rpms
/
kernel
2
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Linux v4.3.3

This commit is contained in:
Josh Boyer 2015-12-15 07:31:12 -05:00
parent be9160e268
commit e7ca3b90d2
5 changed files with 5 additions and 709 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

288
Btrfs-fix-truncation-of-compressed-and-inlined-exten.patch
View File

@ -1,288 +0,0 @@
From 0305cd5f7fca85dae392b9ba85b116896eb7c1c7 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 16 Oct 2015 12:34:25 +0100
Subject: [PATCH] Btrfs: fix truncation of compressed and inlined extents
When truncating a file to a smaller size which consists of an inline
extent that is compressed, we did not discard (or made unusable) the
data between the new file size and the old file size, wasting metadata
space and allowing for the truncated data to be leaked and the data
corruption/loss mentioned below.
We were also not correctly decrementing the number of bytes used by the
inode, we were setting it to zero, giving a wrong report for callers of
the stat(2) syscall. The fsck tool also reported an error about a mismatch
between the nbytes of the file versus the real space used by the file.
Now because we weren't discarding the truncated region of the file, it
was possible for a caller of the clone ioctl to actually read the data
that was truncated, allowing for a security breach without requiring root
access to the system, using only standard filesystem operations. The
scenario is the following:
1) User A creates a file which consists of an inline and compressed
extent with a size of 2000 bytes - the file is not accessible to
any other users (no read, write or execution permission for anyone
else);
2) The user truncates the file to a size of 1000 bytes;
3) User A makes the file world readable;
4) User B creates a file consisting of an inline extent of 2000 bytes;
5) User B issues a clone operation from user A's file into its own
file (using a length argument of 0, clone the whole range);
6) User B now gets to see the 1000 bytes that user A truncated from
its file before it made its file world readbale. User B also lost
the bytes in the range [1000, 2000[ bytes from its own file, but
that might be ok if his/her intention was reading stale data from
user A that was never supposed to be public.
Note that this contrasts with the case where we truncate a file from 2000
bytes to 1000 bytes and then truncate it back from 1000 to 2000 bytes. In
this case reading any byte from the range [1000, 2000[ will return a value
of 0x00, instead of the original data.
This problem exists since the clone ioctl was added and happens both with
and without my recent data loss and file corruption fixes for the clone
ioctl (patch "Btrfs: fix file corruption and data loss after cloning
inline extents").
So fix this by truncating the compressed inline extents as we do for the
non-compressed case, which involves decompressing, if the data isn't already
in the page cache, compressing the truncated version of the extent, writing
the compressed content into the inline extent and then truncate it.
The following test case for fstests reproduces the problem. In order for
the test to pass both this fix and my previous fix for the clone ioctl
that forbids cloning a smaller inline extent into a larger one,
which is titled "Btrfs: fix file corruption and data loss after cloning
inline extents", are needed. Without that other fix the test fails in a
different way that does not leak the truncated data, instead part of
destination file gets replaced with zeroes (because the destination file
has a larger inline extent than the source).
seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"
tmp=/tmp/$$
status=1 # failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15
_cleanup()
{
rm -f $tmp.*
}
# get standard environment, filters and checks
. ./common/rc
. ./common/filter
# real QA test starts here
_need_to_be_root
_supported_fs btrfs
_supported_os Linux
_require_scratch
_require_cloner
rm -f $seqres.full
_scratch_mkfs >>$seqres.full 2>&1
_scratch_mount "-o compress"
# Create our test files. File foo is going to be the source of a clone operation
# and consists of a single inline extent with an uncompressed size of 512 bytes,
# while file bar consists of a single inline extent with an uncompressed size of
# 256 bytes. For our test's purpose, it's important that file bar has an inline
# extent with a size smaller than foo's inline extent.
$XFS_IO_PROG -f -c "pwrite -S 0xa1 0 128" \
-c "pwrite -S 0x2a 128 384" \
$SCRATCH_MNT/foo | _filter_xfs_io
$XFS_IO_PROG -f -c "pwrite -S 0xbb 0 256" $SCRATCH_MNT/bar | _filter_xfs_io
# Now durably persist all metadata and data. We do this to make sure that we get
# on disk an inline extent with a size of 512 bytes for file foo.
sync
# Now truncate our file foo to a smaller size. Because it consists of a
# compressed and inline extent, btrfs did not shrink the inline extent to the
# new size (if the extent was not compressed, btrfs would shrink it to 128
# bytes), it only updates the inode's i_size to 128 bytes.
$XFS_IO_PROG -c "truncate 128" $SCRATCH_MNT/foo
