29 Mar, 2011
7 commits
-
When we clone a xfrm state we have to assign the replay_esn
and the preplay_esn pointers to the state if we use the
new replay detection method. To this end, we add a
xfrm_replay_clone() function that allocates memory for
the replay detection and takes over the necessary values
from the original state.Signed-off-by: Steffen Klassert
Acked-by: Herbert Xu
Signed-off-by: David S. Miller -
As it is, the replay check is just performed if the replay window of the
legacy implementation is nonzero. So we move the test on a nonzero replay
window inside the replay check functions to be sure we are testing for the
right implementation.Signed-off-by: Steffen Klassert
Acked-by: Herbert Xu
Signed-off-by: David S. Miller -
The current code sometimes generates build warnings due to how it checks
the silicon revision, so clean it up and properly document things.Signed-off-by: Mike Frysinger
Signed-off-by: David S. Miller -
The correct usage should be "static inline void" instead of "static void inline"
Signed-off-by: G.Balaji
Signed-off-by: David S. Miller -
While testing the performance of different receive interrupt
coalescing settings on a single stream TCP benchmark, I noticed two
very different results. With rx-usecs=50, most of the time a
connection would hit 8280 Mbps but once in a while it would hit
9330 Mbps.It turns out we are only applying the interrupt coalescing settings
to the first queue and whenever the rx hash would direct us onto
that queue we ran faster.With this patch applied and rx-usecs=50, I get 9330 Mbps
consistently.Signed-off-by: Anton Blanchard
Acked-by: Divy Le Ray
Signed-off-by: David S. Miller -
When analysing performance of the cxgb3 on a ppc64 box I noticed that
we weren't doing much GRO merging. It turns out we are limited by the
number of SKB frags:#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
With a 4kB page size we have 18 frags, but with a 64kB page size we
only have 3 frags.I ran a single stream TCP bandwidth test to compare the performance of
Signed-off-by: David S. Miller
-
Reported-by: Marc Kleine-Budde
Signed-off-by: David S. Miller
28 Mar, 2011
20 commits
-
After commit d5dbda23804156ae6f35025ade5307a49d1db6d7 "ethtool: Add
support for vlan accleration.", drivers that have NETIF_F_HW_VLAN_TX,
and/or NETIF_F_HW_VLAN_RX feature, but do not allow enable/disable vlan
acceleration via ethtool set_flags, always return -EINVAL from that
function. Fix by returning -EINVAL only if requested features do not
match current settings and can not be changed by driver.Change any driver that define ethtool->set_flags to use
ethtool_invalid_flags() to avoid similar problems in the future
(also on drivers that do not have the problem).Tested with modified (to reproduce this bug) myri10ge driver.
Cc: stable@kernel.org # 2.6.37+
Signed-off-by: Stanislaw Gruszka
Signed-off-by: David S. Miller -
The mlx4_en driver uses the combination stop_port/start_port
in a number of places. Unfortunately that causes any promiscuous
mode settings on the hardware to be lost.This patch fixes that problem.
Signed-off-by: Herbert Xu
Signed-off-by: David S. Miller -
The correct usage is "static inline void" not "static void inline".
Signed-off-by: Javier Martinez Canillas
Signed-off-by: David S. Miller -
It is proper style to include linux/foo.h instead asm/foo.h if both exist
Signed-off-by: Javier Martinez Canillas
Signed-off-by: David S. Miller -
Two places in the kernel were doing skb->ip_summed = 0.
Change both to skb->ip_summed = CHECKSUM_NONE, which is more readable.
