[patch added to 3.12-stable] cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind

[patch added to 3.12-stable] cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind

[Jiri Slaby]

From: Bjørn Mork <bjorn@mork.no>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 4d06dd537f95683aba3651098ae288b7cbff8274 upstream.

usbnet_link_change will call schedule_work and should be
avoided if bind is failing. Otherwise we will end up with
scheduled work referring to a netdev which has gone away.

Instead of making the call conditional, we can just defer
it to usbnet_probe, using the driver_info flag made for
this purpose.

Fixes: 8a34b0ae8778 ("usbnet: cdc_ncm: apply usbnet_link_change")
Reported-by: Andrey Konovalov <andreyknvl@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/net/usb/cdc_ncm.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 74581cbcafa7..6ee9665e20b2 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -598,24 +598,13 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
 
 static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
-
 	/* MBIM backwards compatible function? */
 	cdc_ncm_select_altsetting(dev, intf);
 	if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		return -ENODEV;
 
 	/* NCM data altsetting is always 1 */
-	ret = cdc_ncm_bind_common(dev, intf, 1);
-
-	/*
-	 * We should get an event when network connection is "connected" or
-	 * "disconnected". Set network connection in "disconnected" state
-	 * (carrier is OFF) during attach, so the IP network stack does not
-	 * start IPv6 negotiation and more.
-	 */
-	usbnet_link_change(dev, 0, 0);
-	return ret;
+	return cdc_ncm_bind_common(dev, intf, 1);
 }
 
 static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max)
@@ -1161,7 +1150,8 @@ static void cdc_ncm_disconnect(struct usb_interface *intf)
 
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
-	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
+	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+			| FLAG_LINK_INTR,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.check_connect = cdc_ncm_check_connect,
@@ -1175,7 +1165,7 @@ static const struct driver_info cdc_ncm_info = {
 static const struct driver_info wwan_info = {
 	.description = "Mobile Broadband Network Device",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN,
+			| FLAG_LINK_INTR | FLAG_WWAN,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.check_connect = cdc_ncm_check_connect,
@@ -1189,7 +1179,7 @@ static const struct driver_info wwan_info = {
 static const struct driver_info wwan_noarp_info = {
 	.description = "Mobile Broadband Network Device (NO ARP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
-			| FLAG_WWAN | FLAG_NOARP,
+			| FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
 	.check_connect = cdc_ncm_check_connect,
-- 
2.8.1

[patch added to 3.12-stable] fs, seq_file: fallback to vmalloc instead of oom kill processes

[Jiri Slaby]

From: David Rientjes <rientjes@google.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 5cec38ac866bfb8775638e71a86e4d8cac30caae upstream.

Since commit 058504edd026 ("fs/seq_file: fallback to vmalloc allocation"),
seq_buf_alloc() falls back to vmalloc() when the kmalloc() for contiguous
memory fails.  This was done to address order-4 slab allocations for
reading /proc/stat on large machines and noticed because
PAGE_ALLOC_COSTLY_ORDER < 4, so there is no infinite loop in the page
allocator when allocating new slab for such high-order allocations.

Contiguous memory isn't necessary for caller of seq_buf_alloc(), however.
Other GFP_KERNEL high-order allocations that are <=
PAGE_ALLOC_COSTLY_ORDER will simply loop forever in the page allocator and
oom kill processes as a result.

We don't want to kill processes so that we can allocate contiguous memory
in situations when contiguous memory isn't necessary.

This patch does the kmalloc() allocation with __GFP_NORETRY for high-order
allocations.  This still utilizes memory compaction and direct reclaim in
the allocation path, the only difference is that it will fail immediately
instead of oom kill processes when out of memory.

[akpm@linux-foundation.org: add comment]
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 fs/seq_file.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 6e050e26af43..96ae14abce98 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -36,7 +36,11 @@ static void *seq_buf_alloc(unsigned long size)
 {
 	void *buf;
 
-	buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	/*
+	 * __GFP_NORETRY to avoid oom-killings with high-order allocations -
+	 * it's better to fall back to vmalloc() than to kill things.
+	 */
+	buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
 	if (!buf && size > PAGE_SIZE)
 		buf = vmalloc(size);
 	return buf;
-- 
2.8.1

[patch added to 3.12-stable] fs, seqfile: always allow oom killer

[Jiri Slaby]

From: Greg Thelen <gthelen@google.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 0f930902eb8806cff8dcaef9ff9faf3cfa5fd748 upstream.

Since 5cec38ac866b ("fs, seq_file: fallback to vmalloc instead of oom kill
processes") seq_buf_alloc() avoids calling the oom killer for PAGE_SIZE or
smaller allocations; but larger allocations can use the oom killer via
vmalloc().  Thus reads of small files can return ENOMEM, but larger files
use the oom killer to avoid ENOMEM.

The effect of this bug is that reads from /proc and other virtual
filesystems can return ENOMEM instead of the preferred behavior - oom
killing something (possibly the calling process).  I don't know of anyone
except Google who has noticed the issue.

I suspect the fix is more needed in smaller systems where there isn't any
reclaimable memory.  But these seem like the kinds of systems which
probably don't use the oom killer for production situations.

Memory overcommit requires use of the oom killer to select a victim
regardless of file size.

Enable oom killer for small seq_buf_alloc() allocations.

Fixes: 5cec38ac866b ("fs, seq_file: fallback to vmalloc instead of oom kill processes")
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Greg Thelen <gthelen@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 fs/seq_file.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 96ae14abce98..a3e41be17e5e 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -35,12 +35,17 @@ static void seq_set_overflow(struct seq_file *m)
 static void *seq_buf_alloc(unsigned long size)
 {
 	void *buf;
+	gfp_t gfp = GFP_KERNEL;
 
 	/*
-	 * __GFP_NORETRY to avoid oom-killings with high-order allocations -
-	 * it's better to fall back to vmalloc() than to kill things.
+	 * For high order allocations, use __GFP_NORETRY to avoid oom-killing -
+	 * it's better to fall back to vmalloc() than to kill things.  For small
+	 * allocations, just use GFP_KERNEL which will oom kill, thus no need
+	 * for vmalloc fallback.
 	 */
-	buf = kmalloc(size, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
+	if (size > PAGE_SIZE)
+		gfp |= __GFP_NORETRY | __GFP_NOWARN;
+	buf = kmalloc(size, gfp);
 	if (!buf && size > PAGE_SIZE)
 		buf = vmalloc(size);
 	return buf;
-- 
2.8.1

[patch added to 3.12-stable] mmc: Allow forward compatibility for eMMC

[Jiri Slaby]

From: Romain Izard <romain.izard.pro@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 03a59437ef6b6ad7fb0165cb9b96c08d6bf057fc upstream.

