/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include #include #include #include #include #include #include #include #define RETPOLINE_THUNK_SIZE 32 /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include ") but let's not go there. */ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #define __FILL_RETURN_BUFFER(reg, nr, sp) \ mov $(nr/2), reg; \ 771: \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ 773: /* speculation trap */ \ UNWIND_HINT_EMPTY; \ pause; \ lfence; \ jmp 773b; \ 772: \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 774f; \ 775: /* speculation trap */ \ UNWIND_HINT_EMPTY; \ pause; \ lfence; \ jmp 775b; \ 774: \ add $(BITS_PER_LONG/8) * 2, sp; \ dec reg; \ jnz 771b; #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 .Lannotate_\@: .pushsection .discard.retpoline_safe _ASM_PTR .Lannotate_\@ .popsection .endm /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into it's own annotation. */ .macro ANNOTATE_UNRET_END #ifdef CONFIG_DEBUG_ENTRY ANNOTATE_RETPOLINE_SAFE nop #endif .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(). */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 .ifc \reg,\rs .byte 0x2e .endif .endr .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else jmp *%\reg int3 #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) .Lskip_rsb_\@: .endm #ifdef CONFIG_CPU_UNRET_ENTRY #define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" #else #define CALL_ZEN_UNTRAIN_RET "" #endif /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While zen_untrain_ret() doesn't clobber anything but requires stack, * entry_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. */ .macro UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include #undef GEN #ifdef CONFIG_X86_64 /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_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 THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } static inline void indirect_branch_prediction_barrier(void) { u64 val = PRED_CMD_IBPB; alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void write_spec_ctrl_current(u64 val, bool force); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) 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(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); #include /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */