- 07 Jun, 2010 14 commits
-
-
Eric Dumazet authored
Avoid two atomic ops per raw_send_hdrinc() call Avoid two atomic ops per raw6_send_hdrinc() call Signed-off-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Alex Lorca authored
CAIF is using "xxx-AF_MAX" strings for the lock validator. It should use its own strings. Signed-off-by:
Alex Lorca <alex.lorca@gmail.com> Signed-off-by:
-
Tom Herbert authored
This patch address a serious performance issue in reading the TCP sockets table (/proc/net/tcp). Reading the full table is done by a number of sequential read operations. At each read operation, a seek is done to find the last socket that was previously read. This seek operation requires that the sockets in the table need to be counted up to the current file position, and to count each of these requires taking a lock for each non-empty bucket. The whole algorithm is O(n^2). The fix is to cache the last bucket value, offset within the bucket, and the file position returned by the last read operation. On the next sequential read, the bucket and offset are used to find the last read socket immediately without needing ot scan the previous buckets the table. This algorithm t read the whole table is O(n). The improvement offered by this patch is easily show by performing cat'ing /proc/net/tcp on a machine with a lot of connections. With about 182K connections in the table, I see the following: - Without patch time cat /proc/net/tcp > /dev/null real 1m56.729s user 0m0.214s sys 1m56.344s - With patch time cat /proc/net/tcp > /dev/null real 0m0.894s user 0m0.290s sys 0m0.594s Signed-off-by:
Tom Herbert <therbert@google.com> Acked-by:
-
Matt Carlson authored
This patch updates the tg3 version to 3.111. Signed-off-by:
Matt Carlson <mcarlson@broadcom.com> Signed-off-by:
Michael Chan <mchan@broadcom.com> Signed-off-by:
-
Matt Carlson authored
This patch adds the 5719 PCI device and phy IDs. Signed-off-by:
-
Matt Carlson authored
This patch adds the 5719 ASIC revision. Signed-off-by:
-
Matt Carlson authored
The driver sometimes needs to know which function number the current device is. This patch changes the code to use devfn over internal register values. Signed-off-by:
-
Matt Carlson authored
The 5717 serdes phy brings link up via parallel detection without any additional help from the driver. This patch changes the tg3_setup_fiber_mii_phy() function to detect and allow the use of this feature. Signed-off-by:
-
Matt Carlson authored
This patch changes the code to make it legal to allocate only one MSI-X vector. It also fixes a bug where the driver was not checking for error return codes from pci_enable_msix(). Signed-off-by:
-
Matt Carlson authored
The driver was incorrectly programming the indirection table such that rx traffic intended for the second ring went to the first ring, rx traffic intended for the third ring went to the second ring, etc. This patch changes the code so that rx traffic is diverted to the proper ring. Signed-off-by:
-
Matt Carlson authored
The rx resources for MSI-X interrupt vector 0 were not being freed correctly. This happens because the teardown loop continue's to the next loop iteration if it detects the tx ring for that vector is not setup, thus bypassing the rx teardown code. This patch moves the call to tg3_rx_prodring_free() earlier in the loop. Signed-off-by:
-
Matt Carlson authored
In certain edge conditions, internal tx resources can get corrupted. This patch enables a bit that will fix the problem. Signed-off-by:
-
Matt Carlson authored
The 5717 and later devices relocate the APE mutex registers. This patch organizes the code so that the driver can use the mutex registers in the old and new locations. Signed-off-by:
-
David S. Miller authored
Conflicts: drivers/net/sfc/net_driver.h drivers/net/sfc/siena.c
-
- 06 Jun, 2010 2 commits
-
-
Timo Teräs authored
