23 Oct, 2009
2 commits
-
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
move virtrng_remove to .devexit.text
move virtballoon_remove to .devexit.text
virtio_blk: Revert serial number support
virtio: let header files include virtio_ids.h
virtio_blk: revert QUEUE_FLAG_VIRT addition -
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (21 commits)
niu: VLAN_ETH_HLEN should be used to make sure that the whole MAC header was copied to the head buffer in the Vlan packets case
KS8851: Fix ks8851_set_rx_mode() for IFF_MULTICAST
KS8851: Fix MAC address write order
KS8851: Add soft reset at probe time
net: fix section mismatch in fec.c
net: Fix struct inet_timewait_sock bitfield annotation
tcp: Try to catch MSG_PEEK bug
net: Fix IP_MULTICAST_IF
bluetooth: static lock key fix
bluetooth: scheduling while atomic bug fix
tcp: fix TCP_DEFER_ACCEPT retrans calculation
tcp: reduce SYN-ACK retrans for TCP_DEFER_ACCEPT
tcp: accept socket after TCP_DEFER_ACCEPT period
Revert "tcp: fix tcp_defer_accept to consider the timeout"
AF_UNIX: Fix deadlock on connecting to shutdown socket
ethoc: clear only pending irqs
ethoc: inline regs access
vmxnet3: use dev_dbg, fix build for CONFIG_BLOCK=n
virtio_net: use dev_kfree_skb_any() in free_old_xmit_skbs()
be2net: fix support for PCI hot plug
...
22 Oct, 2009
1 commit
-
Rusty,
commit 3ca4f5ca73057a617f9444a91022d7127041970a
virtio: add virtio IDs file
moved all device IDs into a single file. While the change itself is
a very good one, it can break userspace applications. For example
if a userspace tool wanted to get the ID of virtio_net it used to
include virtio_net.h. This does no longer work, since virtio_net.h
does not include virtio_ids.h.
This patch moves all "#include " from the C
files into the header files, making the header files compatible with
the old ones.In addition, this patch exports virtio_ids.h to userspace.
CC: Fernando Luis Vazquez Cao
Signed-off-by: Christian Borntraeger
Signed-off-by: Rusty Russell
20 Oct, 2009
8 commits
-
This patch tries to print out more information when we hit the
MSG_PEEK bug in tcp_recvmsg. It's been around since at least
2005 and it's about time that we finally fix it.Signed-off-by: Herbert Xu
Signed-off-by: David S. Miller -
ipv4/ipv6 setsockopt(IP_MULTICAST_IF) have dubious __dev_get_by_index() calls.
This function should be called only with RTNL or dev_base_lock held, or reader
could see a corrupt hash chain and eventually enter an endless loop.Fix is to call dev_get_by_index()/dev_put().
If this happens to be performance critical, we could define a new dev_exist_by_index()
function to avoid touching dev refcount.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
When shutdown ppp connection, lockdep waring about non-static key
will happen, it is caused by the lock is not initialized properly
at that time.Fix with tuning the lock/skb_queue_head init order
[ 94.339261] INFO: trying to register non-static key.
[ 94.342509] the code is fine but needs lockdep annotation.
[ 94.342509] turning off the locking correctness validator.
