diff options
Diffstat (limited to 'arch/arm64')
41 files changed, 512 insertions, 517 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 2681eb79c40b..6481964b6425 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -148,6 +148,7 @@ config ARM64 select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS @@ -286,7 +287,7 @@ config PGTABLE_LEVELS int default 2 if ARM64_16K_PAGES && ARM64_VA_BITS_36 default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42 - default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52) + default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39 default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47 default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48 @@ -297,6 +298,21 @@ config ARCH_SUPPORTS_UPROBES config ARCH_PROC_KCORE_TEXT def_bool y +config KASAN_SHADOW_OFFSET + hex + depends on KASAN + default 0xdfffa00000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS + default 0xdfffd00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS + default 0xdffffe8000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS + default 0xdfffffd000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS + default 0xdffffffa00000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS + default 0xefff900000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS + default 0xefffc80000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS + default 0xeffffe4000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS + default 0xefffffc800000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS + default 0xeffffff900000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS + default 0xffffffffffffffff + source "arch/arm64/Kconfig.platforms" menu "Kernel Features" @@ -744,13 +760,14 @@ config ARM64_VA_BITS_47 config ARM64_VA_BITS_48 bool "48-bit" -config ARM64_USER_VA_BITS_52 - bool "52-bit (user)" +config ARM64_VA_BITS_52 + bool "52-bit" depends on ARM64_64K_PAGES && (ARM64_PAN || !ARM64_SW_TTBR0_PAN) help Enable 52-bit virtual addressing for userspace when explicitly - requested via a hint to mmap(). The kernel will continue to - use 48-bit virtual addresses for its own mappings. + requested via a hint to mmap(). The kernel will also use 52-bit + virtual addresses for its own mappings (provided HW support for + this feature is available, otherwise it reverts to 48-bit). NOTE: Enabling 52-bit virtual addressing in conjunction with ARMv8.3 Pointer Authentication will result in the PAC being @@ -763,7 +780,7 @@ endchoice config ARM64_FORCE_52BIT bool "Force 52-bit virtual addresses for userspace" - depends on ARM64_USER_VA_BITS_52 && EXPERT + depends on ARM64_VA_BITS_52 && EXPERT help For systems with 52-bit userspace VAs enabled, the kernel will attempt to maintain compatibility with older software by providing 48-bit VAs @@ -780,7 +797,8 @@ config ARM64_VA_BITS default 39 if ARM64_VA_BITS_39 default 42 if ARM64_VA_BITS_42 default 47 if ARM64_VA_BITS_47 - default 48 if ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52 + default 48 if ARM64_VA_BITS_48 + default 52 if ARM64_VA_BITS_52 choice prompt "Physical address space size" @@ -1110,6 +1128,15 @@ config ARM64_SW_TTBR0_PAN zeroed area and reserved ASID. The user access routines restore the valid TTBR0_EL1 temporarily. +config ARM64_TAGGED_ADDR_ABI + bool "Enable the tagged user addresses syscall ABI" + default y + help + When this option is enabled, user applications can opt in to a + relaxed ABI via prctl() allowing tagged addresses to be passed + to system calls as pointer arguments. For details, see + Documentation/arm64/tagged-address-abi.txt. + menuconfig COMPAT bool "Kernel support for 32-bit EL0" depends on ARM64_4K_PAGES || EXPERT diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index dcbbd53b7f5a..2847b36f72ed 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -126,14 +126,6 @@ KBUILD_CFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) -# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) -# - (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) -# in 32-bit arithmetic -KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \ - (0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \ - + (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) \ - - (1 << (64 - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) )) ) - export TEXT_OFFSET GZFLAGS core-y += arch/arm64/ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 9f7395a1177f..b8cf7c85ffa2 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -339,6 +339,13 @@ alternative_endif .endm /* + * tcr_set_t1sz - update TCR.T1SZ + */ + .macro tcr_set_t1sz, valreg, t1sz + bfi \valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH + .endm + +/* * tcr_compute_pa_size - set TCR.(I)PS to the highest supported * ID_AA64MMFR0_EL1.PARange value * @@ -527,9 +534,13 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * In future this may be nop'ed out when dealing with 52-bit kernel VAs. * ttbr: Value of ttbr to set, modified. */ - .macro offset_ttbr1, ttbr -#ifdef CONFIG_ARM64_USER_VA_BITS_52 + .macro offset_ttbr1, ttbr, tmp +#ifdef CONFIG_ARM64_VA_BITS_52 + mrs_s \tmp, SYS_ID_AA64MMFR2_EL1 + and \tmp, \tmp, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + cbnz \tmp, .Lskipoffs_\@ orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET +.Lskipoffs_\@ : #endif .endm @@ -539,7 +550,7 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * to be nop'ed out when dealing with 52-bit kernel VAs. */ .macro restore_ttbr1, ttbr -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 bic \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET #endif .endm diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index c09d633c3109..86aabf1e0199 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -23,6 +23,8 @@ * @cpu_boot: Boots a cpu into the kernel. * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary * synchronisation. Called from the cpu being booted. + * @cpu_can_disable: Determines whether a CPU can be disabled based on + * mechanism-specific information. * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific * reason, which will cause the hot unplug to be aborted. Called * from the cpu to be killed. @@ -42,6 +44,7 @@ struct cpu_operations { int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); #ifdef CONFIG_HOTPLUG_CPU + bool (*cpu_can_disable)(unsigned int cpu); int (*cpu_disable)(unsigned int cpu); void (*cpu_die)(unsigned int cpu); int (*cpu_kill)(unsigned int cpu); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 76a144702586..b54d3a86c444 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -79,7 +79,7 @@ static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base) /* * On arm64, we have to ensure that the initrd ends up in the linear region, - * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is + * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is * guaranteed to cover the kernel Image. * * Since the EFI stub is part of the kernel Image, we can relax the @@ -90,7 +90,7 @@ static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base) static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, unsigned long image_addr) { - return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1)); + return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS_MIN - 1)); } #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index