diff options
Diffstat (limited to 'arch/x86/include/asm/nospec-branch.h')
| -rw-r--r-- | arch/x86/include/asm/nospec-branch.h | 136 |
1 files changed, 85 insertions, 51 deletions
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index fc3a8a3c7ffe..20d754b98f3f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -12,7 +12,6 @@ #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> -#include <asm/current.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow @@ -78,21 +77,21 @@ #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ - movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); + movq $-1, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ - movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); + movq %rax, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ movb $0xfc, %al; \ shl $56, %rax; \ - movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + movq %rax, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ - sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + sarq $5, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else @@ -177,19 +176,7 @@ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; -#ifdef __ASSEMBLY__ - -/* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -.macro ANNOTATE_RETPOLINE_SAFE -.Lhere_\@: - .pushsection .discard.retpoline_safe - .long .Lhere_\@ - .popsection -.endm +#ifdef __ASSEMBLER__ /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions @@ -210,9 +197,8 @@ .endm /* - * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call - * to the retpoline thunk with a CS prefix when the register requires - * a RAX prefix byte to encode. Also see apply_retpolines(). + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 @@ -262,11 +248,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -274,7 +269,7 @@ * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, - * entry_ibpb() will clobber AX, CX, DX. + * write_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. @@ -282,9 +277,9 @@ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", \ibpb_feature, \ + CALL_UNTRAIN_RET + ALTERNATIVE_2 "", \ + "call write_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm @@ -314,21 +309,41 @@ * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS - ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF +#ifdef CONFIG_X86_64 + ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF +#else + /* + * In 32bit mode, the memory operand must be a %cs reference. The data + * segments may not be usable (vm86 mode), and the stack segment may not + * be flat (ESPFIX32). + */ + ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF +#endif +.endm + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP .endm -#else /* __ASSEMBLY__ */ +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif -#define ANNOTATE_RETPOLINE_SAFE \ - "999:\n\t" \ - ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" +#else /* __ASSEMBLER__ */ + +#define ITS_THUNK_SIZE 64 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); @@ -342,6 +357,8 @@ extern void retbleed_return_thunk(void); static inline void retbleed_return_thunk(void) {} #endif +extern void srso_alias_untrain_ret(void); + #ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); @@ -350,12 +367,22 @@ static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); -extern void entry_ibpb(void); +extern void write_ibpb(void); + +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif extern void (*x86_return_thunk)(void); @@ -369,6 +396,8 @@ extern void call_depth_return_thunk(void); __stringify(INCREMENT_CALL_DEPTH), \ X86_FEATURE_CALL_DEPTH) +DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth); + #ifdef CONFIG_CALL_THUNKS_DEBUG DECLARE_PER_CPU(u64, __x86_call_count); DECLARE_PER_CPU(u64, __x86_ret_count); @@ -402,19 +431,22 @@ static inline void call_depth_return_thunk(void) {} #ifdef CONFIG_X86_64 /* + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. + */ +#define __CS_PREFIX(reg) \ + ".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \ + ".ifc \\rs," reg "\n" \ + ".byte 0x2e\n" \ + ".endif\n" \ + ".endr\n" + +/* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ -# define CALL_NOSPEC \ - ALTERNATIVE_2( \ - ANNOTATE_RETPOLINE_SAFE \ - "call *%[thunk_target]\n", \ - "call __x86_indirect_thunk_%V[thunk_target]\n", \ - X86_FEATURE_RETPOLINE, \ - "lfence;\n" \ - ANNOTATE_RETPOLINE_SAFE \ - "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_LFENCE) +#define CALL_NOSPEC __CS_PREFIX("%V[thunk_target]") \ + "call __x86_indirect_thunk_%V[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "r" (addr) @@ -492,11 +524,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } -extern u64 x86_pred_cmd; - static inline void indirect_branch_prediction_barrier(void) { - alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); + asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) + : ASM_CALL_CONSTRAINT + :: "rax", "rcx", "rdx", "memory"); } /* The Intel SPEC CTRL MSR base value cache */ @@ -533,11 +565,13 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); +DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb); + DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); -DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear); extern u16 mds_verw_sel; @@ -577,6 +611,6 @@ static __always_inline void mds_idle_clear_cpu_buffers(void) mds_clear_cpu_buffers(); } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ |