Re: Pipe buffers' limit of 16 * 4K

From: Jens Axboe
Date: Fri May 30 2008 - 06:35:47 EST

On Thu, May 29 2008, Fausto Richetti Blanco wrote:
> On Thu, May 29, 2008 at 11:36 AM, Jan Engelhardt <jengelh@xxxxxxxxxx> wrote:
> >
> > On Thursday 2008-05-29 15:19, Miquel van Smoorenburg wrote:
> >>On Thu, 2008-05-29 at 10:00 -0300, Fausto Richetti Blanco wrote:
> >>
> >>Why not use a socketpair() instead of a pipe(). You can adjust the size
> >>with setsockopt SO_SNDBUF/SO_RCVBUF (see man socket(7))
> >
> > Nah, if there's lots of POST requests, and a large buffer for
> > each of it, you may end up running into allocation failures.
>
> Well, I think it's an alternative.. A good one, indeed :)
>
> However, I implemented it and run into the limit of /proc/sys/net/core/wmem_max
>
> Do you guys think it's a big impact to change this to a higher value ?
> It's meant to only affect the MAX window size, right ? Does it have
> any other way of changing this limit (by process or by user, for
> exemple) ?
>
> The strange thing here is that setsockopt doesn't fail if I change the
> size of the buffer to anything higher than
> /proc/sys/net/core/wmem_max. It doesn't work either :)
>
> The implementation with socketpair, adjusting
> /proc/sys/net/core/wmem_max, seems good to me. However, I still think
> dynamic buffers for pipes a good idea.

I have an old patch that does that, I just looked it up and it was last
updated for 2.6.23. It uses fcntl() with F_SETPIPE_SZ for getting and
setting the pipe size.

Patch updated, the below is the current Linus kernel.

diff --git a/fs/fcntl.c b/fs/fcntl.c
index bfd7765..aea3f5b 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -15,6 +15,7 @@
#include <linux/smp_lock.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/pipe_fs_i.h>
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/signal.h>
@@ -370,6 +371,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
case F_NOTIFY:
err = fcntl_dirnotify(fd, filp, arg);
break;
+ case F_SETPIPE_SZ:
+ case F_GETPIPE_SZ:
+ err = pipe_fcntl(filp, cmd, arg);
+ break;
default:
break;
}
diff --git a/fs/pipe.c b/fs/pipe.c
index ec228bc..d6b5c7e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/log2.h>
#include <linux/mount.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
@@ -342,7 +343,7 @@ redo:
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
- curbuf = (curbuf + 1) & (PIPE_BUFFERS-1);
+ curbuf = (curbuf + 1) & (pipe->buffers - 1);
pipe->curbuf = curbuf;
pipe->nrbufs = --bufs;
do_wakeup = 1;
@@ -424,7 +425,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
if (pipe->nrbufs && chars != 0) {
int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
- (PIPE_BUFFERS-1);
+ (pipe->buffers - 1);
struct pipe_buffer *buf = pipe->bufs + lastbuf;
const struct pipe_buf_operations *ops = buf->ops;
int offset = buf->offset + buf->len;
@@ -470,8 +471,8 @@ redo1:
break;
}
bufs = pipe->nrbufs;
- if (bufs < PIPE_BUFFERS) {
- int newbuf = (pipe->curbuf + bufs) & (PIPE_BUFFERS-1);
+ if (bufs < pipe->buffers) {
+ int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
struct pipe_buffer *buf = pipe->bufs + newbuf;
struct page *page = pipe->tmp_page;
char *src;
@@ -532,7 +533,7 @@ redo2:
if (!total_len)
break;
}
- if (bufs < PIPE_BUFFERS)
+ if (bufs < pipe->buffers)
continue;
if (filp->f_flags & O_NONBLOCK) {
if (!ret)
@@ -592,7 +593,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
nrbufs = pipe->nrbufs;
while (--nrbufs >= 0) {
count += pipe->bufs[buf].len;
- buf = (buf+1) & (PIPE_BUFFERS-1);
+ buf = (buf+1) & (pipe->buffers - 1);
}
mutex_unlock(&inode->i_mutex);

