redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

[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>
hifive-unleashed-5.1
Chen, Kenneth W 2005-09-09 13:02:02 -07:00 committed by Linus Torvalds
parent b0d62e6d5b
commit 383f2835eb
4 changed files with 30 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
arch/ia64/kernel/entry.S
View File

@ -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

1
include/asm-ia64/system.h
View File

@ -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);

5
include/linux/sched.h
View File

@ -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;

1
kernel/sched.c
View File

@ -2888,6 +2888,7 @@ switch_tasks:
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));