As stated by the eMMC 5.0 specification, a chip should not be rejected
only because of the revision stated in the EXT_CSD_REV field of the
EXT_CSD register.

Remove the control on this value, the control of the CSD_STRUCTURE field
should be sufficient to reject future incompatible changes.

Signed-off-by: Romain Izard <romain.izard.pro@gmail.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/mmc/core/mmc.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 6d02012a1d0b..36d6701de972 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -292,13 +292,12 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		}
 	}
 
+	/*
+	 * The EXT_CSD format is meant to be forward compatible. As long
+	 * as CSD_STRUCTURE does not change, all values for EXT_CSD_REV
+	 * are authorized, see JEDEC JESD84-B50 section B.8.
+	 */
 	card->ext_csd.rev = ext_csd[EXT_CSD_REV];
-	if (card->ext_csd.rev > 7) {
-		pr_err("%s: unrecognised EXT_CSD revision %d\n",
-			mmc_hostname(card->host), card->ext_csd.rev);
-		err = -EINVAL;
-		goto out;
-	}
 
 	card->ext_csd.raw_sectors[0] = ext_csd[EXT_CSD_SEC_CNT + 0];
 	card->ext_csd.raw_sectors[1] = ext_csd[EXT_CSD_SEC_CNT + 1];
-- 
2.8.1

[patch added to 3.12-stable] ALSA: timer: Sync timer deletion at closing the system timer

[Jiri Slaby]

From: Takashi Iwai <tiwai@suse.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit f146357f069e71aff8e474c625bcebcd3094b3ab upstream.

ALSA timer core framework has no sync point at stopping because it's
called inside the spinlock.  Thus we need a sync point at close for
avoiding the stray timer task.  This is simply done by implementing
the close callback just calling del_timer_sync().  (It's harmless to
call it unconditionally, as the core timer itself cares of the already
deleted timer instance.)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 sound/core/timer.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/sound/core/timer.c b/sound/core/timer.c
index 38742e826900..10463beae4bb 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1033,11 +1033,21 @@ static int snd_timer_s_stop(struct snd_timer * timer)
 	return 0;
 }
 
+static int snd_timer_s_close(struct snd_timer *timer)
+{
+	struct snd_timer_system_private *priv;
+
+	priv = (struct snd_timer_system_private *)timer->private_data;
+	del_timer_sync(&priv->tlist);
+	return 0;
+}
+
 static struct snd_timer_hardware snd_timer_system =
 {
 	.flags =	SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_TASKLET,
 	.resolution =	1000000000L / HZ,
 	.ticks =	10000000L,
+	.close =	snd_timer_s_close,
 	.start =	snd_timer_s_start,
 	.stop =		snd_timer_s_stop
 };
-- 
2.8.1

[patch added to 3.12-stable] SUNRPC: Fix large reads on NFS/RDMA

[Jiri Slaby]

From: Chuck Lever <chuck.lever@oracle.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 2b7bbc963da8d076f263574af4138b5df2e1581f upstream.

After commit a11a2bf4, "SUNRPC: Optimise away unnecessary data moves
in xdr_align_pages", Thu Aug 2 13:21:43 2012, READs larger than a
few hundred bytes via NFS/RDMA no longer work.  This commit exposed
a long-standing bug in rpcrdma_inline_fixup().

I reproduce this with an rsize=4096 mount using the cthon04 basic
tests.  Test 5 fails with an EIO error.

For my reproducer, kernel log shows:

  NFS: server cheating in read reply: count 4096 > recvd 0

rpcrdma_inline_fixup() is zeroing the xdr_stream::page_len field,
and xdr_align_pages() is now returning that value to the READ XDR
decoder function.

That field is set up by xdr_inline_pages() by the READ XDR encoder
function.  As far as I can tell, it is supposed to be left alone
after that, as it describes the dimensions of the reply xdr_stream,
not the contents of that stream.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=68391
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e03725bfe2b8..96ead526b125 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -649,9 +649,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 				break;
 			page_base = 0;
 		}
-		rqst->rq_rcv_buf.page_len = olen - copy_len;
-	} else
-		rqst->rq_rcv_buf.page_len = 0;
+	}
 
 	if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) {
 		curlen = copy_len;
-- 
2.8.1

[patch added to 3.12-stable] pipe: limit the per-user amount of pages allocated in pipes

[Jiri Slaby]

From: Willy Tarreau <w@1wt.eu>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 759c01142a5d0f364a462346168a56de28a80f52 upstream.

On no-so-small systems, it is possible for a single process to cause an
OOM condition by filling large pipes with data that are never read. A
typical process filling 4000 pipes with 1 MB of data will use 4 GB of
memory. On small systems it may be tricky to set the pipe max size to
prevent this from happening.

This patch makes it possible to enforce a per-user soft limit above
which new pipes will be limited to a single page, effectively limiting
them to 4 kB each, as well as a hard limit above which no new pipes may
be created for this user. This has the effect of protecting the system
against memory abuse without hurting other users, and still allowing
pipes to work correctly though with less data at once.

The limit are controlled by two new sysctls : pipe-user-pages-soft, and
pipe-user-pages-hard. Both may be disabled by setting them to zero. The
default soft limit allows the default number of FDs per process (1024)
to create pipes of the default size (64kB), thus reaching a limit of 64MB
before starting to create only smaller pipes. With 256 processes limited
to 1024 FDs each, this results in 1024*64kB + (256*1024 - 1024) * 4kB =
1084 MB of memory allocated for a user. The hard limit is disabled by
default to avoid breaking existing applications that make intensive use
of pipes (eg: for splicing).

Reported-by: socketpair@gmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Mitigates: CVE-2013-4312 (Linux 2.0+)
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 Documentation/sysctl/fs.txt | 23 ++++++++++++++++++++++
 fs/pipe.c                   | 47 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/pipe_fs_i.h   |  4 ++++
 include/linux/sched.h       |  1 +
 kernel/sysctl.c             | 14 ++++++++++++++
 5 files changed, 87 insertions(+), 2 deletions(-)

diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 88152f214f48..302b5ed616a6 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@@ -159,6 +161,27 @@ The default is 65534.
 
