[ 13/13] splice: fix racy pipe->buffers uses

From: Greg Kroah-Hartman
Date: Thu Oct 03 2013 - 00:06:19 EST


3.0-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <edumazet@xxxxxxxxxx>

commit 047fe3605235888f3ebcda0c728cb31937eadfe6 upstream.

Dave Jones reported a kernel BUG at mm/slub.c:3474! triggered
by splice_shrink_spd() called from vmsplice_to_pipe()

commit 35f3d14dbbc5 (pipe: add support for shrinking and growing pipes)
added capability to adjust pipe->buffers.

Problem is some paths don't hold pipe mutex and assume pipe->buffers
doesn't change for their duration.

Fix this by adding nr_pages_max field in struct splice_pipe_desc, and
use it in place of pipe->buffers where appropriate.

splice_shrink_spd() loses its struct pipe_inode_info argument.

Reported-by: Dave Jones <davej@xxxxxxxxxx>
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Tom Herbert <therbert@xxxxxxxxxx>
Cc: stable <stable@xxxxxxxxxxxxxxx> # 2.6.35
Tested-by: Dave Jones <davej@xxxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Jiri Slaby <jslaby@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
fs/splice.c | 35 ++++++++++++++++++++---------------
include/linux/splice.h | 8 ++++----
kernel/relay.c | 5 +++--
kernel/trace/trace.c | 6 ++++--
net/core/skbuff.c | 3 ++-
5 files changed, 33 insertions(+), 24 deletions(-)

--- a/fs/splice.c
+++ b/fs/splice.c
@@ -274,13 +274,16 @@ static void spd_release_page(struct spli
* 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)
+int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
{
- if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ unsigned int buffers = ACCESS_ONCE(pipe->buffers);
+
+ spd->nr_pages_max = buffers;
+ if (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);
+ spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL);
+ spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL);

if (spd->pages && spd->partial)
return 0;
@@ -290,10 +293,9 @@ int splice_grow_spd(struct pipe_inode_in
return -ENOMEM;
}

-void splice_shrink_spd(struct pipe_inode_info *pipe,
- struct splice_pipe_desc *spd)
+void splice_shrink_spd(struct splice_pipe_desc *spd)
{
- if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ if (spd->nr_pages_max <= PIPE_DEF_BUFFERS)
return;

kfree(spd->pages);
@@ -316,6 +318,7 @@ __generic_file_splice_read(struct file *
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -327,7 +330,7 @@ __generic_file_splice_read(struct file *
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, pipe->buffers);
+ nr_pages = min(req_pages, spd.nr_pages_max);

/*
* Lookup the (hopefully) full range of pages we need.
@@ -498,7 +501,7 @@ fill_it:
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);

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

@@ -599,6 +602,7 @@ ssize_t default_file_splice_read(struct
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &default_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -609,8 +613,8 @@ ssize_t default_file_splice_read(struct

res = -ENOMEM;
vec = __vec;
- if (pipe->buffers > PIPE_DEF_BUFFERS) {
- vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+ if (spd.nr_pages_max > PIPE_DEF_BUFFERS) {
+ vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL);
if (!vec)
goto shrink_ret;
}
@@ -618,7 +622,7 @@ ssize_t default_file_splice_read(struct
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 < spd.nr_pages_max && len; i++) {
struct page *page;

page = alloc_page(GFP_USER);
@@ -666,7 +670,7 @@ ssize_t default_file_splice_read(struct
shrink_ret:
if (vec != __vec)
kfree(vec);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return res;

err:
@@ -1618,6 +1622,7 @@ static long vmsplice_to_pipe(struct file
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &user_page_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -1633,13 +1638,13 @@ static long vmsplice_to_pipe(struct file

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

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

--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -51,7 +51,8 @@ struct partial_page {
struct splice_pipe_desc {
struct page **pages; /* page map */
struct partial_page *partial; /* pages[] may not be contig */
- int nr_pages; /* number of pages in map */
+ int nr_pages; /* number of populated pages in map */
+ unsigned int nr_pages_max; /* pages[] & partial[] arrays size */
unsigned int flags; /* splice flags */
const struct pipe_buf_operations *ops;/* ops associated with output pipe */
void (*spd_release)(struct splice_pipe_desc *, unsigned int);
@@ -85,8 +86,7 @@ extern ssize_t splice_direct_to_actor(st
/*
* 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 *);
+extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *);
+extern void splice_shrink_spd(struct splice_pipe_desc *);

#endif
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struc
struct splice_pipe_desc spd = {
.pages = pages,
.nr_pages = 0,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.partial = partial,
.flags = flags,
.ops = &relay_pipe_buf_ops,
@@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struc
ret += padding;

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

static ssize_t relay_file_splice_read(struct file *in,
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3364,6 +3364,7 @@ static ssize_t tracing_splice_read_pipe(
.pages = pages_def,
.partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &tracing_pipe_buf_ops,
.spd_release = tracing_spd_release_pipe,
@@ -3435,7 +3436,7 @@ static ssize_t tracing_splice_read_pipe(

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

out_err:
@@ -3848,6 +3849,7 @@ tracing_buffers_splice_read(struct file
struct splice_pipe_desc spd = {
.pages = pages_def,
.partial = partial_def,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
@@ -3936,7 +3938,7 @@ tracing_buffers_splice_read(struct file
}

ret = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
out:
return ret;
}
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1535,6 +1535,7 @@ int skb_splice_bits(struct sk_buff *skb,
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = MAX_SKB_FRAGS,
.flags = flags,
.ops = &sock_pipe_buf_ops,
.spd_release = sock_spd_release,
@@ -1581,7 +1582,7 @@ done:
lock_sock(sk);
}

- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
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/