OpenCloudOS-Kernel/arch/x86/lib/retpoline.S

381 lines
9.9 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/stringify.h>
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <asm/asm-offsets.h>
#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
#include <asm/percpu.h>
#include <asm/frame.h>
#include <asm/nops.h>
.section .text..__x86.indirect_thunk
.macro POLINE reg
ANNOTATE_INTRA_FUNCTION_CALL
call .Ldo_rop_\@
int3
.Ldo_rop_\@:
mov %\reg, (%_ASM_SP)
UNWIND_HINT_FUNC
.endm
.macro RETPOLINE reg
POLINE \reg
RET
.endm
.macro THUNK reg
.align RETPOLINE_THUNK_SIZE
SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
__stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
.endm
/*
* Despite being an assembler file we can't just use .irp here
* because __KSYM_DEPS__ only uses the C preprocessor and would
* only see one instance of "__x86_indirect_thunk_\reg" rather
* than one per register with the correct names. So we do it
* the simple and nasty way...
*
* Worse, you can only have a single EXPORT_SYMBOL per line,
* and CPP can't insert newlines, so we have to repeat everything
* at least twice.
*/
#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
.align RETPOLINE_THUNK_SIZE
SYM_CODE_START(__x86_indirect_thunk_array)
#define GEN(reg) THUNK reg
#include <asm/GEN-for-each-reg.h>
#undef GEN
.align RETPOLINE_THUNK_SIZE
SYM_CODE_END(__x86_indirect_thunk_array)
#define GEN(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
#include <asm/GEN-for-each-reg.h>
#undef GEN
#ifdef CONFIG_CALL_DEPTH_TRACKING
.macro CALL_THUNK reg
.align RETPOLINE_THUNK_SIZE
SYM_INNER_LABEL(__x86_indirect_call_thunk_\reg, SYM_L_GLOBAL)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
CALL_DEPTH_ACCOUNT
POLINE \reg
ANNOTATE_UNRET_SAFE
ret
int3
.endm
.align RETPOLINE_THUNK_SIZE
SYM_CODE_START(__x86_indirect_call_thunk_array)
#define GEN(reg) CALL_THUNK reg
#include <asm/GEN-for-each-reg.h>
#undef GEN
.align RETPOLINE_THUNK_SIZE
SYM_CODE_END(__x86_indirect_call_thunk_array)
#define GEN(reg) __EXPORT_THUNK(__x86_indirect_call_thunk_ ## reg)
#include <asm/GEN-for-each-reg.h>
#undef GEN
.macro JUMP_THUNK reg
.align RETPOLINE_THUNK_SIZE
SYM_INNER_LABEL(__x86_indirect_jump_thunk_\reg, SYM_L_GLOBAL)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
POLINE \reg
ANNOTATE_UNRET_SAFE
ret
int3
.endm
.align RETPOLINE_THUNK_SIZE
SYM_CODE_START(__x86_indirect_jump_thunk_array)
#define GEN(reg) JUMP_THUNK reg
#include <asm/GEN-for-each-reg.h>
#undef GEN
.align RETPOLINE_THUNK_SIZE
SYM_CODE_END(__x86_indirect_jump_thunk_array)
#define GEN(reg) __EXPORT_THUNK(__x86_indirect_jump_thunk_ ## reg)
#include <asm/GEN-for-each-reg.h>
#undef GEN
#endif
#ifdef CONFIG_RETHUNK
.section .text..__x86.return_thunk
#ifdef CONFIG_CPU_SRSO
/*
* srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
* special addresses:
*
* - srso_alias_untrain_ret() is 2M aligned
* - srso_alias_safe_ret() is also in the same 2M page but bits 2, 8, 14
* and 20 in its virtual address are set (while those bits in the
* srso_alias_untrain_ret() function are cleared).
*
* This guarantees that those two addresses will alias in the branch
* target buffer of Zen3/4 generations, leading to any potential
* poisoned entries at that BTB slot to get evicted.
*
* As a result, srso_alias_safe_ret() becomes a safe return.
