From: Ming Lei <ming.lei@redhat.com>
To: Caleb Sander Mateos <csander@purestorage.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org,
Uday Shankar <ushankar@purestorage.com>,
Stefani Seibold <stefani@seibold.net>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH V3 01/27] kfifo: add kfifo_alloc_node() helper for NUMA awareness
Date: Sun, 16 Nov 2025 19:59:44 +0800 [thread overview]
Message-ID: <aRm8sDRh2UEjpYH_@fedora> (raw)
In-Reply-To: <CADUfDZrSO5eAwzjzedMf1gHTUv3Bv7JPL-nspqQG4bQE+F=6XA@mail.gmail.com>
On Fri, Nov 14, 2025 at 08:14:29PM -0800, Caleb Sander Mateos wrote:
> On Wed, Nov 12, 2025 at 1:38 AM Ming Lei <ming.lei@redhat.com> wrote:
> >
> > Add __kfifo_alloc_node() by refactoring and reusing __kfifo_alloc(),
> > and define kfifo_alloc_node() macro to support NUMA-aware memory
> > allocation.
> >
> > The new __kfifo_alloc_node() function accepts a NUMA node parameter
> > and uses kmalloc_array_node() instead of kmalloc_array() for
> > node-specific allocation. The existing __kfifo_alloc() now calls
> > __kfifo_alloc_node() with NUMA_NO_NODE to maintain backward
> > compatibility.
> >
> > This enables users to allocate kfifo buffers on specific NUMA nodes,
> > which is important for performance in NUMA systems where the kfifo
> > will be primarily accessed by threads running on specific nodes.
> >
> > Cc: Stefani Seibold <stefani@seibold.net>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > Cc: linux-kernel@vger.kernel.org
> > Signed-off-by: Ming Lei <ming.lei@redhat.com>
> > ---
> > include/linux/kfifo.h | 27 +++++++++++++++++++++++++++
> > lib/kfifo.c | 13 ++++++++++---
> > 2 files changed, 37 insertions(+), 3 deletions(-)
> >
> > diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
> > index fd743d4c4b4b..61d1fe014a6c 100644
> > --- a/include/linux/kfifo.h
> > +++ b/include/linux/kfifo.h
> > @@ -369,6 +369,30 @@ __kfifo_int_must_check_helper( \
> > }) \
> > )
> >
> > +/**
> > + * kfifo_alloc_node - dynamically allocates a new fifo buffer on a NUMA node
> > + * @fifo: pointer to the fifo
> > + * @size: the number of elements in the fifo, this must be a power of 2
> > + * @gfp_mask: get_free_pages mask, passed to kmalloc()
> > + * @node: NUMA node to allocate memory on
> > + *
> > + * This macro dynamically allocates a new fifo buffer with NUMA node awareness.
> > + *
> > + * The number of elements will be rounded-up to a power of 2.
> > + * The fifo will be release with kfifo_free().
> > + * Return 0 if no error, otherwise an error code.
> > + */
> > +#define kfifo_alloc_node(fifo, size, gfp_mask, node) \
> > +__kfifo_int_must_check_helper( \
> > +({ \
> > + typeof((fifo) + 1) __tmp = (fifo); \
> > + struct __kfifo *__kfifo = &__tmp->kfifo; \
> > + __is_kfifo_ptr(__tmp) ? \
> > + __kfifo_alloc_node(__kfifo, size, sizeof(*__tmp->type), gfp_mask, node) : \
> > + -EINVAL; \
> > +}) \
> > +)
> > +
> > /**
> > * kfifo_free - frees the fifo
> > * @fifo: the fifo to be freed
> > @@ -902,6 +926,9 @@ __kfifo_uint_must_check_helper( \
> > extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
> > size_t esize, gfp_t gfp_mask);
> >
> > +extern int __kfifo_alloc_node(struct __kfifo *fifo, unsigned int size,
> > + size_t esize, gfp_t gfp_mask, int node);
> > +
> > extern void __kfifo_free(struct __kfifo *fifo);
> >
> > extern int __kfifo_init(struct __kfifo *fifo, void *buffer,
> > diff --git a/lib/kfifo.c b/lib/kfifo.c
> > index a8b2eed90599..195cf0feecc2 100644
> > --- a/lib/kfifo.c
> > +++ b/lib/kfifo.c
> > @@ -22,8 +22,8 @@ static inline unsigned int kfifo_unused(struct __kfifo *fifo)
> > return (fifo->mask + 1) - (fifo->in - fifo->out);
> > }
> >
> > -int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
> > - size_t esize, gfp_t gfp_mask)
> > +int __kfifo_alloc_node(struct __kfifo *fifo, unsigned int size,
> > + size_t esize, gfp_t gfp_mask, int node)
> > {
> > /*
> > * round up to the next power of 2, since our 'let the indices
> > @@ -41,7 +41,7 @@ int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
> > return -EINVAL;
> > }
> >
> > - fifo->data = kmalloc_array(esize, size, gfp_mask);
> > + fifo->data = kmalloc_array_node(esize, size, gfp_mask, node);
> >
> > if (!fifo->data) {
> > fifo->mask = 0;
> > @@ -51,6 +51,13 @@ int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
> >
> > return 0;
> > }
> > +EXPORT_SYMBOL(__kfifo_alloc_node);
> > +
> > +int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
> > + size_t esize, gfp_t gfp_mask)
> > +{
> > + return __kfifo_alloc_node(fifo, size, esize, gfp_mask, NUMA_NO_NODE);
> > +}
> > EXPORT_SYMBOL(__kfifo_alloc);
>
> Is it worth keeping __kfifo_alloc() as an extern function? Seems like
> it would make the executable smaller to turn __kfifo_alloc() into a
> static inline function that just defers to __kfifo_alloc_node().
