UNHANDLED(el1t, 64, fiq) @@ -644,6 +673,8 @@ static void noinstr el0_svc(struct pt_regs *regs) { enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); + fp_user_discard(); + local_daif_restore(DAIF_PROCCTX); do_el0_svc(regs); exit_to_user_mode(regs); } @@ -783,6 +814,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs) { enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); + local_daif_restore(DAIF_PROCCTX); do_el0_svc_compat(regs); exit_to_user_mode(regs); } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a40e5e50fa55..6ad61de03d0a 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -986,9 +986,13 @@ SYM_CODE_START(__sdei_asm_handler) mov x19, x1 -#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK) + /* Store the registered-event for crash_smp_send_stop() */ ldrb w4, [x19, #SDEI_EVENT_PRIORITY] -#endif + cbnz w4, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str x19, [x5] #ifdef CONFIG_VMAP_STACK /* @@ -1055,6 +1059,14 @@ SYM_CODE_START(__sdei_asm_handler) ldr_l x2, sdei_exit_mode + /* Clear the registered-event seen by crash_smp_send_stop() */ + ldrb w3, [x4, #SDEI_EVENT_PRIORITY] + cbnz w3, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str xzr, [x5] + alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 sdei_handler_exit exit_mode=x2 alternative_else_nop_endif @@ -1065,4 +1077,15 @@ alternative_else_nop_endif #endif SYM_CODE_END(__sdei_asm_handler) NOKPROBE(__sdei_asm_handler) + +SYM_CODE_START(__sdei_handler_abort) + mov_q x0, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME + adr x1, 1f + ldr_l x2, sdei_exit_mode + sdei_handler_exit exit_mode=x2 + // exit the handler and jump to the next instruction. + // Exit will stomp x0-x17, PSTATE, ELR_ELx, and SPSR_ELx. +1: ret +SYM_CODE_END(__sdei_handler_abort) +NOKPROBE(__sdei_handler_abort) #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 087c05aa960e..91e44ac7150f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1179,9 +1179,6 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_zcr_features(void) { - u64 zcr; - unsigned int vq_max; - /* * Set the maximum possible VL, and write zeroes to all other * bits to see if they stick. @@ -1189,12 +1186,8 @@ u64 read_zcr_features(void) sve_kernel_enable(NULL); write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); - zcr = read_sysreg_s(SYS_ZCR_EL1); - zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); - zcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return zcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sve_get_vl()) - 1; } void __init sve_setup(void) @@ -1349,9 +1342,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_smcr_features(void) { - u64 smcr; - unsigned int vq_max; - sme_kernel_enable(NULL); /* @@ -1360,12 +1350,8 @@ u64 read_smcr_features(void) write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, SYS_SMCR_EL1); - smcr = read_sysreg_s(SYS_SMCR_EL1); - smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ - vq_max = sve_vq_from_vl(sme_get_vl()); - smcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return smcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sme_get_vl()) - 1; } void __init sme_setup(void) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 757a0de07f91..7b236994f0e1 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -113,7 +113,7 @@ SYM_CODE_START(primary_entry) */ #if VA_BITS > 48 mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, #0xf << ID_AA64MMFR2_EL1_VARange_SHIFT + tst x0, ID_AA64MMFR2_EL1_VARange_MASK mov x0, #VA_BITS mov x25, #VA_BITS_MIN csel x25, x25, x0, eq @@ -756,7 +756,7 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) b.ne 2f mrs_s x0, SYS_ID_AA64MMFR2_EL1 - and x0, x0, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) + and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f update_early_cpu_boot_status \ diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index db2a1861bb97..35225632d70a 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -654,7 +654,7 @@ static int breakpoint_handler(unsigned long unused, unsigned long esr, perf_bp_event(bp, regs); /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(bp)) + if (uses_default_overflow_handler(bp)) step = 1; unlock: rcu_read_unlock(); @@ -733,7 +733,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, static int watchpoint_report(struct perf_event *wp, unsigned long addr, struct pt_regs *regs) { - int step = is_default_overflow_handler(wp); + int step = uses_default_overflow_handler(wp); struct arch_hw_breakpoint *info = counter_arch_bp(wp); info->trigger = addr; diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 2fe2491b692c..aee12c75b738 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -262,9 +262,9 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) if (!len) return; - len = min(len, ARRAY_SIZE(buf) - 1); - strncpy(buf, cmdline, len); - buf[len] = 0; + len = strscpy(buf, cmdline, ARRAY_SIZE(buf)); + if (len == -E2BIG) + len = ARRAY_SIZE(buf) - 1; if (strcmp(buf, "--") == 0) return; diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index ad02058756b5..bd69a4e7cd60 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -339,7 +339,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (nents) sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL); - if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) + if (!module_init_layout_section(secstrings + dstsec->sh_name)) core_plts += count_plts(syms, rels, numrels, sechdrs[i].sh_info, dstsec); else diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 4c5ef9b20065..4edecaac8f91 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -35,41 +35,18 @@ DEFINE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode); #endif -static void mte_sync_page_tags(struct page *page, pte_t old_pte, - bool check_swap, bool pte_is_tagged) -{ - if (check_swap && is_swap_pte(old_pte)) { - swp_entry_t entry = pte_to_swp_entry(old_pte); - - if (!non_swap_entry(entry)) - mte_restore_tags(entry, page); - } - - if (!pte_is_tagged) - return; - - if (try_page_mte_tagging(page)) { - mte_clear_page_tags(page_address(page)); - set_page_mte_tagged(page); - } -} - -void mte_sync_tags(pte_t old_pte, pte_t pte) +void mte_sync_tags(pte_t pte) { struct page *page = pte_page(pte); long i, nr_pages = compound_nr(page); - bool check_swap = nr_pages == 1; - bool pte_is_tagged = pte_tagged(pte); - - /* Early out if there's nothing to do */ - if (!check_swap && !pte_is_tagged) - return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) - if (!page_mte_tagged(page)) - mte_sync_page_tags(page, old_pte, check_swap, - pte_is_tagged); + for (i = 0; i < nr_pages; i++, page++) { + if (try_page_mte_tagging(page)) { + mte_clear_page_tags(page_address(page)); + set_page_mte_tagged(page); + } + } /* ensure the tags are visible before the PTE is set */ smp_wmb(); diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index 2276689b5411..f872c57e9909 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -11,8 +11,6 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/of_pci.h> -#include <linux/of_platform.h> #include <linux/pci.h> #include <linux/pci-acpi.h> #include <linux/pci-ecam.h> diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 187aa2b175b4..20d7ef82de90 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -891,7 +891,8 @@ static int sve_set_common(struct task_struct *target, break; default: WARN_ON_ONCE(1); - return -EINVAL; + ret = -EINVAL; + goto out; } /* diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 830be01af32d..255d12f881c2 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -47,6 +47,9 @@ DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr); DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr); #endif +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu) { unsigned long *p; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index edd63894d61e..960b98b43506 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -1044,10 +1044,8 @@ void crash_smp_send_stop(void) * If this cpu is the only one alive at this point in time, online or * not, there are no stop messages to be sent around, so just back out. */ - if (num_other_online_cpus() == 0) { - sdei_mask_local_cpu(); - return; - } + if (num_other_online_cpus() == 0) + goto skip_ipi; cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); @@ -1066,7 +1064,9 @@ void crash_smp_send_stop(void) pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(&mask)); +skip_ipi: sdei_mask_local_cpu(); + sdei_handler_abort(); } bool smp_crash_stop_failed(void) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index b1ae2f2eaf77..9a70d9746b66 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -8,7 +8,6 @@ #include <linux/randomize_kstack.h> #include <linux/syscalls.h> -#include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/exception.h> #include <asm/fpsimd.h> @@ -101,8 +100,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * (Similarly for HVC and SMC elsewhere.) */ - local_daif_restore(DAIF_PROCCTX); - if (flags & _TIF_MTE_ASYNC_FAULT) { /* * Process the asynchronous tag check fault before the actual @@ -153,38 +150,8 @@ trace_exit: syscall_trace_exit(regs); } -/* - * As per the ABI exit SME streaming mode and clear the SVE state not - * shared with FPSIMD on syscall entry. - */ -static inline void fp_user_discard(void) -{ - /* - * If SME is active then exit streaming mode. If ZA is active - * then flush the SVE registers but leave userspace access to - * both SVE and SME enabled, otherwise disable SME for the - * task and fall through to disabling SVE too. This means - * that after a syscall we never have any streaming mode - * register state to track, if this changes the KVM code will - * need updating. - */ - if (system_supports_sme()) - sme_smstop_sm(); - - if (!system_supports_sve()) - return; - - if (test_thread_flag(TIF_SVE)) { - unsigned int sve_vq_minus_one; - - sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; - sve_flush_live(true, sve_vq_minus_one); - } -} - void do_el0_svc(struct pt_regs *regs) { - fp_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 6028f1fe2d1c..45354f2ddf70 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -50,9 +50,7 @@ SECTIONS . = ALIGN(4); .altinstructions : { - __alt_instructions = .; *(.altinstructions) - __alt_instructions_end = .; } .dynamic : { *(.dynamic) } :text :dynamic diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 9ddc025e4b86..2250253a6429 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -25,7 +25,7 @@ hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o hyp-obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o -hyp-obj-$(CONFIG_DEBUG_LIST) += list_debug.o +hyp-obj-$(CONFIG_LIST_HARDENED) += list_debug.o hyp-obj-y += $(lib-objs) ## diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c index d68abd7ea124..46a2d4f2b3c6 100644 --- a/arch/arm64/kvm/hyp/nvhe/list_debug.c +++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c @@ -26,8 +26,9 @@ static inline __must_check bool nvhe_check_data_corruption(bool v) /* The predicates checked here are taken from lib/list_debug.c. */ -bool __list_add_valid(struct list_head *new, struct list_head *prev, - struct list_head *next) +__list_valid_slowpath +bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev, + struct list_head *next) { if (NVHE_CHECK_DATA_CORRUPTION(next->prev != prev) || NVHE_CHECK_DATA_CORRUPTION(prev->next != next) || @@ -37,7 +38,8 @@ bool __list_add_valid(struct list_head *new, struct list_head *prev, return true; } -bool __list_del_entry_valid(struct list_head *entry) +__list_valid_slowpath +bool __list_del_entry_valid_or_report(struct list_head *entry) { struct list_head *prev, *next; diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index 924934cb85ee..a635ab83fee3 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -385,6 +385,9 @@ u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg, case AARCH64_INSN_LDST_LOAD_REG_OFFSET: insn = aarch64_insn_get_ldr_reg_value(); break; + case AARCH64_INSN_LDST_SIGNED_LOAD_REG_OFFSET: + insn = aarch64_insn_get_signed_ldr_reg_value(); + break; case AARCH64_INSN_LDST_STORE_REG_OFFSET: insn = aarch64_insn_get_str_reg_value(); break; @@ -430,6 +433,9 @@ u32 aarch64_insn_gen_load_store_imm(enum aarch64_insn_register reg, case AARCH64_INSN_LDST_LOAD_IMM_OFFSET: insn = aarch64_insn_get_ldr_imm_value(); break; + case AARCH64_INSN_LDST_SIGNED_LOAD_IMM_OFFSET: + insn = aarch64_insn_get_signed_load_imm_value(); + break; case AARCH64_INSN_LDST_STORE_IMM_OFFSET: insn = aarch64_insn_get_str_imm_value(); break; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3fe516b32577..2e5d1e238af9 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -587,7 +587,6 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); -#ifdef CONFIG_PER_VMA_LOCK if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; @@ -600,7 +599,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto lock_mmap; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); - vma_end_read(vma); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); @@ -615,7 +615,6 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, return 0; } lock_mmap: -#endif /* CONFIG_PER_VMA_LOCK */ retry: vma = lock_mm_and_find_vma(mm, addr, regs); diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 4e6476094952..013eead9b695 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -51,20 +51,13 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, void __sync_icache_dcache(pte_t pte) { - struct page *page = pte_page(pte); + struct folio *folio = page_folio(pte_page(pte)); - /* - * HugeTLB pages are always fully mapped, so only setting head page's - * PG_dcache_clean flag is enough. - */ - if (PageHuge(page)) - page = compound_head(page); - - if (!test_bit(PG_dcache_clean, &page->flags)) { - sync_icache_aliases((unsigned long)page_address(page), - (unsigned long)page_address(page) + - page_size(page)); - set_bit(PG_dcache_clean, &page->flags); + if (!test_bit(PG_dcache_clean, &folio->flags)) { + sync_icache_aliases((unsigned long)folio_address(folio), + (unsigned long)folio_address(folio) + + folio_size(folio)); + set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); @@ -74,17 +67,16 @@ EXPORT_SYMBOL_GPL(__sync_icache_dcache); * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ -void flush_dcache_page(struct page *page) +void flush_dcache_folio(struct folio *folio) { - /* - * HugeTLB pages are always fully mapped and only head page will be - * set PG_dcache_clean (see comments in __sync_icache_dcache()). - */ - if (PageHuge(page)) - page = compound_head(page); + if (test_bit(PG_dcache_clean, &folio->flags)) + clear_bit(PG_dcache_clean, &folio->flags); +} +EXPORT_SYMBOL(flush_dcache_folio); - if (test_bit(PG_dcache_clean, &page->flags)) - clear_bit(PG_dcache_clean, &page->flags); +void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 21716c940682..9c52718ea750 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -236,7 +236,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) - pte_clear(mm, addr, ptep); + ptep_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d31c3a9290c5..8a0f8604348b 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,6 +73,33 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit; #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) +/* + * To make optimal use of block mappings when laying out the linear + * mapping, round down the base of physical memory to a size that can + * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE + * (64k granule), or a multiple that can be mapped using contiguous bits + * in the page tables: 32 * PMD_SIZE (16k granule) + */ +#if defined(CONFIG_ARM64_4K_PAGES) +#define ARM64_MEMSTART_SHIFT PUD_SHIFT +#elif defined(CONFIG_ARM64_16K_PAGES) +#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT +#else +#define ARM64_MEMSTART_SHIFT PMD_SHIFT +#endif + +/* + * sparsemem vmemmap imposes an additional requirement on the alignment of + * memstart_addr, due to the fact that the base of the vmemmap region + * has a direct correspondence, and needs to appear sufficiently aligned + * in the virtual address space. + */ +#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS +#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) +#else +#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) +#endif + static int __init reserve_crashkernel_low(unsigned long long low_size) { unsigned long long low_base; @@ -434,8 +461,6 @@ void __init bootmem_init(void) arm64_hugetlb_cma_reserve(); #endif - dma_pernuma_cma_reserve(); - kvm_hyp_reserve(); /* diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index c5af103d4ad4..269f2f63ab7d 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -3,20 +3,22 @@ #include <linux/mm.h> #include <linux/io.h> -bool ioremap_allowed(phys_addr_t phys_addr, size_t size, unsigned long prot) +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { unsigned long last_addr = phys_addr + size - 1; /* Don't allow outside PHYS_MASK */ if (last_addr & ~PHYS_MASK) - return false; + return NULL; /* Don't allow RAM to be mapped. */ if (WARN_ON(pfn_is_map_memory(__phys_to_pfn(phys_addr)))) - return false; + return NULL; - return true; + return generic_ioremap_prot(phys_addr, size, __pgprot(prot)); } +EXPORT_SYMBOL(ioremap_prot); /* * Must be called after early_fixmap_init diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 95d360805f8a..47781bec6171 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -426,6 +426,7 @@ static phys_addr_t __pgd_pgtable_alloc(int shift) static phys_addr_t pgd_pgtable_alloc(int shift) { phys_addr_t pa = __pgd_pgtable_alloc(shift); + struct ptdesc *ptdesc = page_ptdesc(phys_to_page(pa)); /* * Call proper page table ctor in case later we need to @@ -433,12 +434,12 @@ static phys_addr_t pgd_pgtable_alloc(int shift) * this pre-allocated page table. * * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is - * folded, and if so pgtable_pmd_page_ctor() becomes nop. + * folded, and if so pagetable_pte_ctor() becomes nop. */ if (shift == PAGE_SHIFT) - BUG_ON(!pgtable_pte_page_ctor(phys_to_page(pa))); + BUG_ON(!pagetable_pte_ctor(ptdesc)); else if (shift == PMD_SHIFT) - BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa))); + BUG_ON(!pagetable_pmd_ctor(ptdesc)); return