[ 94.342509] Pid: 0, comm: swapper Not tainted 2.6.31-mm1 #2
[ 94.342509] Call Trace:
[ 94.342509] [] register_lock_class+0x58/0x241
[ 94.342509] [] ? __lock_acquire+0xb57/0xb73
[ 94.342509] [] __lock_acquire+0xac/0xb73
[ 94.342509] [] ? lock_release_non_nested+0x17b/0x1de
[ 94.342509] [] lock_acquire+0x67/0x84
[ 94.342509] [] ? skb_dequeue+0x15/0x41
[ 94.342509] [] _spin_lock_irqsave+0x2f/0x3f
[ 94.342509] [] ? skb_dequeue+0x15/0x41
[ 94.342509] [] skb_dequeue+0x15/0x41
[ 94.342509] [] ? _read_unlock+0x1d/0x20
[ 94.342509] [] skb_queue_purge+0x14/0x1b
[ 94.342509] [] l2cap_recv_frame+0xea1/0x115a [l2cap]
[ 94.342509] [] ? __lock_acquire+0xb57/0xb73
[ 94.342509] [] ? mark_lock+0x1e/0x1c7
[ 94.342509] [] ? hci_rx_task+0xd2/0x1bc [bluetooth]
[ 94.342509] [] l2cap_recv_acldata+0xb1/0x1c6 [l2cap]
[ 94.342509] [] hci_rx_task+0x106/0x1bc [bluetooth]
[ 94.342509] [] ? l2cap_recv_acldata+0x0/0x1c6 [l2cap]
[ 94.342509] [] tasklet_action+0x69/0xc1
[ 94.342509] [] __do_softirq+0x94/0x11e
[ 94.342509] [] do_softirq+0x36/0x5a
[ 94.342509] [] irq_exit+0x35/0x68
[ 94.342509] [] do_IRQ+0x72/0x89
[ 94.342509] [] common_interrupt+0x2e/0x34
[ 94.342509] [] ? pm_qos_add_requirement+0x63/0x9d
[ 94.342509] [] ? acpi_idle_enter_bm+0x209/0x238
[ 94.342509] [] cpuidle_idle_call+0x5c/0x94
[ 94.342509] [] cpu_idle+0x4e/0x6f
[ 94.342509] [] rest_init+0x53/0x55
[ 94.342509] [] start_kernel+0x2f0/0x2f5
[ 94.342509] [] i386_start_kernel+0x91/0x96Reported-by: Oliver Hartkopp
Signed-off-by: Dave Young
Tested-by: Oliver Hartkopp
Signed-off-by: David S. Miller -
Due to driver core changes dev_set_drvdata will call kzalloc which should be
in might_sleep context, but hci_conn_add will be called in atomic contextLike dev_set_name move dev_set_drvdata to work queue function.
oops as following:
Oct 2 17:41:59 darkstar kernel: [ 438.001341] BUG: sleeping function called from invalid context at mm/slqb.c:1546
Oct 2 17:41:59 darkstar kernel: [ 438.001345] in_atomic(): 1, irqs_disabled(): 0, pid: 2133, name: sdptool
Oct 2 17:41:59 darkstar kernel: [ 438.001348] 2 locks held by sdptool/2133:
Oct 2 17:41:59 darkstar kernel: [ 438.001350] #0: (sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP){+.+.+.}, at: [] lock_sock+0xa/0xc [l2cap]
Oct 2 17:41:59 darkstar kernel: [ 438.001360] #1: (&hdev->lock){+.-.+.}, at: [] l2cap_sock_connect+0x103/0x26b [l2cap]
Oct 2 17:41:59 darkstar kernel: [ 438.001371] Pid: 2133, comm: sdptool Not tainted 2.6.31-mm1 #2
Oct 2 17:41:59 darkstar kernel: [ 438.001373] Call Trace:
Oct 2 17:41:59 darkstar kernel: [ 438.001381] [] __might_sleep+0xde/0xe5
Oct 2 17:41:59 darkstar kernel: [ 438.001386] [] __kmalloc+0x4a/0x15a
Oct 2 17:41:59 darkstar kernel: [ 438.001392] [] ? kzalloc+0xb/0xd
Oct 2 17:41:59 darkstar kernel: [ 438.001396] [] kzalloc+0xb/0xd
Oct 2 17:41:59 darkstar kernel: [ 438.001400] [] device_private_init+0x15/0x3d
Oct 2 17:41:59 darkstar kernel: [ 438.001405] [] dev_set_drvdata+0x18/0x26
Oct 2 17:41:59 darkstar kernel: [ 438.001414] [] hci_conn_init_sysfs+0x40/0xd9 [bluetooth]
Oct 2 17:41:59 darkstar kernel: [ 438.001422] [] ? hci_conn_add+0x128/0x186 [bluetooth]
Oct 2 17:41:59 darkstar kernel: [ 438.001429] [] hci_conn_add+0x177/0x186 [bluetooth]
Oct 2 17:41:59 darkstar kernel: [ 438.001437] [] hci_connect+0x3c/0xfb [bluetooth]
Oct 2 17:41:59 darkstar kernel: [ 438.001442] [] l2cap_sock_connect+0x174/0x26b [l2cap]