 ==============================================================
 
+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:
 
 A long-standing class of security issues is the hardlink-based
diff --git a/fs/pipe.c b/fs/pipe.c
index 50267e6ba688..c281867c453e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -39,6 +39,12 @@ unsigned int pipe_max_size = 1048576;
  */
 unsigned int pipe_min_size = PAGE_SIZE;
 
+/* Maximum allocatable pages per user. Hard limit is unset by default, soft
+ * matches default values.
+ */
+unsigned long pipe_user_pages_hard;
+unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR;
+
 /*
  * We use a start+len construction, which provides full use of the 
  * allocated memory.
@@ -794,20 +800,49 @@ pipe_fasync(int fd, struct file *filp, int on)
 	return retval;
 }
 
+static void account_pipe_buffers(struct pipe_inode_info *pipe,
+                                 unsigned long old, unsigned long new)
+{
+	atomic_long_add(new - old, &pipe->user->pipe_bufs);
+}
+
+static bool too_many_pipe_buffers_soft(struct user_struct *user)
+{
+	return pipe_user_pages_soft &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft;
+}
+
+static bool too_many_pipe_buffers_hard(struct user_struct *user)
+{
+	return pipe_user_pages_hard &&
+	       atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard;
+}
+
 struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
 	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
 	if (pipe) {
-		pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
+		struct user_struct *user = get_current_user();
+
+		if (!too_many_pipe_buffers_hard(user)) {
+			if (too_many_pipe_buffers_soft(user))
+				pipe_bufs = 1;
+			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+		}
+
 		if (pipe->bufs) {
 			init_waitqueue_head(&pipe->wait);
 			pipe->r_counter = pipe->w_counter = 1;
-			pipe->buffers = PIPE_DEF_BUFFERS;
+			pipe->buffers = pipe_bufs;
+			pipe->user = user;
+			account_pipe_buffers(pipe, 0, pipe_bufs);
 			mutex_init(&pipe->mutex);
 			return pipe;
 		}
+		free_uid(user);
 		kfree(pipe);
 	}
 
@@ -818,6 +853,8 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 {
 	int i;
 
+	account_pipe_buffers(pipe, pipe->buffers, 0);
+	free_uid(pipe->user);
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
@@ -1208,6 +1245,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
+	account_pipe_buffers(pipe, pipe->buffers, nr_pages);
 	pipe->curbuf = 0;
 	kfree(pipe->bufs);
 	pipe->bufs = bufs;
@@ -1279,6 +1317,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
+		} else if ((too_many_pipe_buffers_hard(pipe->user) ||
+			    too_many_pipe_buffers_soft(pipe->user)) &&
+		           !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) {
+			ret = -EPERM;
+			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index ab5752692113..b3374f63bc36 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -42,6 +42,7 @@ struct pipe_buffer {
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
+ *	@user: the user who created this pipe
  **/
 struct pipe_inode_info {
 	struct mutex mutex;
@@ -57,6 +58,7 @@ struct pipe_inode_info {
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
+	struct user_struct *user;
 };
 
 /*
@@ -140,6 +142,8 @@ void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
 extern unsigned int pipe_max_size, pipe_min_size;
+extern unsigned long pipe_user_pages_hard;
+extern unsigned long pipe_user_pages_soft;
 int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3ecea51ea060..2bc93e252fef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -665,6 +665,7 @@ struct user_struct {
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
+	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6a9b0c42fb30..37b95a2982af 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1637,6 +1637,20 @@ static struct ctl_table fs_table[] = {
 		.proc_handler	= &pipe_proc_fn,
 		.extra1		= &pipe_min_size,
 	},
+	{
+		.procname	= "pipe-user-pages-hard",
+		.data		= &pipe_user_pages_hard,
+		.maxlen		= sizeof(pipe_user_pages_hard),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+	{
+		.procname	= "pipe-user-pages-soft",
+		.data		= &pipe_user_pages_soft,
+		.maxlen		= sizeof(pipe_user_pages_soft),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
 	{ }
 };
 
-- 
2.8.1

[patch added to 3.12-stable] netfilter: x_tables: validate e->target_offset early

[Jiri Slaby]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit bdf533de6968e9686df777dc178486f600c6e617 upstream.

We should check that e->target_offset is sane before
mark_source_chains gets called since it will fetch the target entry
for loop detection.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 net/ipv4/netfilter/arp_tables.c | 17 ++++++++---------
 net/ipv4/netfilter/ip_tables.c  | 17 ++++++++---------
 net/ipv6/netfilter/ip6_tables.c | 17 ++++++++---------
 3 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index c8abe31961ed..269759dd96f4 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -465,14 +465,12 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	return 1;
 }
 
-static inline int check_entry(const struct arpt_entry *e, const char *name)
+static inline int check_entry(const struct arpt_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!arp_checkentry(&e->arp)) {
-		duprintf("arp_tables: arp check failed %p %s.\n", e, name);
+	if (!arp_checkentry(&e->arp))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
 		return -EINVAL;
@@ -513,10 +511,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
 	struct xt_target *target;
 	int ret;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	t = arpt_get_target(e);
 	target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
 					t->u.user.revision);
@@ -561,6 +555,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 					     unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
@@ -575,6 +570,10 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1232,7 +1231,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct arpt_entry *)e, name);
+	ret = check_entry((struct arpt_entry *)e);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 651c10774d58..5ca478f13080 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -560,14 +560,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ipt_entry *e, const char *name)
+check_entry(const struct ipt_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!ip_checkentry(&e->ip)) {
-		duprintf("ip check failed %p %s.\n", e, name);
+	if (!ip_checkentry(&e->ip))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) >
 	    e->next_offset)
@@ -657,10 +655,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	j = 0;
 	mtpar.net	= net;
 	mtpar.table     = name;
@@ -724,6 +718,7 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
@@ -738,6 +733,10 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1498,7 +1497,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ipt_entry *)e, name);
+	ret = check_entry((struct ipt_entry *)e);
 	if (ret)
 		return ret;
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 89a4e4ddd8bb..597f539f3d33 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -570,14 +570,12 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
 }
 
 static int
-check_entry(const struct ip6t_entry *e, const char *name)
+check_entry(const struct ip6t_entry *e)
 {
 	const struct xt_entry_target *t;
 
-	if (!ip6_checkentry(&e->ipv6)) {
-		duprintf("ip_tables: ip check failed %p %s.\n", e, name);
+	if (!ip6_checkentry(&e->ipv6))
 		return -EINVAL;
-	}
 
 	if (e->target_offset + sizeof(struct xt_entry_target) >
 	    e->next_offset)
@@ -668,10 +666,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	ret = check_entry(e, name);
-	if (ret)
-		return ret;
-
 	j = 0;
 	mtpar.net	= net;
 	mtpar.table     = name;
@@ -735,6 +729,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			   unsigned int valid_hooks)
 {
 	unsigned int h;
+	int err;
 
 	if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 ||
 	    (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) {
@@ -749,6 +744,10 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 		return -EINVAL;
 	}
 
+	err = check_entry(e);
+	if (err)
+		return err;
+
 	/* Check hooks & underflows */
 	for (h = 0; h < NF_INET_NUMHOOKS; h++) {
 		if (!(valid_hooks & (1 << h)))
@@ -1510,7 +1509,7 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e,
 	}
 
 	/* For purposes of check_entry casting the compat entry is fine */
-	ret = check_entry((struct ip6t_entry *)e, name);
+	ret = check_entry((struct ip6t_entry *)e);
 	if (ret)
 		return ret;
 
-- 
2.8.1

[patch added to 3.12-stable] netfilter: x_tables: fix unconditional helper

[Jiri Slaby]

From: Florian Westphal <fw@strlen.de>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 54d83fc74aa9ec72794373cb47432c5f7fb1a309 upstream.

