[PATCH v3 3/6] x86/static_call: Add out-of-line static call implementation

[Josh Poimboeuf <jpoimboe@redhat.com>]

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.

This relies on the fact that call destinations can be atomically updated
as long as they don't cross cache line boundaries.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/Kconfig                   |  1 +
 arch/x86/include/asm/static_call.h | 27 +++++++++++++++++++++
 arch/x86/kernel/Makefile           |  1 +
 arch/x86/kernel/static_call.c      | 38 ++++++++++++++++++++++++++++++
 arch/x86/kernel/vmlinux.lds.S      |  1 +
 include/asm-generic/vmlinux.lds.h  | 15 ++++++++++++
 6 files changed, 83 insertions(+)
 create mode 100644 arch/x86/include/asm/static_call.h
 create mode 100644 arch/x86/kernel/static_call.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6185d4f33296..421097322f1b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -190,6 +190,7 @@ 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
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
new file mode 100644
index 000000000000..fab5facade03
--- /dev/null
+++ b/arch/x86/include/asm/static_call.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STATIC_CALL_H
+#define _ASM_STATIC_CALL_H
+
+#include <asm/asm-offsets.h>
+
+/*
+ * This trampoline is used for out-of-line static calls.  It has a direct jump
+ * which gets patched by static_call_update().
+ *
+ * Trampolines are placed in the .static_call.text section to prevent two-byte
+ * tail calls to the trampoline and two-byte jumps from the trampoline.
+ *
+ * IMPORTANT: The JMP instruction's 4-byte destination must never cross
+ *            cacheline boundaries!  The patching code relies on that to ensure
+ *            atomic updates.
+ */
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(key, func)			\
+	asm(".pushsection .static_call.text, \"ax\"		\n"	\
+	    ".align 8						\n"	\
+	    ".globl " STATIC_CALL_TRAMP_STR(key) "		\n"	\
+	    ".type " STATIC_CALL_TRAMP_STR(key) ", @function	\n"	\
+	    STATIC_CALL_TRAMP_STR(key) ":			\n"	\
+	    "jmp " #func "					\n"	\
+	    ".popsection					\n")
+
+#endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 00b7e27bc2b7..f1329a79fd3b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -63,6 +63,7 @@ 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/
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
new file mode 100644
index 000000000000..e6ef53fbce20
--- /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 __ref arch_static_call_transform(void *site, void *tramp, void *func)
+{
+	s32 dest_relative;
+	unsigned char opcode;
+	void *(*poker)(void *, const void *, size_t);
+	void *insn = tramp;
+
+	mutex_lock(&text_mutex);
+
+	/*
+	 * For x86-64, a 32-bit cross-modifying write to a call destination is
+	 * safe as long as it's within a cache line.
+	 */
+	opcode = *(unsigned char *)insn;
+	if (opcode != 0xe8 && opcode != 0xe9) {
+		WARN_ONCE(1, "unexpected static call insn opcode 0x%x at %pS",
+			  opcode, insn);
+		goto done;
+	}
+
+	dest_relative = (long)(func) - (long)(insn + CALL_INSN_SIZE);
+
+	poker = early_boot_irqs_disabled ? text_poke_early : text_poke;
+	poker(insn + 1, &dest_relative, sizeof(dest_relative));
+
+done:
+	mutex_unlock(&text_mutex);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0d618ee634ac..17470e88ac40 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -128,6 +128,7 @@ SECTIONS
 		CPUIDLE_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		STATIC_CALL_TEXT
 		ALIGN_ENTRY_TEXT_BEGIN
 		ENTRY_TEXT
 		IRQENTRY_TEXT
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3d7a6a9c2370..f2981a0161f2 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -320,6 +320,7 @@
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
+	STATIC_CALL_SITES						\
 	__end_ro_after_init = .;
 #endif
 
@@ -530,6 +531,10 @@
 		*(.kprobes.text)					\
 		__kprobes_text_end = .;
 
+#define STATIC_CALL_TEXT						\
+		ALIGN_FUNCTION();					\
+		*(.static_call.text)
+
 #define ENTRY_TEXT							\
 		ALIGN_FUNCTION();					\
 		__entry_text_start = .;					\
@@ -725,6 +730,16 @@
 #define BUG_TABLE
 #endif
 
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+#define STATIC_CALL_SITES						\
+	. = ALIGN(8);							\
+	__start_static_call_sites = .;					\
+	KEEP(*(.static_call_sites))					\
+	__stop_static_call_sites = .;
+#else
+#define STATIC_CALL_SITES
+#endif
+
 #ifdef CONFIG_UNWINDER_ORC
 #define ORC_UNWIND_TABLE						\
 	. = ALIGN(4);							\
-- 
2.17.2