Oct 2 17:41:59 darkstar kernel: [ 438.001448] [] sys_connect+0x60/0x7a
Oct 2 17:41:59 darkstar kernel: [ 438.001453] [] ? lock_release_non_nested+0x84/0x1de
Oct 2 17:41:59 darkstar kernel: [ 438.001458] [] ? might_fault+0x47/0x81
Oct 2 17:41:59 darkstar kernel: [ 438.001462] [] ? might_fault+0x47/0x81
Oct 2 17:41:59 darkstar kernel: [ 438.001468] [] ? __copy_from_user_ll+0x11/0xce
Oct 2 17:41:59 darkstar kernel: [ 438.001472] [] sys_socketcall+0x82/0x17b
Oct 2 17:41:59 darkstar kernel: [ 438.001477] [] syscall_call+0x7/0xbSigned-off-by: Dave Young
Signed-off-by: David S. Miller -
Fix TCP_DEFER_ACCEPT conversion between seconds and
retransmission to match the TCP SYN-ACK retransmission periods
because the time is converted to such retransmissions. The old
algorithm selects one more retransmission in some cases. Allow
up to 255 retransmissions.Signed-off-by: Julian Anastasov
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller -
Change SYN-ACK retransmitting code for the TCP_DEFER_ACCEPT
users to not retransmit SYN-ACKs during the deferring period if
ACK from client was received. The goal is to reduce traffic
during the deferring period. When the period is finished
we continue with sending SYN-ACKs (at least one) but this time
any traffic from client will change the request to established
socket allowing application to terminate it properly.
Also, do not drop acked request if sending of SYN-ACK fails.Signed-off-by: Julian Anastasov
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller -
Willy Tarreau and many other folks in recent years
were concerned what happens when the TCP_DEFER_ACCEPT period
expires for clients which sent ACK packet. They prefer clients
that actively resend ACK on our SYN-ACK retransmissions to be
converted from open requests to sockets and queued to the
listener for accepting after the deferring period is finished.
Then application server can decide to wait longer for data
or to properly terminate the connection with FIN if read()
returns EAGAIN which is an indication for accepting after
the deferring period. This change still can have side effects
for applications that expect always to see data on the accepted
socket. Others can be prepared to work in both modes (with or
without TCP_DEFER_ACCEPT period) and their data processing can
ignore the read=EAGAIN notification and to allocate resources for
clients which proved to have no data to send during the deferring
period. OTOH, servers that use TCP_DEFER_ACCEPT=1 as flag (not
as a timeout) to wait for data will notice clients that didn't
send data for 3 seconds but that still resend ACKs.
Thanks to Willy Tarreau for the initial idea and to
Eric Dumazet for the review and testing the change.Signed-off-by: Julian Anastasov
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller -
This reverts commit 6d01a026b7d3009a418326bdcf313503a314f1ea.
Julian Anastasov, Willy Tarreau and Eric Dumazet have come up
with a more correct way to deal with this.Signed-off-by: David S. Miller
19 Oct, 2009
1 commit
-
I found a deadlock bug in UNIX domain socket, which makes able to DoS
attack against the local machine by non-root users.How to reproduce:
1. Make a listening AF_UNIX/SOCK_STREAM socket with an abstruct
namespace(*), and shutdown(2) it.
2. Repeat connect(2)ing to the listening socket from the other sockets
until the connection backlog is full-filled.
