mirror of https://gitee.com/openkylin/linux.git
sched/x86: Optimize switch_mm() for multi-threaded workloads
Dick Fowles, Don Zickus and Joe Mario have been working on improvements to perf, and noticed heavy cache line contention on the mm_cpumask, running linpack on a 60 core / 120 thread system. The cause turned out to be unnecessary atomic accesses to the mm_cpumask. When in lazy TLB mode, the CPU is only removed from the mm_cpumask if there is a TLB flush event. Most of the time, no such TLB flush happens, and the kernel skips the TLB reload. It can also skip the atomic memory set & test. Here is a summary of Joe's test results: * The __schedule function dropped from 24% of all program cycles down to 5.5%. * The cacheline contention/hotness for accesses to that bitmask went from being the 1st/2nd hottest - down to the 84th hottest (0.3% of all shared misses which is now quite cold) * The average load latency for the bit-test-n-set instruction in __schedule dropped from 10k-15k cycles down to an average of 600 cycles. * The linpack program results improved from 133 GFlops to 144 GFlops. Peak GFlops rose from 133 to 153. Reported-by: Don Zickus <dzickus@redhat.com> Reported-by: Joe Mario <jmario@redhat.com> Tested-by: Joe Mario <jmario@redhat.com> Signed-off-by: Rik van Riel <riel@redhat.com> Reviewed-by: Paul Turner <pjt@google.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20130731221421.616d3d20@annuminas.surriel.com [ Made the comments consistent around the modified code. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
46591962cb
commit
8f898fbbe5
|
@ -45,12 +45,10 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
||||||
/* Re-load page tables */
|
/* Re-load page tables */
|
||||||
load_cr3(next->pgd);
|
load_cr3(next->pgd);
|
||||||
|
|
||||||
/* stop flush ipis for the previous mm */
|
/* Stop flush ipis for the previous mm */
|
||||||
cpumask_clear_cpu(cpu, mm_cpumask(prev));
|
cpumask_clear_cpu(cpu, mm_cpumask(prev));
|
||||||
|
|
||||||
/*
|
/* Load the LDT, if the LDT is different: */
|
||||||
* load the LDT, if the LDT is different:
|
|
||||||
*/
|
|
||||||
if (unlikely(prev->context.ldt != next->context.ldt))
|
if (unlikely(prev->context.ldt != next->context.ldt))
|
||||||
load_LDT_nolock(&next->context);
|
load_LDT_nolock(&next->context);
|
||||||
}
|
}
|
||||||
|
@ -59,8 +57,16 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
||||||
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
|
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
|
||||||
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
|
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
|
||||||
|
|
||||||
if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
|
if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
|
||||||
/* We were in lazy tlb mode and leave_mm disabled
|
/*
|
||||||
|
* On established mms, the mm_cpumask is only changed
|
||||||
|
* from irq context, from ptep_clear_flush() while in
|
||||||
|
* lazy tlb mode, and here. Irqs are blocked during
|
||||||
|
* schedule, protecting us from simultaneous changes.
|
||||||
|
*/
|
||||||
|
cpumask_set_cpu(cpu, mm_cpumask(next));
|
||||||
|
/*
|
||||||
|
* We were in lazy tlb mode and leave_mm disabled
|
||||||
* tlb flush IPI delivery. We must reload CR3
|
* tlb flush IPI delivery. We must reload CR3
|
||||||
* to make sure to use no freed page tables.
|
* to make sure to use no freed page tables.
|
||||||
*/
|
*/
|
||||||
|
|
Loading…
Reference in New Issue