diff options
Diffstat (limited to 'arch/x86/lib')
-rw-r--r-- | arch/x86/lib/Makefile | 5 | ||||
-rw-r--r-- | arch/x86/lib/bhi.S | 147 | ||||
-rw-r--r-- | arch/x86/lib/clear_page_64.S | 9 | ||||
-rw-r--r-- | arch/x86/lib/cmpxchg8b_emu.S | 2 | ||||
-rw-r--r-- | arch/x86/lib/copy_page_64.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/copy_user_64.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/copy_user_uncached_64.S | 2 | ||||
-rw-r--r-- | arch/x86/lib/delay.c | 2 | ||||
-rw-r--r-- | arch/x86/lib/getuser.S | 16 | ||||
-rw-r--r-- | arch/x86/lib/hweight.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/memmove_64.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/memset_64.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/msr-reg.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/msr.c | 2 | ||||
-rw-r--r-- | arch/x86/lib/putuser.S | 9 | ||||
-rw-r--r-- | arch/x86/lib/retpoline.S | 3 | ||||
-rw-r--r-- | arch/x86/lib/usercopy_64.c | 2 |
17 files changed, 199 insertions, 18 deletions
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 8a59c61624c2..64ccecedc9f8 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -56,7 +56,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += string_32.o lib-y += memmove_32.o lib-y += cmpxchg8b_emu.o -ifneq ($(CONFIG_X86_CMPXCHG64),y) +ifneq ($(CONFIG_X86_CX8),y) lib-y += atomic64_386_32.o endif else @@ -66,5 +66,6 @@ endif lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o lib-y += copy_user_64.o copy_user_uncached_64.o - lib-y += cmpxchg16b_emu.o + lib-y += cmpxchg16b_emu.o + lib-y += bhi.o endif diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S new file mode 100644 index 000000000000..58891681261b --- /dev/null +++ b/arch/x86/lib/bhi.S @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/linkage.h> +#include <asm/unwind_hints.h> +#include <asm/nospec-branch.h> + +/* + * Notably, the FineIBT preamble calling these will have ZF set and r10 zero. + * + * The very last element is in fact larger than 32 bytes, but since its the + * last element, this does not matter, + * + * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they + * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently + * big alignment holes for this to not stagger the array. + */ + +.pushsection .noinstr.text, "ax" + + .align 32 +SYM_CODE_START(__bhi_args) + +#ifdef CONFIG_FINEIBT_BHI + + .align 32 +SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_1 + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_1 + cmovne %r10, %rdi + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 8 + ANNOTATE_REACHABLE +.Lud_1: ud2 + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_1 + cmovne %r10, %rdi + cmovne %r10, %rsi + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_1 + cmovne %r10, %rdi + cmovne %r10, %rsi + cmovne %r10, %rdx + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_2 + cmovne %r10, %rdi + cmovne %r10, %rsi + cmovne %r10, %rdx + cmovne %r10, %rcx + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_2 + cmovne %r10, %rdi + cmovne %r10, %rsi + cmovne %r10, %rdx + cmovne %r10, %rcx + cmovne %r10, %r8 + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 8 + ANNOTATE_REACHABLE +.Lud_2: ud2 + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_2 + cmovne %r10, %rdi + cmovne %r10, %rsi + cmovne %r10, %rdx + cmovne %r10, %rcx + cmovne %r10, %r8 + cmovne %r10, %r9 + ANNOTATE_UNRET_SAFE + ret + int3 + + .align 32 +SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + jne .Lud_2 + cmovne %r10, %rdi + cmovne %r10, %rsi + cmovne %r10, %rdx + cmovne %r10, %rcx + cmovne %r10, %r8 + cmovne %r10, %r9 + cmovne %r10, %rsp + ANNOTATE_UNRET_SAFE + ret + int3 + +#endif /* CONFIG_FINEIBT_BHI */ + + .align 32 +SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL) + ANNOTATE_NOENDBR + nop /* Work around toolchain+objtool quirk */ +SYM_CODE_END(__bhi_args) + +.popsection diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 2760a15fbc00..a508e4a8c66a 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> +#include <linux/objtool.h> #include <asm/asm.h> /* @@ -14,7 +16,7 @@ * Zero a page. * %rdi - page */ -SYM_FUNC_START(clear_page_rep) +SYM_TYPED_FUNC_START(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq @@ -22,7 +24,7 @@ SYM_FUNC_START(clear_page_rep) SYM_FUNC_END(clear_page_rep) EXPORT_SYMBOL_GPL(clear_page_rep) -SYM_FUNC_START(clear_page_orig) +SYM_TYPED_FUNC_START(clear_page_orig) xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -44,7 +46,7 @@ SYM_FUNC_START(clear_page_orig) SYM_FUNC_END(clear_page_orig) EXPORT_SYMBOL_GPL(clear_page_orig) -SYM_FUNC_START(clear_page_erms) +SYM_TYPED_FUNC_START(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb @@ -63,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms) * rcx: uncleared bytes or 0 if successful. */ SYM_FUNC_START(rep_stos_alternative) + ANNOTATE_NOENDBR cmpq $64,%rcx jae .Lunrolled diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 1c96be769adc..d4bb24347ff8 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -7,7 +7,7 @@ .text -#ifndef CONFIG_X86_CMPXCHG64 +#ifndef CONFIG_X86_CX8 /* * Emulate 'cmpxchg8b (%esi)' on UP diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index d6ae793d08fa..d8e87fedc20d 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -3,6 +3,7 @@ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> @@ -13,7 +14,7 @@ * prefetch distance based on SMP/UP. */ ALIGN -SYM_FUNC_START(copy_page) +SYM_TYPED_FUNC_START(copy_page) ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index fc9fb5d06174..aa8c341b2441 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -8,6 +8,8 @@ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> +#include <linux/objtool.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> #include <asm/asm.h> @@ -30,6 +32,7 @@ * it simpler for us, we can clobber rsi/rdi and rax freely. */ SYM_FUNC_START(rep_movs_alternative) + ANNOTATE_NOENDBR cmpq $64,%rcx jae .Llarge diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S index 2918e36eece2..18350b343c2a 100644 --- a/arch/x86/lib/copy_user_uncached_64.S +++ b/arch/x86/lib/copy_user_uncached_64.S @@ -5,6 +5,7 @@ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/asm.h> /* @@ -27,6 +28,7 @@ * rax uncopied bytes or 0 if successful. */ SYM_FUNC_START(__copy_user_nocache) + ANNOTATE_NOENDBR /* If destination is not 7-byte aligned, we'll have to align it */ testb $7,%dil jne .Lalign diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 23f81ca3f06b..e86eda2c0b04 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -131,7 +131,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles) * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu * variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 89ecd57c9d42..9d5654b8a72a 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -28,22 +28,20 @@ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/page_types.h> #include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/runtime-const.h> #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC .macro check_range size:req .if IS_ENABLED(CONFIG_X86_64) - movq $0x0123456789abcdef,%rdx - 1: - .pushsection runtime_ptr_USER_PTR_MAX,"a" - .long 1b - 8 - . - .popsection + RUNTIME_CONST_PTR USER_PTR_MAX, rdx cmp %rdx, %rax cmova %rdx, %rax .else @@ -62,6 +60,7 @@ .text SYM_FUNC_START(__get_user_1) + ANNOTATE_NOENDBR check_range size=1 ASM_STAC UACCESS movzbl (%_ASM_AX),%edx @@ -72,6 +71,7 @@ SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1) SYM_FUNC_START(__get_user_2) + ANNOTATE_NOENDBR check_range size=2 ASM_STAC UACCESS movzwl (%_ASM_AX),%edx @@ -82,6 +82,7 @@ SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2) SYM_FUNC_START(__get_user_4) + ANNOTATE_NOENDBR check_range size=4 ASM_STAC UACCESS movl (%_ASM_AX),%edx @@ -92,6 +93,7 @@ SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4) SYM_FUNC_START(__get_user_8) + ANNOTATE_NOENDBR #ifndef CONFIG_X86_64 xor %ecx,%ecx #endif @@ -111,6 +113,7 @@ EXPORT_SYMBOL(__get_user_8) /* .. and the same for __get_user, just without the range checks */ SYM_FUNC_START(__get_user_nocheck_1) + ANNOTATE_NOENDBR ASM_STAC ASM_BARRIER_NOSPEC UACCESS movzbl (%_ASM_AX),%edx @@ -121,6 +124,7 @@ SYM_FUNC_END(__get_user_nocheck_1) EXPORT_SYMBOL(__get_user_nocheck_1) SYM_FUNC_START(__get_user_nocheck_2) + ANNOTATE_NOENDBR ASM_STAC ASM_BARRIER_NOSPEC UACCESS movzwl (%_ASM_AX),%edx @@ -131,6 +135,7 @@ SYM_FUNC_END(__get_user_nocheck_2) EXPORT_SYMBOL(__get_user_nocheck_2) SYM_FUNC_START(__get_user_nocheck_4) + ANNOTATE_NOENDBR ASM_STAC ASM_BARRIER_NOSPEC UACCESS movl (%_ASM_AX),%edx @@ -141,6 +146,7 @@ SYM_FUNC_END(__get_user_nocheck_4) EXPORT_SYMBOL(__get_user_nocheck_4) SYM_FUNC_START(__get_user_nocheck_8) + ANNOTATE_NOENDBR ASM_STAC ASM_BARRIER_NOSPEC #ifdef CONFIG_X86_64 diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 