[patch] pipe: add support for shrinking and growing pipes

From: Miklos Szeredi
Date: Wed May 19 2010 - 12:46:18 EST

This is a forward port to 2.6.34 of this patch from Jens:

http://git.kernel.dk/?p=linux-2.6-block.git;a=commitdiff_plain;h=24547ac4d97bebb58caf9ce58bd507a95c812a3f

One issue I see is that it's possible to grow pipes indefinitely.
Should this be restricted to privileged users?

Thanks,
Miklos


From: Jens Axboe <jens.axboe@xxxxxxxxxx>

This patch adds F_GETPIPE_SZ and F_SETPIPE_SZ fcntl() actions for
growing and shrinking the size of a pipe and adjusts pipe.c and splice.c
(and relay and network splice) usage to work with these larger (or smaller)
pipes.

Signed-off-by: Jens Axboe <jens.axboe@xxxxxxxxxx>
Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxx>
---
fs/fcntl.c | 5 +
fs/pipe.c | 107 ++++++++++++++++++++++++++---
fs/splice.c | 160 +++++++++++++++++++++++++++++---------------
include/asm-generic/fcntl.h | 7 +
include/linux/pipe_fs_i.h | 11 +--
include/linux/splice.h | 7 +
kernel/relay.c | 19 +++--
kernel/trace/trace.c | 60 +++++++++-------
net/core/skbuff.c | 39 ++++++----
9 files changed, 299 insertions(+), 116 deletions(-)

Index: linux-2.6/fs/fcntl.c
===================================================================
--- linux-2.6.orig/fs/fcntl.c 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/fs/fcntl.c 2010-05-14 18:23:06.000000000 +0200
@@ -14,6 +14,7 @@
#include <linux/dnotify.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>
@@ -412,6 +413,10 @@ static long do_fcntl(int fd, unsigned in
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;
}
Index: linux-2.6/fs/pipe.c
===================================================================
--- linux-2.6.orig/fs/pipe.c 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/fs/pipe.c 2010-05-14 18:23:06.000000000 +0200
@@ -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>
@@ -390,7 +391,7 @@ 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;
@@ -472,7 +473,7 @@ pipe_write(struct kiocb *iocb, const str
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;
@@ -518,8 +519,8 @@ 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;
@@ -580,7 +581,7 @@ redo2:
if (!total_len)
break;
}
- if (bufs < PIPE_BUFFERS)
+ if (bufs < pipe->buffers)
continue;
if (filp->f_flags & O_NONBLOCK) {
if (!ret)
@@ -640,7 +641,7 @@ static long pipe_ioctl(struct file *filp
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);

@@ -671,7 +672,7 @@ pipe_poll(struct file *filp, poll_table
}

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().
@@ -877,25 +878,32 @@ struct pipe_inode_info * alloc_pipe_info

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);
}

@@ -1094,6 +1102,81 @@ SYSCALL_DEFINE1(pipe, int __user *, fild
}

/*
+ * 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
Index: linux-2.6/fs/splice.c
===================================================================
--- linux-2.6.orig/fs/splice.c 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/fs/splice.c 2010-05-14 18:23:06.000000000 +0200
@@ -193,8 +193,8 @@ ssize_t splice_to_pipe(struct pipe_inode
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];
@@ -214,7 +214,7 @@ ssize_t splice_to_pipe(struct pipe_inode

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 spli
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,
@@ -272,29 +302,32 @@ __generic_file_splice_read(struct file *
{
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_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
int error, page_nr;
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.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 *
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 *
* 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,
@@ -393,8 +426,8 @@ __generic_file_splice_read(struct file *
error = -ENOMEM;
break;
}
- page_cache_release(pages[page_nr]);
- pages[page_nr] = page;
+ page_cache_release(spd.pages[page_nr]);
+ spd.pages[page_nr] = page;
}
/*
* page was already under io and is now done, great
@@ -451,8 +484,8 @@ 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++;
@@ -464,12 +497,13 @@ 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;
}

@@ -560,27 +594,36 @@ ssize_t default_file_splice_read(struct
unsigned int nr_pages;
unsigned int nr_freed;
size_t offset;
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
- struct iovec vec[PIPE_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
+ struct iovec *vec;
pgoff_t index;
ssize_t res;
size_t this_len;
int error;
int i;
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &default_pipe_buf_ops,
.spd_release = spd_release_page,
};

+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
+ vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+ if (!vec) {
+ res = -ENOMEM;
+ goto out;
+ }
+
index = *ppos >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