Some configurations need delay between the "write completed" indication and new write to work reliably. Realtek driver seems to use longer delay when polling the "write complete" bit, so it waits long enough between writes with high probability (but could probably break too). This patch adds a new udelay to make sure we wait unconditionally some time after the write complete indication. This caused a regression with XID 18000000 boards when the board specific phy configuration writing many mdio registers was added in commit 2e955856 (r8169: phy init for the 8169scd). Some of the configration mdio writes would almost always fail, and depending on failure might leave the PHY in non-working state. Signed-off-by:
Timo Teräs <timo.teras@iki.fi> Acked-off-by:
Francois Romieu <romieu@fr.zoreil.com> Signed-off-by:
-
Eric Dumazet authored
Signed-off-by:
-
- 05 Jun, 2010 10 commits
-
-
Shirley Ma authored
Enable GRO by default for performance. Signed-off-by:
Shirley Ma <xma@us.ibm.com> Acked-by:
Greg Rose <gregory.v.rose@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
-
Eric Dumazet authored
With mtu=9000, mld_newpack() use order-2 GFP_ATOMIC allocations, that are very unreliable, on machines where PAGE_SIZE=4K Limit allocated skbs to be at most one page. (order-0 allocations) Signed-off-by:
-
Denis Kirjanov authored
This patch compile tested only. Convert legacy PM hooks to dev_pm_ops Signed-off-by:
Denis Kirjanov <dkirjanov@kernel.org> Signed-off-by:
-
Andy Gospodarek authored
v2: changed bonding module version, modified to apply on top of changes from previous patch in series, and updated documentation to elaborate on multiqueue awareness that now exists in bonding driver. This patch give the user the ability to control the output slave for round-robin and active-backup bonding. Similar functionality was discussed in the past, but Jay Vosburgh indicated he would rather see a feature like this added to existing modes rather than creating a completely new mode. Jay's thoughts as well as Neil's input surrounding some of the issues with the first implementation pushed us toward a design that relied on the queue_mapping rather than skb marks. Round-robin and active-backup modes were chosen as the first users of this slave selection as they seemed like the most logical choices when considering a multi-switch environment. Round-robin mode works without any modification, but active-backup does require inclusion of the first patch in this series and setting the 'all_slaves_active' flag. This will allow reception of unicast traffic on any of the backup interfaces. This was tested with IPv4-based filters as well as VLAN-based filters with good results. More information as well as a configuration example is available in the patch to Documentation/networking/bonding.txt. Signed-off-by:
Andy Gospodarek <andy@greyhouse.net> Signed-off-by:
Neil Horman <nhorman@tuxdriver.com> Signed-off-by:
-
Andy Gospodarek authored
v2: changed parameter name from 'keep_all' to 'all_slaves_active' and skipped setting slaves to inactive rather than creating a new flag at Jay's suggestion. In an effort to suppress duplicate frames on certain bonding modes (specifically the modes that do not require additional configuration on the switch or switches connected to the host), code was added in the generic receive patch in 2.6.16. The current behavior works quite well for most users, but there are some times it would be nice to restore old functionality and allow all frames to make their way up the stack. This patch adds support for a new module option and sysfs file called 'all_slaves_active' that will restore pre-2.6.16 functionality if the user desires. The default value is '0' and retains existing behavior, but the user can set it to '1' and allow all frames up if desired. Signed-off-by:
Jay Vosburgh <fubar@us.ibm.com> Signed-off-by:
-
Alexander Duyck authored
We can avoid an unecessary cache miss by checking if the skb is non-linear before accessing gso_size/gso_type in skb_warn_if_lro, the same can also be done to avoid a cache miss on nr_frags if data_len is 0. Signed-off-by:
Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by:
-
Rami Rosen authored
Hi, __pppoe_xmit() in drivers/net/pppoe always returns 1. When the methods fails (via goto abort), it should return 0 and not 1. Regards, Rami Rosen Signed-off-by:
Rami Rosen <ramirose@gmail.com> Signed-off-by:
-
Florian Westphal authored
- ipv6 msstab: account for ipv6 header size - ipv4 msstab: add mss for Jumbograms. Signed-off-by:
