diff options
author | Peter Zijlstra <peterz@infradead.org> | 2021-10-26 15:01:48 +0300 |
---|---|---|
committer | Peter Zijlstra <peterz@infradead.org> | 2021-10-29 00:25:29 +0300 |
commit | 87c87ecd00c54ecd677798cb49ef27329e0fab41 (patch) | |
tree | 8ecf4f231899f81011fcfe802c8f89dd424820dc /arch/x86/net | |
parent | dceba0817ca329868a15e2e1dd46eb6340b69206 (diff) | |
download | linux-87c87ecd00c54ecd677798cb49ef27329e0fab41.tar.xz |
bpf,x86: Respect X86_FEATURE_RETPOLINE*
Current BPF codegen doesn't respect X86_FEATURE_RETPOLINE* flags and
unconditionally emits a thunk call, this is sub-optimal and doesn't
match the regular, compiler generated, code.
Update the i386 JIT to emit code equal to what the compiler emits for
the regular kernel text (IOW. a plain THUNK call).
Update the x86_64 JIT to emit code similar to the result of compiler
and kernel rewrites as according to X86_FEATURE_RETPOLINE* flags.
Inlining RETPOLINE_AMD (lfence; jmp *%reg) and !RETPOLINE (jmp *%reg),
while doing a THUNK call for RETPOLINE.
This removes the hard-coded retpoline thunks and shrinks the generated
code. Leaving a single retpoline thunk definition in the kernel.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/r/20211026120310.614772675@infradead.org
Diffstat (limited to 'arch/x86/net')
-rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 46 | ||||
-rw-r--r-- | arch/x86/net/bpf_jit_comp32.c | 22 |
2 files changed, 41 insertions, 27 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index b5c5fb42fd59..39c802525fce 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -387,6 +387,25 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); } +#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8) + +static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) +{ + u8 *prog = *pprog; + +#ifdef CONFIG_RETPOLINE + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + EMIT_LFENCE(); + EMIT2(0xFF, 0xE0 + reg); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); + } else +#endif + EMIT2(0xFF, 0xE0 + reg); + + *pprog = prog; +} + /* * Generate the following code: * @@ -468,7 +487,7 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, * rdi == ctx (1st arg) * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET */ - RETPOLINE_RCX_BPF_JIT(); + emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start)); /* out: */ ctx->tail_call_indirect_label = prog - start; @@ -1179,8 +1198,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* speculation barrier */ case BPF_ST | BPF_NOSPEC: if (boot_cpu_has(X86_FEATURE_XMM2)) - /* Emit 'lfence' */ - EMIT3(0x0F, 0xAE, 0xE8); + EMIT_LFENCE(); break; /* ST: *(u8*)(dst_reg + off) = imm */ @@ -2084,24 +2102,6 @@ cleanup: return ret; } -static int emit_fallback_jump(u8 **pprog) -{ - u8 *prog = *pprog; - int err = 0; - -#ifdef CONFIG_RETPOLINE - /* Note that this assumes the the compiler uses external - * thunks for indirect calls. Both clang and GCC use the same - * naming convention for external thunks. - */ - err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog); -#else - EMIT2(0xFF, 0xE2); /* jmp rdx */ -#endif - *pprog = prog; - return err; -} - static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { u8 *jg_reloc, *prog = *pprog; @@ -2123,9 +2123,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) if (err) return err; - err = emit_fallback_jump(&prog); /* jmp thunk/indirect */ - if (err) - return err; + emit_indirect_jump(&prog, 2 /* rdx */, prog); *pprog = prog; return 0; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 3bfda5f502cb..da9b7cfa4632 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -15,6 +15,7 @@ #include <asm/cacheflush.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> +#include <asm/asm-prototypes.h> #include <linux/bpf.h> /* @@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) *pprog = prog; } +static int emit_jmp_edx(u8 **pprog, u8 *ip) +{ + u8 *prog = *pprog; + int cnt = 0; + +#ifdef CONFIG_RETPOLINE + EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); +#else + EMIT2(0xFF, 0xE2); +#endif + *pprog = prog; + + return cnt; +} + /* * Generate the following code: * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... @@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call(u8 **pprog) +static void emit_bpf_tail_call(u8 **pprog, u8 *ip) { u8 *prog = *pprog; int cnt = 0; @@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog) * eax == ctx (1st arg) * edx == prog->bpf_func + prologue_size */ - RETPOLINE_EDX_BPF_JIT(); + cnt += emit_jmp_edx(&prog, ip + cnt); if (jmp_label1 == -1) jmp_label1 = cnt; @@ -2122,7 +2138,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; } case BPF_JMP | BPF_TAIL_CALL: - emit_bpf_tail_call(&prog); + emit_bpf_tail_call(&prog, image + addrs[i - 1]); break; /* cond jump */ |