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
  ...

1 files changed, 42 insertions, 12 deletions

diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 09d344269652..79bd454b78a3 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -2,9 +2,13 @@
 
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
 
 /*
- * ISO C memset - set a memory block to a byte value.
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the orignal function as well.
  *	
  * rdi   destination
  * rsi   value (char) 
@@ -31,6 +35,28 @@
 .Lmemset_e:
 	.previous
 
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses
+ * enhanced rep stosb to override the fast string function.
+ * The code is simpler and shorter than the fast string function as well.
+ *
+ * rdi   destination
+ * rsi   value (char)
+ * rdx   count (bytes)
+ *
+ * rax   original destination
+ */
+	.section .altinstr_replacement, "ax", @progbits
+.Lmemset_c_e:
+	movq %rdi,%r9
+	movb %sil,%al
+	movl %edx,%ecx
+	rep stosb
+	movq %r9,%rax
+	ret
+.Lmemset_e_e:
+	.previous
+
 ENTRY(memset)
 ENTRY(__memset)
 	CFI_STARTPROC
@@ -112,16 +138,20 @@ ENTRY(__memset)
 ENDPROC(memset)
 ENDPROC(__memset)
 
-	/* Some CPUs run faster using the string instructions.
-	   It is also a lot simpler. Use this when possible */
-
-#include <asm/cpufeature.h>
-
+	/* Some CPUs support enhanced REP MOVSB/STOSB feature.
+	 * It is recommended to use this when possible.
+	 *
+	 * If enhanced REP MOVSB/STOSB feature is not available, use fast string
+	 * instructions.
+	 *
+	 * Otherwise, use original memset function.
+	 *
+	 * In .altinstructions section, ERMS feature is placed after REG_GOOD
+         * feature to implement the right patch order.
+	 */
 	.section .altinstructions,"a"
-	.align 8
-	.quad memset
-	.quad .Lmemset_c
-	.word X86_FEATURE_REP_GOOD
-	.byte .Lfinal - memset
-	.byte .Lmemset_e - .Lmemset_c
+	altinstruction_entry memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\
+			     .Lfinal-memset,.Lmemset_e-.Lmemset_c
+	altinstruction_entry memset,.Lmemset_c_e,X86_FEATURE_ERMS, \
+			     .Lfinal-memset,.Lmemset_e_e-.Lmemset_c_e
 	.previous