- for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+ for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
struct page *page;

page = alloc_page(GFP_USER);
@@ -591,7 +634,7 @@ ssize_t default_file_splice_read(struct
this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
vec[i].iov_base = (void __user *) page_address(page);
vec[i].iov_len = this_len;
- pages[i] = page;
+ spd.pages[i] = page;
spd.nr_pages++;
len -= this_len;
offset = 0;
@@ -610,11 +653,11 @@ ssize_t default_file_splice_read(struct
nr_freed = 0;
for (i = 0; i < spd.nr_pages; i++) {
this_len = min_t(size_t, vec[i].iov_len, res);
- partial[i].offset = 0;
- partial[i].len = this_len;
+ spd.partial[i].offset = 0;
+ spd.partial[i].len = this_len;
if (!this_len) {
- __free_page(pages[i]);
- pages[i] = NULL;
+ __free_page(spd.pages[i]);
+ spd.pages[i] = NULL;
nr_freed++;
}
res -= this_len;
@@ -625,13 +668,17 @@ ssize_t default_file_splice_read(struct
if (res > 0)
*ppos += res;

+out:
+ splice_shrink_spd(pipe, &spd);
+ kfree(vec);
return res;

err:
for (i = 0; i < spd.nr_pages; i++)
- __free_page(pages[i]);
+ __free_page(spd.pages[i]);

- return error;
+ res = error;
+ goto out;
}
EXPORT_SYMBOL(default_file_splice_read);

@@ -784,7 +831,7 @@ int splice_from_pipe_feed(struct pipe_in
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)
sd->need_wakeup = true;
@@ -1211,7 +1258,7 @@ 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) {
@@ -1371,7 +1418,8 @@ static long do_splice(struct file *in, l
*/
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;

@@ -1414,8 +1462,8 @@ static int get_iovec_page_array(const st
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_fast((unsigned long)base, npages,
0, &pages[buffers]);
@@ -1450,7 +1498,7 @@ static int get_iovec_page_array(const st
* 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--;
@@ -1593,26 +1641,34 @@ static long vmsplice_to_pipe(struct file
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_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.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;
}

/*
@@ -1738,13 +1794,13 @@ static int opipe_prep(struct pipe_inode_
* 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;
pipe_lock(pipe);

- while (pipe->nrbufs >= PIPE_BUFFERS) {
+ while (pipe->nrbufs >= pipe->buffers) {
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
@@ -1810,7 +1866,7 @@ retry:
* Cannot make any progress, because either the input
* pipe is empty or the output pipe is full.
*/
- if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) {
+ if (!ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) {
/* Already processed some buffers, break */
if (ret)
break;
@@ -1831,7 +1887,7 @@ retry:
}

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

if (len >= ibuf->len) {
@@ -1841,7 +1897,7 @@ retry:
*obuf = *ibuf;
ibuf->ops = NULL;
opipe->nrbufs++;
- ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS;
+ ipipe->curbuf = (ipipe->curbuf + 1) & (ipipe->buffers - 1);
ipipe->nrbufs--;
input_wakeup = true;
} else {
@@ -1914,11 +1970,11 @@ static int link_pipe(struct pipe_inode_i
* 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,
Index: linux-2.6/include/asm-generic/fcntl.h
===================================================================
--- linux-2.6.orig/include/asm-generic/fcntl.h 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/include/asm-generic/fcntl.h 2010-05-14 18:23:06.000000000 +0200
@@ -104,6 +104,13 @@
#define F_GETOWN_EX 16
#endif

+#ifndef F_SETPIPE_SZ /* for growing pipe sizes */
+#define F_SETPIPE_SZ 17
+#endif
+#ifndef F_GETPIPE_SZ
+#define F_GETPIPE_SZ 18
+#endif
+
#define F_OWNER_TID 0
#define F_OWNER_PID 1
#define F_OWNER_PGRP 2
Index: linux-2.6/include/linux/pipe_fs_i.h
===================================================================
--- linux-2.6.orig/include/linux/pipe_fs_i.h 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/include/linux/pipe_fs_i.h 2010-05-14 18:23:06.000000000 +0200
@@ -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;
};

