diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 15:03:00 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 15:03:00 -0800 |
commit | 94a855111ed9106971ca2617c5d075269e6aefde (patch) | |
tree | 330c762a403cf70c2cdbf12e7394e5e7c2a69a79 /arch/x86/net | |
parent | 93761c93e9da28d8a020777cee2a84133082b477 (diff) | |
parent | f1a033cc6b9eb6d80322008422df3c87aa5d47a0 (diff) | |
download | linux-stable-94a855111ed9106971ca2617c5d075269e6aefde.tar.gz linux-stable-94a855111ed9106971ca2617c5d075269e6aefde.tar.bz2 linux-stable-94a855111ed9106971ca2617c5d075269e6aefde.zip |
Merge tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 core updates from Borislav Petkov:
- Add the call depth tracking mitigation for Retbleed which has been
long in the making. It is a lighterweight software-only fix for
Skylake-based cores where enabling IBRS is a big hammer and causes a
significant performance impact.
What it basically does is, it aligns all kernel functions to 16 bytes
boundary and adds a 16-byte padding before the function, objtool
collects all functions' locations and when the mitigation gets
applied, it patches a call accounting thunk which is used to track
the call depth of the stack at any time.
When that call depth reaches a magical, microarchitecture-specific
value for the Return Stack Buffer, the code stuffs that RSB and
avoids its underflow which could otherwise lead to the Intel variant
of Retbleed.
This software-only solution brings a lot of the lost performance
back, as benchmarks suggest:
https://lore.kernel.org/all/20220915111039.092790446@infradead.org/
That page above also contains a lot more detailed explanation of the
whole mechanism
- Implement a new control flow integrity scheme called FineIBT which is
based on the software kCFI implementation and uses hardware IBT
support where present to annotate and track indirect branches using a
hash to validate them
- Other misc fixes and cleanups
* tag 'x86_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (80 commits)
x86/paravirt: Use common macro for creating simple asm paravirt functions
x86/paravirt: Remove clobber bitmask from .parainstructions
x86/debug: Include percpu.h in debugreg.h to get DECLARE_PER_CPU() et al
x86/cpufeatures: Move X86_FEATURE_CALL_DEPTH from bit 18 to bit 19 of word 11, to leave space for WIP X86_FEATURE_SGX_EDECCSSA bit
x86/Kconfig: Enable kernel IBT by default
x86,pm: Force out-of-line memcpy()
objtool: Fix weak hole vs prefix symbol
objtool: Optimize elf_dirty_reloc_sym()
x86/cfi: Add boot time hash randomization
x86/cfi: Boot time selection of CFI scheme
x86/ibt: Implement FineIBT
objtool: Add --cfi to generate the .cfi_sites section
x86: Add prefix symbols for function padding
objtool: Add option to generate prefix symbols
objtool: Avoid O(bloody terrible) behaviour -- an ode to libelf
objtool: Slice up elf_create_section_symbol()
kallsyms: Revert "Take callthunks into account"
x86: Unconfuse CONFIG_ and X86_FEATURE_ namespaces
x86/retpoline: Fix crash printing warning
x86/paravirt: Fix a !PARAVIRT build warning
...
Diffstat (limited to 'arch/x86/net')
-rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 45 |
1 files changed, 34 insertions, 11 deletions
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 36ffe67ad6e5..b808be77635e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -12,6 +12,7 @@ #include <linux/memory.h> #include <linux/sort.h> #include <asm/extable.h> +#include <asm/ftrace.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> @@ -340,6 +341,13 @@ static int emit_call(u8 **pprog, void *func, void *ip) return emit_patch(pprog, func, ip, 0xE8); } +static int emit_rsb_call(u8 **pprog, void *func, void *ip) +{ + OPTIMIZER_HIDE_VAR(func); + x86_call_depth_emit_accounting(pprog, func); + return emit_patch(pprog, func, ip, 0xE8); +} + static int emit_jump(u8 **pprog, void *func, void *ip) { return emit_patch(pprog, func, ip, 0xE9); @@ -417,7 +425,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { OPTIMIZER_HIDE_VAR(reg); - emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); + if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) + emit_jump(&prog, &__x86_indirect_jump_thunk_array[reg], ip); + else + emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) @@ -432,7 +443,7 @@ static void emit_return(u8 **pprog, u8 *ip) u8 *prog = *pprog; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - emit_jump(&prog, &__x86_return_thunk, ip); + emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_SLS)) @@ -1514,19 +1525,26 @@ st: if (is_imm8(insn->off)) break; /* call */ - case BPF_JMP | BPF_CALL: + case BPF_JMP | BPF_CALL: { + int offs; + func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ EMIT3_off32(0x48, 0x8B, 0x85, -round_up(bpf_prog->aux->stack_depth, 8) - 8); - if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) + if (!imm32) return -EINVAL; + offs = 7 + x86_call_depth_emit_accounting(&prog, func); } else { - if (!imm32 || emit_call(&prog, func, image + addrs[i - 1])) + if (!imm32) return -EINVAL; + offs = x86_call_depth_emit_accounting(&prog, func); } + if (emit_call(&prog, func, image + addrs[i - 1] + offs)) + return -EINVAL; break; + } case BPF_JMP | BPF_TAIL_CALL: if (imm32) @@ -1917,7 +1935,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, /* arg2: lea rsi, [rbp - ctx_cookie_off] */ EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_call(&prog, bpf_trampoline_enter(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog)) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -1938,7 +1956,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ - if (emit_call(&prog, p->bpf_func, prog)) + if (emit_rsb_call(&prog, p->bpf_func, prog)) return -EINVAL; /* @@ -1962,7 +1980,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_call(&prog, bpf_trampoline_exit(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog)) return -EINVAL; *pprog = prog; @@ -2184,6 +2202,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i prog = image; EMIT_ENDBR(); + /* + * This is the direct-call trampoline, as such it needs accounting + * for the __fentry__ call. + */ + x86_call_depth_emit_accounting(&prog, NULL); EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ @@ -2210,7 +2233,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_call(&prog, __bpf_tramp_enter, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) { ret = -EINVAL; goto cleanup; } @@ -2242,7 +2265,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT2(0xff, 0xd0); /* call *rax */ } else { /* call original function */ - if (emit_call(&prog, orig_call, prog)) { + if (emit_rsb_call(&prog, orig_call, prog)) { ret = -EINVAL; goto cleanup; } @@ -2286,7 +2309,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i im->ip_epilogue = prog; /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_call(&prog, __bpf_tramp_exit, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) { ret = -EINVAL; goto cleanup; } |