# Now clone foo's inline extent into bar.
# This clone operation should fail with errno EOPNOTSUPP because the source
# file consists only of an inline extent and the file's size is smaller than
# the inline extent of the destination (128 bytes < 256 bytes). However the
# clone ioctl was not prepared to deal with a file that has a size smaller
# than the size of its inline extent (something that happens only for compressed
# inline extents), resulting in copying the full inline extent from the source
# file into the destination file.
#
# Note that btrfs' clone operation for inline extents consists of removing the
# inline extent from the destination inode and copy the inline extent from the
# source inode into the destination inode, meaning that if the destination
# inode's inline extent is larger (N bytes) than the source inode's inline
# extent (M bytes), some bytes (N - M bytes) will be lost from the destination
# file. Btrfs could copy the source inline extent's data into the destination's
# inline extent so that we would not lose any data, but that's currently not
# done due to the complexity that would be needed to deal with such cases
# (specially when one or both extents are compressed), returning EOPNOTSUPP, as
# it's normally not a very common case to clone very small files (only case
# where we get inline extents) and copying inline extents does not save any
# space (unlike for normal, non-inlined extents).
$CLONER_PROG -s 0 -d 0 -l 0 $SCRATCH_MNT/foo $SCRATCH_MNT/bar
# Now because the above clone operation used to succeed, and due to foo's inline
# extent not being shinked by the truncate operation, our file bar got the whole
# inline extent copied from foo, making us lose the last 128 bytes from bar
# which got replaced by the bytes in range [128, 256[ from foo before foo was
# truncated - in other words, data loss from bar and being able to read old and
# stale data from foo that should not be possible to read anymore through normal
# filesystem operations. Contrast with the case where we truncate a file from a
# size N to a smaller size M, truncate it back to size N and then read the range
# [M, N[, we should always get the value 0x00 for all the bytes in that range.
# We expected the clone operation to fail with errno EOPNOTSUPP and therefore
# not modify our file's bar data/metadata. So its content should be 256 bytes
# long with all bytes having the value 0xbb.
#
# Without the btrfs bug fix, the clone operation succeeded and resulted in
# leaking truncated data from foo, the bytes that belonged to its range
# [128, 256[, and losing data from bar in that same range. So reading the
# file gave us the following content:
#
# 0000000 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1 a1
# *
# 0000200 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a 2a
# *
# 0000400
echo "File bar's content after the clone operation:"
od -t x1 $SCRATCH_MNT/bar
# Also because the foo's inline extent was not shrunk by the truncate
# operation, btrfs' fsck, which is run by the fstests framework everytime a
# test completes, failed reporting the following error:
#
# root 5 inode 257 errors 400, nbytes wrong
status=0
exit
Cc: stable@vger.kernel.org
Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
fs/btrfs/inode.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 68 insertions(+), 14 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 208db4e835f0..cbb4286490a1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4217,6 +4217,47 @@ static int truncate_space_check(struct btrfs_trans_handle *trans,
}
+static int truncate_inline_extent(struct inode *inode,
+ struct btrfs_path *path,
+ struct btrfs_key *found_key,
+ const u64 item_end,
+ const u64 new_size)
+{
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ struct btrfs_file_extent_item *fi;
+ u32 size = (u32)(new_size - found_key->offset);
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+
+ fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) {
+ loff_t offset = new_size;
+ loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE);
+
+ /*
+ * Zero out the remaining of the last page of our inline extent,
+ * instead of directly truncating our inline extent here - that
+ * would be much more complex (decompressing all the data, then
+ * compressing the truncated data, which might be bigger than
+ * the size of the inline extent, resize the extent, etc).
+ * We release the path because to get the page we might need to
+ * read the extent item from disk (data not in the page cache).
+ */
+ btrfs_release_path(path);
+ return btrfs_truncate_page(inode, offset, page_end - offset, 0);
+ }
+
+ btrfs_set_file_extent_ram_bytes(leaf, fi, size);
+ size = btrfs_file_extent_calc_inline_size(size);
+ btrfs_truncate_item(root, path, size, 1);
+
+ if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+ inode_sub_bytes(inode, item_end + 1 - new_size);
+
+ return 0;
+}
+
/*
* this can truncate away extent items, csum items and directory items.
* It starts at a high offset and removes keys until it can't find
@@ -4411,27 +4452,40 @@ search_again:
* special encodings
*/
if (!del_item &&
- btrfs_file_extent_compression(leaf, fi) == 0 &&
btrfs_file_extent_encryption(leaf, fi) == 0 &&
btrfs_file_extent_other_encoding(leaf, fi) == 0) {
- u32 size = new_size - found_key.offset;
-
- if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
- inode_sub_bytes(inode, item_end + 1 -
- new_size);
/*
- * update the ram bytes to properly reflect
- * the new size of our item
+ * Need to release path in order to truncate a
+ * compressed extent. So delete any accumulated
+ * extent items so far.
*/
- btrfs_set_file_extent_ram_bytes(leaf, fi, size);
- size =
- btrfs_file_extent_calc_inline_size(size);
- btrfs_truncate_item(root, path, size, 1);
+ if (btrfs_file_extent_compression(leaf, fi) !=
+ BTRFS_COMPRESS_NONE && pending_del_nr) {
+ err = btrfs_del_items(trans, root, path,
+ pending_del_slot,
+ pending_del_nr);
+ if (err) {
+ btrfs_abort_transaction(trans,
+ root,
+ err);
+ goto error;
+ }
+ pending_del_nr = 0;
+ }
+
+ err = truncate_inline_extent(inode, path,
+ &found_key,
+ item_end,
+ new_size);
+ if (err) {
+ btrfs_abort_transaction(trans,
+ root, err);
+ goto error;
+ }
} else if (test_bit(BTRFS_ROOT_REF_COWS,
&root->state)) {
- inode_sub_bytes(inode, item_end + 1 -
- found_key.offset);
+ inode_sub_bytes(inode, item_end + 1 - new_size);
}
}
delete:
--
2.5.0