OK, will convert to inline __kfifo_alloc() in next version.
Thanks,
Ming
next prev parent reply other threads:[~2025-11-16 12:00 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-12 9:37 [PATCH V3 00/27] ublk: add UBLK_F_BATCH_IO Ming Lei
2025-11-12 9:37 ` [PATCH V3 01/27] kfifo: add kfifo_alloc_node() helper for NUMA awareness Ming Lei
2025-11-12 19:29 ` Andrew Morton
2025-11-13 1:21 ` Ming Lei
2025-11-13 22:06 ` Andrew Morton
2025-11-15 4:14 ` Caleb Sander Mateos
2025-11-16 11:59 ` Ming Lei [this message]
2025-11-12 9:37 ` [PATCH V3 02/27] ublk: add parameter `struct io_uring_cmd *` to ublk_prep_auto_buf_reg() Ming Lei
2025-11-12 9:37 ` [PATCH V3 03/27] ublk: add `union ublk_io_buf` with improved naming Ming Lei
2025-11-12 9:37 ` [PATCH V3 04/27] ublk: refactor auto buffer register in ublk_dispatch_req() Ming Lei
2025-11-15 5:10 ` Caleb Sander Mateos
2025-11-12 9:37 ` [PATCH V3 05/27] ublk: pass const pointer to ublk_queue_is_zoned() Ming Lei
2025-11-15 5:11 ` Caleb Sander Mateos
2025-11-12 9:37 ` [PATCH V3 06/27] ublk: add helper of __ublk_fetch() Ming Lei
2025-11-15 5:21 ` Caleb Sander Mateos
2025-11-16 12:02 ` Ming Lei
2025-11-17 18:29 ` Caleb Sander Mateos
2025-11-12 9:37 ` [PATCH V3 07/27] ublk: define ublk_ch_batch_io_fops for the coming feature F_BATCH_IO Ming Lei
2025-11-12 9:37 ` [PATCH V3 08/27] ublk: prepare for not tracking task context for command batch Ming Lei
2025-11-15 5:25 ` Caleb Sander Mateos
2025-11-16 12:02 ` Ming Lei
2025-11-12 9:37 ` [PATCH V3 09/27] ublk: add new batch command UBLK_U_IO_PREP_IO_CMDS & UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2025-11-17 21:08 ` Caleb Sander Mateos
2025-11-18 2:11 ` Ming Lei
2025-11-18 2:38 ` Caleb Sander Mateos
2025-11-19 2:37 ` Caleb Sander Mateos
2025-11-19 2:39 ` Caleb Sander Mateos
2025-11-19 9:49 ` Ming Lei
2025-11-12 9:37 ` [PATCH V3 10/27] ublk: handle UBLK_U_IO_PREP_IO_CMDS Ming Lei
2025-11-19 2:49 ` Caleb Sander Mateos
2025-11-19 9:56 ` Ming Lei
2025-11-19 16:09 ` Caleb Sander Mateos
2025-11-12 9:37 ` [PATCH V3 11/27] ublk: handle UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2025-11-12 9:37 ` [PATCH V3 12/27] ublk: add io events fifo structure Ming Lei
2025-11-12 9:37 ` [PATCH V3 13/27] ublk: add batch I/O dispatch infrastructure Ming Lei
2025-11-12 9:37 ` [PATCH V3 14/27] ublk: add UBLK_U_IO_FETCH_IO_CMDS for batch I/O processing Ming Lei
2025-11-12 9:37 ` [PATCH V3 15/27] ublk: abort requests filled in event kfifo Ming Lei
2025-11-12 9:37 ` [PATCH V3 16/27] ublk: add new feature UBLK_F_BATCH_IO Ming Lei
2025-11-12 9:37 ` [PATCH V3 17/27] ublk: document " Ming Lei
2025-11-12 9:37 ` [PATCH V3 18/27] ublk: implement batch request completion via blk_mq_end_request_batch() Ming Lei
2025-11-12 9:37 ` [PATCH V3 19/27] selftests: ublk: fix user_data truncation for tgt_data >= 256 Ming Lei
2025-11-12 9:37 ` [PATCH V3 20/27] selftests: ublk: replace assert() with ublk_assert() Ming Lei
2025-11-12 9:37 ` [PATCH V3 21/27] selftests: ublk: add ublk_io_buf_idx() for returning io buffer index Ming Lei
2025-11-12 9:38 ` [PATCH V3 22/27] selftests: ublk: add batch buffer management infrastructure Ming Lei
2025-11-12 9:38 ` [PATCH V3 23/27] selftests: ublk: handle UBLK_U_IO_PREP_IO_CMDS Ming Lei
2025-11-12 9:38 ` [PATCH V3 24/27] selftests: ublk: handle UBLK_U_IO_COMMIT_IO_CMDS Ming Lei
2025-11-12 9:38 ` [PATCH V3 25/27] selftests: ublk: handle UBLK_U_IO_FETCH_IO_CMDS Ming Lei
2025-11-12 9:38 ` [PATCH V3 26/27] selftests: ublk: add --batch/-b for enabling F_BATCH_IO Ming Lei
2025-11-12 9:38 ` [PATCH V3 27/27] selftests: ublk: support arbitrary threads/queues combination Ming Lei
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aRm8sDRh2UEjpYH_@fedora \
--to=ming.lei@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=csander@purestorage.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stefani@seibold.net \
--cc=ushankar@purestorage.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).