- Mar 29, 2011
-
-
Anton Blanchard authored
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 <davem@davemloft.net>
-
David S. Miller authored
Reported-by:
Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Mar 28, 2011
-
-
Stanislaw Gruszka authored
After commit d5dbda23 "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 <sgruszka@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Herbert Xu authored
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 <herbert@gondor.apana.org.au> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
The correct usage is "static inline void" not "static void inline". Signed-off-by:
Javier Martinez Canillas <martinez.javier@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Javier Martinez Canillas authored
It is proper style to include linux/foo.h instead asm/foo.h if both exist Signed-off-by:
Javier Martinez Canillas <martinez.javier@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Cesar Eduardo Barros authored
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 <cesarb@cesarb.net> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Rafael J. Wysocki authored
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 <rjw@sisk.pl> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Stanislaw Gruszka authored
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 lro On the way reduce myri10ge_rx_done() number of arguments and calls by moving mgp->small_bytes check into that function. That reduce code size from: text data bss dec hex filename 36644 248 100 36992 9080 drivers/net/myri10ge/myri10ge.o to: text data bss dec hex filename 36037 247 100 36384 8e20 drivers/net/myri10ge/myri10ge.o on my i686 system, what should also make myri10ge_clean_rx_done() being faster. Signed-off-by:
Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
stephen hemminger authored
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 <shemminger@vyatta.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jan Luebbe authored
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 IP This 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 <= optlen'. The second bug is using sptr as the start of the option, when it really is set to 'skb_network_header(skb)'. I just use dptr instead which points to the timestamp option. Finally it would only timestamp for non-local IPs, which we shouldn't do. So instead we exclude all unicast destinations, similar to what we do in ip_options_compile(). Signed-off-by:
Jan Luebbe <jluebbe@debian.org> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jan Altenberg authored
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 register Signed-off-by:
Jan Altenberg <jan@linutronix.de> Acked-by:
Kurt Van Dijck <kurt.van.dijck@eia.be> Acked-by:
Wolfgang Grandegger <wg@grandegger.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Marc Kleine-Budde authored
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 *" against <= 0. Use "platform_get_irq" instead. Signed-off-by:
Marc Kleine-Budde <mkl@pengutronix.de> Cc: Bhupesh Sharma <bhupesh.sharma@st.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Marc Kleine-Budde authored
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 <jan@linutronix.de> Signed-off-by:
Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by:
Kurt Van Dijck <kurt.van.dijck@eia.be> Cc: Bhupesh Sharma <bhupesh.sharma@st.com> Acked-by:
Wolfgang Grandegger <wg@grandegger.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Oliver Hartkopp authored
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.c Signed-off-by:
Kurt Van Dijck <kurt.van.dijck@eia.be> Signed-off-by:
Oliver Hartkopp <socketcan@hartkopp.net> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Amerigo Wang authored
The code itself can explain what it is doing, no need these comments. Signed-off-by:
WANG Cong <amwang@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Ben Hutchings authored
Define some constant offsets for CALL_REQUEST based on the description at <http://www.techfest.com/networking/wan/x25plp.htm> 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 <ben@decadent.org.uk> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Dan Rosenberg authored
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 <drosenberg@vsecurity.com> Cc: stable@kernel.org Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Dan Rosenberg authored
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 <drosenberg@vsecurity.com> Cc: stable@kernel.org Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Dan Rosenberg authored
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 <drosenberg@vsecurity.com> Cc: stable@kernel.org Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Steffen Klassert authored
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 <steffen.klassert@secunet.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Steffen Klassert authored
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 <steffen.klassert@secunet.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Mar 26, 2011
-
-
Julian Anastasov authored
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 <ja@ssi.bg> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Mar 25, 2011
-
-
Steffen Klassert authored
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 5e2b61f7 ("ipv4: Remove flowi from struct rtable.") Signed-off-by:
Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
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 <ja@ssi.bg> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Any operation that: 1) Brings up an interface 2) Adds an IP address to an interface 3) Deletes an IP address from an interface can potentially invalidate the nh_saddr value, requiring it to be recomputed. Perform the recomputation lazily using a generation ID. Reported-by:
Julian Anastasov <ja@ssi.bg> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Randy Dunlap authored
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, *_console Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eric Dumazet authored
Alessandro Suardi reported that we could not change route metrics : ip ro change default .... advmss 1400 This regression came with commit 9c150e82 (Allocate fib metrics dynamically). fib_metrics is no longer an array, but a pointer to an array. Reported-by:
Alessandro Suardi <alessandro.suardi@gmail.com> Signed-off-by:
Eric Dumazet <eric.dumazet@gmail.com> Tested-by:
Alessandro Suardi <alessandro.suardi@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Yevgeny Petrilin authored
Avoiding abuse of ethtool_drvinfo.driver field. HW specific info can be retrieved using lspci. Signed-off-by:
Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- Mar 24, 2011
-
-
Eric Dumazet authored
commit fd245a4a (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 fd245a4a, 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 37112105 (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 <eric.dumazet@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
-
Julia Lawall authored
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/) // <smpl> @@ expression x,E; @@ *x = request_mem_region(...) ... when != release_mem_region(x) when != x = E * release_resource(x); // </smpl> Signed-off-by:
Julia Lawall <julia@diku.dk> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Julia Lawall authored
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/) // <smpl> @@ expression x,E; @@ *x = request_mem_region(...) ... when != release_mem_region(x) when != x = E * release_resource(x); // </smpl> Signed-off-by:
Julia Lawall <julia@diku.dk> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jiri Pirko authored
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" message Reported-by:
Nicolas de Pesloüan <nicolas.2p.debian@gmail.com> Signed-off-by:
Jiri Pirko <jpirko@redhat.com> Signed-off-by:
Andy Gospodarek <andy@greyhouse.net> Tested-by:
Nicolas de Pesloüan <nicolas.2p.debian@free.fr> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Stanislaw Gruszka authored
Rmmod myri10ge crash at free_netdev() -> netif_napi_del(), because napi structures are already deallocated. To fix call netif_napi_del() before kfree() at myri10ge_free_slices(). Cc: stable@kernel.org Signed-off-by:
Stanislaw Gruszka <sgruszka@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Yevgeny Petrilin authored
Signed-off-by:
Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Yevgeny Petrilin authored
Doorbell is used according to usage of BlueFlame. For Blue Flame to work in Ethernet mode QP number should have 0 at bits 6,7. Allocating range of QPs accordingly. Signed-off-by:
Yevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eli Cohen authored
Do not allow a kernel consumer to allocate a UAR to serve for blue flame if the number of available UARs gets below MLX4_NUM_RESERVED_UARS (currently 8). This will allow userspace apps to open a device file and run things like ibv_devinfo. Signed-off-by:
Eli Cohen <eli@mellanox.co.il> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Eli Cohen authored
Add mlx4_bitmap_avail() to give the number of available resources. We want to use this as a hint to whether to allocate a resources or not. This patch is introduced to be used with allocation blue flame registers. Signed-off-by:
Eli Cohen <eli@mellanox.co.il> Signed-off-by:
David S. Miller <davem@davemloft.net>
-