77
RDS-fix-race-condition-when-sending-a-message-on-unb.patch
View File

@ -1,77 +0,0 @@
From 8e92c2b0cb50a31e2956760498bc8cdb72993fb3 Mon Sep 17 00:00:00 2001
From: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Date: Fri, 16 Oct 2015 17:11:42 +0200
Subject: [PATCH] RDS: fix race condition when sending a message on unbound
socket.
Sasha's found a NULL pointer dereference in the RDS connection code when
sending a message to an apparently unbound socket. The problem is caused
by the code checking if the socket is bound in rds_sendmsg(), which checks
the rs_bound_addr field without taking a lock on the socket. This opens a
race where rs_bound_addr is temporarily set but where the transport is not
in rds_bind(), leading to a NULL pointer dereference when trying to
dereference 'trans' in __rds_conn_create().
Vegard wrote a reproducer for this issue, so kindly ask him to share if
you're interested.
I cannot reproduce the NULL pointer dereference using Vegard's reproducer
with this patch, whereas I could without.
Complete earlier incomplete fix to CVE-2015-6937:
74e98eb08588 ("RDS: verify the underlying transport exists before creating a connection")
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Chien Yen <chien.yen@oracle.com>
Cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org
---
net/rds/connection.c | 6 ------
net/rds/send.c | 4 +++-
2 files changed, 3 insertions(+), 7 deletions(-)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 49adeef8090c..9b2de5e67d79 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -190,12 +190,6 @@ new_conn:
}
}
- if (trans == NULL) {
- kmem_cache_free(rds_conn_slab, conn);
- conn = ERR_PTR(-ENODEV);
- goto out;
- }
-
conn->c_trans = trans;
ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index 4df61a515b83..859de6f32521 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,11 +1009,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
release_sock(sk);
}
- /* racing with another thread binding seems ok here */
+ lock_sock(sk);
if (daddr == 0 || rs->rs_bound_addr == 0) {
+ release_sock(sk);
ret = -ENOTCONN; /* XXX not a great errno */
goto out;
}
+ release_sock(sk);
if (payload_len > rds_sk_sndbuf(rs)) {
ret = -EMSGSIZE;
--
2.4.3