b52aacd2c526..b0dc4abc3589 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -18,11 +18,8 @@ * KASAN_SHADOW_START: beginning of the kernel virtual addresses. * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, * where N = (1 << KASAN_SHADOW_SCALE_SHIFT). - */ -#define KASAN_SHADOW_START (VA_START) -#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) - -/* + * + * KASAN_SHADOW_OFFSET: * This value is used to map an address to the corresponding shadow * address by the following formula: * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET @@ -33,8 +30,8 @@ * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT)) */ -#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ - (64 - KASAN_SHADOW_SCALE_SHIFT))) +#define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT))) +#define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual) void kasan_init(void); void kasan_copy_shadow(pgd_t *pgdir); diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index fb04f10a78ab..b61b50bf68b1 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -12,10 +12,10 @@ #include <linux/compiler.h> #include <linux/const.h> +#include <linux/sizes.h> #include <linux/types.h> #include <asm/bug.h> #include <asm/page-def.h> -#include <linux/sizes.h> /* * Size of the PCI I/O space. This must remain a power of two so that @@ -26,37 +26,50 @@ /* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array + * + * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE + * needs to cover the memory region from the beginning of the 52-bit + * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to + * keep a constant PAGE_OFFSET and "fallback" to using the higher end + * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)) +#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) \ + >> (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT)) /* - * PAGE_OFFSET - the virtual address of the start of the linear map (top - * (VA_BITS - 1)) - * KIMAGE_VADDR - the virtual address of the start of the kernel image + * PAGE_OFFSET - the virtual address of the start of the linear map, at the + * start of the TTBR1 address space. + * PAGE_END - the end of the linear map, where all other kernel mappings begin. + * KIMAGE_VADDR - the virtual address of the start of the kernel image. * VA_BITS - the maximum number of bits for virtual addresses. - * VA_START - the first kernel virtual address. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) -#define VA_START (UL(0xffffffffffffffff) - \ - (UL(1) << VA_BITS) + 1) -#define PAGE_OFFSET (UL(0xffffffffffffffff) - \ - (UL(1) << (VA_BITS - 1)) + 1) +#define _PAGE_OFFSET(va) (-(UL(1) << (va))) +#define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS)) #define KIMAGE_VADDR (MODULES_END) -#define BPF_JIT_REGION_START (VA_START + KASAN_SHADOW_SIZE) +#define BPF_JIT_REGION_START (KASAN_SHADOW_END) #define BPF_JIT_REGION_SIZE (SZ_128M) #define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (BPF_JIT_REGION_END) #define MODULES_VSIZE (SZ_128M) -#define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE) +#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M) #define PCI_IO_END (VMEMMAP_START - SZ_2M) #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) #define FIXADDR_TOP (PCI_IO_START - SZ_2M) -#define KERNEL_START _text -#define KERNEL_END _end +#if VA_BITS > 48 +#define VA_BITS_MIN (48) +#else +#define VA_BITS_MIN (VA_BITS) +#endif + +#define _PAGE_END(va) (-(UL(1) << ((va) - 1))) -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#define KERNEL_START _text +#define KERNEL_END _end + +#ifdef CONFIG_ARM64_VA_BITS_52 #define MAX_USER_VA_BITS 52 #else #define MAX_USER_VA_BITS VA_BITS @@ -68,12 +81,14 @@ * significantly, so double the (minimum) stack size when they are in use. */ #ifdef CONFIG_KASAN -#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \ + + KASAN_SHADOW_OFFSET) #define KASAN_THREAD_SHIFT 1 #else -#define KASAN_SHADOW_SIZE (0) #define KASAN_THREAD_SHIFT 0 -#endif +#define KASAN_SHADOW_END (_PAGE_END(VA_BITS_MIN)) +#endif /* CONFIG_KASAN */ #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) @@ -117,14 +132,14 @@ * 16 KB granule: 128 level 3 entries, with contiguous bit * 64 KB granule: 32 level 3 entries, with contiguous bit */ -#define SEGMENT_ALIGN SZ_2M +#define SEGMENT_ALIGN SZ_2M #else /* * 4 KB granule: 16 level 3 entries, with contiguous bit * 16 KB granule: 4 level 3 entries, without contiguous bit * 64 KB granule: 1 level 3 entry */ -#define SEGMENT_ALIGN SZ_64K +#define SEGMENT_ALIGN SZ_64K #endif /* @@ -157,10 +172,13 @@ #endif #ifndef __ASSEMBLY__ +extern u64 vabits_actual; +#define PAGE_END (_PAGE_END(vabits_actual)) #include <linux/bitops.h> #include <linux/mmdebug.h> +extern s64 physvirt_offset; 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; }) @@ -176,9 +194,6 @@ static inline unsigned long kaslr_offset(void) return kimage_vaddr - KIMAGE_VADDR; } -/* the actual size of a user virtual address */ -extern u64 vabits_user; - /* * Allow all memory at the discovery stage. We will clip it later. */ @@ -201,24 +216,24 @@ extern u64 vabits_user; * pass on to access_ok(), for instance. */ #define untagged_addr(addr) \ - ((__typeof__(addr))sign_extend64((u64)(addr), 55)) + ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #ifdef CONFIG_KASAN_SW_TAGS #define __tag_shifted(tag) ((u64)(tag) << 56) -#define __tag_set(addr, tag) (__typeof__(addr))( \ - ((u64)(addr) & ~__tag_shifted(0xff)) | __tag_shifted(tag)) #define __tag_reset(addr) untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else +#define __tag_shifted(tag) 0UL +#define __tag_reset(addr) (addr) +#define __tag_get(addr) 0 +#endif /* CONFIG_KASAN_SW_TAGS */ + static inline const void *__tag_set(const void *addr, u8 tag) { - return addr; + u64 __addr = (u64)addr & ~__tag_shifted(0xff); + return (const void *)(__addr | __tag_shifted(tag)); } -#define __tag_reset(addr) (addr) -#define __tag_get(addr) 0 -#endif - /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h @@ -227,19 +242,18 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts in the middle of the virtual adddress + * The linear kernel range starts at the bottom of the virtual address * space. Testing the top bit for the start of the region is a - * sufficient check. + * sufficient check and avoids having to worry about the tag. */ -#define __is_lm_address(addr) (!!