From: Rusty Russell <rusty@rustcorp.com.au>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Dave Chinner <david@fromorbit.com>, Jens Axboe <axboe@kernel.dk>,
Minchan Kim <minchan@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm <linux-mm@kvack.org>, "H. Peter Anvin" <hpa@zytor.com>,
Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Mel Gorman <mgorman@suse.de>, Rik van Riel <riel@redhat.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Dave Hansen <dave.hansen@intel.com>,
Steven Rostedt <rostedt@goodmis.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Subject: [PATCH 3/4] virtio_ring: assume sgs are always well-formed.
Date: Thu, 29 May 2014 16:56:44 +0930 [thread overview]
Message-ID: <1401348405-18614-4-git-send-email-rusty@rustcorp.com.au> (raw)
In-Reply-To: <1401348405-18614-1-git-send-email-rusty@rustcorp.com.au>
We used to have several callers which just used arrays. They're
gone, so we can use sg_next() everywhere, simplifying the code.
Before:
gcc 4.8.2: virtio_blk: stack used = 392
gcc 4.6.4: virtio_blk: stack used = 528
After:
gcc 4.8.2: virtio_blk: stack used = 392
gcc 4.6.4: virtio_blk: stack used = 480
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
drivers/virtio/virtio_ring.c | 68 +++++++++++++-------------------------------
1 file changed, 19 insertions(+), 49 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index f6ad99ffdc40..5d29cd85d6cf 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -107,28 +107,10 @@ struct vring_virtqueue
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
-static inline struct scatterlist *sg_next_chained(struct scatterlist *sg,
- unsigned int *count)
-{
- return sg_next(sg);
-}
-
-static inline struct scatterlist *sg_next_arr(struct scatterlist *sg,
- unsigned int *count)
-{
- if (--(*count) == 0)
- return NULL;
- return sg + 1;
-}
-
/* Set up an indirect table of descriptors and add it to the queue. */
static inline int vring_add_indirect(struct vring_virtqueue *vq,
struct scatterlist *sgs[],
- struct scatterlist *(*next)
- (struct scatterlist *, unsigned int *),
unsigned int total_sg,
- unsigned int total_out,
- unsigned int total_in,
unsigned int out_sgs,
unsigned int in_sgs,
gfp_t gfp)
@@ -155,7 +137,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
/* Transfer entries from the sg lists into the indirect page */
i = 0;
for (n = 0; n < out_sgs; n++) {
- for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
desc[i].flags = VRING_DESC_F_NEXT;
desc[i].addr = sg_phys(sg);
desc[i].len = sg->length;
@@ -164,7 +146,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
}
}
for (; n < (out_sgs + in_sgs); n++) {
- for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
desc[i].addr = sg_phys(sg);
desc[i].len = sg->length;
@@ -197,10 +179,7 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
static inline int virtqueue_add(struct virtqueue *_vq,
struct scatterlist *sgs[],
- struct scatterlist *(*next)
- (struct scatterlist *, unsigned int *),
- unsigned int total_out,
- unsigned int total_in,
+ unsigned int total_sg,
unsigned int out_sgs,
unsigned int in_sgs,
void *data,
@@ -208,7 +187,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
{
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
- unsigned int i, n, avail, uninitialized_var(prev), total_sg;
+ unsigned int i, n, avail, uninitialized_var(prev);
int head;
START_USE(vq);
@@ -233,13 +212,10 @@ static inline int virtqueue_add(struct virtqueue *_vq,
}
#endif
- total_sg = total_in + total_out;
-
/* If the host supports indirect descriptor tables, and we have multiple
* buffers, then go indirect. FIXME: tune this threshold */
if (vq->indirect && total_sg > 1 && vq->vq.num_free) {
- head = vring_add_indirect(vq, sgs, next, total_sg, total_out,
- total_in,
+ head = vring_add_indirect(vq, sgs, total_sg,
out_sgs, in_sgs, gfp);
if (likely(head >= 0))
goto add_head;
@@ -265,7 +241,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
head = i = vq->free_head;
for (n = 0; n < out_sgs; n++) {
- for (sg = sgs[n]; sg; sg = next(sg, &total_out)) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
vq->vring.desc[i].flags = VRING_DESC_F_NEXT;
vq->vring.desc[i].addr = sg_phys(sg);
vq->vring.desc[i].len = sg->length;
@@ -274,7 +250,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
}
}
for (; n < (out_sgs + in_sgs); n++) {
- for (sg = sgs[n]; sg; sg = next(sg, &total_in)) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
vq->vring.desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
vq->vring.desc[i].addr = sg_phys(sg);
vq->vring.desc[i].len = sg->length;
@@ -335,29 +311,23 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
void *data,
gfp_t gfp)
{
- unsigned int i, total_out, total_in;
+ unsigned int i, total_sg = 0;
/* Count them first. */
- for (i = total_out = total_in = 0; i < out_sgs; i++) {
- struct scatterlist *sg;
- for (sg = sgs[i]; sg; sg = sg_next(sg))
- total_out++;
- }
- for (; i < out_sgs + in_sgs; i++) {
+ for (i = 0; i < out_sgs + in_sgs; i++) {
struct scatterlist *sg;
for (sg = sgs[i]; sg; sg = sg_next(sg))
- total_in++;
+ total_sg++;
}
- return virtqueue_add(_vq, sgs, sg_next_chained,
- total_out, total_in, out_sgs, in_sgs, data, gfp);
+ return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
/**
* virtqueue_add_outbuf - expose output buffers to other end
* @vq: the struct virtqueue we're talking about.
