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 4/4] virtio_ring: unify direct/indirect code paths.
Date: Thu, 29 May 2014 16:56:45 +0930 [thread overview]
Message-ID: <1401348405-18614-5-git-send-email-rusty@rustcorp.com.au> (raw)
In-Reply-To: <1401348405-18614-1-git-send-email-rusty@rustcorp.com.au>
virtqueue_add() populates the virtqueue descriptor table from the sgs
given. If it uses an indirect descriptor table, then it puts a single
descriptor in the descriptor table pointing to the kmalloc'ed indirect
table where the sg is populated.
Previously vring_add_indirect() did the allocation and the simple
linear layout. We replace that with alloc_indirect() which allocates
the indirect table then chains it like the normal descriptor table so
we can reuse the core logic.
Before:
gcc 4.8.2: virtio_blk: stack used = 392
gcc 4.6.4: virtio_blk: stack used = 480
After:
gcc 4.8.2: virtio_blk: stack used = 408
gcc 4.6.4: virtio_blk: stack used = 432
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
drivers/virtio/virtio_ring.c | 120 ++++++++++++++++---------------------------
1 file changed, 45 insertions(+), 75 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 5d29cd85d6cf..3adf5978b92b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -107,18 +107,10 @@ struct vring_virtqueue
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
-/* 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[],
- unsigned int total_sg,
- unsigned int out_sgs,
- unsigned int in_sgs,
- gfp_t gfp)
+static struct vring_desc *alloc_indirect(unsigned int total_sg, gfp_t gfp)
{
- struct vring_desc *desc;
- unsigned head;
- struct scatterlist *sg;
- int i, n;
+ struct vring_desc *desc;
+ unsigned int i;
/*
* We require lowmem mappings for the descriptors because
@@ -130,51 +122,13 @@ static inline int vring_add_indirect(struct vring_virtqueue *vq,
if (record_stack == current)
__asm__ __volatile__("movq %%rsp,%0" : "=g" (stack_top));
- desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
- if (!desc)
- return -ENOMEM;
-
- /* 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 = sg_next(sg)) {
- desc[i].flags = VRING_DESC_F_NEXT;
- desc[i].addr = sg_phys(sg);
- desc[i].len = sg->length;
- desc[i].next = i+1;
- i++;
- }
- }
- for (; n < (out_sgs + in_sgs); n++) {
- 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;
- desc[i].next = i+1;
- i++;
- }
- }
- BUG_ON(i != total_sg);
-
- /* Last one doesn't continue. */
- desc[i-1].flags &= ~VRING_DESC_F_NEXT;
- desc[i-1].next = 0;
-
- /* We're about to use a buffer */
- vq->vq.num_free--;
-
- /* Use a single buffer which doesn't continue */
- head = vq->free_head;
- vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
- vq->vring.desc[head].addr = virt_to_phys(desc);
- /* kmemleak gives a false positive, as it's hidden by virt_to_phys */
- kmemleak_ignore(desc);
- vq->vring.desc[head].len = i * sizeof(struct vring_desc);
-
- /* Update free pointer */
- vq->free_head = vq->vring.desc[head].next;
+ desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
+ if (!desc)
+ return NULL;
- return head;
+ for (i = 0; i < total_sg; i++)
+ desc[i].next = i+1;
+ return desc;
}
static inline int virtqueue_add(struct virtqueue *_vq,
@@ -187,6 +141,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
{
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
+ struct vring_desc *desc = NULL;
unsigned int i, n, avail, uninitialized_var(prev);
int head;
@@ -212,18 +167,32 @@ static inline int virtqueue_add(struct virtqueue *_vq,
}
#endif
+ BUG_ON(total_sg > vq->vring.num);
+ BUG_ON(total_sg == 0);
+
+ head = vq->free_head;
+
/* 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, total_sg,
- out_sgs, in_sgs, gfp);
- if (likely(head >= 0))
- goto add_head;
+ if (vq->indirect && total_sg > 1 && vq->vq.num_free)
+ desc = alloc_indirect(total_sg, gfp);
+
+ if (desc) {
+ /* Use a single buffer which doesn't continue */
+ vq->vring.desc[head].flags = VRING_DESC_F_INDIRECT;
+ vq->vring.desc[head].addr = virt_to_phys(desc);
+ /* avoid kmemleak false positive (tis hidden by virt_to_phys) */
+ kmemleak_ignore(desc);
+ vq->vring.desc[head].len = total_sg * sizeof(struct vring_desc);
+
+ /* Set up rest to use this indirect table. */
+ i = 0;
+ total_sg = 1;
+ } else {
+ desc = vq->vring.desc;
+ i = head;
}
- BUG_ON(total_sg > vq->vring.num);
- BUG_ON(total_sg == 0);
-
if (vq->vq.num_free < total_sg) {
pr_debug("Can't add buf len %i - avail = %i\n",
total_sg, vq->vq.num_free);
@@ -239,32 +208,33 @@ static inline int virtqueue_add(struct virtqueue *_vq,
/* We're about to use some buffers from the free list. */
vq->vq.num_free -= total_sg;
- head = i = vq->free_head;
for (n = 0; n < out_sgs; n++) {
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;
+ desc[i].flags = VRING_DESC_F_NEXT;
+ desc[i].addr = sg_phys(sg);
+ desc[i].len = sg->length;
prev = i;
- i = vq->vring.desc[i].next;
+ i = desc[i].next;
}
}
for (; n < (out_sgs + in_sgs); n++) {
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;
+ desc[i].flags = VRING_DESC_F_NEXT|VRING_DESC_F_WRITE;
+ desc[i].addr = sg_phys(sg);
+ desc[i].len = sg->length;
prev = i;
- i = vq->vring.desc[i].next;
+ i = desc[i].next;
}
}
/* Last one doesn't continue. */
- vq->vring.desc[prev].flags &= ~VRING_DESC_F_NEXT;
+ desc[prev].flags &= ~VRING_DESC_F_NEXT;
/* Update free pointer */
- vq->free_head = i;
+ if (desc == vq->vring.desc)
+ vq->free_head = i;
+ else
+ vq->free_head = vq->vring.desc[head].next;
-add_head:
/* Set token. */
vq->data[head] = data;
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2014-05-29 7:28 UTC|newest]
Thread overview: 97+ 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
2014-05-28 9:27 ` 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
2014-05-29 2:42 ` 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 ` [PATCH 3/4] virtio_ring: assume sgs are always well-formed Rusty Russell
2014-05-29 11:18 ` Michael S. Tsirkin
2014-05-29 7:26 ` Rusty Russell [this message]
2014-05-29 7:52 ` [PATCH 4/4] virtio_ring: unify direct/indirect code paths 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
2014-05-29 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
2014-05-30 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=1401348405-18614-5-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).