static_call: Add static_call_cond()

Extend the static_call infrastructure to optimize the following common
pattern:

	if (func_ptr)
		func_ptr(args...)

For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.

For the in-line sites we replace the CALL with a NOP5.

NOTE: this is 'obviously' limited to functions with a 'void' return type.

NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
      to a full function.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org

1 files changed, 32 insertions, 10 deletions

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 5ff2b639a1a6..ead6726fb06d 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -4,19 +4,41 @@
 #include <linux/bug.h>
 #include <asm/text-patching.h>
 
-static void __static_call_transform(void *insn, u8 opcode, void *func)
+enum insn_type {
+	CALL = 0, /* site call */
+	NOP = 1,  /* site cond-call */
+	JMP = 2,  /* tramp / site tail-call */
+	RET = 3,  /* tramp / site cond-tail-call */
+};
+
+static void __static_call_transform(void *insn, enum insn_type type, void *func)
 {
-	const void *code = text_gen_insn(opcode, insn, func);
+	int size = CALL_INSN_SIZE;
+	const void *code;
 
-	if (WARN_ONCE(*(u8 *)insn != opcode,
-		      "unexpected static call insn opcode 0x%x at %pS\n",
-		      opcode, insn))
-		return;
+	switch (type) {
+	case CALL:
+		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+		break;
+
+	case NOP:
+		code = ideal_nops[NOP_ATOMIC5];
+		break;
+
+	case JMP:
+		code = text_gen_insn(JMP32_INSN_OPCODE, insn, func);
+		break;
+
+	case RET:
+		code = text_gen_insn(RET_INSN_OPCODE, insn, func);
+		size = RET_INSN_SIZE;
+		break;
+	}
 
-	if (memcmp(insn, code, CALL_INSN_SIZE) == 0)
+	if (memcmp(insn, code, size) == 0)
 		return;
 
-	text_poke_bp(insn, code, CALL_INSN_SIZE, NULL);
+	text_poke_bp(insn, code, size, NULL);
 }
 
 void arch_static_call_transform(void *site, void *tramp, void *func)
@@ -24,10 +46,10 @@ void arch_static_call_transform(void *site, void *tramp, void *func)
 	mutex_lock(&text_mutex);
 
 	if (tramp)
-		__static_call_transform(tramp, JMP32_INSN_OPCODE, func);
+		__static_call_transform(tramp, func ? JMP : RET, func);
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
-		__static_call_transform(site, CALL_INSN_OPCODE, func);
+		__static_call_transform(site, func ? CALL : NOP, func);
 
 	mutex_unlock(&text_mutex);
 }