[PATCH] Prefetch kernel stacks to speed up context switch

For architecture like ia64, the switch stack structure is fairly large
(currently 528 bytes).  For context switch intensive application, we found
that significant amount of cache misses occurs in switch_to() function.
The following patch adds a hook in the schedule() function to prefetch
switch stack structure as soon as 'next' task is determined.  This allows
maximum overlap in prefetch cache lines for that structure.

Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 23 insertions, 0 deletions

diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 3c8821024509..915e12791836 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -470,6 +470,29 @@ ENTRY(load_switch_stack)
         br.cond.sptk.many b7
 END(load_switch_stack)
 
+GLOBAL_ENTRY(prefetch_stack)
+        add r14 = -IA64_SWITCH_STACK_SIZE, sp
+        add r15 = IA64_TASK_THREAD_KSP_OFFSET, in0
+        ;;
+        ld8 r16 = [r15]                         // load next's stack pointer
+        lfetch.fault.excl [r14], 128
+        ;;
+        lfetch.fault.excl [r14], 128
+        lfetch.fault [r16], 128
+        ;;
+        lfetch.fault.excl [r14], 128
+        lfetch.fault [r16], 128
+        ;;
+        lfetch.fault.excl [r14], 128
+        lfetch.fault [r16], 128
+        ;;
+        lfetch.fault.excl [r14], 128
+        lfetch.fault [r16], 128
+        ;;
+        lfetch.fault [r16], 128
+        br.ret.sptk.many rp
+END(prefetch_switch_stack)
+
 GLOBAL_ENTRY(execve)
         mov r15=__NR_execve                     // put syscall number in place
         break __BREAK_SYSCALL