3. connect(2) takes the CPU forever. If every core is taken, the
system hangs.PoC code: (Run as many times as cores on SMP machines.)
int main(void)
{
int ret;
int csd;
int lsd;
struct sockaddr_un sun;/* make an abstruct name address (*) */
memset(&sun, 0, sizeof(sun));
sun.sun_family = PF_UNIX;
sprintf(&sun.sun_path[1], "%d", getpid());/* create the listening socket and shutdown */
lsd = socket(AF_UNIX, SOCK_STREAM, 0);
bind(lsd, (struct sockaddr *)&sun, sizeof(sun));
listen(lsd, 1);
shutdown(lsd, SHUT_RDWR);/* connect loop */
alarm(15); /* forcely exit the loop after 15 sec */
for (;;) {
csd = socket(AF_UNIX, SOCK_STREAM, 0);
ret = connect(csd, (struct sockaddr *)&sun, sizeof(sun));
if (-1 == ret) {
perror("connect()");
break;
}
puts("Connection OK");
}
return 0;
}(*) Make sun_path[0] = 0 to use the abstruct namespace.
If a file-based socket is used, the system doesn't deadlock because
of context switches in the file system layer.Why this happens:
Error checks between unix_socket_connect() and unix_wait_for_peer() are
inconsistent. The former calls the latter to wait until the backlog is
processed. Despite the latter returns without doing anything when the
socket is shutdown, the former doesn't check the shutdown state and
just retries calling the latter forever.Patch:
The patch below adds shutdown check into unix_socket_connect(), so
connect(2) to the shutdown socket will return -ECONREFUSED.Signed-off-by: Tomoki Sekiyama
Signed-off-by: Masanori Yoshida
Signed-off-by: David S. Miller
16 Oct, 2009
1 commit
-
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (53 commits)
vmxnet: fix 2 build problems
net: add support for STMicroelectronics Ethernet controllers.
net: ks8851_mll uses mii interfaces
net/fec_mpc52xx: Fix kernel panic on FEC error
net: Fix OF platform drivers coldplug/hotplug when compiled as modules
TI DaVinci EMAC: Clear statistics register properly.
r8169: partial support and phy init for the 8168d
irda/sa1100_ir: check return value of startup hook
udp: Fix udp_poll() and ioctl()
WAN: fix Cisco HDLC handshaking.
tcp: fix tcp_defer_accept to consider the timeout
3c574_cs: spin_lock the set_multicast_list function
net: Teach pegasus driver to ignore bluetoother adapters with clashing Vendor:Product IDs
netxen: fix pci bar mapping
ethoc: fix warning from 32bit build
libertas: fix build
net: VMware virtual Ethernet NIC driver: vmxnet3
net: Fix IXP 2000 network driver building.
libertas: fix build
mac80211: document ieee80211_rx() context requirement
...
14 Oct, 2009
1 commit
13 Oct, 2009
5 commits
-
udp_poll() can in some circumstances drop frames with incorrect checksums.
Problem is we now have to lock the socket while dropping frames, or risk
sk_forward corruption.This bug is present since commit 95766fff6b9a78d1
([UDP]: Add memory accounting.)While we are at it, we can correct ioctl(SIOCINQ) to also drop bad frames.
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
I was trying to use TCP_DEFER_ACCEPT and noticed that if the
client does not talk, the connection is never accepted and
remains in SYN_RECV state until the retransmits expire, where
it finally is deleted. This is bad when some firewall such as
netfilter sits between the client and the server because the
firewall sees the connection in ESTABLISHED state while the
server will finally silently drop it without sending an RST.This behaviour contradicts the man page which says it should
wait only for some time :TCP_DEFER_ACCEPT (since Linux 2.4)
Allows a listener to be awakened only when data arrives
on the socket. Takes an integer value (seconds), this
can bound the maximum number of attempts TCP will
make to complete the connection. This option should not
be used in code intended to be portable.Also, looking at ipv4/tcp.c, a retransmit counter is correctly
computed :case TCP_DEFER_ACCEPT:
icsk->icsk_accept_queue.rskq_defer_accept = 0;
if (val > 0) {
/* Translate value in seconds to number of
* retransmits */
while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
val > ((TCP_TIMEOUT_INIT / HZ) <<
icsk->icsk_accept_queue.rskq_defer_accept))
icsk->icsk_accept_queue.rskq_defer_accept++;
icsk->icsk_accept_queue.rskq_defer_accept++;
}
break;==> rskq_defer_accept is used as a counter of retransmits.
