mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-09-04 20:19:47 +08:00
452cddbff7
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
41 lines
1.6 KiB
C
41 lines
1.6 KiB
C
/* 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_INLINE, this is a temporary trampoline which
|
|
* uses the current value of the key->func pointer to do an indirect jump to
|
|
* the function. This trampoline is only used during boot, before the call
|
|
* sites get patched by static_call_update(). The name of this trampoline has
|
|
* a magical aspect: objtool uses it to find static call sites so it can create
|
|
* the .static_call_sites section.
|
|
*
|
|
* 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().
|
|
*
|
|
* Having the trampoline in a special section forces GCC to emit a JMP.d32 when
|
|
* it does tail-call optimization on the call; since you cannot compute the
|
|
* relative displacement across sections.
|
|
*/
|
|
|
|
#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \
|
|
asm(".pushsection .static_call.text, \"ax\" \n" \
|
|
".align 4 \n" \
|
|
".globl " STATIC_CALL_TRAMP_STR(name) " \n" \
|
|
STATIC_CALL_TRAMP_STR(name) ": \n" \
|
|
insns " \n" \
|
|
".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \
|
|
".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
|
|
".popsection \n")
|
|
|
|
#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \
|
|
__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
|
|
|
|
#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \
|
|
__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
|
|
|
|
#endif /* _ASM_STATIC_CALL_H */
|