((addr) & BIT(VA_BITS - 1))) +#define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) -#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) +#define __lm_to_phys(addr) (((addr) + physvirt_offset)) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ - phys_addr_t __x = (phys_addr_t)(x); \ - __is_lm_address(__x) ? __lm_to_phys(__x) : \ - __kimg_to_phys(__x); \ + phys_addr_t __x = (phys_addr_t)(__tag_reset(x)); \ + __is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x); \ }) #define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x)) @@ -250,9 +264,9 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #else #define __virt_to_phys(x) __virt_to_phys_nodebug(x) #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) -#endif +#endif /* CONFIG_DEBUG_VIRTUAL */ -#define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) +#define __phys_to_virt(x) ((unsigned long)((x) - physvirt_offset)) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* @@ -286,41 +300,38 @@ static inline void *phys_to_virt(phys_addr_t x) #define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) -#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) +#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) /* - * virt_to_page(k) convert a _valid_ virtual address to struct page * - * virt_addr_valid(k) indicates whether a virtual address is valid + * virt_to_page(x) convert a _valid_ virtual address to struct page * + * virt_addr_valid(x) indicates whether a virtual address is valid */ #define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) #if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL) -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +#define virt_to_page(x) pfn_to_page(virt_to_pfn(x)) #else -#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page)) -#define __page_to_voff(kaddr) (((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) - -#define page_to_virt(page) ({ \ - unsigned long __addr = \ - ((__page_to_voff(page)) | PAGE_OFFSET); \ - const void *__addr_tag = \ - __tag_set((void *)__addr, page_kasan_tag(page)); \ - ((void *)__addr_tag); \ +#define page_to_virt(x) ({ \ + __typeof__(x) __page = x; \ + u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\ + u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE); \ + (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) -#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START)) +#define virt_to_page(x) ({ \ + u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE; \ + u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \ + (struct page *)__addr; \ +}) +#endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */ -#define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \ - + PHYS_OFFSET) >> PAGE_SHIFT) -#endif -#endif +#define virt_addr_valid(addr) ({ \ + __typeof__(addr) __addr = addr; \ + __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ +}) -#define _virt_addr_is_linear(kaddr) \ - (__tag_reset((u64)(kaddr)) >= PAGE_OFFSET) -#define virt_addr_valid(kaddr) \ - (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) +#endif /* !ASSEMBLY */ /* * Given that the GIC architecture permits ITS implementations that can only be @@ -335,4 +346,4 @@ static inline void *phys_to_virt(phys_addr_t x) #include <asm-generic/memory_model.h> -#endif +#endif /* __ASM_MEMORY_H */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index fd6161336653..f217e3292919 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -126,7 +126,7 @@ extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); -extern void *fixmap_remap_fdt(phys_addr_t dt_phys); +extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); #define INIT_MM_CONTEXT(name) \ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 7ed0adb187a8..3827ff4040a3 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -63,7 +63,7 @@ extern u64 idmap_ptrs_per_pgd; static inline bool __cpu_uses_extended_idmap(void) { - if (IS_ENABLED(CONFIG_ARM64_USER_VA_BITS_52)) + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52)) return false; return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)); @@ -95,7 +95,7 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) isb(); } -#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS)) +#define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index db92950bb1a0..3df60f97da1f 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -304,7 +304,7 @@ #define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2) #endif -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 /* Must be at least 64-byte aligned to prevent corruption of the TTBR */ #define TTBR1_BADDR_4852_OFFSET (((UL(1) << (52 - PGDIR_SHIFT)) - \ (UL(1) << (48 - PGDIR_SHIFT))) * 8) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 5fdcfe237338..9a8f7e51c2b1 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -21,9 +21,7 @@ * and fixed mappings */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) - -#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) +#define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define FIRST_USER_ADDRESS 0UL @@ -35,6 +33,8 @@ #include <linux/mm_types.h> #include <linux/sched.h> +extern struct page *vmemmap; + extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); @@ -220,8 +220,10 @@ static inline void set_pte(pte_t *ptep, pte_t pte) * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ - if (pte_valid_not_user(pte)) + if (pte_valid_not_user(pte)) { dsb(ishst); + isb(); + } } extern void __sync_icache_dcache(pte_t pteval); @@ -481,8 +483,10 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) WRITE_ONCE(*pmdp, pmd); - if (pmd_valid(pmd)) + if (pmd_valid(pmd)) { dsb(ishst); + isb(); + } } static inline void pmd_clear(pmd_t *pmdp) @@ -540,8 +544,10 @@ static inline void set_pud(pud_t *pudp, pud_t pud) WRITE_ONCE(*pudp, pud); - if (pud_valid(pud)) + if (pud_valid(pud)) { dsb(ishst); + isb(); + } } static inline void pud_clear(pud_t *pudp) @@ -599,6 +605,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) WRITE_ONCE(*pgdp, pgd); dsb(ishst); + isb(); } static inline void pgd_clear(pgd_t *pgdp) @@ -856,8 +863,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) -#define kc_vaddr_to_offset(v) ((v) & ~VA_START) -#define kc_offset_to_vaddr(o) ((o) | VA_START) +#define kc_vaddr_to_offset(v) ((v) & ~PAGE_END) +#define kc_offset_to_vaddr(o) ((o) | PAGE_END) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index d328540cb85e..7a24bad1a58b 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -69,7 +69,7 @@ extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg); * The EL0 pointer bits used by a pointer authentication code. * This is dependent on TBI0 being enabled, or bits 63:56 would also apply. */ -#define ptrauth_user_pac_mask() GENMASK(54, vabits_user) +#define ptrauth_user_pac_mask() GENMASK(54, vabits_actual) /* Only valid for EL0 TTBR0 instruction pointers */ static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fa7a6f63308f..c67848c55009 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -41,8 +41,8 @@ * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ -#define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS) -#define TASK_SIZE_64 (UL(1) << vabits_user) +#define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) +#define TASK_SIZE_64 (UL(1) << vabits_actual) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) @@ -303,6 +303,14 @@ extern void __init minsigstksz_setup(void); /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) +#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI +/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ +long set_tagged_addr_ctrl(unsigned long arg); +long get_tagged_addr_ctrl(void); +#define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(arg) +#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl() +#endif + /* * For CONFIG_GCC_PLUGIN_STACKLEAK * diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 1dcf63a9ac1f..fbebb411ae20 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -301,6 +301,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->regs[0]; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->regs[0] = rc; +} + /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 1df45c7ffcf7..972d196c7714 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -212,6 +212,9 @@ #define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) +#define SYS_PAR_EL1_F BIT(1) +#define SYS_PAR_EL1_FST GENMASK(6, 1) + /*** Statistical Profiling Extension ***/ /* ID registers */ #define SYS_PMSIDR_EL1 sys_reg(3, 0, 9, 9, 7) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 2a408dd64f5c..f0cec4160136 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -77,6 +77,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_SVE 23 /* Scalable Vector Extension in use */ #define TIF_SVE_VL_INHERIT 24 /* Inherit sve_vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ +#define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 8af7a85f76bd..bc3949064725 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -251,6 +251,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) dsb(ishst); __tlbi(vaae1is, addr); dsb(ish); + isb(); } #endif diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 0524f2438649..a4d945db95a2 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -4,29 +4,6 @@ #include <linux/cpumask.h> -struct cpu_topology { - int thread_id; - int core_id; - int package_id; - int llc_id; - cpumask_t thread_sibling; - cpumask_t core_sibling; - cpumask_t llc_sibling; -}; - -extern struct cpu_topology cpu_topology[NR_CPUS]; - -#define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) -#define topology_core_id(cpu) (cpu_topology[cpu].core_id) -#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) -#define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) - -void init_cpu_topology(void); -void store_cpu_topology(unsigned int cpuid); -void remove_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(int cpu); - #ifdef CONFIG_NUMA struct pci_bus; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 5a1c32260c1f..097d6bfac0b7 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -62,6 +62,10 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si { unsigned long ret, limit = current_thread_info()->addr_limit; + if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) && + test_thread_flag(TIF_TAGGED_ADDR)) + addr = untagged_addr(addr); + __chk_user_ptr(addr); asm volatile( // A + B <= C + 1 for all A,B,C, in four easy steps: @@ -215,7 +219,8 @@ static inline void uaccess_enable_not_uao(void) /* * Sanitise a uaccess pointer such that it becomes NULL if above the - * current addr_limit. + * current addr_limit. In case the pointer is tagged (has the top byte set), + * untag the pointer before checking. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) @@ -223,10 +228,11 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) void __user *safe_ptr; asm volatile( - " bics xzr, %1, %2\n" + " bics xzr, %3, %2\n" " csel %0, %1, xzr, eq\n" : "=&r" (safe_ptr) - : "r" (ptr), "r" (current_thread_info()->addr_limit) + : "r" (ptr), "r" (current_thread_info()->addr_limit), + "r" (untagged_addr(ptr)) : "cc"); csdb(); diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index d1048173fd8a..e4d6af2fdec7 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -11,6 +11,7 @@ #include <linux/cpu_pm.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/psci.h> #include <asm/cpuidle.h> #include <asm/cpu_ops.h> @@ -46,17 +47,58 @@ int arm_cpuidle_suspend(int index) #define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags)) +static int psci_acpi_cpu_init_idle(unsigned int cpu) +{ + int i, count; + struct acpi_lpi_state *lpi; + struct acpi_processor *pr = per_cpu(processors, cpu); + + /* + * If the PSCI cpu_suspend function hook has not been initialized + * idle states must not be enabled, so bail out + */ + if (!psci_ops.cpu_suspend) + return -EOPNOTSUPP; + + if (unlikely(!pr || !pr->flags.has_lpi)) + return -EINVAL; + + count = pr->power.count - 1; + if (count <= 0) + return -ENODEV; + + for (i = 0; i < count; i++) { + u32 state; + + lpi = &pr->power.lpi_states[i + 1]; + /* + * Only bits[31:0] represent a PSCI power_state while + * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification + */ + state = lpi->address; + if (!psci_power_state_is_valid(state)) { + pr_warn("Invalid PSCI power state %#x\n", state); + return -EINVAL; + } + } + + return 0; +} + int acpi_processor_ffh_lpi_probe(unsigned int cpu) { - return arm_cpuidle_init(cpu); + return psci_acpi_cpu_init_idle(cpu); } int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) { + u32 state = lpi->address; + if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags)) - return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend, - lpi->index); + return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter, + lpi->index, state); else - return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index); + return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, + lpi->index, state); } #endif diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index cc23302e9d95..989b1944cb71 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -310,15 +310,15 @@ __create_page_tables: adrp x0, idmap_pg_dir adrp x3, __idmap_text_start // __pa(__idmap_text_start) -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 mrs_s x6, SYS_ID_AA64MMFR2_EL1 and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) mov x5, #52 cbnz x6, 1f #endif - mov x5, #VA_BITS + mov x5, #VA_BITS_MIN 1: - adr_l x6, vabits_user + adr_l x6, vabits_actual str x5, [x6] dmb sy dc ivac, x6 // Invalidate potentially stale cache line @@ -726,14 +726,22 @@ __secondary_switched: adr_l x0, secondary_data ldr x1, [x0, #CPU_BOOT_STACK] // get secondary_data.stack + cbz x1, __secondary_too_slow mov sp, x1 ldr x2, [x0, #CPU_BOOT_TASK] + cbz x2, __secondary_too_slow msr sp_el0, x2 mov x29, #0 mov x30, #0 b secondary_start_kernel ENDPROC(__secondary_switched) +__secondary_too_slow: + wfe + wfi + b __secondary_too_slow +ENDPROC(__secondary_too_slow) + /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. @@ -774,7 +782,7 @@ ENTRY(__enable_mmu) phys_to_ttbr x1, x1 phys_to_ttbr x2, x2 msr ttbr0_el1, x2 // load TTBR0 - offset_ttbr1 x1 + offset_ttbr1 x1, x3 msr ttbr1_el1, x1 // load TTBR1 isb msr sctlr_el1, x0 @@ -791,8 +799,8 @@ ENTRY(__enable_mmu) ENDPROC(__enable_mmu) ENTRY(__cpu_secondary_check52bitva) -#ifdef CONFIG_ARM64_USER_VA_BITS_52 - ldr_l x0, vabits_user +#ifdef CONFIG_ARM64_VA_BITS_52 + ldr_l x0, vabits_actual cmp x0, #52 b.ne 2f diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 2f4a2ce7264b..38bcd4d4e43b 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -22,14 +22,14 @@ * Even switching to our copied tables will cause a changed output address at * each stage of the walk. */ -.macro break_before_make_ttbr_switch zero_page, page_table, tmp +.