x86/static_call: Add out-of-line static call implementation

Add the x86 out-of-line static call implementation.  For each key, a
permanent trampoline is created which is the destination for all static
calls for the given key.  The trampoline has a direct jump which gets
patched by static_call_update() when the destination function changes.

[peterz: fixed trampoline, rewrote patching code]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
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/20200818135804.804315175@infradead.org

Author: jpoimboe

arch/x86/Kconfig

@@ -215,6 +215,7 @@ config X86
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
+	select HAVE_STATIC_CALL
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK

arch/x86/include/asm/static_call.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STATIC_CALL_H
+#define _ASM_STATIC_CALL_H
+
+#include <asm/text-patching.h>
+
+/*
+ * For CONFIG_HAVE_STATIC_CALL, this is a permanent trampoline which
+ * does a direct jump to the function.  The direct jump gets patched by
+ * static_call_update().
+ */
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+	asm(".pushsection .text, \"ax\"				\n"	\
+	    ".align 4						\n"	\
+	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
+	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
+	    "	.byte 0xe9 # jmp.d32				\n"	\
+	    "	.long " #func " - (. + 4)			\n"	\
+	    ".type " STATIC_CALL_TRAMP_STR(name) ", @function	\n"	\
+	    ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
+	    ".popsection					\n")
+
+#endif /* _ASM_STATIC_CALL_H */

arch/x86/kernel/Makefile

@@ -68,6 +68,7 @@ obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 obj-y			+= irqflags.o
+obj-y			+= static_call.o
 
 obj-y				+= process.o
 obj-y				+= fpu/

arch/x86/kernel/static_call.c

@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/static_call.h>
+#include <linux/memory.h>
+#include <linux/bug.h>
+#include <asm/text-patching.h>
+
+static void __static_call_transform(void *insn, u8 opcode, void *func)
+{
+	const void *code = text_gen_insn(opcode, insn, func);
+
+	if (WARN_ONCE(*(u8 *)insn != opcode,
+		      "unexpected static call insn opcode 0x%x at %pS\n",
+		      opcode, insn))
+		return;
+
+	if (memcmp(insn, code, CALL_INSN_SIZE) == 0)
+		return;
+
+	text_poke_bp(insn, code, CALL_INSN_SIZE, NULL);
+}
+
+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);
+
+	mutex_unlock(&text_mutex);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);