- * @sgs: array of scatterlists (need not be terminated!)
- * @num: the number of scatterlists readable by other side
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg readable by other side
* @data: the token identifying the buffer.
* @gfp: how to do memory allocations (if necessary).
*
@@ -367,19 +337,19 @@ EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
* Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
*/
int virtqueue_add_outbuf(struct virtqueue *vq,
- struct scatterlist sg[], unsigned int num,
+ struct scatterlist *sg, unsigned int num,
void *data,
gfp_t gfp)
{
- return virtqueue_add(vq, &sg, sg_next_arr, num, 0, 1, 0, data, gfp);
+ return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
/**
* virtqueue_add_inbuf - expose input buffers to other end
* @vq: the struct virtqueue we're talking about.
- * @sgs: array of scatterlists (need not be terminated!)
- * @num: the number of scatterlists writable by other side
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
* @data: the token identifying the buffer.
* @gfp: how to do memory allocations (if necessary).
*
@@ -389,11 +359,11 @@ EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
* Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
*/
int virtqueue_add_inbuf(struct virtqueue *vq,
- struct scatterlist sg[], unsigned int num,
+ struct scatterlist *sg, unsigned int num,
void *data,
gfp_t gfp)
{
- return virtqueue_add(vq, &sg, sg_next_arr, 0, num, 0, 1, data, gfp);
+ return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
--
1.9.1
next prev parent reply other threads:[~2014-05-29 7:29 UTC|newest]
Thread overview: 107+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-28 6:53 [PATCH 1/2] ftrace: print stack usage right before Oops Minchan Kim
2014-05-28 6:53 ` [RFC 2/2] x86_64: expand kernel stack to 16K Minchan Kim
2014-05-28 8:37 ` Dave Chinner
2014-05-28 9:13 ` Dave Chinner
2014-05-28 16:06 ` Johannes Weiner
2014-05-28 21:55 ` Dave Chinner
2014-05-29 6:06 ` Minchan Kim
2014-05-28 9:04 ` Michael S. Tsirkin
2014-05-29 1:09 ` Minchan Kim
2014-05-29 2:44 ` Steven Rostedt
2014-05-29 4:11 ` Minchan Kim
2014-05-29 2:47 ` Rusty Russell
2014-05-29 4:10 ` virtio_ring stack usage Rusty Russell
2014-05-28 9:27 ` [RFC 2/2] x86_64: expand kernel stack to 16K Borislav Petkov
2014-05-29 13:23 ` One Thousand Gnomes
2014-05-28 14:14 ` Steven Rostedt
2014-05-28 14:23 ` H. Peter Anvin
2014-05-28 22:11 ` Dave Chinner
2014-05-28 22:42 ` H. Peter Anvin
2014-05-28 23:17 ` Dave Chinner
2014-05-28 23:21 ` H. Peter Anvin
2014-05-28 15:43 ` Richard Weinberger
2014-05-28 16:08 ` Steven Rostedt
2014-05-28 16:11 ` Richard Weinberger
2014-05-28 16:13 ` Linus Torvalds
2014-05-28 16:09 ` Linus Torvalds
2014-05-28 22:31 ` Dave Chinner
2014-05-28 22:41 ` Linus Torvalds
2014-05-29 1:30 ` Dave Chinner
2014-05-29 1:58 ` Dave Chinner
2014-05-29 2:51 ` Linus Torvalds
2014-05-29 23:36 ` Minchan Kim
2014-05-30 0:05 ` Linus Torvalds
2014-05-30 0:20 ` Minchan Kim
2014-05-30 0:31 ` Linus Torvalds
2014-05-30 0:50 ` Minchan Kim
2014-05-30 1:24 ` Linus Torvalds
2014-05-30 1:58 ` Dave Chinner
2014-05-30 2:13 ` Linus Torvalds
2014-05-30 6:21 ` Minchan Kim
2014-05-30 1:30 ` Linus Torvalds
2014-05-30 0:15 ` Dave Chinner
2014-05-30 2:12 ` Minchan Kim
2014-05-30 4:37 ` Linus Torvalds