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2 phys_to_ttbr \tmp, \zero_page msr ttbr1_el1, \tmp isb tlbi vmalle1 dsb nsh phys_to_ttbr \tmp, \page_table - offset_ttbr1 \tmp + offset_ttbr1 \tmp, \tmp2 msr ttbr1_el1, \tmp isb .endm @@ -70,7 +70,7 @@ ENTRY(swsusp_arch_suspend_exit) * We execute from ttbr0, change ttbr1 to our copied linear map tables * with a break-before-make via the zero page */ - break_before_make_ttbr_switch x5, x0, x6 + break_before_make_ttbr_switch x5, x0, x6, x8 mov x21, x1 mov x30, x2 @@ -101,7 +101,7 @@ ENTRY(swsusp_arch_suspend_exit) dsb ish /* wait for PoU cleaning to finish */ /* switch to the restored kernels page tables */ - break_before_make_ttbr_switch x25, x21, x6 + break_before_make_ttbr_switch x25, x21, x6, x8 ic ialluis dsb ish diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 9341fcc6e809..e0a7fce0e01c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -496,7 +496,7 @@ int swsusp_arch_resume(void) rc = -ENOMEM; goto out; } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END); if (rc) goto out; diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 708051655ad9..416f537bf614 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -62,9 +62,6 @@ out: return default_cmdline; } -extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, - pgprot_t prot); - /* * This routine will be executed with the kernel mapped at its default virtual * address, and if it returns successfully, the kernel will be remapped, and @@ -93,7 +90,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * attempt at mapping the FDT in setup_machine() */ early_fixmap_init(); - fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); + fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); if (!fdt) return 0; @@ -116,15 +113,15 @@ u64 __init kaslr_early_init(u64 dt_phys) /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the - * middle half of the VMALLOC area (VA_BITS - 2), and stay clear of + * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of * the lower and upper quarters to avoid colliding with other * allocations. * Even if we could randomize at page granularity for 16k and 64k pages, * let's always round to 2 MB so we don't interfere with the ability to * map using contiguous PTEs */ - mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1); - offset = BIT(VA_BITS - 3) + (seed & mask); + mask = ((1UL << (VA_BITS_MIN - 2)) - 1) & ~(SZ_2M - 1); + offset = BIT(VA_BITS_MIN - 3) + (seed & mask); /* use the top 16 bits to randomize the linear region */ memstart_offset_seed = seed >> 48; diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index ba78ee7ca990..7b08bf9499b6 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -27,6 +27,8 @@ #define FDT_PROP_INITRD_END "linux,initrd-end" #define FDT_PROP_BOOTARGS "bootargs" #define FDT_PROP_KASLR_SEED "kaslr-seed" +#define FDT_PROP_RNG_SEED "rng-seed" +#define RNG_SEED_SIZE 128 const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_image_ops, @@ -102,6 +104,19 @@ static int setup_dtb(struct kimage *image, FDT_PROP_KASLR_SEED); } + /* add rng-seed */ + if (rng_is_initialized()) { + u8 rng_seed[RNG_SEED_SIZE]; + get_random_bytes(rng_seed, RNG_SEED_SIZE); + ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed, + RNG_SEED_SIZE); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_RNG_SEED); + } + out: if (ret) return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL; @@ -110,7 +125,8 @@ out: } /* - * More space needed so that we can add initrd, bootargs and kaslr-seed. + * More space needed so that we can add initrd, bootargs, kaslr-seed, and + * rng-seed. */ #define DTB_EXTRA_SPACE 0x1000 diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 96e90e270042..a0b4f1bca491 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -19,6 +19,7 @@ #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> +#include <linux/smp.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -157,7 +158,6 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR_RESOLVE(m) #m #define ARMV8_EVENT_ATTR(name, config) \ PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ config, armv8pmu_events_sysfs_show) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index f674f28df663..03689c0beb34 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/stddef.h> +#include <linux/sysctl.h> #include <linux/unistd.h> #include <linux/user.h> #include <linux/delay.h> @@ -38,6 +39,7 @@ #include <trace/events/power.h> #include <linux/percpu.h> #include <linux/thread_info.h> +#include <linux/prctl.h> #include <asm/alternative.h> #include <asm/arch_gicv3.h> @@ -307,11 +309,18 @@ static void tls_thread_flush(void) } } +static void flush_tagged_addr_state(void) +{ + if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI)) + clear_thread_flag(TIF_TAGGED_ADDR); +} + void flush_thread(void) { fpsimd_flush_thread(); tls_thread_flush(); flush_ptrace_hw_breakpoint(current); + flush_tagged_addr_state(); } void release_thread(struct task_struct *dead_task) @@ -565,3 +574,70 @@ void arch_setup_new_exec(void) ptrauth_thread_init_user(current); } + +#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI +/* + * Control the relaxed ABI allowing tagged user addresses into the kernel. + */ +static unsigned int tagged_addr_disabled; + +long set_tagged_addr_ctrl(unsigned long arg) +{ + if (is_compat_task()) + return -EINVAL; + if (arg & ~PR_TAGGED_ADDR_ENABLE) + return -EINVAL; + + /* + * Do not allow the enabling of the tagged address ABI if globally + * disabled via sysctl abi.tagged_addr_disabled. + */ + if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled) + return -EINVAL; + + update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE); + + return 0; +} + +long get_tagged_addr_ctrl(void) +{ + if (is_compat_task()) + return -EINVAL; + + if (test_thread_flag(TIF_TAGGED_ADDR)) + return PR_TAGGED_ADDR_ENABLE; + + return 0; +} + +/* + * Global sysctl to disable the tagged user addresses support. This control + * only prevents the tagged address ABI enabling via prctl() and does not + * disable it for tasks that already opted in to the relaxed ABI. + */ +static int zero; +static int one = 1; + +static struct ctl_table tagged_addr_sysctl_table[] = { + { + .procname = "tagged_addr_disabled", + .mode = 0644, + .data = &tagged_addr_disabled, + .maxlen = sizeof(int), + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; + +static int __init tagged_addr_init(void) +{ + if (!register_sysctl("abi", tagged_addr_sysctl_table)) + return -EINVAL; + return 0; +} + +core_initcall(tagged_addr_init); +#endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */ diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 85ee7d07889e..c9f72b2665f1 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -46,6 +46,11 @@ static int cpu_psci_cpu_boot(unsigned int cpu) } #ifdef CONFIG_HOTPLUG_CPU +static bool cpu_psci_cpu_can_disable(unsigned int cpu) +{ + return !psci_tos_resident_on(cpu); +} + static int cpu_psci_cpu_disable(unsigned int cpu) { /* Fail early if we don't have CPU_OFF support */ @@ -105,14 +110,11 @@ static int cpu_psci_cpu_kill(unsigned int cpu) const struct cpu_operations cpu_psci_ops = { .name = "psci", -#ifdef CONFIG_CPU_IDLE - .cpu_init_idle = psci_cpu_init_idle, - .cpu_suspend = psci_cpu_suspend_enter, -#endif .