@@ -623,7 +624,7 @@ pipe_poll(struct file *filp, poll_table *wait)
}

if (filp->f_mode & FMODE_WRITE) {
- mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0;
+ mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0;
/*
* Most Unices do not set POLLERR for FIFOs but on Linux they
* behave exactly like pipes for poll().
@@ -858,25 +859,32 @@ struct pipe_inode_info * alloc_pipe_info(struct inode *inode)

pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
if (pipe) {
- init_waitqueue_head(&pipe->wait);
- pipe->r_counter = pipe->w_counter = 1;
- pipe->inode = inode;
+ pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+ if (pipe->bufs) {
+ init_waitqueue_head(&pipe->wait);
+ pipe->r_counter = pipe->w_counter = 1;
+ pipe->inode = inode;
+ pipe->buffers = PIPE_DEF_BUFFERS;
+ return pipe;
+ }
+ kfree(pipe);
}

- return pipe;
+ return NULL;
}

void __free_pipe_info(struct pipe_inode_info *pipe)
{
int i;

- for (i = 0; i < PIPE_BUFFERS; i++) {
+ for (i = 0; i < pipe->buffers; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
if (buf->ops)
buf->ops->release(pipe, buf);
}
if (pipe->tmp_page)
__free_page(pipe->tmp_page);
+ kfree(pipe->bufs);
kfree(pipe);
}

@@ -1097,6 +1105,81 @@ asmlinkage long __weak sys_pipe(int __user *fildes)
}

/*
+ * Allocate a new array of pipe buffers and copy the info over. Returns the
+ * pipe size if successful, or return -ERROR on error.
+ */
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+{
+ struct pipe_buffer *bufs;
+
+ /*
+ * Must be a power-of-2 currently
+ */
+ if (!is_power_of_2(arg))
+ return -EINVAL;
+
+ /*
+ * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
+ * expect a lot of shrink+grow operations, just free and allocate
+ * again like we would do for growing. If the pipe currently
+ * contains more buffers than arg, then return busy.
+ */
+ if (arg < pipe->nrbufs)
+ return -EBUSY;
+
+ bufs = kcalloc(arg, sizeof(struct pipe_buffer), GFP_KERNEL);
+ if (unlikely(!bufs))
+ return -ENOMEM;
+
+ /*
+ * The pipe array wraps around, so just start the new one at zero
+ * and adjust the indexes.
+ */
+ if (pipe->nrbufs) {
+ const unsigned int tail = pipe->nrbufs & (pipe->buffers - 1);
+ const unsigned int head = pipe->nrbufs - tail;
+
+ if (head)
+ memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
+ if (tail)
+ memcpy(bufs + head, pipe->bufs + pipe->curbuf, tail * sizeof(struct pipe_buffer));
+ }
+
+ pipe->curbuf = 0;
+ kfree(pipe->bufs);
+ pipe->bufs = bufs;
+ pipe->buffers = arg;
+ return arg;
+}
+
+long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pipe_inode_info *pipe;
+ long ret;
+
+ pipe = file->f_path.dentry->d_inode->i_pipe;
+ if (!pipe)
+ return -EBADF;
+
+ mutex_lock(&pipe->inode->i_mutex);
+
+ switch (cmd) {
+ case F_SETPIPE_SZ:
+ ret = pipe_set_size(pipe, arg);
+ break;
+ case F_GETPIPE_SZ:
+ ret = pipe->buffers;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ mutex_unlock(&pipe->inode->i_mutex);
+ return ret;
+}
+
+/*
* pipefs should _never_ be mounted by userland - too much of security hassle,
* no real gain from having the whole whorehouse mounted. So we don't need
* any operations on the root directory. However, we need a non-trivial
diff --git a/fs/splice.c b/fs/splice.c
index aa5f6f6..8e11996 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -191,8 +191,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
break;
}

- if (pipe->nrbufs < PIPE_BUFFERS) {
- int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
+ if (pipe->nrbufs < pipe->buffers) {
+ int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
struct pipe_buffer *buf = pipe->bufs + newbuf;

buf->page = spd->pages[page_nr];
@@ -212,7 +212,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,

if (!--spd->nr_pages)
break;
- if (pipe->nrbufs < PIPE_BUFFERS)
+ if (pipe->nrbufs < pipe->buffers)
continue;

break;
@@ -265,6 +265,36 @@ static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
page_cache_release(spd->pages[i]);
}