*/
.pushsection .text..__x86.rethunk_untrain
SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
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)
.popsection
.pushsection .text..__x86.rethunk_safe
SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
lea 8(%_ASM_SP), %_ASM_SP
UNWIND_HINT_FUNC
ANNOTATE_UNRET_SAFE
ret
int3
SYM_FUNC_END(srso_alias_safe_ret)
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_START(srso_untrain_ret, SYM_L_LOCAL, SYM_A_NONE)
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"
#else /* !CONFIG_CPU_SRSO */
#define JMP_SRSO_UNTRAIN_RET "ud2"
/* Dummy for the alternative in CALL_UNTRAIN_RET. */
SYM_CODE_START(srso_alias_untrain_ret)
ANNOTATE_UNRET_SAFE
ANNOTATE_NOENDBR
ret
int3
SYM_FUNC_END(srso_alias_untrain_ret)
__EXPORT_THUNK(srso_alias_untrain_ret)
#endif /* CONFIG_CPU_SRSO */
#ifdef CONFIG_CPU_UNRET_ENTRY
/*
* Some generic notes on the untraining sequences:
*
* They are interchangeable when it comes to flushing potentially wrong
* RET predictions from the BTB.
*
* The SRSO Zen1/2 (MOVABS) untraining sequence is longer than the
* Retbleed sequence because the return sequence done there
* (srso_safe_ret()) is longer and the return sequence must fully nest
* (end before) the untraining sequence. Therefore, the untraining
* sequence must fully overlap the return sequence.
*
* Regarding alignment - the instructions which need to be untrained,
* must all start at a cacheline boundary for Zen1/2 generations. That
* is, instruction sequences starting at srso_safe_ret() and
* the respective instruction sequences at retbleed_return_thunk()
* must start at a cacheline boundary.
*/
/*
* Safety details here pertain to the AMD Zen{1,2} microarchitecture:
* 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for
* alignment within the BTB.
* 2) The instruction at retbleed_untrain_ret must contain, and not
* end with, the 0xc3 byte of the RET.
* 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread
* from re-poisioning the BTB prediction.
*/
.align 64
.skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc
SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
ANNOTATE_NOENDBR
/*
* As executed from retbleed_untrain_ret, this is:
*
* TEST $0xcc, %bl
* LFENCE
* JMP retbleed_return_thunk
*
* Executing the TEST instruction has a side effect of evicting any BTB
* prediction (potentially attacker controlled) attached to the RET, as
* retbleed_return_thunk + 1 isn't an instruction boundary at the moment.
*/
.byte 0xf6
/*
* As executed from retbleed_return_thunk, this is a plain RET.
*
* As part of the TEST above, RET is the ModRM byte, and INT3 the imm8.
*
* We subsequently jump backwards and architecturally execute the RET.
* This creates a correct BTB prediction (type=ret), but in the
* meantime we suffer Straight Line Speculation (because the type was
* no branch) which is halted by the INT3.
*
* With SMT enabled and STIBP active, a sibling thread cannot poison
* RET's prediction to a type of its choice, but can evict the
* prediction due to competitive sharing. If the prediction is
* evicted, retbleed_return_thunk will suffer Straight Line Speculation
* which will be contained safely by the INT3.
*/
SYM_INNER_LABEL(retbleed_return_thunk, SYM_L_GLOBAL)
ret
int3
SYM_CODE_END(retbleed_return_thunk)
/*
* Ensure the TEST decoding / BTB invalidation is complete.
*/
lfence
/*
* Jump back and execute the RET in the middle of the TEST instruction.
* INT3 is for SLS protection.
*/
jmp retbleed_return_thunk
int3
SYM_FUNC_END(retbleed_untrain_ret)
__EXPORT_THUNK(retbleed_untrain_ret)
#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 */
#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
SYM_FUNC_START(entry_untrain_ret)
ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
#ifdef CONFIG_CALL_DEPTH_TRACKING
.align 64
SYM_FUNC_START(__x86_return_skl)
ANNOTATE_NOENDBR
/*
* Keep the hotpath in a 16byte I-fetch for the non-debug
* case.
*/
CALL_THUNKS_DEBUG_INC_RETS
shlq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
jz 1f
ANNOTATE_UNRET_SAFE
ret
int3
1:
CALL_THUNKS_DEBUG_INC_STUFFS
.rept 16
ANNOTATE_INTRA_FUNCTION_CALL
call 2f
int3
2:
.endr
add $(8*16), %rsp
CREDIT_CALL_DEPTH
ANNOTATE_UNRET_SAFE
ret
int3
SYM_FUNC_END(__x86_return_skl)
#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().
*/
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 */