From: Peter Zijlstra peterz@infradead.org
commit 923510c88d2b7d947c4217835fd9ca6bd65cc56c upstream.
Clang likes to create conditional tail calls like:
0000000000000350 <amd_pmu_add_event>: 350: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 351: R_X86_64_NONE __fentry__-0x4 355: 48 83 bf 20 01 00 00 00 cmpq $0x0,0x120(%rdi) 35d: 0f 85 00 00 00 00 jne 363 <amd_pmu_add_event+0x13> 35f: R_X86_64_PLT32 __SCT__amd_pmu_branch_add-0x4 363: e9 00 00 00 00 jmp 368 <amd_pmu_add_event+0x18> 364: R_X86_64_PLT32 __x86_return_thunk-0x4
Where 0x35d is a static call site that's turned into a conditional tail-call using the Jcc class of instructions.
Teach the in-line static call text patching about this.
Notably, since there is no conditional-ret, in that case patch the Jcc to point at an empty stub function that does the ret -- or the return thunk when needed.
Reported-by: "Erhard F." erhard_f@mailbox.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Masami Hiramatsu (Google) mhiramat@kernel.org Link: https://lore.kernel.org/r/Y9Kdg9QjHkr9G5b5@hirez.programming.kicks-ass.net [nathan: Backport to 6.1: - Use __x86_return_thunk instead of x86_return_thunk for func in __static_call_transform() - Remove ASM_FUNC_ALIGN in __static_call_return() asm, as call depth tracking was merged in 6.2] Signed-off-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [cascardo: __static_call_validate didn't have the bool tramp argument] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@igalia.com --- arch/x86/kernel/static_call.c | 49 ++++++++++++++++++++++++++++++++--- 1 file changed, 46 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index e25050c7ff1e..94378f202c50 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -9,6 +9,7 @@ enum insn_type { NOP = 1, /* site cond-call */ JMP = 2, /* tramp / site tail-call */ RET = 3, /* tramp / site cond-tail-call */ + JCC = 4, };
/* @@ -25,12 +26,39 @@ static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
+static u8 __is_Jcc(u8 *insn) /* Jcc.d32 */ +{ + u8 ret = 0; + + if (insn[0] == 0x0f) { + u8 tmp = insn[1]; + if ((tmp & 0xf0) == 0x80) + ret = tmp; + } + + return ret; +} + +extern void __static_call_return(void); + +asm (".global __static_call_return\n\t" + ".type __static_call_return, @function\n\t" + "__static_call_return:\n\t" + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + "ret; int3\n\t" + ".size __static_call_return, . - __static_call_return \n\t"); + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; + u8 op, buf[6]; + + if ((type == JMP || type == RET) && (op = __is_Jcc(insn))) + type = JCC;
switch (type) { case CALL: @@ -56,6 +84,20 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, else code = &retinsn; break; + + case JCC: + if (!func) { + func = __static_call_return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + func = __x86_return_thunk; + } + + buf[0] = 0x0f; + __text_gen_insn(buf+1, op, insn+1, func, 5); + code = buf; + size = 6; + + break; }
if (memcmp(insn, code, size) == 0) @@ -67,13 +109,14 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, text_poke_bp(insn, code, size, emulate); }
-static void __static_call_validate(void *insn, bool tail) +static void __static_call_validate(u8 *insn, bool tail) { - u8 opcode = *(u8 *)insn; + u8 opcode = insn[0];
if (tail) { if (opcode == JMP32_INSN_OPCODE || - opcode == RET_INSN_OPCODE) + opcode == RET_INSN_OPCODE || + __is_Jcc(insn)) return; } else { if (opcode == CALL_INSN_OPCODE ||