Ben Hawkes says:

 In the mark_source_chains function (net/ipv4/netfilter/ip_tables.c) it
 is possible for a user-supplied ipt_entry structure to have a large
 next_offset field. This field is not bounds checked prior to writing a
 counter value at the supplied offset.

Problem is that mark_source_chains should not have been called --
the rule doesn't have a next entry, so its supposed to return
an absolute verdict of either ACCEPT or DROP.

However, the function conditional() doesn't work as the name implies.
It only checks that the rule is using wildcard address matching.

However, an unconditional rule must also not be using any matches
(no -m args).

The underflow validator only checked the addresses, therefore
passing the 'unconditional absolute verdict' test, while
mark_source_chains also tested for presence of matches, and thus
proceeeded to the next (not-existent) rule.

Unify this so that all the callers have same idea of 'unconditional rule'.

Reported-by: Ben Hawkes <hawkes@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 net/ipv4/netfilter/arp_tables.c | 18 +++++++++---------
 net/ipv4/netfilter/ip_tables.c  | 23 +++++++++++------------
 net/ipv6/netfilter/ip6_tables.c | 23 +++++++++++------------
 3 files changed, 31 insertions(+), 33 deletions(-)

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 269759dd96f4..29aa90ea4c8d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -350,11 +350,12 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 }
 
 /* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
 {
 	static const struct arpt_arp uncond;
 
-	return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct arpt_entry) &&
+	       memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -393,11 +394,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct arpt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->arp)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -536,7 +536,7 @@ static bool check_underflow(const struct arpt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->arp))
+	if (!unconditional(e))
 		return false;
 	t = arpt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -582,9 +582,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 5ca478f13080..d400a2ad7c56 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
 {
 	static const struct ipt_ip uncond;
 
-	return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ipt_entry) &&
+	       memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
 #undef FWINV
 }
 
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ipt_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		   t->verdict < 0 &&
-		   unconditional(&s->ip)) {
+		   t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -467,11 +467,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ipt_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 && unconditional(&e->ip)) ||
-			    visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -698,7 +697,7 @@ static bool check_underflow(const struct ipt_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ip))
+	if (!unconditional(e))
 		return false;
 	t = ipt_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -745,9 +744,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 597f539f3d33..e0538df697c8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -195,11 +195,12 @@ get_entry(const void *base, unsigned int offset)
 
 /* All zeroes == unconditional rule. */
 /* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ip6t_ip6 *ipv6)
+static inline bool unconditional(const struct ip6t_entry *e)
 {
 	static const struct ip6t_ip6 uncond;
 
-	return memcmp(ipv6, &uncond, sizeof(uncond)) == 0;
+	return e->target_offset == sizeof(struct ip6t_entry) &&
+	       memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0;
 }
 
 static inline const struct xt_entry_target *
@@ -255,11 +256,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e,
 	} else if (s == e) {
 		(*rulenum)++;
 
-		if (s->target_offset == sizeof(struct ip6t_entry) &&
+		if (unconditional(s) &&
 		    strcmp(t->target.u.kernel.target->name,
 			   XT_STANDARD_TARGET) == 0 &&
-		    t->verdict < 0 &&
-		    unconditional(&s->ipv6)) {
+		    t->verdict < 0) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
 				? comments[NF_IP6_TRACE_COMMENT_POLICY]
@@ -477,11 +477,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 			e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
 
 			/* Unconditional return/END. */
-			if ((e->target_offset == sizeof(struct ip6t_entry) &&
+			if ((unconditional(e) &&
 			     (strcmp(t->target.u.user.name,
 				     XT_STANDARD_TARGET) == 0) &&
-			     t->verdict < 0 &&
-			     unconditional(&e->ipv6)) || visited) {
+			     t->verdict < 0) || visited) {
 				unsigned int oldpos, size;
 
 				if ((strcmp(t->target.u.user.name,
@@ -709,7 +708,7 @@ static bool check_underflow(const struct ip6t_entry *e)
 	const struct xt_entry_target *t;
 	unsigned int verdict;
 
-	if (!unconditional(&e->ipv6))
+	if (!unconditional(e))
 		return false;
 	t = ip6t_get_target_c(e);
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -756,9 +755,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e,
 			newinfo->hook_entry[h] = hook_entries[h];
 		if ((unsigned char *)e - base == underflows[h]) {
 			if (!check_underflow(e)) {
-				pr_err("Underflows must be unconditional and "
-				       "use the STANDARD target with "
-				       "ACCEPT/DROP\n");
+				pr_debug("Underflows must be unconditional and "
+					 "use the STANDARD target with "
+					 "ACCEPT/DROP\n");
 				return -EINVAL;
 			}
 			newinfo->underflow[h] = underflows[h];
-- 
2.8.1

Re: [patch added to 3.12-stable] netfilter: x_tables: fix unconditional helper

[Michal Kubecek]

On Thu, Apr 21, 2016 at 02:14:22PM +0200, Jiri Slaby wrote:
> From: Florian Westphal <fw@strlen.de>
> 
> This patch has been added to the 3.12 stable tree. If you have any
> objections, please let us know.
> 
> ===============
> 
> commit 54d83fc74aa9ec72794373cb47432c5f7fb1a309 upstream.
...

You picked

  bdf533de6968 ("netfilter: x_tables: validate e->target_offset early")
  54d83fc74aa9 ("netfilter: x_tables: fix unconditional helper")

but omitted

  6e94e0cfb088 ("netfilter: x_tables: make sure e->next_offset covers remaining blob size")

from the same series. Is it on purpose?

Michal Kubecek

Re: [patch added to 3.12-stable] netfilter: x_tables: fix unconditional helper

[Jiri Slaby]

On 04/22/2016, 05:38 PM, Michal Kubecek wrote:
> On Thu, Apr 21, 2016 at 02:14:22PM +0200, Jiri Slaby wrote:
>> From: Florian Westphal <fw@strlen.de>
>>
>> This patch has been added to the 3.12 stable tree. If you have any
>> objections, please let us know.
>>
>> ===============
>>
>> commit 54d83fc74aa9ec72794373cb47432c5f7fb1a309 upstream.
> ...
> 
> You picked
> 
>   bdf533de6968 ("netfilter: x_tables: validate e->target_offset early")
>   54d83fc74aa9 ("netfilter: x_tables: fix unconditional helper")
> 
> but omitted
> 
>   6e94e0cfb088 ("netfilter: x_tables: make sure e->next_offset covers remaining blob size")
> 
> from the same series. Is it on purpose?