But in tcp_minisocks.c, this counter is only checked. And in
fact, I have found no location which updates it. So I think
that what was intended was to decrease it in tcp_minisocks
whenever it is checked, which the trivial patch below does.Signed-off-by: Willy Tarreau
Signed-off-by: David S. Miller -
ieee80211_rx() must be called with softirqs disabled
since the networking stack requires this for netif_rx()
and some code in mac80211 can assume that it can not
be processing its own tasklet and this call at the same
time.It may be possible to remove this requirement after a
careful audit of mac80211 and doing any needed locking
improvements in it along with disabling softirqs around
netif_rx(). An alternative might be to push all packet
processing to process context in mac80211, instead of
to the tasklet, and add other synchronisation.Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
When a scan completes, we call ieee80211_sta_find_ibss(),
which is also called from other places. When the scan was
done in software, there's no problem as both run from the
single-threaded mac80211 workqueue and are thus serialised
against each other, but with hardware scan the completion
can be in a different context and race against callers of
this function from the workqueue (e.g. due to beacon RX).
So instead of calling ieee80211_sta_find_ibss() directly,
just arm the timer and have it fire, scheduling the work,
which will invoke ieee80211_sta_find_ibss() (if that is
appropriate in the current state).Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
Signed-off-by: Felix Fietkau
Acked-by: Johannes Berg
Signed-off-by: John W. Linville
12 Oct, 2009
2 commits
-
This probably deserves to go into -stable.
Pedit will reject a policy that is large because it
uses the wrong structure in the policy validation.
This fixes it.Signed-off-by: Jamal Hadi Salim
Signed-off-by: David S. Miller -
After m68k's task_thread_info() doesn't refer to current,
it's possible to remove sched.h from interrupt.h and not break m68k!
Many thanks to Heiko Carstens for allowing this.Signed-off-by: Alexey Dobriyan
09 Oct, 2009
3 commits
-
The error unwinding code in set_netns has a bug
that will make it run into a BUG_ON if passed a
bad wiphy index, fix by not trying to unlock a
wiphy that doesn't exist.Signed-off-by: Johannes Berg
Signed-off-by: John W. Linville -
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (40 commits)
ethoc: limit the number of buffers to 128
ethoc: use system memory as buffer
ethoc: align received packet to make IP header at word boundary
ethoc: fix buffer address mapping
ethoc: fix typo to compute number of tx descriptors
au1000_eth: Duplicate test of RX_OVERLEN bit in update_rx_stats()
netxen: Fix Unlikely(x) > y
pasemi_mac: ethtool get settings fix
add maintainer for network drop monitor kernel service
tg3: Fix phylib locking strategy
rndis_host: support ETHTOOL_GPERMADDR
ipv4: arp_notify address list bug
gigaset: add kerneldoc comments
gigaset: correct debugging output selection
gigaset: improve error recovery
gigaset: fix device ERROR response handling
gigaset: announce if built with debugging
gigaset: handle isoc frame errors more gracefully
gigaset: linearize skb
gigaset: fix reject/hangup handling
...
08 Oct, 2009
3 commits
-
Commit 9ef1d4c7c7aca1cd436612b6ca785b726ffb8ed8 ("[NETLINK]: Missing
initializations in dumped data") introduced a typo in
initialization. This patch fixes this.Signed-off-by: Jiri Pirko
Signed-off-by: David S. Miller -
kfree_skb() should be used to free struct sk_buff pointers.
