diff options
Diffstat (limited to 'arch/x86/lib/retpoline.S')
| -rw-r--r-- | arch/x86/lib/retpoline.S | 104 |
1 files changed, 104 insertions, 0 deletions
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..480edc3a5e03 --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,104 @@ +/* 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-asm.h> +#include <asm/export.h> +#include <asm/nospec-branch.h> +#include <asm/bitsperlong.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.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... + */ +#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) +#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif + +/* + * 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. + * + * 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. + */ +.macro STUFF_RSB nr:req sp:req + mov $(\nr / 2), %_ASM_BX + .align 16 +771: + call 772f +773: /* speculation trap */ + pause + lfence + jmp 773b + .align 16 +772: + call 774f +775: /* speculation trap */ + pause + lfence + jmp 775b + .align 16 +774: + dec %_ASM_BX + jnz 771b + add $((BITS_PER_LONG/8) * \nr), \sp +.endm + +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +ENTRY(__fill_rsb) + STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP + ret +END(__fill_rsb) +EXPORT_SYMBOL_GPL(__fill_rsb) + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +ENTRY(__clear_rsb) + STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP + ret +END(__clear_rsb) +EXPORT_SYMBOL_GPL(__clear_rsb) |