[PATCH 12/15] x86/static_call: Add out-of-line static call implementation

[Peter Zijlstra]

From: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>

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.

Cc: x86@xxxxxxxxxx
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Julia Cartwright <julia@xxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
Cc: Jason Baron <jbaron@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Jiri Kosina <jkosina@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: David Laight <David.Laight@xxxxxxxxxx>
Cc: Jessica Yu <jeyu@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/00b08f2194e80241decbf206624b6580b9b8855b.1543200841.git.jpoimboe@xxxxxxxxxx
---
 arch/x86/Kconfig                   |    1 
 arch/x86/include/asm/static_call.h |   28 +++++++++++++++++++++++++++
 arch/x86/kernel/Makefile           |    1 
 arch/x86/kernel/static_call.c      |   38 +++++++++++++++++++++++++++++++++++++
 4 files changed, 68 insertions(+)
 create mode 100644 arch/x86/include/asm/static_call.h
 create mode 100644 arch/x86/kernel/static_call.c

--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -198,6 +198,7 @@ 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
--- /dev/null
+++ b/arch/x86/include/asm/static_call.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STATIC_CALL_H
+#define _ASM_STATIC_CALL_H
+
+/*
+ * Manually construct a 5-byte direct JMP to prevent the assembler from
+ * optimizing it into a 2-byte JMP.
+ */
+#define __ARCH_STATIC_CALL_JMP_LABEL(key) ".L" __stringify(key ## _after_jmp)
+#define __ARCH_STATIC_CALL_TRAMP_JMP(key, func)				\
+	".byte 0xe9						\n"	\
+	".long " #func " - " __ARCH_STATIC_CALL_JMP_LABEL(key) "\n"	\
+	__ARCH_STATIC_CALL_JMP_LABEL(key) ":"
+
+/*
+ * This is a permanent trampoline which does a direct jump to the function.
+ * The direct jump get patched by static_call_update().
+ */
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(key, func)			\
+	asm(".pushsection .text, \"ax\"				\n"	\
+	    ".align 4						\n"	\
+	    ".globl " STATIC_CALL_TRAMP_STR(key) "		\n"	\
+	    ".type " STATIC_CALL_TRAMP_STR(key) ", @function	\n"	\
+	    STATIC_CALL_TRAMP_STR(key) ":			\n"	\
+	    __ARCH_STATIC_CALL_TRAMP_JMP(key, func) "           \n"	\
+	    ".popsection					\n")
+
+#endif /* _ASM_STATIC_CALL_H */
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -63,6 +63,7 @@ obj-y			+= tsc.o tsc_msr.o io_delay.o rt
 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/
--- /dev/null
+++ b/arch/x86/kernel/static_call.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/static_call.h>
+#include <linux/memory.h>
+#include <linux/bug.h>
+#include <asm/text-patching.h>
+#include <asm/nospec-branch.h>
+
+#define CALL_INSN_SIZE 5
+
+void arch_static_call_transform(void *site, void *tramp, void *func)
+{
+	unsigned char opcodes[CALL_INSN_SIZE];
+	unsigned char insn_opcode;
+	unsigned long insn;
+	s32 dest_relative;
+
+	mutex_lock(&text_mutex);
+
+	insn = (unsigned long)tramp;
+
+	insn_opcode = *(unsigned char *)insn;
+	if (insn_opcode != 0xE9) {
+		WARN_ONCE(1, "unexpected static call insn opcode 0x%x at %pS",
+			  insn_opcode, (void *)insn);
+		goto unlock;
+	}
+
+	dest_relative = (long)(func) - (long)(insn + CALL_INSN_SIZE);
+
+	opcodes[0] = insn_opcode;
+	memcpy(&opcodes[1], &dest_relative, CALL_INSN_SIZE - 1);
+
+	text_poke_bp((void *)insn, opcodes, CALL_INSN_SIZE, NULL);
+
+unlock:
+	mutex_unlock(&text_mutex);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);