Signed-off-by: Cesar Eduardo Barros
Signed-off-by: David S. Miller -
The jme driver uses the legacy PCI power management, so it has to do
some PCI-specific things in its ->suspend() and ->resume() callbacks,
which isn't necessary and should better be done by the PCI
sybsystem-level power management code. It also doesn't use device
wakeup flags correctly.Convert jme to the new PCI power management framework and make it
let the PCI subsystem take care of all the PCI-specific aspects of
device handling during system power transitions.Signed-off-by: Rafael J. Wysocki
Signed-off-by: David S. Miller -
Avoid theoretical race condition regarding accessing dev->features
NETIF_F_LRO flag, which is illustrated below.CPU1 CPU2
myri10ge_clean_rx_done(): myri10ge_set_flags():
or
myri10ge_set_rx_csum():if (dev->features & NETIF_F_LRO)
setup lro
dev->features |= NETIF_F_LRO
or
dev->features &= ~NETIF_F_LRO;
if (dev->features & NETIF_F_LRO)
flush lroOn the way reduce myri10ge_rx_done() number of arguments and calls by
moving mgp->small_bytes check into that function. That reduce code sizefrom:
text data bss dec hex filename
36644 248 100 36992 9080 drivers/net/myri10ge/myri10ge.oto:
text data bss dec hex filename
36037 247 100 36384 8e20 drivers/net/myri10ge/myri10ge.oon my i686 system, what should also make myri10ge_clean_rx_done()
being faster.Signed-off-by: Stanislaw Gruszka
Signed-off-by: David S. Miller -
The mac address of the bridge device may be changed when a new interface
is added to the bridge. If this happens, then the bridge needs to call
the network notifiers to tickle any other systems that care. Since bridge
can be a module, this also means exporting the notifier function.Signed-off-by: Stephen Hemminger
Signed-off-by: David S. Miller -
The current handling of echoed IP timestamp options with prespecified
addresses is rather broken since the 2.2.x kernels. As far as i understand
it, it should behave like when originating packets.Currently it will only timestamp the next free slot if:
- there is space for *two* timestamps
- some random data from the echoed packet taken as an IP is *not* a local IPThis first is caused by an off-by-one error. 'soffset' points to the next
free slot and so we only need to have 'soffset + 7
Signed-off-by: David S. Miller -
The current SocketCAN implementation for the Bosch c_can cell doesn't
account the TX bytes correctly, because it calls
c_can_inval_msg_object() (which clears the msg ctrl register) before
reading the DLC value:for (/* nix */; (priv->tx_next - priv->tx_echo) > 0; priv->tx_echo++) {
msg_obj_no = get_tx_echo_msg_obj(priv);
c_can_inval_msg_object(dev, 0, msg_obj_no);
val = c_can_read_reg32(priv, &priv->regs->txrqst1);
if (!(val & (1 << msg_obj_no))) {
can_get_echo_skb(dev,
msg_obj_no - C_CAN_MSG_OBJ_TX_FIRST);
stats->tx_bytes += priv->read_reg(priv,
&priv->regs->ifregs[0].msg_cntrl)
& IF_MCONT_DLC_MASK;
stats->tx_packets++;
}
}So, we will always read 0 for the DLC value and "ifconfig" will report
*0* TX Bytes.The fix is quite easy: Just move c_can_inval_msg_object() to the end of
the if() statement. So:
* We only call c_can_inval_msg_object() if the message was
actually transmitted
* We read out the DLC value _before_ clearing the msg ctrl
registerSigned-off-by: Jan Altenberg
Acked-by: Kurt Van Dijck
Acked-by: Wolfgang Grandegger
Signed-off-by: David S. Miller -
This patch fixes the check in the probe function whether a IRQ was supplied
to the driver. The original driver check the irq "struct resource *" againstCc: Bhupesh Sharma
Signed-off-by: David S. Miller -
This patch disables the one shot mode, until the driver has been fixed and
tested to support it.> I'm quite sure I've seen a situation where msg_obj 17 "seemed" to be
> pending, while msg_obj 18 and 19 already have been transmitted. But
> in that case, I enabled ONESHOT for the can interface, which enables
> the DA mode (automatic retransmission is disabled).Reported-by: Jan Altenberg
Signed-off-by: Marc Kleine-Budde
Signed-off-by: Kurt Van Dijck
Cc: Bhupesh Sharma
Acked-by: Wolfgang Grandegger
Signed-off-by: David S. Miller -
can_ioctl is the only reason for struct proto to be non-const.
script/check-patch.pl suggests struct proto be const.Setting the reference to the common can_ioctl() in all CAN protocols directly
removes the need to make the struct proto writable in af_can.cSigned-off-by: Kurt Van Dijck
Signed-off-by: Oliver Hartkopp
Signed-off-by: David S. Miller -
The code itself can explain what it is doing, no need these comments.
Signed-off-by: WANG Cong
Signed-off-by: David S. Miller -
Define some constant offsets for CALL_REQUEST based on the description
at and the
definition of ROSE as using 10-digit (5-byte) addresses. Use them
consistently. Validate all implicit and explicit facilities lengths.