/*
@@ -154,4 +154,7 @@ int generic_pipe_buf_confirm(struct pipe
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(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
Index: linux-2.6/include/linux/splice.h
===================================================================
--- linux-2.6.orig/include/linux/splice.h 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/include/linux/splice.h 2010-05-14 18:23:06.000000000 +0200
@@ -82,4 +82,11 @@ extern ssize_t splice_to_pipe(struct pip
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
Index: linux-2.6/kernel/relay.c
===================================================================
--- linux-2.6.orig/kernel/relay.c 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/kernel/relay.c 2010-05-14 18:23:06.000000000 +0200
@@ -1231,12 +1231,12 @@ static ssize_t subbuf_splice_actor(struc
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_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
+ .pages = pages_def,
.nr_pages = 0,
- .partial = partial,
+ .partial = partial_def,
.flags = flags,
.ops = &relay_pipe_buf_ops,
.spd_release = relay_page_release,
@@ -1245,6 +1245,8 @@ static ssize_t subbuf_splice_actor(struc

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
@@ -1255,7 +1257,7 @@ static ssize_t subbuf_splice_actor(struc
subbuf_pages = rbuf->chan->alloc_size >> PAGE_SHIFT;
pidx = (read_start / PAGE_SIZE) % subbuf_pages;
poff = read_start & ~PAGE_MASK;
- nr_pages = min_t(unsigned int, subbuf_pages, PIPE_BUFFERS);
+ nr_pages = min_t(unsigned int, subbuf_pages, pipe->buffers);

for (total_len = 0; spd.nr_pages < nr_pages; spd.nr_pages++) {
unsigned int this_len, this_end, private;
@@ -1289,16 +1291,19 @@ static ssize_t subbuf_splice_actor(struc
}
}

+ 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;
}

Index: linux-2.6/net/core/skbuff.c
===================================================================
--- linux-2.6.orig/net/core/skbuff.c 2010-05-14 18:23:05.000000000 +0200
+++ linux-2.6/net/core/skbuff.c 2010-05-14 18:23:06.000000000 +0200
@@ -1417,12 +1417,13 @@ new_page:
/*
* Fill page/offset/length into spd, if it can hold more pages.
*/
-static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
+static inline int spd_fill_page(struct splice_pipe_desc *spd,
+ struct pipe_inode_info *pipe, struct page *page,
unsigned int *len, unsigned int offset,
struct sk_buff *skb, int linear,
struct sock *sk)
{
- if (unlikely(spd->nr_pages == PIPE_BUFFERS))
+ if (unlikely(spd->nr_pages == pipe->buffers))
return 1;

if (linear) {
@@ -1457,8 +1458,9 @@ static inline void __segment_seek(struct
static inline int __splice_segment(struct page *page, unsigned int poff,
unsigned int plen, unsigned int *off,
unsigned int *len, struct sk_buff *skb,
- struct splice_pipe_desc *spd, int linear,
- struct sock *sk)
+ struct splice_pipe_desc *spd,
+ struct pipe_inode_info *pipe,
+ int linear, struct sock *sk)
{
if (!*len)
return 1;
@@ -1481,7 +1483,7 @@ static inline int __splice_segment(struc
/* the linear region may spread across several pages */
flen = min_t(unsigned int, flen, PAGE_SIZE - poff);

- if (spd_fill_page(spd, page, &flen, poff, skb, linear, sk))
+ if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk))
return 1;

__segment_seek(&page, &poff, &plen, flen);
@@ -1498,7 +1500,7 @@ static inline int __splice_segment(struc
*/
static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset,
unsigned int *len, struct splice_pipe_desc *spd,
- struct sock *sk)
+ struct pipe_inode_info *pipe, struct sock *sk)
{
int seg;

@@ -1508,7 +1510,7 @@ static int __skb_splice_bits(struct sk_b
if (__splice_segment(virt_to_page(skb->data),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
- offset, len, skb, spd, 1, sk))
+ offset, len, skb, spd, pipe, 1, sk))
return 1;

/*
@@ -1518,7 +1520,7 @@ static int __skb_splice_bits(struct sk_b
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];

if (__splice_segment(f->page, f->page_offset, f->size,
- offset, len, skb, spd, 0, sk))
+ offset, len, skb, spd, pipe, 0, sk))
return 1;
}

@@ -1535,23 +1537,27 @@ int skb_splice_bits(struct sk_buff *skb,
struct pipe_inode_info *pipe, unsigned int tlen,
unsigned int flags)
{
- struct partial_page partial[PIPE_BUFFERS];
- struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &sock_pipe_buf_ops,
.spd_release = sock_spd_release,
};
struct sk_buff *frag_iter;
struct sock *sk = skb->sk;
+ int ret = 0;
+
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;