No, I omitted that. Now fixed. Thanks.


-- 
js
suse labs

[patch added to 3.12-stable] USB: usbip: fix potential out-of-bounds write

[Jiri Slaby]

From: Ignat Korchagin <ignat.korchagin@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit b348d7dddb6c4fbfc810b7a0626e8ec9e29f7cbb upstream.

Fix potential out-of-bounds write to urb->transfer_buffer
usbip handles network communication directly in the kernel. When receiving a
packet from its peer, usbip code parses headers according to protocol. As
part of this parsing urb->actual_length is filled. Since the input for
urb->actual_length comes from the network, it should be treated as untrusted.
Any entity controlling the network may put any value in the input and the
preallocated urb->transfer_buffer may not be large enough to hold the data.
Thus, the malicious entity is able to write arbitrary data to kernel memory.

Signed-off-by: Ignat Korchagin <ignat.korchagin@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/staging/usbip/usbip_common.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/staging/usbip/usbip_common.c b/drivers/staging/usbip/usbip_common.c
index e3fc749c1e7e..15aeb41f7c84 100644
--- a/drivers/staging/usbip/usbip_common.c
+++ b/drivers/staging/usbip/usbip_common.c
@@ -785,6 +785,17 @@ int usbip_recv_xbuff(struct usbip_device *ud, struct urb *urb)
 	if (!(size > 0))
 		return 0;
 
+	if (size > urb->transfer_buffer_length) {
+		/* should not happen, probably malicious packet */
+		if (ud->side == USBIP_STUB) {
+			usbip_event_add(ud, SDEV_EVENT_ERROR_TCP);
+			return 0;
+		} else {
+			usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
+			return -EPIPE;
+		}
+	}
+
 	ret = usbip_recv(ud->tcp_socket, urb->transfer_buffer, size);
 	if (ret != size) {
 		dev_err(&urb->dev->dev, "recv xbuf, %d\n", ret);
-- 
2.8.1

[patch added to 3.12-stable] fs/pipe.c: skip file_update_time on frozen fs

[Jiri Slaby]

From: Dmitry Monakhov <dmonakhov@openvz.org>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 7e775f46a125f894a1d71e96797c776dbec161f0 upstream.

Pipe has no data associated with fs so it is not good idea to block
pipe_write() if FS is frozen, but we can not update file's time on such
filesystem.  Let's use same idea as we use in touch_time().

Addresses https://bugzilla.kernel.org/show_bug.cgi?id=65701

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 fs/pipe.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index c281867c453e..fff8057a0809 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -681,10 +681,11 @@ out:
 		wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	}
-	if (ret > 0) {
+	if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) {
 		int err = file_update_time(filp);
 		if (err)
 			ret = err;
+		sb_end_write(file_inode(filp)->i_sb);
 	}
 	return ret;
 }
-- 
2.8.1

[patch added to 3.12-stable] mnt: Move the clear of MNT_LOCKED from copy_tree to it's callers.

[Jiri Slaby]

From: "Eric W. Biederman" <ebiederm@xmission.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 8486a7882b5ba906992fd78bbfcefaae7fe285cc upstream.

Clear MNT_LOCKED in the callers of copy_tree except copy_mnt_ns, and
collect_mounts.  In copy_mnt_ns it is necessary to create an exact
copy of a mount tree, so not clearing MNT_LOCKED is important.
Similarly collect_mounts is used to take a snapshot of the mount tree
for audit logging purposes and auditing using a faithful copy of the
tree is important.

This becomes particularly significant when we start setting MNT_LOCKED
on rootfs to prevent it from being unmounted.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 fs/namespace.c | 1 -
 fs/pnode.c     | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index d727b0ce11df..f67473272010 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1416,7 +1416,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 	if (IS_ERR(q))
 		return q;
 
-	q->mnt.mnt_flags &= ~MNT_LOCKED;
 	q->mnt_mountpoint = mnt->mnt_mountpoint;
 
 	p = mnt;
diff --git a/fs/pnode.c b/fs/pnode.c
index 9af0df15256e..509d046e2b3e 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -249,6 +249,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 			list_splice(tree_list, tmp_list.prev);
 			goto out;
 		}
+		child->mnt.mnt_flags &= ~MNT_LOCKED;
 
 		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
 			mnt_set_mountpoint(m, dest_mp, child);
-- 
2.8.1

[patch added to 3.12-stable] KEYS: Fix handling of stored error in a negatively instantiated user key

[Jiri Slaby]

From: David Howells <dhowells@redhat.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 096fe9eaea40a17e125569f9e657e34cdb6d73bd upstream.

If a user key gets negatively instantiated, an error code is cached in the
payload area.  A negatively instantiated key may be then be positively
instantiated by updating it with valid data.  However, the ->update key
type method must be aware that the error code may be there.

The following may be used to trigger the bug in the user key type:

    keyctl request2 user user "" @u
    keyctl add user user "a" @u

which manifests itself as:

	BUG: unable to handle kernel paging request at 00000000ffffff8a
	IP: [<ffffffff810a376f>] __call_rcu.constprop.76+0x1f/0x280 kernel/rcu/tree.c:3046
	PGD 7cc30067 PUD 0
	Oops: 0002 [#1] SMP
	Modules linked in:
	CPU: 3 PID: 2644 Comm: a.out Not tainted 4.3.0+ #49
	Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
	task: ffff88003ddea700 ti: ffff88003dd88000 task.ti: ffff88003dd88000
	RIP: 0010:[<ffffffff810a376f>]  [<ffffffff810a376f>] __call_rcu.constprop.76+0x1f/0x280
	 [<ffffffff810a376f>] __call_rcu.constprop.76+0x1f/0x280 kernel/rcu/tree.c:3046
	RSP: 0018:ffff88003dd8bdb0  EFLAGS: 00010246
	RAX: 00000000ffffff82 RBX: 0000000000000000 RCX: 0000000000000001
	RDX: ffffffff81e3fe40 RSI: 0000000000000000 RDI: 00000000ffffff82
	RBP: ffff88003dd8bde0 R08: ffff88007d2d2da0 R09: 0000000000000000
	R10: 0000000000000000 R11: ffff88003e8073c0 R12: 00000000ffffff82
	R13: ffff88003dd8be68 R14: ffff88007d027600 R15: ffff88003ddea700
	FS:  0000000000b92880(0063) GS:ffff88007fd00000(0000) knlGS:0000000000000000
	CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
	CR2: 00000000ffffff8a CR3: 000000007cc5f000 CR4: 00000000000006e0
	Stack:
	 ffff88003dd8bdf0 ffffffff81160a8a 0000000000000000 00000000ffffff82
	 ffff88003dd8be68 ffff88007d027600 ffff88003dd8bdf0 ffffffff810a39e5
	 ffff88003dd8be20 ffffffff812a31ab ffff88007d027600 ffff88007d027620
	Call Trace:
	 [<ffffffff810a39e5>] kfree_call_rcu+0x15/0x20 kernel/rcu/tree.c:3136
	 [<ffffffff812a31ab>] user_update+0x8b/0xb0 security/keys/user_defined.c:129
	 [<     inline     >] __key_update security/keys/key.c:730
	 [<ffffffff8129e5c1>] key_create_or_update+0x291/0x440 security/keys/key.c:908
	 [<     inline     >] SYSC_add_key security/keys/keyctl.c:125
	 [<ffffffff8129fc21>] SyS_add_key+0x101/0x1e0 security/keys/keyctl.c:60
	 [<ffffffff8185f617>] entry_SYSCALL_64_fastpath+0x12/0x6a arch/x86/entry/entry_64.S:185