14
kernel.spec
View File

@ -52,7 +52,7 @@ Summary: The Linux kernel
%if 0%{?released_kernel}
# Do we have a -stable update to apply?
%define stable_update 2
%define stable_update 3
# Set rpm version accordingly
%if 0%{?stable_update}
%define stablerev %{stable_update}
@ -592,9 +592,6 @@ Patch503: drm-i915-turn-off-wc-mmaps.patch
Patch508: kexec-uefi-copy-secure_boot-flag-in-boot-params.patch
#CVE-2015-7990 rhbz 1276437 1276438
Patch524: RDS-fix-race-condition-when-sending-a-message-on-unb.patch
#CVE-2015-7799 rhbz 1271134 1271135
Patch512: isdn_ppp-Add-checks-for-allocation-failure-in-isdn_p.patch
Patch513: ppp-slip-Validate-VJ-compression-slot-parameters-com.patch
@ -613,9 +610,6 @@ Patch556: netfilter-ipset-Fix-extension-alignment.patch
Patch557: netfilter-ipset-Fix-hash-type-expiration.patch
Patch558: netfilter-ipset-Fix-hash-type-expire-release-empty-h.patch
#CVE-2015-8374 rhbz 1286261 1286262
Patch565: Btrfs-fix-truncation-of-compressed-and-inlined-exten.patch
#rhbz 1284059
Patch566: KEYS-Fix-handling-of-stored-error-in-a-negatively-in.patch
@ -634,9 +628,6 @@ Patch571: ideapad-laptop-Add-Lenovo-ideapad-Y700-17ISK-to-no_h.patch
#rhbz 1288687
Patch572: alua_fix.patch
#CVE-2013-7446 rhbz 1282688 1282712
Patch573: unix-avoid-use-after-free-in-ep_remove_wait_queue.patch
#CVE-XXXX-XXXX rhbz 1291329 1291332
Patch574: ovl-fix-permission-checking-for-setattr.patch
@ -2086,6 +2077,9 @@ fi
#
#
%changelog
* Tue Dec 15 2015 Josh Boyer <jwboyer@fedoraproject.org>
- Linux v4.3.3
* Mon Dec 14 2015 Josh Boyer <jwboyer@fedoraproject.org>
- CVE-2015-7550 Race between read and revoke keys (rhbz 1291197 1291198)
- CVE-XXXX-XXXX permission bypass on overlayfs (rhbz 1291329 1291332)

2
sources
View File

@ -1,3 +1,3 @@
58b35794eee3b6d52ce7be39357801e7 linux-4.3.tar.xz
7c516c9528b9f9aac0136944b0200b7e perf-man-4.3.tar.gz
3a465c7cf55ec9dbf2d72d9292aa5fde patch-4.3.2.xz
d3235b3640ae6ac1ab579171943fda4b patch-4.3.3.xz