Signed-off-by: Roel Kluin
Acked-by: Johannes Berg
Cc: stable@kernel.org
Signed-off-by: John W. Linville -
When receiving data frames, we can send them only to
the interface they belong to based on transmitting
station (this doesn't work for probe requests). Also,
don't try to handle other frames for AP_VLAN at all
since those interface should only receive data.Additionally, the transmit side must check that the
station we're sending a frame to is actually on the
interface we're transmitting on, and not transmit
packets to functions that live on other interfaces,
so validate that as well.Another bug fix is needed in sta_info.c where in the
VLAN case when adding/removing stations we overwrite
the sdata variable we still need.Signed-off-by: Johannes Berg
Cc: stable@kernel.org
Signed-off-by: John W. Linville
07 Oct, 2009
1 commit
-
This fixes a bug with arp_notify.
If arp_notify is enabled, kernel will crash if address is changed
and no IP address is assigned.
http://bugzilla.kernel.org/show_bug.cgi?id=14330Reported-by: Hannes Frederic Sowa
Signed-off-by: Stephen Hemminger
Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller
05 Oct, 2009
4 commits
-
A number of drivers (recently including cfg80211-based ones)
assume that all wireless handlers, including statistics, can
sleep and they often also implicitly assume that the rtnl is
held around their invocation. This is almost always true now
except when reading from sysfs:BUG: sleeping function called from invalid context at kernel/mutex.c:280
in_atomic(): 1, irqs_disabled(): 0, pid: 10450, name: head
2 locks held by head/10450:
#0: (&buffer->mutex){+.+.+.}, at: [] sysfs_read_file+0x24/0xf4
#1: (dev_base_lock){++.?..}, at: [] wireless_show+0x1a/0x4c
Pid: 10450, comm: head Not tainted 2.6.32-rc3 #1
Call Trace:
[] __might_sleep+0xf0/0xf7
[] mutex_lock_nested+0x1a/0x33
[] wdev_lock+0xd/0xf [cfg80211]
[] cfg80211_wireless_stats+0x45/0x12d [cfg80211]
[] get_wireless_stats+0x16/0x1c
[] wireless_show+0x2a/0x4cFix this by using the rtnl instead of dev_base_lock.
Reported-by: Miles Lane
Signed-off-by: Johannes Berg
Signed-off-by: David S. Miller -
Commit fd29cf72 (pktgen: convert to use ktime_t)
inadvertantly converted "delay" parameter from nanosec to microsec.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
It is not currently possible to instruct pktgen to use one selected tx queue.
When Robert added multiqueue support in commit 45b270f8, he added
an interval (queue_map_min, queue_map_max), and his code doesnt take
into account the case of min = max, to select one tx queue exactly.I suspect a high performance setup on a eight txqueue device wants
to use exactly eight cpus, and assign one tx queue to each sender.This patchs makes pktgen select the right tx queue, not the first one.
Also updates Documentation to reflect Robert changes.
Signed-off-by: Eric Dumazet
Signed-off-by: Robert Olsson
Signed-off-by: David S. Miller -
Signed-off-by: Alexey Dobriyan
Signed-off-by: Linus Torvalds
03 Oct, 2009
2 commits
-
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (46 commits)
cnic: Fix NETDEV_UP event processing.
uvesafb/connector: Disallow unpliviged users to send netlink packets
pohmelfs/connector: Disallow unpliviged users to configure pohmelfs
dst/connector: Disallow unpliviged users to configure dst
dm/connector: Only process connector packages from privileged processes
connector: Removed the destruct_data callback since it is always kfree_skb()
connector/dm: Fixed a compilation warning
connector: Provide the sender's credentials to the callback
connector: Keep the skb in cn_callback_data
e1000e/igb/ixgbe: Don't report an error if devices don't support AER
net: Fix wrong sizeof
net: splice() from tcp to pipe should take into account O_NONBLOCK
net: Use sk_mark for routing lookup in more places
sky2: irqname based on pci address
skge: use unique IRQ name
IPv4 TCP fails to send window scale option when window scale is zero
net/ipv4/tcp.c: fix min() type mismatch warning
Kconfig: STRIP: Remove stale bits of STRIP help text
NET: mkiss: Fix typo
tg3: Remove prev_vlan_tag from struct tx_ring_info
... -
tcp_splice_read() doesnt take into account socket's O_NONBLOCK flag
Before this patch :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE);
causes a random endless block (if pipe is full) and
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK);
will return 0 immediately if the TCP buffer is empty.User application has no way to instruct splice() that socket should be in blocking mode
but pipe in nonblock more.Many projects cannot use splice(tcp -> pipe) because of this flaw.
