From 85c675d0d09a45a135bddd15d7b385f8758c32fb Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 19:35:05 +0200 Subject: Adding upstream version 6.7.7. Signed-off-by: Daniel Baumann --- arch/x86/lib/checksum_32.S | 2 +- arch/x86/lib/clear_page_64.S | 2 +- arch/x86/lib/cmpxchg8b_emu.S | 2 +- arch/x86/lib/copy_page_64.S | 2 +- arch/x86/lib/copy_user_64.S | 2 +- arch/x86/lib/copy_user_uncached_64.S | 2 +- arch/x86/lib/csum-wrappers_64.c | 5 - arch/x86/lib/getuser.S | 26 ++--- arch/x86/lib/hweight.S | 22 ++-- arch/x86/lib/memcpy_64.S | 2 +- arch/x86/lib/memmove_32.S | 2 +- arch/x86/lib/memmove_64.S | 2 +- arch/x86/lib/memset_64.S | 2 +- arch/x86/lib/putuser.S | 23 ++--- arch/x86/lib/retpoline.S | 188 ++++++++++++++++++++--------------- 15 files changed, 149 insertions(+), 135 deletions(-) (limited to 'arch/x86/lib') diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 23318c338d..68f7fa3e13 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -21,10 +21,10 @@ * converted to pure assembler */ +#include #include #include #include -#include #include /* diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index f74a3e704a..2760a15fbc 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include #include #include -#include /* * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 49805257b1..873e4ef23e 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include #include -#include #include #include diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 30ea644bf4..d6ae793d08 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ +#include #include #include #include -#include /* * Some CPUs run faster using the string copy instructions (sane microcode). diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 0a81aafed7..fc9fb5d061 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -6,11 +6,11 @@ * Functions to copy from and to user space. */ +#include #include #include #include #include -#include /* * rep_movs_alternative - memory copy with exception handling. diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S index 5c5f38d326..2918e36eec 100644 --- a/arch/x86/lib/copy_user_uncached_64.S +++ b/arch/x86/lib/copy_user_uncached_64.S @@ -3,9 +3,9 @@ * Copyright 2023 Linus Torvalds */ +#include #include #include -#include /* * copy_user_nocache - Uncached memory copy with exception handling diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 145f9a0bde..f4df4d2415 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -14,8 +14,6 @@ * @src: source address (user space) * @dst: destination address * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) - * @errp: set to -EFAULT for an bad source address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. @@ -38,8 +36,6 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len) * @src: source address * @dst: destination address (user space) * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) - * @errp: set to -EFAULT for an bad destination address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. @@ -62,7 +58,6 @@ csum_and_copy_to_user(const void *src, void __user *dst, int len) * @src: source address * @dst: destination address * @len: number of bytes to be copied. - * @sum: initial sum that is added into the result (32bit unfolded) * * Returns an 32bit unfolded checksum of the buffer. */ diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 9c63713477..10d5ed8b59 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -26,6 +26,7 @@ * as they get called from within inline assembly. */ +#include #include #include #include @@ -33,7 +34,6 @@ #include #include #include -#include #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC @@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception) #endif /* get_user */ - _ASM_EXTABLE(1b, __get_user_handle_exception) - _ASM_EXTABLE(2b, __get_user_handle_exception) - _ASM_EXTABLE(3b, __get_user_handle_exception) + _ASM_EXTABLE_UA(1b, __get_user_handle_exception) + _ASM_EXTABLE_UA(2b, __get_user_handle_exception) + _ASM_EXTABLE_UA(3b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(4b, __get_user_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_handle_exception) #else - _ASM_EXTABLE(4b, __get_user_8_handle_exception) - _ASM_EXTABLE(5b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(4b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(5b, __get_user_8_handle_exception) #endif /* __get_user */ - _ASM_EXTABLE(6b, __get_user_handle_exception) - _ASM_EXTABLE(7b, __get_user_handle_exception) - _ASM_EXTABLE(8b, __get_user_handle_exception) + _ASM_EXTABLE_UA(6b, __get_user_handle_exception) + _ASM_EXTABLE_UA(7b, __get_user_handle_exception) + _ASM_EXTABLE_UA(8b, __get_user_handle_exception) #ifdef CONFIG_X86_64 - _ASM_EXTABLE(9b, __get_user_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_handle_exception) #else - _ASM_EXTABLE(9b, __get_user_8_handle_exception) - _ASM_EXTABLE(10b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(9b, __get_user_8_handle_exception) + _ASM_EXTABLE_UA(10b, __get_user_8_handle_exception) #endif diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 12c16c6aa4..774bdf3e6f 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include -#include #include @@ -36,8 +36,12 @@ SYM_FUNC_START(__sw_hweight32) SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32) -SYM_FUNC_START(__sw_hweight64) +/* + * No 32-bit variant, because it's implemented as an inline wrapper + * on top of __arch_hweight32(): + */ #ifdef CONFIG_X86_64 +SYM_FUNC_START(__sw_hweight64) pushq %rdi pushq %rdx @@ -66,18 +70,6 @@ SYM_FUNC_START(__sw_hweight64) popq %rdx popq %rdi RET -#else /* CONFIG_X86_32 */ - /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ - pushl %ecx - - call __sw_hweight32 - movl %eax, %ecx # stash away result - movl %edx, %eax # second part of input - call __sw_hweight32 - addl %ecx, %eax # result - - popl %ecx - RET -#endif SYM_FUNC_END(__sw_hweight64) EXPORT_SYMBOL(__sw_hweight64) +#endif diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 76697df8df..0ae2e1712e 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright 2002 Andi Kleen */ +#include #include #include #include #include #include -#include .section .noinstr.text, "ax" diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S index 0588b2c0fc..35010ba3dd 100644 --- a/arch/x86/lib/memmove_32.S +++ b/arch/x86/lib/memmove_32.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include -#include SYM_FUNC_START(memmove) /* diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index ccdf3a5970..1b60ae81ec 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -6,10 +6,10 @@ * This assembly file is re-written from memmove_64.c file. * - Copyright 2011 Fenghua Yu */ +#include #include #include #include -#include #undef memmove diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 3d818b849e..0199d56cb4 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2002 Andi Kleen, SuSE Labs */ +#include #include #include #include -#include .section .noinstr.text, "ax" diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 235bbda6fc..975c9c1826 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -11,13 +11,12 @@ * return an error value in addition to the "real" * return value. */ +#include #include #include #include #include #include -#include - /* * __put_user_X @@ -134,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception) RET SYM_CODE_END(__put_user_handle_exception) - _ASM_EXTABLE(1b, __put_user_handle_exception) - _ASM_EXTABLE(2b, __put_user_handle_exception) - _ASM_EXTABLE(3b, __put_user_handle_exception) - _ASM_EXTABLE(4b, __put_user_handle_exception) - _ASM_EXTABLE(5b, __put_user_handle_exception) - _ASM_EXTABLE(6b, __put_user_handle_exception) - _ASM_EXTABLE(7b, __put_user_handle_exception) - _ASM_EXTABLE(9b, __put_user_handle_exception) + _ASM_EXTABLE_UA(1b, __put_user_handle_exception) + _ASM_EXTABLE_UA(2b, __put_user_handle_exception) + _ASM_EXTABLE_UA(3b, __put_user_handle_exception) + _ASM_EXTABLE_UA(4b, __put_user_handle_exception) + _ASM_EXTABLE_UA(5b, __put_user_handle_exception) + _ASM_EXTABLE_UA(6b, __put_user_handle_exception) + _ASM_EXTABLE_UA(7b, __put_user_handle_exception) + _ASM_EXTABLE_UA(9b, __put_user_handle_exception) #ifdef CONFIG_X86_32 - _ASM_EXTABLE(8b, __put_user_handle_exception) - _ASM_EXTABLE(10b, __put_user_handle_exception) + _ASM_EXTABLE_UA(8b, __put_user_handle_exception) + _ASM_EXTABLE_UA(10b, __put_user_handle_exception) #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index cd86aeb5fd..7b2589877d 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include #include #include #include #include #include -#include #include #include #include @@ -126,11 +126,19 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #include #undef GEN #endif + +#ifdef CONFIG_RETHUNK + /* - * This function name is magical and is used by -mfunction-return=thunk-extern - * for the compiler to generate JMPs to it. + * Be careful here: that label cannot really be removed because in + * some configurations and toolchains, the JMP __x86_return_thunk the + * compiler issues is either a short one or the compiler doesn't use + * relocations for same-section JMPs and that breaks the returns + * detection logic in apply_returns() and in objtool. */ -#ifdef CONFIG_RETHUNK + .section .text..__x86.return_thunk + +#ifdef CONFIG_CPU_SRSO /* * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at @@ -147,29 +155,18 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) * * As a result, srso_alias_safe_ret() becomes a safe return. */ -#ifdef CONFIG_CPU_SRSO - .section .text..__x86.rethunk_untrain - -SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + .pushsection .text..__x86.rethunk_untrain +SYM_CODE_START_NOALIGN(srso_alias_untrain_ret) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ASM_NOP2 lfence jmp srso_alias_return_thunk SYM_FUNC_END(srso_alias_untrain_ret) -__EXPORT_THUNK(srso_alias_untrain_ret) - - .section .text..__x86.rethunk_safe -#else -/* dummy definition for alternatives */ -SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_FUNC_END(srso_alias_untrain_ret) -#endif + .popsection -SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) + .pushsection .text..