333
unix-avoid-use-after-free-in-ep_remove_wait_queue.patch
View File

@ -1,333 +0,0 @@
From a46b9d2bac864f3ef6b21eb96864ddd88794222d Mon Sep 17 00:00:00 2001
From: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Date: Fri, 20 Nov 2015 22:07:23 +0000
Subject: [PATCH 05/43] unix: avoid use-after-free in ep_remove_wait_queue
[ Upstream commit 7d267278a9ece963d77eefec61630223fce08c6c ]
Rainer Weikusat <rweikusat@mobileactivedefense.com> writes:
An AF_UNIX datagram socket being the client in an n:1 association with
some server socket is only allowed to send messages to the server if the
receive queue of this socket contains at most sk_max_ack_backlog
datagrams. This implies that prospective writers might be forced to go
to sleep despite none of the message presently enqueued on the server
receive queue were sent by them. In order to ensure that these will be
woken up once space becomes again available, the present unix_dgram_poll
routine does a second sock_poll_wait call with the peer_wait wait queue
of the server socket as queue argument (unix_dgram_recvmsg does a wake
up on this queue after a datagram was received). This is inherently
problematic because the server socket is only guaranteed to remain alive
for as long as the client still holds a reference to it. In case the
connection is dissolved via connect or by the dead peer detection logic
in unix_dgram_sendmsg, the server socket may be freed despite "the
polling mechanism" (in particular, epoll) still has a pointer to the
corresponding peer_wait queue. There's no way to forcibly deregister a
wait queue with epoll.
Based on an idea by Jason Baron, the patch below changes the code such
that a wait_queue_t belonging to the client socket is enqueued on the
peer_wait queue of the server whenever the peer receive queue full
condition is detected by either a sendmsg or a poll. A wake up on the
peer queue is then relayed to the ordinary wait queue of the client
socket via wake function. The connection to the peer wait queue is again
dissolved if either a wake up is about to be relayed or the client
socket reconnects or a dead peer is detected or the client socket is
itself closed. This enables removing the second sock_poll_wait from
unix_dgram_poll, thus avoiding the use-after-free, while still ensuring
that no blocked writer sleeps forever.
Signed-off-by: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Fixes: ec0d215f9420 ("af_unix: fix 'poll for write'/connected DGRAM sockets")
Reviewed-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/af_unix.h | 1 +
net/unix/af_unix.c | 183 ++++++++++++++++++++++++++++++++++++++++++++------
2 files changed, 165 insertions(+), 19 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b36d837..2a91a05 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
#define UNIX_GC_CANDIDATE 0
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
+ wait_queue_t peer_wake;
};
static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 42ab2cc..153b2f2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
return s;
}
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+ void *key)
+{
+ struct unix_sock *u;
+ wait_queue_head_t *u_sleep;
+
+ u = container_of(q, struct unix_sock, peer_wake);
+
+ __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+ q);
+ u->peer_wake.private = NULL;
+
+ /* relaying can only happen while the wq still exists */
+ u_sleep = sk_sleep(&u->sk);
+ if (u_sleep)
+ wake_up_interruptible_poll(u_sleep, key);
+
+ return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+ int rc;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ rc = 0;
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (!u->peer_wake.private) {
+ u->peer_wake.private = other;
+ __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+ rc = 1;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+ return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+ struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (u->peer_wake.private == other) {
+ __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+ u->peer_wake.private = NULL;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+ struct sock *other)
+{
+ unix_dgram_peer_wake_disconnect(sk, other);
+ wake_up_interruptible_poll(sk_sleep(sk),
+ POLLOUT |
+ POLLWRNORM |
+ POLLWRBAND);
+}
+
+/* preconditions:
+ * - unix_peer(sk) == other
+ * - association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+ int connected;
+
+ connected = unix_dgram_peer_wake_connect(sk, other);
+
+ if (unix_recvq_full(other))
+ return 1;
+
+ if (connected)
+ unix_dgram_peer_wake_disconnect(sk, other);
+
+ return 0;
+}
+
static inline int unix_writable(struct sock *sk)
{
return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
@@ -430,6 +542,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
skpair->sk_state_change(skpair);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
}
+
+ unix_dgram_peer_wake_disconnect(sk, skpair);
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
}
@@ -665,6 +779,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
+ init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -1032,6 +1147,8 @@ restart:
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
unix_peer(sk) = other;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
unix_state_double_unlock(sk, other);
if (other != old_peer)
@@ -1471,6 +1588,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
struct scm_cookie scm;
int max_level;
int data_len = 0;
+ int sk_locked;
wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
@@ -1549,12 +1667,14 @@ restart:
goto out_free;
}
+ sk_locked = 0;
unix_state_lock(other);
+restart_locked:
err = -EPERM;
if (!unix_may_send(sk, other))
goto out_unlock;
- if (sock_flag(other, SOCK_DEAD)) {
+ if (unlikely(sock_flag(other, SOCK_DEAD))) {
/*
* Check with 1003.1g - what should
* datagram error
@@ -1562,10 +1682,14 @@ restart:
unix_state_unlock(other);
sock_put(other);
+ if (!sk_locked)
+ unix_state_lock(sk);
+
err = 0;
- unix_state_lock(sk);
if (unix_peer(sk) == other) {
unix_peer(sk) = NULL;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
unix_state_unlock(sk);
unix_dgram_disconnected(sk, other);
@@ -1591,21 +1715,38 @@ restart:
goto out_unlock;
}
- if (unix_peer(other) != sk && unix_recvq_full(other)) {
- if (!timeo) {
- err = -EAGAIN;
- goto out_unlock;
+ if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+ if (timeo) {
+ timeo = unix_wait_for_peer(other, timeo);
+
+ err = sock_intr_errno(timeo);
+ if (signal_pending(current))
+ goto out_free;
+
+ goto restart;
}
- timeo = unix_wait_for_peer(other, timeo);
+ if (!sk_locked) {
+ unix_state_unlock(other);
+ unix_state_double_lock(sk, other);
+ }
- err = sock_intr_errno(timeo);
- if (signal_pending(current))
- goto out_free;
+ if (unix_peer(sk) != other ||
+ unix_dgram_peer_wake_me(sk, other)) {
+ err = -EAGAIN;
+ sk_locked = 1;
+ goto out_unlock;
+ }
- goto restart;
+ if (!sk_locked) {
+ sk_locked = 1;
+ goto restart_locked;
+ }
}
+ if (unlikely(sk_locked))
+ unix_state_unlock(sk);
+
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
maybe_add_creds(skb, sock, other);
@@ -1619,6 +1760,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -2475,14 +2618,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
return mask;
writable = unix_writable(sk);
- other = unix_peer_get(sk);
- if (other) {
- if (unix_peer(other) != sk) {
- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
- if (unix_recvq_full(other))
- writable = 0;
- }
- sock_put(other);
+ if (writable) {
+ unix_state_lock(sk);
+
+ other = unix_peer(sk);
+ if (other && unix_peer(other) != sk &&
+ unix_recvq_full(other) &&
+ unix_dgram_peer_wake_me(sk, other))
+ writable = 0;
+
+ unix_state_unlock(sk);
}
if (writable)
--
2.1.0