/*
* __skb_splice_bits() only fails if the output has no room left,
* so no point in going over the frag_list for the error case.
*/
- if (__skb_splice_bits(skb, &offset, &tlen, &spd, sk))
+ if (__skb_splice_bits(skb, &offset, &tlen, &spd, pipe, sk))
goto done;
else if (!tlen)
goto done;
@@ -1562,13 +1568,12 @@ int skb_splice_bits(struct sk_buff *skb,
skb_walk_frags(skb, frag_iter) {
if (!tlen)
break;
- if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, sk))
+ if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, pipe, sk))
break;
}

done:
if (spd.nr_pages) {
- int ret;

/*
* Drop the socket lock, otherwise we have reverse
@@ -1582,10 +1587,10 @@ done:
release_sock(sk);
ret = splice_to_pipe(pipe, &spd);
lock_sock(sk);
- return ret;
}

- return 0;
+ splice_shrink_spd(pipe, &spd);
+ return ret;
}

/**
Index: linux-2.6/kernel/trace/trace.c
===================================================================
--- linux-2.6.orig/kernel/trace/trace.c 2010-05-12 11:19:25.000000000 +0200
+++ linux-2.6/kernel/trace/trace.c 2010-05-14 18:27:42.000000000 +0200
@@ -3269,12 +3269,12 @@ static ssize_t tracing_splice_read_pipe(
size_t len,
unsigned int flags)
{
- struct page *pages[PIPE_BUFFERS];
- struct partial_page partial[PIPE_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
struct trace_iterator *iter = filp->private_data;
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
.flags = flags,
.ops = &tracing_pipe_buf_ops,
@@ -3285,6 +3285,9 @@ static ssize_t tracing_splice_read_pipe(
size_t rem;
unsigned int i;

+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
/* copy the tracer to avoid using a global lock all around */
mutex_lock(&trace_types_lock);
if (unlikely(old_tracer != current_trace && current_trace)) {
@@ -3315,23 +3318,23 @@ static ssize_t tracing_splice_read_pipe(
trace_access_lock(iter->cpu_file);

/* Fill as many pages as possible. */
- for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
- pages[i] = alloc_page(GFP_KERNEL);
- if (!pages[i])
+ for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+ spd.pages[i] = alloc_page(GFP_KERNEL);
+ if (!spd.pages[i])
break;

rem = tracing_fill_pipe_page(rem, iter);

/* Copy the data into the page, so we can start over. */
ret = trace_seq_to_buffer(&iter->seq,
- page_address(pages[i]),
+ page_address(spd.pages[i]),
iter->seq.len);
if (ret < 0) {
- __free_page(pages[i]);
+ __free_page(spd.pages[i]);
break;
}
- partial[i].offset = 0;
- partial[i].len = iter->seq.len;
+ spd.partial[i].offset = 0;
+ spd.partial[i].len = iter->seq.len;

trace_seq_init(&iter->seq);
}
@@ -3342,12 +3345,14 @@ static ssize_t tracing_splice_read_pipe(

spd.nr_pages = i;

- return splice_to_pipe(pipe, &spd);
+ ret = splice_to_pipe(pipe, &spd);
+out:
+ splice_shrink_spd(pipe, &spd);
+ return ret;

out_err:
mutex_unlock(&iter->mutex);
-
- return ret;
+ goto out;
}

static ssize_t
@@ -3746,11 +3751,11 @@ tracing_buffers_splice_read(struct file
unsigned int flags)
{
struct ftrace_buffer_info *info = file->private_data;
- struct partial_page partial[PIPE_BUFFERS];
- struct page *pages[PIPE_BUFFERS];
+ struct partial_page partial_def[PIPE_DEF_BUFFERS];
+ struct page *pages_def[PIPE_DEF_BUFFERS];
struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
+ .pages = pages_def,
+ .partial = partial_def,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
@@ -3759,22 +3764,28 @@ tracing_buffers_splice_read(struct file
int entries, size, i;
size_t ret;

+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
if (*ppos & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: previous read must page-align\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}

if (len & (PAGE_SIZE - 1)) {
WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
- if (len < PAGE_SIZE)
- return -EINVAL;
+ if (len < PAGE_SIZE) {
+ ret = -EINVAL;
+ goto out;
+ }
len &= PAGE_MASK;
}

trace_access_lock(info->cpu);
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);

- for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+ for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
struct page *page;
int r;

@@ -3829,11 +3840,12 @@ tracing_buffers_splice_read(struct file
else
ret = 0;
/* TODO: block */
- return ret;
+ goto out;
}

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

--
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/