Note the error code (-ENOKEY) in EDX.

A similar bug can be tripped by:

    keyctl request2 trusted user "" @u
    keyctl add trusted user "a" @u

This should also affect encrypted keys - but that has to be correctly
parameterised or it will fail with EINVAL before getting to the bit that
will crashes.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 security/keys/encrypted-keys/encrypted.c | 2 ++
 security/keys/trusted.c                  | 5 ++++-
 security/keys/user_defined.c             | 5 ++++-
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index c4c8df4b214d..45d5c5926d03 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -845,6 +845,8 @@ static int encrypted_update(struct key *key, struct key_preparsed_payload *prep)
 	size_t datalen = prep->datalen;
 	int ret = 0;
 
+	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+		return -ENOKEY;
 	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		return -EINVAL;
 
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index e13fcf7636f7..d72ff37e3da9 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -984,13 +984,16 @@ static void trusted_rcu_free(struct rcu_head *rcu)
  */
 static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 {
-	struct trusted_key_payload *p = key->payload.data;
+	struct trusted_key_payload *p;
 	struct trusted_key_payload *new_p;
 	struct trusted_key_options *new_o;
 	size_t datalen = prep->datalen;
 	char *datablob;
 	int ret = 0;
 
+	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+		return -ENOKEY;
+	p = key->payload.data;
 	if (!p->migratable)
 		return -EPERM;
 	if (datalen <= 0 || datalen > 32767 || !prep->data)
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 55dc88939185..637f43d45b28 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -119,7 +119,10 @@ int user_update(struct key *key, struct key_preparsed_payload *prep)
 
 	if (ret == 0) {
 		/* attach the new data, displacing the old */
-		zap = key->payload.data;
+		if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+			zap = key->payload.data;
+		else
+			zap = NULL;
 		rcu_assign_keypointer(key, upayload);
 		key->expiry = 0;
 	}
-- 
2.8.1

[patch added to 3.12-stable] crypto: crypto_memneq - add equality testing of memory regions w/o timing leaks

[Jiri Slaby]

From: James Yonan <james@openvpn.net>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 6bf37e5aa90f18baf5acf4874bca505dd667c37f upstream.

When comparing MAC hashes, AEAD authentication tags, or other hash
values in the context of authentication or integrity checking, it
is important not to leak timing information to a potential attacker,
i.e. when communication happens over a network.

Bytewise memory comparisons (such as memcmp) are usually optimized so
that they return a nonzero value as soon as a mismatch is found. E.g,
on x86_64/i5 for 512 bytes this can be ~50 cyc for a full mismatch
and up to ~850 cyc for a full match (cold). This early-return behavior
can leak timing information as a side channel, allowing an attacker to
iteratively guess the correct result.

This patch adds a new method crypto_memneq ("memory not equal to each
other") to the crypto API that compares memory areas of the same length
in roughly "constant time" (cache misses could change the timing, but
since they don't reveal information about the content of the strings
being compared, they are effectively benign). Iow, best and worst case
behaviour take the same amount of time to complete (in contrast to
memcmp).

Note that crypto_memneq (unlike memcmp) can only be used to test for
equality or inequality, NOT for lexicographical order. This, however,
is not an issue for its use-cases within the crypto API.

We tried to locate all of the places in the crypto API where memcmp was
being used for authentication or integrity checking, and convert them
over to crypto_memneq.

crypto_memneq is declared noinline, placed in its own source file,
and compiled with optimizations that might increase code size disabled
("Os") because a smart compiler (or LTO) might notice that the return
value is always compared against zero/nonzero, and might then
reintroduce the same early-return optimization that we are trying to
avoid.

Using #pragma or __attribute__ optimization annotations of the code
for disabling optimization was avoided as it seems to be considered
broken or unmaintained for long time in GCC [1]. Therefore, we work
around that by specifying the compile flag for memneq.o directly in
the Makefile. We found that this seems to be most appropriate.

As we use ("Os"), this patch also provides a loop-free "fast-path" for
frequently used 16 byte digests. Similarly to kernel library string
functions, leave an option for future even further optimized architecture
specific assembler implementations.

This was a joint work of James Yonan and Daniel Borkmann. Also thanks
for feedback from Florian Weimer on this and earlier proposals [2].

  [1] http://gcc.gnu.org/ml/gcc/2012-07/msg00211.html
  [2] https://lkml.org/lkml/2013/2/10/131

Signed-off-by: James Yonan <james@openvpn.net>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 crypto/Makefile              |   7 ++-
 crypto/asymmetric_keys/rsa.c |   5 +-
 crypto/authenc.c             |   6 +-
 crypto/authencesn.c          |   8 +--
 crypto/ccm.c                 |   4 +-
 crypto/gcm.c                 |   2 +-
 crypto/memneq.c              | 138 +++++++++++++++++++++++++++++++++++++++++++
 include/crypto/algapi.h      |  18 +++++-
 8 files changed, 174 insertions(+), 14 deletions(-)
 create mode 100644 crypto/memneq.c

diff --git a/crypto/Makefile b/crypto/Makefile
index 80019ba8da3a..e0ec1c0e0eee 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -2,8 +2,13 @@
 # Cryptographic API
 #
 