774bdf3e6f0a..edbeb3ecad38 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/asm.h> @@ -9,6 +10,7 @@ * %rdi: w */ SYM_FUNC_START(__sw_hweight32) + ANNOTATE_NOENDBR #ifdef CONFIG_X86_64 movl %edi, %eax # w @@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32) */ #ifdef CONFIG_X86_64 SYM_FUNC_START(__sw_hweight64) + ANNOTATE_NOENDBR pushq %rdi pushq %rdx diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 1b60ae81ecd8..aa1f92ee6b2e 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -8,6 +8,7 @@ */ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> @@ -26,7 +27,7 @@ * Output: * rax: dest */ -SYM_FUNC_START(__memmove) +SYM_TYPED_FUNC_START(__memmove) mov %rdi, %rax diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 0199d56cb479..d66b710d628f 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -3,6 +3,7 @@ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> @@ -28,7 +29,7 @@ * only for the return value that is the same as the source input, * which the compiler could/should do much better anyway. */ -SYM_FUNC_START(__memset) +SYM_TYPED_FUNC_START(__memset) ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index ebd259f31496..5ef8494896e8 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <linux/errno.h> +#include <linux/cfi_types.h> #include <asm/asm.h> #include <asm/msr.h> @@ -12,7 +13,7 @@ * */ .macro op_safe_regs op -SYM_FUNC_START(\op\()_safe_regs) +SYM_TYPED_FUNC_START(\op\()_safe_regs) pushq %rbx pushq %r12 movq %rdi, %r10 /* Save pointer */ diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 4bf4fad5b148..5a18ecc04a6c 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -103,6 +103,7 @@ int msr_set_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, true); } +EXPORT_SYMBOL_GPL(msr_set_bit); /** * msr_clear_bit - Clear @bit in a MSR @msr. @@ -118,6 +119,7 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } +EXPORT_SYMBOL_GPL(msr_clear_bit); #ifdef CONFIG_TRACEPOINTS void do_trace_write_msr(unsigned int msr, u64 val, int failed) diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 975c9c18263d..46d9e9b98a61 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -13,6 +13,7 @@ */ #include <linux/export.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/thread_info.h> #include <asm/errno.h> #include <asm/asm.h> @@ -45,6 +46,7 @@ .text SYM_FUNC_START(__put_user_1) + ANNOTATE_NOENDBR check_range size=1 ASM_STAC 1: movb %al,(%_ASM_CX) @@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) SYM_FUNC_START(__put_user_nocheck_1) + ANNOTATE_NOENDBR ASM_STAC 2: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1) EXPORT_SYMBOL(__put_user_nocheck_1) SYM_FUNC_START(__put_user_2) + ANNOTATE_NOENDBR check_range size=2 ASM_STAC 3: movw %ax,(%_ASM_CX) @@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) SYM_FUNC_START(__put_user_nocheck_2) + ANNOTATE_NOENDBR ASM_STAC 4: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2) EXPORT_SYMBOL(__put_user_nocheck_2) SYM_FUNC_START(__put_user_4) + ANNOTATE_NOENDBR check_range size=4 ASM_STAC 5: movl %eax,(%_ASM_CX) @@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) SYM_FUNC_START(__put_user_nocheck_4) + ANNOTATE_NOENDBR ASM_STAC 6: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4) EXPORT_SYMBOL(__put_user_nocheck_4) SYM_FUNC_START(__put_user_8) + ANNOTATE_NOENDBR check_range size=8 ASM_STAC 7: mov %_ASM_AX,(%_ASM_CX) @@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) SYM_FUNC_START(__put_user_nocheck_8) + ANNOTATE_NOENDBR ASM_STAC 9: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 391059b2c6fb..a26c43abd47d 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -326,6 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret) #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) SYM_FUNC_START(entry_untrain_ret) + ANNOTATE_NOENDBR ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) @@ -342,7 +343,7 @@ SYM_FUNC_START(call_depth_return_thunk) * case. */ CALL_THUNKS_DEBUG_INC_RETS - shlq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth) + shlq $5, PER_CPU_VAR(__x86_call_depth) jz 1f ANNOTATE_UNRET_SAFE ret diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index e9251b89a9e9..654280aaa3e9 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -18,7 +18,7 @@ #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB - * @vaddr: virtual start address + * @addr: virtual start address * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) |