| Message ID | 20221024081435.204970-4-bhe@redhat.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Cleanup and optimization patches for percpu | expand |
On Mon, Oct 24, 2022 at 04:14:30PM +0800, Baoquan He wrote: > The lock pcpu_alloc_mutex taking code has been moved to the beginning of > pcpu_allo() if it's non atomic allocation. So the code comment above Typo here ^ pcpu_alloc(). > above pcpu_create_chunk() callsite need be updated. > > Signed-off-by: Baoquan He <bhe@redhat.com> > --- > mm/percpu.c | 6 +----- > 1 file changed, 1 insertion(+), 5 deletions(-) > > diff --git a/mm/percpu.c b/mm/percpu.c > index a3fde4ac03a4..a8121302a79c 100644 > --- a/mm/percpu.c > +++ b/mm/percpu.c > @@ -1817,16 +1817,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, > > spin_unlock_irqrestore(&pcpu_lock, flags); > > - /* > - * No space left. Create a new chunk. We don't want multiple > - * tasks to create chunks simultaneously. Serialize and create iff > - * there's still no empty chunk after grabbing the mutex. > - */ > if (is_atomic) { > err = "atomic alloc failed, no space left"; > goto fail; > } > > + /* No space left. Create a new chunk. */ > if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { > chunk = pcpu_create_chunk(pcpu_gfp); > if (!chunk) { > -- > 2.34.1 > > Acked-by: Dennis Zhou <dennis@kernel.org> Thanks, Dennis
diff --git a/mm/percpu.c b/mm/percpu.c index a3fde4ac03a4..a8121302a79c 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1817,16 +1817,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, spin_unlock_irqrestore(&pcpu_lock, flags); - /* - * No space left. Create a new chunk. We don't want multiple - * tasks to create chunks simultaneously. Serialize and create iff - * there's still no empty chunk after grabbing the mutex. - */ if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } + /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) {
The lock pcpu_alloc_mutex taking code has been moved to the beginning of pcpu_allo() if it's non atomic allocation. So the code comment above above pcpu_create_chunk() callsite need be updated. Signed-off-by: Baoquan He <bhe@redhat.com> --- mm/percpu.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)