pa; } diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index cd508ba80ab1..a31833e3ddc5 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -33,8 +33,9 @@ int mte_save_tags(struct page *page) mte_save_page_tags(page_address(page), tag_storage); - /* page_private contains the swap entry.val set in do_swap_page */ - ret = xa_store(&mte_pages, page_private(page), tag_storage, GFP_KERNEL); + /* lookup the swap entry.val from the page */ + ret = xa_store(&mte_pages, page_swap_entry(page).val, tag_storage, + GFP_KERNEL); if (WARN(xa_is_err(ret), "Failed to store MTE tags")) { mte_free_tag_storage(tag_storage); return xa_err(ret); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 2baeec419f62..14fdf645edc8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -447,7 +447,7 @@ SYM_FUNC_START(__cpu_setup) * via capabilities. */ mrs x9, ID_AA64MMFR1_EL1 - and x9, x9, #0xf + and x9, x9, ID_AA64MMFR1_EL1_HAFDBS_MASK cbz x9, 1f orr tcr, tcr, #TCR_HA // hardware Access flag update 1: diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index c2edadb8ec6a..23b1b34db088 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -59,10 +59,13 @@ AARCH64_INSN_LDST_##type##_REG_OFFSET) #define A64_STRB(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 8, STORE) #define A64_LDRB(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 8, LOAD) +#define A64_LDRSB(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 8, SIGNED_LOAD) #define A64_STRH(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 16, STORE) #define A64_LDRH(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 16, LOAD) +#define A64_LDRSH(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 16, SIGNED_LOAD) #define A64_STR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, STORE) #define A64_LDR32(Wt, Xn, Xm) A64_LS_REG(Wt, Xn, Xm, 32, LOAD) +#define A64_LDRSW(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 32, SIGNED_LOAD) #define A64_STR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, STORE) #define A64_LDR64(Xt, Xn, Xm) A64_LS_REG(Xt, Xn, Xm, 64, LOAD) @@ -73,10 +76,13 @@ AARCH64_INSN_LDST_##type##_IMM_OFFSET) #define A64_STRBI(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 8, STORE) #define A64_LDRBI(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 8, LOAD) +#define A64_LDRSBI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 8, SIGNED_LOAD) #define A64_STRHI(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 16, STORE) #define A64_LDRHI(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 16, LOAD) +#define A64_LDRSHI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 16, SIGNED_LOAD) #define A64_STR32I(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 32, STORE) #define A64_LDR32I(Wt, Xn, imm) A64_LS_IMM(Wt, Xn, imm, 32, LOAD) +#define A64_LDRSWI(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 32, SIGNED_LOAD) #define A64_STR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, STORE) #define A64_LDR64I(Xt, Xn, imm) A64_LS_IMM(Xt, Xn, imm, 64, LOAD) @@ -186,6 +192,11 @@ #define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15) #define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31) +/* Sign extend */ +#define A64_SXTB(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 7) +#define A64_SXTH(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 15) +#define A64_SXTW(sf, Rd, Rn) A64_SBFM(sf, Rd, Rn, 0, 31) + /* Move wide (immediate) */ #define A64_MOVEW(sf, Rd, imm16, shift, type) \ aarch64_insn_gen_movewide(Rd, imm16, shift, \ @@ -223,6 +234,7 @@ #define A64_DATA2(sf, Rd, Rn, Rm, type) aarch64_insn_gen_data2(Rd, Rn, Rm, \ A64_VARIANT(sf), AARCH64_INSN_DATA2_##type) #define A64_UDIV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, UDIV) +#define A64_SDIV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, SDIV) #define A64_LSLV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, LSLV) #define A64_LSRV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, LSRV) #define A64_ASRV(sf, Rd, Rn, Rm) A64_DATA2(sf, Rd, Rn, Rm, ASRV) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index ec2174838f2a..150d1c6543f7 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -715,7 +715,8 @@ static int add_exception_handler(const struct bpf_insn *insn, /* First pass */ return 0; - if (BPF_MODE(insn->code) != BPF_PROBE_MEM) + if (BPF_MODE(insn->code) != BPF_PROBE_MEM && + BPF_MODE(insn->code) != BPF_PROBE_MEMSX) return 0; if (!ctx->prog->aux->extable || @@ -779,12 +780,26 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, u8 dst_adj; int off_adj; int ret; + bool sign_extend; switch (code) { /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: case BPF_ALU64 | BPF_MOV | BPF_X: - emit(A64_MOV(is64, dst, src), ctx); + switch (insn->off) { + case 0: + emit(A64_MOV(is64, dst, src), ctx); + break; + case 8: + emit(A64_SXTB(is64, dst, src), ctx); + break; + case 16: + emit(A64_SXTH(is64, dst, src), ctx); + break; + case 32: + emit(A64_SXTW(is64, dst, src), ctx); + break; + } break; /* dst = dst OP src */ case BPF_ALU | BPF_ADD | BPF_X: @@ -813,11 +828,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: - emit(A64_UDIV(is64, dst, dst, src), ctx); + if (!off) + emit(A64_UDIV(is64, dst, dst, src), ctx); + else + emit(A64_SDIV(is64, dst, dst, src), ctx); break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - emit(A64_UDIV(is64, tmp, dst, src), ctx); + if (!off) + emit(A64_UDIV(is64, tmp, dst, src), ctx); + else + emit(A64_SDIV(is64, tmp, dst, src), ctx); emit(A64_MSUB(is64, dst, dst, tmp, src), ctx); break; case BPF_ALU | BPF_LSH | BPF_X: @@ -840,11 +861,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, /* dst = BSWAP##imm(dst) */ case BPF_ALU | BPF_END | BPF_FROM_LE: case BPF_ALU | BPF_END | BPF_FROM_BE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: #ifdef CONFIG_CPU_BIG_ENDIAN - if (BPF_SRC(code) == BPF_FROM_BE) + if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_BE) goto emit_bswap_uxt; #else /* !CONFIG_CPU_BIG_ENDIAN */ - if (BPF_SRC(code) == BPF_FROM_LE) + if (BPF_CLASS(code) == BPF_ALU && BPF_SRC(code) == BPF_FROM_LE) goto emit_bswap_uxt; #endif switch (imm) { @@ -943,12 +965,18 @@ emit_bswap_uxt: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: emit_a64_mov_i(is64, tmp, imm, ctx); - emit(A64_UDIV(is64, dst, dst, tmp), ctx); + if (!off) + emit(A64_UDIV(is64, dst, dst, tmp), ctx); + else + emit(A64_SDIV(is64, dst, dst, tmp), ctx); break; case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: emit_a64_mov_i(is64, tmp2, imm, ctx); - emit(A64_UDIV(is64, tmp, dst, tmp2), ctx); + if (!off) + emit(A64_UDIV(is64, tmp, dst, tmp2), ctx); + else + emit(A64_SDIV(is64, tmp, dst, tmp2), ctx); emit(A64_MSUB(is64, dst, dst, tmp, tmp2), ctx); break; case BPF_ALU | BPF_LSH | BPF_K: @@ -966,7 +994,11 @@ emit_bswap_uxt: /* JUMP off */ case BPF_JMP | BPF_JA: - jmp_offset = bpf2a64_offset(i, off, ctx); + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(code) == BPF_JMP) + jmp_offset = bpf2a64_offset(i, off, ctx); + else + jmp_offset = bpf2a64_offset(i, imm, ctx); check_imm26(jmp_offset); emit(A64_B(jmp_offset), ctx); break; @@ -1122,7 +1154,7 @@ emit_cond_jmp: return 1; } - /* LDX: dst = *(size *)(src + off) */ + /* LDX: dst = (u64)*(unsigned size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_W: case BPF_LDX | BPF_MEM | BPF_H: case BPF_LDX | BPF_MEM | BPF_B: @@ -1131,6 +1163,13 @@ emit_cond_jmp: case BPF_LDX | BPF_PROBE_MEM | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_B: + /* LDXS: dst_reg = (s64)*(signed size *)(src_reg + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: if (ctx->fpb_offset > 0 && src == fp) { src_adj = fpb; off_adj = off + ctx->fpb_offset; @@ -1138,29 +1177,49 @@ emit_cond_jmp: src_adj = src; off_adj = off; } + sign_extend = (BPF_MODE(insn->code) == BPF_MEMSX || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX); switch (BPF_SIZE(code)) { case BPF_W: if (is_lsi_offset(off_adj, 2)) { - emit(A64_LDR32I(dst, src_adj, off_adj), ctx); + if (sign_extend) + emit(A64_LDRSWI(dst, src_adj, off_adj), ctx); + else + emit(A64_LDR32I(dst, src_adj, off_adj), ctx); } else { emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_LDR32(dst, src, tmp), ctx); + if (sign_extend) + emit(A64_LDRSW(dst, src_adj, off_adj), ctx); + else + emit(A64_LDR32(dst, src, tmp), ctx); } break; case BPF_H: if (is_lsi_offset(off_adj, 1)) { - emit(A64_LDRHI(dst, src_adj, off_adj), ctx); + if (sign_extend) + emit(A64_LDRSHI(dst, src_adj, off_adj), ctx); + else + emit(A64_LDRHI(dst, src_adj, off_adj), ctx); } else { emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_LDRH(dst, src, tmp), ctx); + if (sign_extend) + emit(A64_LDRSH(dst, src, tmp), ctx); + else + emit(A64_LDRH(dst, src, tmp), ctx); } break; case BPF_B: if (is_lsi_offset(off_adj, 0)) { - emit(A64_LDRBI(dst, src_adj, off_adj), ctx); + if (sign_extend) + emit(A64_LDRSBI(dst, src_adj, off_adj), ctx); + else + emit(A64_LDRBI(dst, src_adj, off_adj), ctx); } else { emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_LDRB(dst, src, tmp), ctx); + if (sign_extend) + emit(A64_LDRSB(dst, src, tmp), ctx); + else + emit(A64_LDRB(dst, src, tmp), ctx); } break; case BPF_DW: |