Validate the address length byte rather than either trusting or
assuming its value.Signed-off-by: Ben Hutchings
Signed-off-by: David S. Miller -
When parsing the FAC_NATIONAL_DIGIS facilities field, it's possible for
a remote host to provide more digipeaters than expected, resulting in
heap corruption. Check against ROSE_MAX_DIGIS to prevent overflows, and
abort facilities parsing on failure.Additionally, when parsing the FAC_CCITT_DEST_NSAP and
FAC_CCITT_SRC_NSAP facilities fields, a remote host can provide a length
of less than 10, resulting in an underflow in a memcpy size, causing a
kernel panic due to massive heap corruption. A length of greater than
20 results in a stack overflow of the callsign array. Abort facilities
parsing on these invalid length values.Signed-off-by: Dan Rosenberg
Cc: stable@kernel.org
Signed-off-by: David S. Miller -
Length fields provided by a peer for names and attributes may be longer
than the destination array sizes. Validate lengths to prevent stack
buffer overflows.Signed-off-by: Dan Rosenberg
Cc: stable@kernel.org
Signed-off-by: David S. Miller -
Invalid nicknames containing only spaces will result in an underflow in
a memcpy size calculation, subsequently destroying the heap and
panicking.v2 also catches the case where the provided nickname is longer than the
buffer size, which can result in controllable heap corruption.Signed-off-by: Dan Rosenberg
Cc: stable@kernel.org
Signed-off-by: David S. Miller -
We clone the child entry in skb_dst_pop before we call
skb_dst_drop(). Otherwise we might kill the child right
before we return it to the caller.Signed-off-by: Steffen Klassert
Signed-off-by: David S. Miller -
Crypto requests might return asynchronous. In this case we leave
the rcu protected region, so force a refcount on the skb's
destination entry before we enter the xfrm type input/output
handlers.This fixes a crash when a route is deleted whilst sending IPsec
data that is transformed by an asynchronous algorithm.Signed-off-by: Steffen Klassert
Signed-off-by: David S. Miller
26 Mar, 2011
1 commit
-
The "ipv4: Inline fib_semantic_match into check_leaf"
change forgets to return the route errors. check_leaf should
return the same results as fib_table_lookup.Signed-off-by: Julian Anastasov
Signed-off-by: David S. Miller
25 Mar, 2011
7 commits
-
When we set up the flow informations in ip_route_newports(), we take
the address informations from the the rt_key_src and rt_key_dst fields
of the rtable. They appear to be empty. So take the address
informations from rt_src and rt_dst instead. This issue was introduced
by commit 5e2b61f78411be25f0b84f97d5b5d312f184dfd1 ("ipv4: Remove
flowi from struct rtable.")Signed-off-by: Steffen Klassert
Signed-off-by: David S. Miller -
Move the scope value out of the fib alias entries and into fib_info,
so that we always use the correct scope when recomputing the nexthop
cached source address.Reported-by: Julian Anastasov
Signed-off-by: David S. Miller -
Any operation that:
1) Brings up an interface
2) Adds an IP address to an interface
3) Deletes an IP address from an interfacecan potentially invalidate the nh_saddr value, requiring
it to be recomputed.Perform the recomputation lazily using a generation ID.
Reported-by: Julian Anastasov
Signed-off-by: David S. Miller -
Fix section mismatch warning by renaming the pci_driver variable to a
recognized (whitelisted) name.WARNING: drivers/net/pch_gbe/pch_gbe.o(.data+0x1f8): Section mismatch in reference from the variable pch_gbe_pcidev to the variable .devinit.rodata:pch_gbe_pcidev_id
The variable pch_gbe_pcidev references
the variable __devinitconst pch_gbe_pcidev_id
If the reference is valid then annotate the
variable with __init* or __refdata (see linux/init.h) or name the variable:
*driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_consoleSigned-off-by: Randy Dunlap
Signed-off-by: David S. Miller -
Alessandro Suardi reported that we could not change route metrics :
ip ro change default .... advmss 1400
This regression came with commit 9c150e82ac50 (Allocate fib metrics
dynamically). fib_metrics is no longer an array, but a pointer to an
array.Reported-by: Alessandro Suardi
Signed-off-by: Eric Dumazet
Tested-by: Alessandro Suardi
Signed-off-by: David S. Miller -
Avoiding abuse of ethtool_drvinfo.driver field.
HW specific info can be retrieved using lspci.Signed-off-by: Yevgeny Petrilin
Signed-off-by: David S. Miller
24 Mar, 2011
5 commits
-
commit fd245a4adb52 (net_sched: move TCQ_F_THROTTLED flag)
added a race.qdisc_watchdog() is run from softirq, so special care should be taken or
we can lose one state transition (THROTTLED/RUNNING)Prior to fd245a4adb52, we were manipulating q->flags (qdisc->flags &=
~TCQ_F_THROTTLED;) and this manipulation could only race with
qdisc_warn_nonwc().Since we want to avoid atomic ops in qdisc fast path - it was the
meaning of commit 371121057607e (QDISC_STATE_RUNNING dont need atomic
bit ops) - fix is to move THROTTLE bit into 'state' field, this one
being manipulated with SMP and IRQ safe operations.Signed-off-by: Eric Dumazet
Signed-off-by: David S. Miller -
Request_mem_region should be used with release_mem_region, not
release_resource.The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)//
@@
expression x,E;
@@
*x = request_mem_region(...)
... when != release_mem_region(x)
when != x = E
* release_resource(x);
//Signed-off-by: Julia Lawall
Signed-off-by: David S. Miller -
Request_mem_region should be used with release_mem_region, not
release_resource.The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)//
@@
expression x,E;
@@
*x = request_mem_region(...)
... when != release_mem_region(x)
when != x = E
* release_resource(x);
//Signed-off-by: Julia Lawall
Signed-off-by: David S. Miller -
This prevents possible race between bond_enslave and bond_handle_frame
as reported by Nicolas by moving rx_handler register/unregister.
slave->bond is added to hold pointer to master bonding sructure. That
way dev->master is no longer used in bond_handler_frame.
Also, this removes "BUG: scheduling while atomic" messageReported-by: Nicolas de Pesloüan
Signed-off-by: Jiri Pirko
Signed-off-by: Andy Gospodarek
Tested-by: Nicolas de Pesloüan
Signed-off-by: David S. Miller