http://git.samba.org/?p=samba.git;a=history;f=source3/lib/recvfile.c;h=ea0159642137390a0f7e57a123684e6e63e47581;hb=HEAD
http://lkml.indiana.edu/hypermail/linux/kernel/0807.2/0687.htmlLinus introduced SPLICE_F_NONBLOCK in commit 29e350944fdc2dfca102500790d8ad6d6ff4f69d
(splice: add SPLICE_F_NONBLOCK flag )It doesn't make the splice itself necessarily nonblocking (because the
actual file descriptors that are spliced from/to may block unless they
have the O_NONBLOCK flag set), but it makes the splice pipe operations
nonblocking.Linus intention was clear : let SPLICE_F_NONBLOCK control the splice pipe mode only
This patch instruct tcp_splice_read() to use the underlying file O_NONBLOCK
flag, as other socket operations do.Users will then call :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK );
to block on data coming from socket (if file is in blocking mode),
and not block on pipe output (to avoid deadlock)First version of this patch was submitted by Octavian Purdila
Reported-by: Volker Lendecke
Reported-by: Jason Gunthorpe
Signed-off-by: Eric Dumazet
Signed-off-by: Octavian Purdila
Acked-by: Linus Torvalds
Acked-by: Jens Axboe
Signed-off-by: David S. Miller
02 Oct, 2009
5 commits
-
This patch against v2.6.31 adds support for route lookup using sk_mark in some
more places. The benefits from this patch are the following.
First, SO_MARK option now has effect on UDP sockets too.
Second, ip_queue_xmit() and inet_sk_rebuild_header() could fail to do routing
lookup correctly if TCP sockets with SO_MARK were used.Signed-off-by: Atis Elsts
Acked-by: Eric Dumazet -
Acknowledge TCP window scale support by inserting the proper option in SYN/ACK
and SYN headers even if our window scale is zero.This fixes the following observed behavior:
1. Client sends a SYN with TCP window scaling option and non zero window scale
value to a Linux box.
2. Linux box notes large receive window from client.
3. Linux decides on a zero value of window scale for its part.
4. Due to compare against requested window scale size option, Linux does not to
send windows scale TCP option header on SYN/ACK at all.With the following result:
Client box thinks TCP window scaling is not supported, since SYN/ACK had no
TCP window scale option, while Linux thinks that TCP window scaling is
supported (and scale might be non zero), since SYN had TCP window scale
option and we have a mismatched idea between the client and server
regarding window sizes.Probably it also fixes up the following bug (not observed in practice):
1. Linux box opens TCP connection to some server.
2. Linux decides on zero value of window scale.
3. Due to compare against computed window scale size option, Linux does
not to set windows scale TCP option header on SYN.With the expected result that the server OS does not use window scale option
due to not receiving such an option in the SYN headers, leading to suboptimal
performance.Signed-off-by: Gilad Ben-Yossef
Signed-off-by: Ori Finkelman
Acked-by: Eric Dumazet
Signed-off-by: David S. Miller -
net/ipv4/tcp.c: In function 'do_tcp_setsockopt':
net/ipv4/tcp.c:2050: warning: comparison of distinct pointer types lacks a castSigned-off-by: Andrew Morton
Signed-off-by: David S. Miller -
After last pktgen changes, delay handling is wrong.
pktgen actually sends packets at full line speed.
Fix is to update pkt_dev->next_tx even if spin() returns early,
so that next spin() calls have a chance to see a positive delay.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller
01 Oct, 2009
1 commit
-
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
ax25: Fix possible oops in ax25_make_new
net: restore tx timestamping for accelerated vlans
Phonet: fix mutex imbalance
sit: fix off-by-one in ipip6_tunnel_get_prl
net: Fix sock_wfree() race
net: Make setsockopt() optlen be unsigned.