Florian Westphal <fw@strlen.de> Signed-off-by:
-
Florian Westphal authored
caller: if (!th->rst && !th->syn && th->ack) callee: if (!th->ack) make the caller only check for !syn (common for 3whs), and move the !rst / ack test to the callee. Signed-off-by:
-
Florian Westphal authored
both syn_flood_warning functions print a message, but ipv4 version only prints a warning if CONFIG_SYN_COOKIES=y. Make the v4 one behave like the v6 one. Signed-off-by:
-
- 04 Jun, 2010 12 commits
-
-
Huang Weiyi authored
Remove duplicated #include('s) in drivers/net/wan/x25_asy.c Signed-off-by:Huang Weiyi <weiyi.huang@gmail.com> Signed-off-by:
-
Eric Dumazet authored
Its better to make a route lookup in appropriate namespace. Signed-off-by:
-
Eric Dumazet authored
I believe a moderate SYN flood attack can corrupt RFS flow table (rps_sock_flow_table), making RPS/RFS much less effective. Even in a normal situation, server handling short lived sessions suffer from bad steering for the first data packet of a session, if another SYN packet is received for another session. We do following action in tcp_v4_rcv() : sock_rps_save_rxhash(sk, skb->rxhash); We should _not_ do this if sk is a LISTEN socket, as about each packet received on a LISTEN socket has a different rxhash than previous one. -> RPS_NO_CPU markers are spread all over rps_sock_flow_table. Also, it makes sense to protect sk->rxhash field changes with socket lock (We currently can change it even if user thread owns the lock and might use rxhash) This patch moves sock_rps_save_rxhash() to a sock locked section, and only for non LISTEN sockets. Signed-off-by:
-
Ben McKeegan authored
Fix bug in multilink fragment size calculation introduced by commit 9c705260 "ppp: ppp_mp_explode() redesign" Signed-off-by:
Ben McKeegan <ben@netservers.co.uk> Signed-off-by:
-
Florian Westphal authored
syncookies default to on since e994b7c9 (tcp: Don't make syn cookies initial setting depend on CONFIG_SYSCTL). Signed-off-by:
-
John Fastabend authored
Only check pfc bits in hang logic if PFC is enabled. Previously, if DCB was enabled but PFC was disabled the incorrect pause bits would be checked. Signed-off-by:
John Fastabend <john.r.fastabend@intel.com> Acked-by:
Don Skidmore <donald.c.skidmore@intel.com> Signed-off-by:
-
Steffen Klassert authored
xfrm triggers a warning if dst_pop() drops a refcount on a noref dst. This patch changes dst_pop() to skb_dst_pop(). skb_dst_pop() drops the refcnt only on a refcounted dst. Also we don't clone the child dst_entry, so it is not refcounted and we can use skb_dst_set_noref() in xfrm_output_one(). Signed-off-by:
Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by:
-
Anirban Chakraborty authored
Original code was placed incorrectly inside a block of code marked with CONFIG_INET directive. Fix by moving it outside. Signed-off-by:
Anirban Chakraborty <anirban.chakraborty@qlogic.com> Reported-by:
Randy Dunlap <randy.dunlap@oracle.com> Tested-by:
-
Eric Dumazet authored
From: Eric Dumazet <eric.dumazet@gmail.com> Date: Thu, 3 Jun 2010 04:29:41 +0000 Subject: [PATCH 2/3] net: net/socket.c and net/compat.c cleanups cleanup patch, to match modern coding style. Signed-off-by:
-
Emil Tantilov authored
This patch is alternative to a previous patch submitted by Joe Perches. Create common macros e_<level> and e_dev_<level> that use netdev_<level> and dev_<level> similar to e1000e. Redefined pr_fmt for driver messages. Use %pM to display MAC address. Aligned text to better match the new format. CC: Joe Perches <joe@perches.com> Signed-off-by:
Emil Tantilov <emil.s.tantilov@intel.com> Signed-off-by:
-
Eric Dumazet authored
Avoid two atomic ops in arp_fwd_proxy() Avoid two atomic ops in arp_process() Valid optims since arp_rcv() is run under rcu_read_lock() Signed-off-by:
-
Eric Dumazet authored
Avoid two atomic ops on output device refcount Signed-off-by:
-
- 03 Jun, 2010 2 commits
-
-
-
Jeff Kirsher authored
Based on original patch from Shirley Ma <xma@us.ibm.com> Return IXGBE_ERR_RAR_INDEX when RAR index is out of range, instead of returning IXGBE_SUCCESS. CC: Shirley Ma <xma@us.ibm.com> Signed-off-by:
-