+# memneq MUST be built with -Os or -O0 to prevent early-return optimizations
+# that will defeat memneq's actual purpose to prevent timing attacks.
+CFLAGS_REMOVE_memneq.o := -O1 -O2 -O3
+CFLAGS_memneq.o := -Os
+
 obj-$(CONFIG_CRYPTO) += crypto.o
-crypto-y := api.o cipher.o compress.o
+crypto-y := api.o cipher.o compress.o memneq.o
 
 obj-$(CONFIG_CRYPTO_WORKQUEUE) += crypto_wq.o
 
diff --git a/crypto/asymmetric_keys/rsa.c b/crypto/asymmetric_keys/rsa.c
index 4a6a0696f8a3..1912b9be5043 100644
--- a/crypto/asymmetric_keys/rsa.c
+++ b/crypto/asymmetric_keys/rsa.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <crypto/algapi.h>
 #include "public_key.h"
 
 MODULE_LICENSE("GPL");
@@ -189,12 +190,12 @@ static int RSA_verify(const u8 *H, const u8 *EM, size_t k, size_t hash_size,
 		}
 	}
 
-	if (memcmp(asn1_template, EM + T_offset, asn1_size) != 0) {
+	if (crypto_memneq(asn1_template, EM + T_offset, asn1_size) != 0) {
 		kleave(" = -EBADMSG [EM[T] ASN.1 mismatch]");
 		return -EBADMSG;
 	}
 
-	if (memcmp(H, EM + T_offset + asn1_size, hash_size) != 0) {
+	if (crypto_memneq(H, EM + T_offset + asn1_size, hash_size) != 0) {
 		kleave(" = -EKEYREJECTED [EM[T] hash mismatch]");
 		return -EKEYREJECTED;
 	}
diff --git a/crypto/authenc.c b/crypto/authenc.c
index a2cfae251dd5..65bcd076b18b 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -188,7 +188,7 @@ static void authenc_verify_ahash_update_done(struct crypto_async_request *areq,
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
+	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -227,7 +227,7 @@ static void authenc_verify_ahash_done(struct crypto_async_request *areq,
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
+	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -463,7 +463,7 @@ static int crypto_authenc_verify(struct aead_request *req,
 	ihash = ohash + authsize;
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
-	return memcmp(ihash, ohash, authsize) ? -EBADMSG : 0;
+	return crypto_memneq(ihash, ohash, authsize) ? -EBADMSG : 0;
 }
 
 static int crypto_authenc_iverify(struct aead_request *req, u8 *iv,
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 16c225cb28c2..a3ef98be2064 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -247,7 +247,7 @@ static void authenc_esn_verify_ahash_update_done(struct crypto_async_request *ar
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
+	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -296,7 +296,7 @@ static void authenc_esn_verify_ahash_update_done2(struct crypto_async_request *a
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
+	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -336,7 +336,7 @@ static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq,
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
+	err = crypto_memneq(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -568,7 +568,7 @@ static int crypto_authenc_esn_verify(struct aead_request *req)
 	ihash = ohash + authsize;
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
-	return memcmp(ihash, ohash, authsize) ? -EBADMSG : 0;
+	return crypto_memneq(ihash, ohash, authsize) ? -EBADMSG : 0;
 }
 
 static int crypto_authenc_esn_iverify(struct aead_request *req, u8 *iv,
diff --git a/crypto/ccm.c b/crypto/ccm.c
index c569c9c6afe3..003bbbd21a2b 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -364,7 +364,7 @@ static void crypto_ccm_decrypt_done(struct crypto_async_request *areq,
 
 	if (!err) {
 		err = crypto_ccm_auth(req, req->dst, cryptlen);
-		if (!err && memcmp(pctx->auth_tag, pctx->odata, authsize))
+		if (!err && crypto_memneq(pctx->auth_tag, pctx->odata, authsize))
 			err = -EBADMSG;
 	}
 	aead_request_complete(req, err);
@@ -423,7 +423,7 @@ static int crypto_ccm_decrypt(struct aead_request *req)
 		return err;
 
 	/* verify */
-	if (memcmp(authtag, odata, authsize))
+	if (crypto_memneq(authtag, odata, authsize))
 		return -EBADMSG;
 
 	return err;
diff --git a/crypto/gcm.c b/crypto/gcm.c
index b4c252066f7b..9cea4d0b6904 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -582,7 +582,7 @@ static int crypto_gcm_verify(struct aead_request *req,
 
 	crypto_xor(auth_tag, iauth_tag, 16);
 	scatterwalk_map_and_copy(iauth_tag, req->src, cryptlen, authsize, 0);
-	return memcmp(iauth_tag, auth_tag, authsize) ? -EBADMSG : 0;
+	return crypto_memneq(iauth_tag, auth_tag, authsize) ? -EBADMSG : 0;
 }
 
 static void gcm_decrypt_done(struct crypto_async_request *areq, int err)
diff --git a/crypto/memneq.c b/crypto/memneq.c
new file mode 100644
index 000000000000..cd0162221c14
--- /dev/null
+++ b/crypto/memneq.c
@@ -0,0 +1,138 @@
+/*
+ * Constant-time equality testing of memory regions.
+ *
+ * Authors:
+ *
+ *   James Yonan <james@openvpn.net>
+ *   Daniel Borkmann <dborkman@redhat.com>
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2013 OpenVPN Technologies, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ * The full GNU General Public License is included in this distribution
+ * in the file called LICENSE.GPL.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2013 OpenVPN Technologies, Inc. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of OpenVPN Technologies nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <crypto/algapi.h>
+
+#ifndef __HAVE_ARCH_CRYPTO_MEMNEQ
+
+/* Generic path for arbitrary size */
+static inline unsigned long
+__crypto_memneq_generic(const void *a, const void *b, size_t size)
+{
+	unsigned long neq = 0;
+
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+	while (size >= sizeof(unsigned long)) {
+		neq |= *(unsigned long *)a ^ *(unsigned long *)b;
+		a += sizeof(unsigned long);
+		b += sizeof(unsigned long);
+		size -= sizeof(unsigned long);
+	}
+#endif /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
+	while (size > 0) {
+		neq |= *(unsigned char *)a ^ *(unsigned char *)b;
+		a += 1;
+		b += 1;
+		size -= 1;
+	}
+	return neq;
+}
+
+/* Loop-free fast-path for frequently used 16-byte size */
+static inline unsigned long __crypto_memneq_16(const void *a, const void *b)
+{
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	if (sizeof(unsigned long) == 8)
+		return ((*(unsigned long *)(a)   ^ *(unsigned long *)(b))
+		      | (*(unsigned long *)(a+8) ^ *(unsigned long *)(b+8)));
+	else if (sizeof(unsigned int) == 4)
+		return ((*(unsigned int *)(a)    ^ *(unsigned int *)(b))
+                      | (*(unsigned int *)(a+4)  ^ *(unsigned int *)(b+4))
+		      | (*(unsigned int *)(a+8)  ^ *(unsigned int *)(b+8))
+	              | (*(unsigned int *)(a+12) ^ *(unsigned int *)(b+12)));
+	else
+#endif /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
+		return ((*(unsigned char *)(a)    ^ *(unsigned char *)(b))
+		      | (*(unsigned char *)(a+1)  ^ *(unsigned char *)(b+1))
+		      | (*(unsigned char *)(a+2)  ^ *(unsigned char *)(b+2))
+		      | (*(unsigned char *)(a+3)  ^ *(unsigned char *)(b+3))
+		      | (*(unsigned char *)(a+4)  ^ *(unsigned char *)(b+4))
+		      | (*(unsigned char *)(a+5)  ^ *(unsigned char *)(b+5))
+		      | (*(unsigned char *)(a+6)  ^ *(unsigned char *)(b+6))
+		      | (*(unsigned char *)(a+7)  ^ *(unsigned char *)(b+7))
+		      | (*(unsigned char *)(a+8)  ^ *(unsigned char *)(b+8))
+		      | (*(unsigned char *)(a+9)  ^ *(unsigned char *)(b+9))
+		      | (*(unsigned char *)(a+10) ^ *(unsigned char *)(b+10))
+		      | (*(unsigned char *)(a+11) ^ *(unsigned char *)(b+11))
+		      | (*(unsigned char *)(a+12) ^ *(unsigned char *)(b+12))
+		      | (*(unsigned char *)(a+13) ^ *(unsigned char *)(b+13))
+		      | (*(unsigned char *)(a+14) ^ *(unsigned char *)(b+14))
+		      | (*(unsigned char *)(a+15) ^ *(unsigned char *)(b+15)));
+}
+
+/* Compare two areas of memory without leaking timing information,
+ * and with special optimizations for common sizes.  Users should
+ * not call this function directly, but should instead use
+ * crypto_memneq defined in crypto/algapi.h.
+ */
+noinline unsigned long __crypto_memneq(const void *a, const void *b,
+				       size_t size)
+{
+	switch (size) {
+	case 16:
+		return __crypto_memneq_16(a, b);
+	default:
+		return __crypto_memneq_generic(a, b, size);
+	}
+}
+EXPORT_SYMBOL(__crypto_memneq);
+
+#endif /* __HAVE_ARCH_CRYPTO_MEMNEQ */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 418d270e1806..e73c19e90e38 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -386,5 +386,21 @@ static inline int crypto_requires_sync(u32 type, u32 mask)
 	return (type ^ CRYPTO_ALG_ASYNC) & mask & CRYPTO_ALG_ASYNC;
 }
 
