diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-05-19 17:36:08 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-05-19 17:36:08 -0700 |
| commit | df48d8716eab9608fe93924e4ae06ff110e8674f (patch) | |
| tree | 0fe10733a414b3651e1dae29518b7960a4da0aa4 /arch/x86/lib/clear_page_64.S | |
| parent | acd30250d7d0f495685d1c7c6184636a22fcdf7f (diff) | |
| parent | 29510ec3b626c86de9707bb8904ff940d430289b (diff) | |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (107 commits)
perf stat: Add more cache-miss percentage printouts
perf stat: Add -d -d and -d -d -d options to show more CPU events
ftrace/kbuild: Add recordmcount files to force full build
ftrace: Add self-tests for multiple function trace users
ftrace: Modify ftrace_set_filter/notrace to take ops
ftrace: Allow dynamically allocated function tracers
ftrace: Implement separate user function filtering
ftrace: Free hash with call_rcu_sched()
ftrace: Have global_ops store the functions that are to be traced
ftrace: Add ops parameter to ftrace_startup/shutdown functions
ftrace: Add enabled_functions file
ftrace: Use counters to enable functions to trace
ftrace: Separate hash allocation and assignment
ftrace: Create a global_ops to hold the filter and notrace hashes
ftrace: Use hash instead for FTRACE_FL_FILTER
ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions
perf bench, x86: Add alternatives-asm.h wrapper
x86, 64-bit: Fix copy_[to/from]_user() checks for the userspace address limit
x86, mem: memset_64.S: Optimize memset by enhanced REP MOVSB/STOSB
x86, mem: memmove_64.S: Optimize memmove by enhanced REP MOVSB/STOSB
...
Diffstat (limited to 'arch/x86/lib/clear_page_64.S')
| -rw-r--r-- | arch/x86/lib/clear_page_64.S | 33 |
1 files changed, 24 insertions, 9 deletions
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index aa4326bfb24..f2145cfa12a 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,6 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> +#include <asm/alternative-asm.h> /* * Zero a page. @@ -14,6 +15,15 @@ ENTRY(clear_page_c) CFI_ENDPROC ENDPROC(clear_page_c) +ENTRY(clear_page_c_e) + CFI_STARTPROC + movl $4096,%ecx + xorl %eax,%eax + rep stosb + ret + CFI_ENDPROC +ENDPROC(clear_page_c_e) + ENTRY(clear_page) CFI_STARTPROC xorl %eax,%eax @@ -38,21 +48,26 @@ ENTRY(clear_page) .Lclear_page_end: ENDPROC(clear_page) - /* Some CPUs run faster using the string instructions. - It is also a lot simpler. Use this when possible */ + /* + * Some CPUs support enhanced REP MOVSB/STOSB instructions. + * It is recommended to use this when possible. + * If enhanced REP MOVSB/STOSB is not available, try to use fast string. + * Otherwise, use original function. + * + */ #include <asm/cpufeature.h> .section .altinstr_replacement,"ax" 1: .byte 0xeb /* jmp <disp8> */ .byte (clear_page_c - clear_page) - (2f - 1b) /* offset */ -2: +2: .byte 0xeb /* jmp <disp8> */ + .byte (clear_page_c_e - clear_page) - (3f - 2b) /* offset */ +3: .previous .section .altinstructions,"a" - .align 8 - .quad clear_page - .quad 1b - .word X86_FEATURE_REP_GOOD - .byte .Lclear_page_end - clear_page - .byte 2b - 1b + altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\ + .Lclear_page_end-clear_page, 2b-1b + altinstruction_entry clear_page,2b,X86_FEATURE_ERMS, \ + .Lclear_page_end-clear_page,3b-2b .previous |