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, .cpu_boot = cpu_psci_cpu_boot, #ifdef CONFIG_HOTPLUG_CPU + .cpu_can_disable = cpu_psci_cpu_can_disable, .cpu_disable = cpu_psci_cpu_disable, .cpu_die = cpu_psci_cpu_die, .cpu_kill = cpu_psci_cpu_kill, diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 9c4bad7d7131..56f664561754 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -170,9 +170,13 @@ static void __init smp_build_mpidr_hash(void) static void __init setup_machine_fdt(phys_addr_t dt_phys) { - void *dt_virt = fixmap_remap_fdt(dt_phys); + int size; + void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); const char *name; + if (dt_virt) + memblock_reserve(dt_phys, size); + if (!dt_virt || !early_init_dt_scan(dt_virt)) { pr_crit("\n" "Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n" @@ -184,6 +188,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) cpu_relax(); } + /* Early fixups are done, map the FDT as read-only now */ + fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); + name = of_flat_dt_get_machine_name(); if (!name) return; @@ -357,6 +364,15 @@ void __init setup_arch(char **cmdline_p) } } +static inline bool cpu_can_disable(unsigned int cpu) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable) + return cpu_ops[cpu]->cpu_can_disable(cpu); +#endif + return false; +} + static int __init topology_init(void) { int i; @@ -366,7 +382,7 @@ static int __init topology_init(void) for_each_possible_cpu(i) { struct cpu *cpu = &per_cpu(cpu_data.cpu, i); - cpu->hotpluggable = 1; + cpu->hotpluggable = cpu_can_disable(i); register_cpu(cpu, i); } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 018a33e01b0e..dc9fe879c279 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -123,7 +123,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * time out. */ wait_for_completion_timeout(&cpu_running, - msecs_to_jiffies(1000)); + msecs_to_jiffies(5000)); if (!cpu_online(cpu)) { pr_crit("CPU%u: failed to come online\n", cpu); @@ -136,6 +136,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) secondary_data.task = NULL; secondary_data.stack = NULL; + __flush_dcache_area(&secondary_data, sizeof(secondary_data)); status = READ_ONCE(secondary_data.status); if (ret && status) { @@ -146,6 +147,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) default: pr_err("CPU%u: failed in unknown state : 0x%lx\n", cpu, status); + cpus_stuck_in_kernel++; break; case CPU_KILL_ME: if (!op_cpu_kill(cpu)) { diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 0825c4a856e3..fa9528dfd0ce 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -14,250 +14,13 @@ #include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/cacheinfo.h> -#include <linux/cpu.h> -#include <linux/cpumask.h> #include <linux/init.h> #include <linux/percpu.h> -#include <linux/node.h> -#include <linux/nodemask.h> -#include <linux/of.h> -#include <linux/sched.h> -#include <linux/sched/topology.h> -#include <linux/slab.h> -#include <linux/smp.h> -#include <linux/string.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/topology.h> -static int __init get_cpu_for_node(struct device_node *node) -{ - struct device_node *cpu_node; - int cpu; - - cpu_node = of_parse_phandle(node, "cpu", 0); - if (!cpu_node) - return -1; - - cpu = of_cpu_node_to_id(cpu_node); - if (cpu >= 0) - topology_parse_cpu_capacity(cpu_node, cpu); - else - pr_crit("Unable to find CPU node for %pOF\n", cpu_node); - - of_node_put(cpu_node); - return cpu; -} - -static int __init parse_core(struct device_node *core, int package_id, - int core_id) -{ - char name[10]; - bool leaf = true; - int i = 0; - int cpu; - struct device_node *t; - - do { - snprintf(name, sizeof(name), "thread%d", i); - t = of_get_child_by_name(core, name); - if (t) { - leaf = false; - cpu = get_cpu_for_node(t); - if (cpu >= 0) { - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - cpu_topology[cpu].thread_id = i; - } else { - pr_err("%pOF: Can't get CPU for thread\n", - t); - of_node_put(t); - return -EINVAL; - } - of_node_put(t); - } - i++; - } while (t); - - cpu = get_cpu_for_node(core); - if (cpu >= 0) { - if (!leaf) { - pr_err("%pOF: Core has both threads and CPU\n", - core); - return -EINVAL; - } - - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - } else if (leaf) { - pr_err("%pOF: Can't get CPU for leaf core\n", core); - return -EINVAL; - } - - return 0; -} - -static int __init parse_cluster(struct device_node *cluster, int depth) -{ - char name[10]; - bool leaf = true; - bool has_cores = false; - struct device_node *c; - static int package_id __initdata; - int core_id = 0; - int i, ret; - - /* - * First check for child clusters; we currently ignore any - * information about the nesting of clusters and present the - * scheduler with a flat list of them. - */ - i = 0; - do { - snprintf(name, sizeof(name), "cluster%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - leaf = false; - ret = parse_cluster(c, depth + 1); - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - /* Now check for cores */ - i = 0; - do { - snprintf(name, sizeof(name), "core%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - has_cores = true; - - if (depth == 0) { - pr_err("%pOF: cpu-map children should be clusters\n", - c); - of_node_put(c); - return -EINVAL; - } - - if (leaf) { - ret = parse_core(c, package_id, core_id++); - } else { - pr_err("%pOF: Non-leaf cluster with core %s\n", - cluster, name); - ret = -EINVAL; - } - - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - if (leaf && !has_cores) - pr_warn("%pOF: empty cluster\n", cluster); - - if (leaf) - package_id++; - - return 0; -} - -static int __init parse_dt_topology(void) -{ - struct device_node *cn, *map; - int ret = 0; - int cpu; - - cn = of_find_node_by_path("/cpus"); - if (!cn) { - pr_err("No CPU information found in DT\n"); - return 0; - } - - /* - * When topology is provided cpu-map is essentially a root - * cluster with restricted subnodes. - */ - map = of_get_child_by_name(cn, "cpu-map"); - if (!map) - goto out; - - ret = parse_cluster(map, 0); - if (ret != 0) - goto out_map; - - topology_normalize_cpu_scale(); - - /* - * Check that all cores are in the topology; the SMP code will - * only mark cores described in the DT as possible. - */ - for_each_possible_cpu(cpu) - if (cpu_topology[cpu].package_id == -1) - ret = -EINVAL; - -out_map: - of_node_put(map); -out: - of_node_put(cn); - return ret; -} - -/* - * cpu topology table - */ -struct cpu_topology cpu_topology[NR_CPUS]; -EXPORT_SYMBOL_GPL(cpu_topology); - -const struct cpumask *cpu_coregroup_mask(int cpu) -{ - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); - - /* Find the smaller of NUMA, core or LLC siblings */ - if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { - /* not numa in package, lets use the package siblings */ - core_mask = &cpu_topology[cpu].core_sibling; - } - if (cpu_topology[cpu].llc_id != -1) { - if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) - core_mask = &cpu_topology[cpu].llc_sibling; - } - - return core_mask; -} - -static void update_siblings_masks(unsigned int cpuid) -{ - struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; - - /* update core and thread sibling masks */ - for_each_online_cpu(cpu) { - cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->llc_id == cpu_topo->llc_id) { - cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); - cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); - } - - if (cpuid_topo->package_id != cpu_topo->package_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id != cpu_topo->core_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); - } -} - void store_cpu_topology(unsigned int cpuid) { struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; @@ -296,60 +59,31 @@ topology_populated: update_siblings_masks(cpuid); } -static void clear_cpu_topology(int cpu) -{ - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpumask_clear(&cpu_topo->llc_sibling); - cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); - - cpumask_clear(&cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); -} - -static void __init reset_cpu_topology(void) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpu_topo->thread_id = -1; - cpu_topo->core_id = 0; - cpu_topo->package_id = -1; - cpu_topo->llc_id = -1; - - clear_cpu_topology(cpu); - } -} - -void remove_cpu_topology(unsigned int cpu) +#ifdef CONFIG_ACPI +static bool __init acpi_cpu_is_threaded(int cpu) { - int sibling; + int is_threaded = acpi_pptt_cpu_is_thread(cpu); - for_each_cpu(sibling, topology_core_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); - for_each_cpu(sibling, topology_llc_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); + /* + * if the PPTT doesn't have thread information, assume a homogeneous + * machine and return the current CPU's thread state. + */ + if (is_threaded < 0) + is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK; - clear_cpu_topology(cpu); + return !!is_threaded; } -#ifdef CONFIG_ACPI /* * Propagate the topology information of the processor_topology_node tree to the * cpu_topology array. */ -static int __init parse_acpi_topology(void) +int __init parse_acpi_topology(void) { - bool is_threaded; int cpu, topology_id; - is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK; + if (acpi_disabled) + return 0; for_each_possible_cpu(cpu) { int i, cache_id; @@ -358,7 +92,7 @@ static int __init parse_acpi_topology(void) if (topology_id < 0) return topology_id; - if (is_threaded) { + if (acpi_cpu_is_threaded(cpu)) { cpu_topology[cpu].thread_id = topology_id; topology_id = find_acpi_cpu_topology(cpu, 1); cpu_topology[cpu].core_id = topology_id; @@ -384,24 +118,6 @@ static int __init parse_acpi_topology(void) return 0; } - -#else -static inline int __init parse_acpi_topology(void) -{ - return -EINVAL; -} #endif -void __init init_cpu_topology(void) -{ - reset_cpu_topology(); - /* - * Discard anything that was parsed if we hit an error so we - * don't use partial information. - */ - if (!acpi_disabled && parse_acpi_topology()) - reset_cpu_topology(); - else if (of_have_populated_dt() && parse_dt_topology()) - reset_cpu_topology(); -} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index adaf266d8de8..bd978ad71936 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -264,7 +264,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) tmp = read_sysreg(par_el1); write_sysreg(par, par_el1); - if (unlikely(tmp & 1)) + if (unlikely(tmp & SYS_PAR_EL1_F)) return false; /* Translation failed, back to guest */ /* Convert PAR to HPFAR format */ diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index acd8084f1f2c..2cf7d4b606c3 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -29,25 +29,25 @@ static void compute_layout(void) int kva_msb; /* Where is my RAM region? */ - hyp_va_msb = idmap_addr & BIT(VA_BITS - 1); - hyp_va_msb ^= BIT(VA_BITS - 1); + hyp_va_msb = idmap_addr & BIT(vabits_actual - 1); + hyp_va_msb ^= BIT(vabits_actual - 1); kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^ (u64)(high_memory - 1)); - if (kva_msb == (VA_BITS - 1)) { + if (kva_msb == (vabits_actual - 1)) { /* * No space in the address, let's compute the mask so - * that it covers (VA_BITS - 1) bits, and the region + * that it covers (vabits_actual - 1) bits, and the region * bit. The tag stays set to zero. */ - va_mask = BIT(VA_BITS - 1) - 1; + va_mask = BIT(vabits_actual - 1) - 1; va_mask |= hyp_va_msb; } else { /* * We do have some free bits to insert a random tag. * Hyp VAs are now created from kernel linear map VAs - * using the following formula (with V == VA_BITS): + * using the following formula (with V == vabits_actual): * * 63 ... V | V-1 | V-2 .. tag_lsb | tag_lsb - 1 .. 0 * --------------------------------------------------------- @@ -55,7 +55,7 @@ static void compute_layout(void) */ tag_lsb = kva_msb; va_mask = GENMASK_ULL(tag_lsb - 1, 0); - tag_val = get_random_long() & GENMASK_ULL(VA_BITS - 2, tag_lsb); + tag_val = get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); tag_val |= hyp_va_msb; tag_val >>= tag_lsb; } diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 33c2a4abda04..f182ccb0438e 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -33,3 +33,5 @@ UBSAN_SANITIZE_atomic_ll_sc.o := n lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o obj-$(CONFIG_CRC32) += crc32.o + +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/arm64/lib/error-inject.c b/arch/arm64/lib/error-inject.c new file mode 100644 index 000000000000..ed15021da3ed --- /dev/null +++ b/arch/arm64/lib/error-inject.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/error-injection.h> +#include <linux/kprobes.h> + +void override_function_with_return(struct pt_regs *regs) +{ + /* + * 'regs' represents the state on entry of a predefined function in + * the kernel/module and which is captured on a kprobe. + * + * When kprobe returns back from exception it will override the end + * of probed function and directly return to the predefined + * function's caller. + */ + instruction_pointer_set(regs, procedure_link_pointer(regs)); +} +NOKPROBE_SYMBOL(override_function_with_return); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 82b3a7fdb4a6..93f9f77582ae 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -25,9 +25,20 @@ #include <asm/pgtable-hwdef.h> #include <asm/ptdump.h> -static const struct addr_marker address_markers[] = { + +enum address_markers_idx { + PAGE_OFFSET_NR = 0, + PAGE_END_NR, #ifdef CONFIG_KASAN - { KASAN_SHADOW_START, "Kasan shadow start" }, + KASAN_START_NR, +#endif +}; + +static struct addr_marker address_markers[] = { + { PAGE_OFFSET, "Linear Mapping start" }, + { 0 /* PAGE_END */, "Linear Mapping end" }, +#ifdef CONFIG_KASAN + { 0 /* KASAN_SHADOW_START */, "Kasan shadow start" }, { KASAN_SHADOW_END, "Kasan shadow end" }, #endif { MODULES_VADDR, "Modules start" }, @@ -42,7 +53,6 @@ static const struct addr_marker address_markers[] = { { VMEMMAP_START, "vmemmap start" }, { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" }, #endif - { PAGE_OFFSET, "Linear mapping" }, { -1, NULL }, }; @@ -376,7 +386,7 @@ static void ptdump_initialize(void) static struct ptdump_info kernel_ptdump_info = { .mm = &init_mm, .markers = address_markers, - .base_addr = VA_START, + .base_addr = PAGE_OFFSET, }; void ptdump_check_wx(void) @@ -390,7 +400,7 @@ void ptdump_check_wx(void) .check_wx = true, }; - walk_pgd(&st, &init_mm, VA_START); + walk_pgd(&st, &init_mm, PAGE_OFFSET); note_page(&st, 0, 0, 0); if (st.wx_pages || st.uxn_pages) pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n", @@ -401,6 +411,10 @@ void ptdump_check_wx(void) static int ptdump_init(void) { + address_markers[PAGE_END_NR].start_address = PAGE_END; +#ifdef CONFIG_KASAN + address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START; +#endif ptdump_initialize(); ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); return 0; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index ad4980a27edb..115d7a0e4b08 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -8,6 +8,7 @@ */ #include <linux/acpi.h> +#include <linux/bitfield.h> #include <linux/extable.h> #include <linux/signal.h> #include <linux/mm.h> @@ -109,7 +110,7 @@ static inline bool is_ttbr0_addr(unsigned long addr) static inline bool is_ttbr1_addr(unsigned long addr) { /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ - return arch_kasan_reset_tag(addr) >= VA_START; + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; } /* @@ -138,10 +139,9 @@ static void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp=%016lx\n", + pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - mm == &init_mm ? VA_BITS : (int)vabits_user, - (unsigned long)virt_to_phys(mm->pgd)); + vabits_actual, (unsigned long)virt_to_phys(mm->pgd)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -242,6 +242,34 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, return false; } +static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, + unsigned int esr, + struct pt_regs *regs) +{ + unsigned long flags; + u64 par, dfsc; + + if (ESR_ELx_EC(esr) != ESR_ELx_EC_DABT_CUR || + (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT) + return false; + + local_irq_save(flags); + asm volatile("at s1e1r, %0" :: "r" (addr)); + isb(); + par = read_sysreg(par_el1); + local_irq_restore(flags); + + if (!