-#endif	/* _CRYPTO_ALGAPI_H */
+noinline unsigned long __crypto_memneq(const void *a, const void *b, size_t size);
+
+/**
+ * crypto_memneq - Compare two areas of memory without leaking
+ *		   timing information.
+ *
+ * @a: One area of memory
+ * @b: Another area of memory
+ * @size: The size of the area.
+ *
+ * Returns 0 when data is equal, 1 otherwise.
+ */
+static inline int crypto_memneq(const void *a, const void *b, size_t size)
+{
+	return __crypto_memneq(a, b, size) != 0UL ? 1 : 0;
+}
 
+#endif	/* _CRYPTO_ALGAPI_H */
-- 
2.8.1

[patch added to 3.12-stable] EVM: Use crypto_memneq() for digest comparisons

[Jiri Slaby]

From: Ryan Ware <ware@linux.intel.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 613317bd212c585c20796c10afe5daaa95d4b0a1 upstream.

This patch fixes vulnerability CVE-2016-2085.  The problem exists
because the vm_verify_hmac() function includes a use of memcmp().
Unfortunately, this allows timing side channel attacks; specifically
a MAC forgery complexity drop from 2^128 to 2^12.  This patch changes
the memcmp() to the cryptographically safe crypto_memneq().

Reported-by: Xiaofei Rex Guo <xiaofei.rex.guo@intel.com>
Signed-off-by: Ryan Ware <ware@linux.intel.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 security/integrity/evm/evm_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index d43b62c4a8e5..5bf01c8648a8 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -21,6 +21,7 @@
 #include <linux/integrity.h>
 #include <linux/evm.h>
 #include <crypto/hash.h>
+#include <crypto/algapi.h>
 #include "evm.h"
 
 int evm_initialized;
@@ -132,7 +133,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 				   xattr_value_len, calc.digest);
 		if (rc)
 			break;
-		rc = memcmp(xattr_data->digest, calc.digest,
+		rc = crypto_memneq(xattr_data->digest, calc.digest,
 			    sizeof(calc.digest));
 		if (rc)
 			rc = -EINVAL;
-- 
2.8.1

[patch added to 3.12-stable] KVM: x86: removing unused variable

[Jiri Slaby]

From: Saurabh Sengar <saurabh.truth@gmail.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 2da29bccc5045ea10c70cb3a69be777768fd0b66 upstream.

removing unused variables, found by coccinelle

Signed-off-by: Saurabh Sengar <saurabh.truth@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 arch/x86/kvm/x86.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c47a4ecb584c..1962a3999adf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3471,41 +3471,35 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 
 static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
 	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
-	int r = 0;
-
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
 		sizeof(ps->channels));
 	ps->flags = kvm->arch.vpit->pit_state.flags;
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	memset(&ps->reserved, 0, sizeof(ps->reserved));
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
-	int r = 0, start = 0;
+	int start = 0;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3517,7 +3511,7 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	kvm->arch.vpit->pit_state.flags = ps->flags;
 	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
-	return r;
+	return 0;
 }
 
 static int kvm_vm_ioctl_reinject(struct kvm *kvm,
-- 
2.8.1

[patch added to 3.12-stable] KVM: x86: Reload pit counters for all channels when restoring state

[Jiri Slaby]

From: Andrew Honig <ahonig@google.com>

This patch has been added to the 3.12 stable tree. If you have any
objections, please let us know.

===============

commit 0185604c2d82c560dab2f2933a18f797e74ab5a8 upstream.

Currently if userspace restores the pit counters with a count of 0
on channels 1 or 2 and the guest attempts to read the count on those
channels, then KVM will perform a mod of 0 and crash.  This will ensure
that 0 values are converted to 65536 as per the spec.

This is CVE-2015-7513.

Signed-off-by: Andy Honig <ahonig@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 arch/x86/kvm/x86.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1962a3999adf..e0c859e1999a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3479,9 +3479,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 
 static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
+	int i;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
-	kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, ps->channels[i].count, 0);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3500,6 +3502,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 {
 	int start = 0;
+	int i;
 	u32 prev_legacy, cur_legacy;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
@@ -3509,7 +3512,8 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
 	memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels,
 	       sizeof(kvm->arch.vpit->pit_state.channels));
 	kvm->arch.vpit->pit_state.flags = ps->flags;
-	kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start);
+	for (i = 0; i < 3; i++)
+		kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, start);
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
-- 
2.8.1