__x86.rethunk_safe +SYM_CODE_START_NOALIGN(srso_alias_safe_ret) lea 8(%_ASM_SP), %_ASM_SP UNWIND_HINT_FUNC ANNOTATE_UNRET_SAFE @@ -177,14 +174,63 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) int3 SYM_FUNC_END(srso_alias_safe_ret) - .section .text..__x86.return_thunk - -SYM_CODE_START(srso_alias_return_thunk) +SYM_CODE_START_NOALIGN(srso_alias_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR call srso_alias_safe_ret ud2 SYM_CODE_END(srso_alias_return_thunk) + .popsection + +/* + * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccc30824648d48,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_CODE_START_LOCAL_NOALIGN(srso_untrain_ret) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +/* + * This forces the function return instruction to speculate into a trap + * (UD2 in srso_return_thunk() below). This RET will then mispredict + * and execution will continue at the return site read from the top of + * the stack. + */ +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + lea 8(%_ASM_SP), %_ASM_SP + ret + int3 + int3 + /* end of movabs */ + lfence + call srso_safe_ret + ud2 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) + +SYM_CODE_START(srso_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret + ud2 +SYM_CODE_END(srso_return_thunk) + +#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" +#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret" +#else /* !CONFIG_CPU_SRSO */ +#define JMP_SRSO_UNTRAIN_RET "ud2" +#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" +#endif /* CONFIG_CPU_SRSO */ + +#ifdef CONFIG_CPU_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -216,7 +262,7 @@ SYM_CODE_END(srso_alias_return_thunk) */ .align 64 .skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc -SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) +SYM_CODE_START_LOCAL_NOALIGN(retbleed_untrain_ret) ANNOTATE_NOENDBR /* * As executed from retbleed_untrain_ret, this is: @@ -264,72 +310,27 @@ SYM_CODE_END(retbleed_return_thunk) jmp retbleed_return_thunk int3 SYM_FUNC_END(retbleed_untrain_ret) -__EXPORT_THUNK(retbleed_untrain_ret) -/* - * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() - * above. On kernel entry, srso_untrain_ret() is executed which is a - * - * movabs $0xccccc30824648d48,%rax - * - * and when the return thunk executes the inner label srso_safe_ret() - * later, it is a stack manipulation and a RET which is mispredicted and - * thus a "safe" one to use. - */ - .align 64 - .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc -SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_NOENDBR - .byte 0x48, 0xb8 +#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" +#else /* !CONFIG_CPU_UNRET_ENTRY */ +#define JMP_RETBLEED_UNTRAIN_RET "ud2" +#endif /* CONFIG_CPU_UNRET_ENTRY */ -/* - * This forces the function return instruction to speculate into a trap - * (UD2 in srso_return_thunk() below). This RET will then mispredict - * and execution will continue at the return site read from the top of - * the stack. - */ -SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) - lea 8(%_ASM_SP), %_ASM_SP - ret - int3 - int3 - /* end of movabs */ - lfence - call srso_safe_ret - ud2 -SYM_CODE_END(srso_safe_ret) -SYM_FUNC_END(srso_untrain_ret) -__EXPORT_THUNK(srso_untrain_ret) - -SYM_CODE_START(srso_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - call srso_safe_ret - ud2 -SYM_CODE_END(srso_return_thunk) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ + JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \ + JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -SYM_CODE_START(__x86_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_CODE_END(__x86_return_thunk) -EXPORT_SYMBOL(__x86_return_thunk) - -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ #ifdef CONFIG_CALL_DEPTH_TRACKING .align 64 -SYM_FUNC_START(__x86_return_skl) +SYM_FUNC_START(call_depth_return_thunk) ANNOTATE_NOENDBR /* * Keep the hotpath in a 16byte I-fetch for the non-debug @@ -356,6 +357,33 @@ SYM_FUNC_START(__x86_return_skl) ANNOTATE_UNRET_SAFE ret int3 -SYM_FUNC_END(__x86_return_skl) +SYM_FUNC_END(call_depth_return_thunk) #endif /* CONFIG_CALL_DEPTH_TRACKING */ + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + * + * This code is only used during kernel boot or module init. All + * 'JMP __x86_return_thunk' sites are changed to something else by + * apply_returns(). + * + * This should be converted eventually to call a warning function which + * should scream loudly when the default return thunk is called after + * alternatives have been applied. + * + * That warning function cannot BUG() because the bug splat cannot be + * displayed in all possible configurations, leading to users not really + * knowing why the machine froze. + */ +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(__x86_return_thunk) +EXPORT_SYMBOL(__x86_return_thunk) + +#endif /* CONFIG_RETHUNK */ -- cgit v1.2.3