arm64: implement support for static call trampolines

Implement arm64 support for the 'unoptimized' static call variety, which routes all calls through a single trampoline that is patched to perform a tail call to the selected function.

It is expected that the direct branch instruction will be able to cover the common case. However, given that static call targets may be located in modules loaded out of direct branching range, we need a fallback path that loads the address into R16 and uses a branch-to-register (BR) instruction to perform an indirect call.

Unlike on x86, there is no pressing need on arm64 to avoid indirect calls at all cost, but hiding it from the compiler as is done here does have some benefits:
- the literal is located in .text, which gives us the same robustness advantage that code patching does;
- no performance hit on CFI enabled Clang builds that decorate compiler emitted indirect calls with branch target validity checks.

---
This is a follow-up to Frederic's rebase [0] of my v3 sent out a while ago [1]. Even though Frederic's changes depend on the static call API, this patch can be reviewed in isolation, so I am sending it as a single patch.

[0] https://lore.kernel.org/all/[email protected]/
[1] https://lore.kernel.org/linux-arm-kernel/[email protected]/

 arch/arm64/Kconfig                   |  1 +
 arch/arm64/include/asm/static_call.h | 25 ++++++++++
 arch/arm64/kernel/patching.c         | 51 ++++++++++++++++++--
 arch/arm64/kernel/vmlinux.lds.S      |  1 +
 4 files changed, 75 insertions(+), 3 deletions(-)

index 5c7ae4c3954b..5b51b359ccda 100644
@@ -192,6 +192,7 @@ config ARM64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_STATIC_CALL
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select MMU_GATHER_RCU_TABLE_FREE

new file mode 100644
index 000000000000..143879efc382
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STATIC_CALL_H
+#define _ASM_STATIC_CALL_H
+
+#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insn)			    \
+	asm("	.pushsection	.static_call.text, \"ax\"		\n" \
+	    "	.align		4					\n" \
+	    "	.globl		" STATIC_CALL_TRAMP_STR(name) "		\n" \
+	    "0:	.quad	0x0						\n" \
+	    STATIC_CALL_TRAMP_STR(name) ":				\n" \
+	    "	hint 	34	/* BTI C */				\n" \
+		insn "							\n" \
+	    "	ldr	x16, 0b						\n" \
+	    "	cbz	x16, 1f						\n" \
+	    "	br	x16						\n" \
+	    "1:	ret							\n" \
+	    "	.popsection						\n")
+
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "b " #func)
+
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret")
+
+#endif /* _ASM_STATIC_CALL_H */

index f6b1a88245db..ceb35c35192c 100644
@@ -161,6 +161,7 @@ SECTIONS
 			IDMAP_TEXT
 			HIBERNATE_TEXT
 			TRAMP_TEXT
+			STATIC_CALL_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);

2.30.2


_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel