Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 383f2835 authored by Kenneth W Chen's avatar Kenneth W Chen Committed by Linus Torvalds
Browse files

[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: default avatarKen Chen <kenneth.w.chen@intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent b0d62e6d

arch/ia64/kernel/entry.S

+23 −0
Original line number Diff line number Diff line
@@ -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

include/asm-ia64/system.h

+1 −0
Original line number Diff line number Diff line
@@ -275,6 +275,7 @@ extern void ia64_load_extra (struct task_struct *task); 
 */

#define __ARCH_WANT_UNLOCKED_CTXSW



#define ARCH_HAS_PREFETCH_SWITCH_STACK

#define ia64_platform_is(x) (strcmp(x, platform_name) == 0)



void cpu_idle_wait(void);

include/linux/sched.h

+5 −0
Original line number Diff line number Diff line
@@ -604,6 +604,11 @@ extern int groups_search(struct group_info *group_info, gid_t grp); 
#define GROUP_AT(gi, i) \

    ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK])



#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK

extern void prefetch_stack(struct task_struct*);

#else

static inline void prefetch_stack(struct task_struct *t) { }

#endif



struct audit_context;		/* See audit.c */

struct mempolicy;

kernel/sched.c

+1 −0
Original line number Diff line number Diff line
@@ -2888,6 +2888,7 @@ asmlinkage void __sched schedule(void) 
	if (next == rq->idle)

		schedstat_inc(rq, sched_goidle);

	prefetch(next);

	prefetch_stack(next);

	clear_tsk_need_resched(prev);

	rcu_qsctr_inc(task_cpu(prev));