+/*
+ * Check if we need to grow the arrays holding pages and partial page
+ * descriptions.
+ */
+int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+{
+ if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ return 0;
+
+ spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
+ spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);
+
+ if (spd->pages && spd->partial)
+ return 0;
+
+ kfree(spd->pages);
+ kfree(spd->partial);
+ return -ENOMEM;
+}
+
+void splice_shrink_spd(struct pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd)
+{
+ if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ return;
+
+ kfree(spd->pages);
+ kfree(spd->partial);
+}
+
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
@@ -272,8 +302,8 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages, req_pages;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
@@ -286,15 +316,18 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
.spd_release = spd_release_page,
};

+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS);
+ nr_pages = min(req_pages, pipe->buffers);

/*
* Lookup the (hopefully) full range of pages we need.
*/
- spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
+ spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, spd.pages);
index += spd.nr_pages;

/*
@@ -335,7 +368,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
unlock_page(page);
}

- pages[spd.nr_pages++] = page;
+ spd.pages[spd.nr_pages++] = page;
index++;
}

@@ -356,7 +389,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
- page = pages[page_nr];
+ page = spd.pages[page_nr];

if (PageReadahead(page))
page_cache_async_readahead(mapping, &in->f_ra, in,
@@ -442,8 +475,8 @@ fill_it:
len = this_len;
}

- partial[page_nr].offset = loff;
- partial[page_nr].len = this_len;
+ spd.partial[page_nr].offset = loff;
+ spd.partial[page_nr].len = this_len;
len -= this_len;
loff = 0;
spd.nr_pages++;
@@ -455,12 +488,13 @@ fill_it:
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
- page_cache_release(pages[page_nr++]);
+ page_cache_release(spd.pages[page_nr++]);
in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;

if (spd.nr_pages)
- return splice_to_pipe(pipe, &spd);
+ error = splice_to_pipe(pipe, &spd);

+ splice_shrink_spd(pipe, &spd);
return error;
}

@@ -641,7 +675,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
- pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
+ pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
pipe->nrbufs--;
if (pipe->inode)
do_wakeup = 1;
@@ -1024,7 +1058,7 @@ out_release:
* If we did an incomplete transfer we must release
* the pipe buffers in question:
*/
- for (i = 0; i < PIPE_BUFFERS; i++) {
+ for (i = 0; i < pipe->buffers; i++) {
struct pipe_buffer *buf = pipe->bufs + i;

if (buf->ops) {
@@ -1190,7 +1224,8 @@ static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
*/
static int get_iovec_page_array(const struct iovec __user *iov,
unsigned int nr_vecs, struct page **pages,
- struct partial_page *partial, int aligned)
+ struct partial_page *partial, int aligned,
+ unsigned int pipe_buffers)
{
int buffers = 0, error = 0;

@@ -1235,8 +1270,8 @@ static int get_iovec_page_array(const struct iovec __user *iov,
break;

npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (npages > PIPE_BUFFERS - buffers)
- npages = PIPE_BUFFERS - buffers;
+ if (npages > pipe_buffers - buffers)
+ npages = pipe_buffers - buffers;

error = get_user_pages(current, current->mm,
(unsigned long) base, npages, 0, 0,
@@ -1272,7 +1307,7 @@ static int get_iovec_page_array(const struct iovec __user *iov,
* or if we mapped the max number of pages that we have
* room for.
*/
- if (error < npages || buffers == PIPE_BUFFERS)
+ if (error < npages || buffers == pipe_buffers)
break;

nr_vecs--;
@@ -1419,8 +1454,8 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
unsigned long nr_segs, unsigned int flags)
{
struct pipe_inode_info *pipe;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
@@ -1428,17 +1463,25 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
.ops = &user_page_pipe_buf_ops,
.spd_release = spd_release_page,
};
+ long ret;

pipe = pipe_info(file->f_path.dentry->d_inode);
if (!pipe)
return -EBADF;

- spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
- flags & SPLICE_F_GIFT);
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
+ spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
+ spd.partial, flags & SPLICE_F_GIFT,
+ pipe->buffers);
if (spd.nr_pages <= 0)
- return spd.nr_pages;
+ ret = spd.nr_pages;
+ else
+ ret = splice_to_pipe(pipe, &spd);

- return splice_to_pipe(pipe, &spd);
+ splice_shrink_spd(pipe, &spd);
+ return ret;
}

/*
@@ -1564,13 +1607,13 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
* Check ->nrbufs without the inode lock first. This function
* is speculative anyways, so missing one is ok.
*/
- if (pipe->nrbufs < PIPE_BUFFERS)
+ if (pipe->nrbufs < pipe->buffers)
return 0;

ret = 0;
mutex_lock(&pipe->inode->i_mutex);

- while (pipe->nrbufs >= PIPE_BUFFERS) {
+ while (pipe->nrbufs >= pipe->buffers) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
@@ -1622,11 +1665,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
* If we have iterated all input buffers or ran out of
* output room, break.
*/
- if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS)
+ if (i >= ipipe->nrbufs || opipe->nrbufs >= opipe->buffers)
break;

- ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
- nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);
+ ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (ipipe->buffers-1));
+ nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1);

/*
* Get a reference to this pipe buffer,
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index b847741..1d50973 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -73,6 +73,13 @@
#define F_SETSIG 10 /* for sockets. */
#define F_GETSIG 11 /* for sockets. */
#endif
+#ifndef F_SETPIPE_SZ /* for growing pipe sizes */
+#define F_SETPIPE_SZ 12
+#endif
+#ifndef F_GETPIPE_SZ
+#define F_GETPIPE_SZ 13
+#endif
+

/* for F_[GET|SET]FL */
#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8e41202..4765076 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -3,7 +3,7 @@

#define PIPEFS_MAGIC 0x50495045

-#define PIPE_BUFFERS (16)
+#define PIPE_DEF_BUFFERS 16

#define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */
#define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */
@@ -44,17 +44,17 @@ struct pipe_buffer {
**/
struct pipe_inode_info {
wait_queue_head_t wait;
- unsigned int nrbufs, curbuf;
- struct page *tmp_page;
+ unsigned int nrbufs, curbuf, buffers;
unsigned int readers;
unsigned int writers;
unsigned int waiting_writers;
unsigned int r_counter;
unsigned int w_counter;
+ struct page *tmp_page;
struct fasync_struct *fasync_readers;
struct fasync_struct *fasync_writers;
struct inode *inode;
- struct pipe_buffer bufs[PIPE_BUFFERS];
+ struct pipe_buffer *bufs;
};

/*
@@ -148,4 +148,7 @@ void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);

+/* for F_SETPIPE_SZ and F_GETPIPE_SZ */
+long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
+
#endif
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 528dcb9..dcdb0b0 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -71,4 +71,11 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *,
extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
splice_direct_actor *);

+/*
+ * for dynamic pipe sizing
+ */
+extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *);
+extern void splice_shrink_spd(struct pipe_inode_info *,
+ struct splice_pipe_desc *);
+
#endif
diff --git a/kernel/relay.c b/kernel/relay.c
index 7de644c..5e71a9d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1108,8 +1108,8 @@ static int subbuf_splice_actor(struct file *in,
size_t read_subbuf = read_start / subbuf_size;
size_t padding = rbuf->padding[read_subbuf];
size_t nonpad_end = read_subbuf * subbuf_size + subbuf_size - padding;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
.pages = pages,
.nr_pages = 0,
@@ -1121,6 +1121,8 @@ static int subbuf_splice_actor(struct file *in,

if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
return 0;
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;

/*
* Adjust read len, if longer than what is available
@@ -1165,16 +1167,19 @@ static int subbuf_splice_actor(struct file *in,
}
}

+ ret = 0;
if (!spd.nr_pages)
- return 0;
+ goto out;

ret = *nonpad_ret = splice_to_pipe(pipe, &spd);
if (ret < 0 || ret < total_len)
- return ret;
+ goto out;

if (read_start + ret == nonpad_end)
ret += padding;

+out:
+ splice_shrink_spd(pipe, &spd);
return ret;
}


--
Jens Axboe

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/