mm/memcontrol: hoist pstatc_pcpu assignment out of CPU loop
Subsystems (3)
PATCH 1/1 mm/memcontrol: hoist pstatc_pcpu assignment out of CPU loop
From: Hui Zhu <[email protected]>
In mem_cgroup_alloc(), the assignment of pstatc_pcpu is invariant with respect to the for_each_possible_cpu() loop: both the 'parent' pointer and 'parent->vmstats_percpu' remain constant throughout all iterations.
The original code redundantly re-evaluated the 'if (parent)' condition and reassigned pstatc_pcpu on every CPU iteration, then repeated the same ternary check 'parent ? pstatc_pcpu : NULL' when storing into statc->parent_pcpu.
Move the single conditional assignment of pstatc_pcpu to before the loop, resolving both the loop-invariant placement issue and the duplicated null check. On systems with a large number of possible CPUs, this eliminates repeated branch evaluation with no functional change.
No functional change intended.
--- mm/memcontrol.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
mm/memcontrol.c +2 -3
@@ -3993,11 +3993,10 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)if (!memcg1_alloc_events (memcg)) goto fail; + pstatc_pcpu = parent ? parent->vmstats_percpu :NULL ;for_each_possible_cpu (cpu) { -if (parent) - pstatc_pcpu = parent->vmstats_percpu; statc =per_cpu_ptr (memcg->vmstats_percpu, cpu); - statc->parent_pcpu = parent ? pstatc_pcpu :NULL ; + statc->parent_pcpu = pstatc_pcpu; statc->vmstats = memcg->vmstats; }
Signature · 1 line
2.43.0
Andrew Morton
maintainerQuoted 27 lines · On Wed, 29 Apr 2026 16:42:16 +0800 Hui Zhu <[email protected]> wrote:
From: Hui Zhu <[email protected]>
In
mem_cgroup_alloc(), the assignment ofpstatc_pcpuis invariant with respect to thefor_each_possible_cpu()loop: both the 'parent' pointer and 'parent->vmstats_percpu' remain constant throughout all iterations.The original code redundantly re-evaluated the 'if (parent)' condition and reassigned
pstatc_pcpuon every CPU iteration, then repeated the same ternary check 'parent ?pstatc_pcpu: NULL' when storing intostatc->parent_pcpu.Move the single conditional assignment of
pstatc_pcputo before the loop, resolving both the loop-invariant placement issue and the duplicated null check. On systems with a large number of possible CPUs, this eliminates repeated branch evaluation with no functional change.No functional change intended.
...
mm/memcontrol.c +0
-0@@ -3993,11 +3993,10 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)if (!memcg1_alloc_events (memcg)) goto fail;
mm/memcontrol.c static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent) · line 4001
Quoted 10 lines
mm/memcontrol.c +2
-3+ pstatc_pcpu = parent ? parent->vmstats_percpu :NULL ;for_each_possible_cpu (cpu) { -if (parent) - pstatc_pcpu = parent->vmstats_percpu; statc =per_cpu_ptr (memcg->vmstats_percpu, cpu); - statc->parent_pcpu = parent ? pstatc_pcpu :NULL ; + statc->parent_pcpu = pstatc_pcpu; statc->vmstats = memcg->vmstats; }
lgtm.
I expected this to make no change to generated code but it actually reduces memcontrol.o text by nearly 300 bytes (x86_64 allmodconfig).
Quoted 12 lines · On Wed, 29 Apr 2026 16:42:16 +0800 Hui Zhu <[email protected]> wrote:
From: Hui Zhu <[email protected]>
In
mem_cgroup_alloc(), the assignment ofpstatc_pcpuis invariant with respect to thefor_each_possible_cpu()loop: both the 'parent' pointer and 'parent->vmstats_percpu' remain constant throughout all iterations.The original code redundantly re-evaluated the 'if (parent)' condition and reassigned
pstatc_pcpuon every CPU iteration, then repeated the same ternary check 'parent ?pstatc_pcpu: NULL' when storing intostatc->parent_pcpu.
Quoted 7 lines
Move the single conditional assignment of
pstatc_pcputo before the loop, resolving both the loop-invariant placement issue and the duplicated null check. On systems with a large number of possible CPUs, this eliminates repeated branch evaluation with no functional change.No functional change intended.
Makes sense and looks good to me.
Quoted 2 lines
Signed-off-by Hui Zhu <[email protected]>
Thanks,
SJ
[...]
Quoted 18 lines · Hui Zhu
From: Hui Zhu <[email protected]>
In
mem_cgroup_alloc(), the assignment ofpstatc_pcpuis invariant with respect to thefor_each_possible_cpu()loop: both the 'parent' pointer and 'parent->vmstats_percpu' remain constant throughout all iterations.The original code redundantly re-evaluated the 'if (parent)' condition and reassigned
pstatc_pcpuon every CPU iteration, then repeated the same ternary check 'parent ?pstatc_pcpu: NULL' when storing intostatc->parent_pcpu.Move the single conditional assignment of
pstatc_pcputo before the loop, resolving both the loop-invariant placement issue and the duplicated null check. On systems with a large number of possible CPUs, this eliminates repeated branch evaluation with no functional change.
Quoted 3 lines
No functional change intended.
Signed-off-by Hui Zhu <[email protected]>