Use atomic64_inc_return(&ref) instead of atomic64_add_return(1, &ref)
to use optimized implementation on targets that define
atomic_inc_return() and to remove now unneeded initialization of
%eax/%edx register pair before the call toatomic64_inc_return().
On x86_32 the code improves from:
1b0: b9 00 00 00 00 mov $0x0,%ecx
1b1: R_386_32 .bss
1b5: 89 43 0c mov %eax,0xc(%ebx)
1b8: 31 d2 xor %edx,%edx
1ba: b8 01 00 00 00 mov $0x1,%eax
1bf: e8 fc ff ff ff call 1c0 <ksys_ioperm+0xa8>
1c0: R_386_PC32 atomic64_add_return_cx8
1c4: 89 03 mov %eax,(%ebx)
1c6: 89 53 04 mov %edx,0x4(%ebx)
to:
1b0: be 00 00 00 00 mov $0x0,%esi
1b1: R_386_32 .bss
1b5: 89 43 0c mov %eax,0xc(%ebx)
1b8: e8 fc ff ff ff call 1b9 <ksys_ioperm+0xa1>
1b9: R_386_PC32 atomic64_inc_return_cx8
1bd: 89 03 mov %eax,(%ebx)
1bf: 89 53 04 mov %edx,0x4(%ebx)
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
---
v2: Mention specific code improvement on x86_32 target instead
of register pressure issue
---
arch/x86/kernel/ioport.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index e2fab3ceb09f..6290dd120f5e 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -144,7 +144,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
* Update the sequence number to force a TSS update on return to
* user mode.
*/
- iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
+ iobm->sequence = atomic64_inc_return(&io_bitmap_sequence);
return 0;
}
--
2.42.0