(par & SYS_PAR_EL1_F)) + return false; + + /* + * If we got a different type of fault from the AT instruction, + * treat the translation fault as spurious. + */ + dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par); + return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; +} + static void die_kernel_fault(const char *msg, unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -270,6 +298,10 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; + if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), + "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) + return; + if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index b1ee6cb4b17f..45c00a54909c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -50,6 +50,12 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); +s64 physvirt_offset __ro_after_init; +EXPORT_SYMBOL(physvirt_offset); + +struct page *vmemmap __ro_after_init; +EXPORT_SYMBOL(vmemmap); + phys_addr_t arm64_dma_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE @@ -301,7 +307,7 @@ static void __init fdt_enforce_memory_region(void) void __init arm64_memblock_init(void) { - const s64 linear_region_size = -(s64)PAGE_OFFSET; + const s64 linear_region_size = BIT(vabits_actual - 1); /* Handle linux,usable-memory-range property */ fdt_enforce_memory_region(); @@ -310,18 +316,25 @@ void __init arm64_memblock_init(void) memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX); /* - * Ensure that the linear region takes up exactly half of the kernel - * virtual address space. This way, we can distinguish a linear address - * from a kernel/module/vmalloc address by testing a single bit. - */ - BUILD_BUG_ON(linear_region_size != BIT(VA_BITS - 1)); - - /* * Select a suitable value for the base of physical memory. */ memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); + physvirt_offset = PHYS_OFFSET - PAGE_OFFSET; + + vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)); + + /* + * If we are running with a 52-bit kernel VA config on a system that + * does not support it, we have to offset our vmemmap and physvirt_offset + * s.t. we avoid the 52-bit portion of the direct linear map + */ + if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) { + vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT; + physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48); + } + /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6cf97b904ebb..f87a32484ea8 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -156,7 +156,8 @@ asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true); @@ -225,10 +226,10 @@ void __init kasan_init(void) kasan_map_populate(kimg_shadow_start, kimg_shadow_end, early_pfn_to_nid(virt_to_pfn(lm_alias(_text)))); - kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)mod_shadow_start); + kasan_populate_early_shadow(kasan_mem_to_shadow((void *)PAGE_END), + (void *)mod_shadow_start); kasan_populate_early_shadow((void *)kimg_shadow_end, - kasan_mem_to_shadow((void *)PAGE_OFFSET)); + (void *)KASAN_SHADOW_END); if (kimg_shadow_start > mod_shadow_end) kasan_populate_early_shadow((void *)mod_shadow_end, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 750a69dde39b..53dc6f24cfb7 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -40,8 +40,9 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS); u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; -u64 vabits_user __ro_after_init; -EXPORT_SYMBOL(vabits_user); + +u64 __section(".mmuoff.data.write") vabits_actual; +EXPORT_SYMBOL(vabits_actual); u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -398,7 +399,7 @@ static phys_addr_t pgd_pgtable_alloc(int shift) static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if (virt < VMALLOC_START) { + if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -425,7 +426,7 @@ void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, static void update_mapping_prot(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { - if (virt < VMALLOC_START) { + if ((virt >= PAGE_END) && (virt < VMALLOC_START)) { pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n", &phys, virt); return; @@ -646,6 +647,8 @@ static void __init map_kernel(pgd_t *pgdp) set_pgd(pgd_offset_raw(pgdp, FIXADDR_START), READ_ONCE(*pgd_offset_k(FIXADDR_START))); } else if (CONFIG_PGTABLE_LEVELS > 3) { + pgd_t *bm_pgdp; + pud_t *bm_pudp; /* * The fixmap shares its top level pgd entry with the kernel * mapping. This can really only occur when we are running @@ -653,9 +656,9 @@ static void __init map_kernel(pgd_t *pgdp) * entry instead. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - pud_populate(&init_mm, - pud_set_fixmap_offset(pgdp, FIXADDR_START), - lm_alias(bm_pmd)); + bm_pgdp = pgd_offset_raw(pgdp, FIXADDR_START); + bm_pudp = pud_set_fixmap_offset(bm_pgdp, FIXADDR_START); + pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd)); pud_clear_fixmap(); } else { BUG(); @@ -876,7 +879,7 @@ void __set_fixmap(enum fixed_addresses idx, } } -void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) +void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); int offset; @@ -929,19 +932,6 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } -void *__init fixmap_remap_fdt(phys_addr_t dt_phys) -{ - void *dt_virt; - int size; - - dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); - if (!dt_virt) - return NULL; - - memblock_reserve(dt_phys, size); - return dt_virt; -} - int __init arch_ioremap_p4d_supported(void) { return 0; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 28a8f7b87ff0..a1e0592d1fbc 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -168,7 +168,7 @@ ENDPROC(cpu_do_switch_mm) .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 adrp \tmp1, empty_zero_page phys_to_ttbr \tmp2, \tmp1 - offset_ttbr1 \tmp2 + offset_ttbr1 \tmp2, \tmp1 msr ttbr1_el1, \tmp2 isb tlbi vmalle1 @@ -187,7 +187,7 @@ ENTRY(idmap_cpu_replace_ttbr1) __idmap_cpu_set_reserved_ttbr1 x1, x3 - offset_ttbr1 x0 + offset_ttbr1 x0, x3 msr ttbr1_el1, x0 isb @@ -371,7 +371,7 @@ __idmap_kpti_secondary: cbnz w18, 1b /* All done, act like nothing happened */ - offset_ttbr1 swapper_ttb + offset_ttbr1 swapper_ttb, x18 msr ttbr1_el1, swapper_ttb isb ret @@ -447,10 +447,11 @@ ENTRY(__cpu_setup) TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS tcr_clear_errata_bits x10, x9, x5 -#ifdef CONFIG_ARM64_USER_VA_BITS_52 - ldr_l x9, vabits_user +#ifdef CONFIG_ARM64_VA_BITS_52 + ldr_l x9, vabits_actual sub x9, xzr, x9 add x9, x9, #64 + tcr_set_t1sz x10, x9 #else ldr_l x9, idmap_t0sz #endif |