2014-05-31 1:45 ` Linus Torvalds
2014-05-30 6:12 ` Minchan Kim
2014-06-03 13:28 ` Rasmus Villemoes
2014-06-03 19:04 ` Linus Torvalds
2014-06-10 12:29 ` [PATCH 0/2] Per-task wait_queue_t Rasmus Villemoes
2014-06-10 12:29 ` [PATCH 1/2] wait: Introduce per-task wait_queue_t Rasmus Villemoes
2014-06-11 15:16 ` Oleg Nesterov
2014-06-10 12:29 ` [PATCH 2/2] wait: Use the per-task wait_queue_t in ___wait_event macro Rasmus Villemoes
2014-06-10 15:50 ` [PATCH 0/2] Per-task wait_queue_t Peter Zijlstra
2014-06-12 21:46 ` Rasmus Villemoes
2014-05-29 2:42 ` [RFC 2/2] x86_64: expand kernel stack to 16K Linus Torvalds
2014-05-29 5:14 ` H. Peter Anvin
2014-05-29 6:01 ` Rusty Russell
2014-05-29 7:26 ` virtio ring cleanups, which save stack on older gcc Rusty Russell
2014-05-29 7:26 ` [PATCH 1/4] Hack: measure stack taken by vring from virtio_blk Rusty Russell
2014-05-29 15:39 ` Linus Torvalds
2014-05-29 7:26 ` [PATCH 2/4] virtio_net: pass well-formed sg to virtqueue_add_inbuf() Rusty Russell
2014-05-29 10:07 ` Michael S. Tsirkin
2014-05-29 7:26 ` Rusty Russell [this message]
2014-05-29 11:18 ` [PATCH 3/4] virtio_ring: assume sgs are always well-formed Michael S. Tsirkin
2014-05-29 7:26 ` [PATCH 4/4] virtio_ring: unify direct/indirect code paths Rusty Russell
2014-05-29 7:52 ` Peter Zijlstra
2014-05-29 11:05 ` Rusty Russell
2014-05-29 11:33 ` Michael S. Tsirkin
2014-05-29 11:29 ` Michael S. Tsirkin
2014-05-30 2:37 ` Rusty Russell
2014-05-30 6:21 ` Rusty Russell
2014-05-29 7:41 ` virtio ring cleanups, which save stack on older gcc Minchan Kim
2014-05-29 10:39 ` Dave Chinner
2014-05-29 11:08 ` Rusty Russell
2014-05-29 23:45 ` Minchan Kim
2014-05-30 1:06 ` Minchan Kim
2014-05-30 6:56 ` Rusty Russell
2014-05-29 7:26 ` [RFC 2/2] x86_64: expand kernel stack to 16K Dave Chinner
2014-05-29 15:24 ` Linus Torvalds
2014-05-29 23:40 ` Minchan Kim
2014-05-29 23:53 ` Dave Chinner
2014-05-30 0:06 ` Dave Jones
2014-05-30 0:21 ` Dave Chinner
2014-05-30 0:29 ` Dave Jones
2014-05-30 0:32 ` Minchan Kim
2014-05-30 1:34 ` Dave Chinner
2014-05-30 15:25 ` H. Peter Anvin
2014-05-30 15:41 ` Linus Torvalds
2014-05-30 15:52 ` H. Peter Anvin
2014-05-30 16:06 ` Linus Torvalds
2014-05-30 17:24 ` Dave Hansen
2014-05-30 18:12 ` H. Peter Anvin
2014-10-21 2:00 ` Dave Jones
2014-10-21 4:59 ` Andy Lutomirski
2014-05-30 9:48 ` Richard Weinberger
2014-05-30 15:36 ` Linus Torvalds
2014-05-31 2:06 ` Jens Axboe
2014-06-02 22:59 ` Dave Chinner
2014-06-03 13:02 ` Konstantin Khlebnikov
2014-05-29 3:46 ` Minchan Kim
2014-05-29 4:13 ` Linus Torvalds
2014-05-29 5:10 ` Minchan Kim
2014-05-30 21:23 ` Andi Kleen
2014-05-28 16:18 ` [PATCH 1/2] ftrace: print stack usage right before Oops Steven Rostedt
2014-05-29 3:52 ` Minchan Kim
2014-05-29 3:01 ` Steven Rostedt
2014-05-29 3:49 ` Minchan Kim
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=1401348405-18614-4-git-send-email-rusty@rustcorp.com.au \
--to=rusty@rustcorp.com.au \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=dave.hansen@intel.com \
--cc=david@fromorbit.com \
--cc=hannes@cmpxchg.org \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=minchan@kernel.org \
--cc=mingo@kernel.org \
--cc=mst@redhat.com \
--cc=riel@redhat.com \
--cc=rostedt@goodmis.org \
--cc=torvalds@linux-foundation.org \
/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).