summaryrefslogtreecommitdiffstats
path: root/drivers/net
Commit message (Collapse)AuthorAgeFilesLines
* can: SJA1000 driver for EMS PCI cardsWolfgang Grandegger2009-05-183-0/+337
| | | | | | | | | | The patch adds support for the one or two channel CPC-PCI and CPC-PCIe cards from EMS Dr. Thomas Wuensche (http://www.ems-wuensche.de). Signed-off-by: Sebastian Haas <haas@ems-wuensche.com> Signed-off-by: Markus Plessing <plessing@ems-wuensche.com> Signed-off-by: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* can: SJA1000 generic platform bus driverWolfgang Grandegger2009-05-183-0/+175
| | | | | | | | | | | This driver adds support for the SJA1000 chips connected to the "platform bus", which can be found on various embedded systems. Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* can: Driver for the SJA1000 CAN controllerWolfgang Grandegger2009-05-185-0/+832
| | | | | | | | | This patch adds the generic Socket-CAN driver for the Philips SJA1000 full CAN controller. Signed-off-by: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* can: CAN Network device driver and Netlink interfaceWolfgang Grandegger2009-05-183-0/+685
| | | | | | | | | | | | | | | | | The CAN network device driver interface provides a generic interface to setup, configure and monitor CAN network devices. It exports a set of common data structures and functions, which all real CAN network device drivers should use. Please have a look to the SJA1000 or MSCAN driver to understand how to use them. The name of the module is can-dev.ko. Furthermore, it adds a Netlink interface allowing to configure the CAN device using the program "ip" from the iproute2 utility suite. For further information please check "Documentation/networking/can.txt" Signed-off-by: Wolfgang Grandegger <wg@grandegger.com> Signed-off-by: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: Add TI DaVinci EMAC driverAnant Gole2009-05-183-0/+2844
| | | | | | | | | | | | | | | | Add support for TI DaVinci EMAC driver. TI DaVinci Ethernet Media Access Controller module is based upon TI CPPI 3.0 DMA engine and supports 10/100 Mbps on all and Gigabit modes on some TI devices. It supports MII/RMII and has up to 8Kbytes of internal descriptor memory. This driver has been working on several TI devices including DM644x, DM646x and DA830 platforms. The specs of this device are available at: http://www.ti.com/litv/pdf/sprue24a Signed-off-by: Anant Gole <anantgole@ti.com> Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com> Signed-off-by: Chaithrika U S <chaithrika@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ixgbe: Increase the driver version numberPeter P Waskiewicz Jr2009-05-181-1/+1
| | | | | | | | | Marching along, let's bump the version number to indicate things actually have happened to the driver. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ixgbe: Add generic XAUI support to 82599Peter P Waskiewicz Jr2009-05-183-0/+7
| | | | | | | | This patch adds the generic XAUI device support for 82599 controllers. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* ixgbe: set max desc to prevent total RSC packet size of 64KAlexander Duyck2009-05-182-11/+20
| | | | | | | | | | The performance of hardware RSC is greatly reduced if the total for max rsc descriptors multiplied by the buffer size is greater than 65535. To prevent this we need to adjust the max rsc descriptors appropriately. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'master' of ↵David S. Miller2009-05-1823-483/+252
|\ | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6
| * ath9k: Cleanup ineffective return valuesVasanthakumar Thiagarajan2009-05-116-85/+36
| | | | | | | | | | | | | | | | This patch makes the return type of some of the functions void as those functions always return true Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * ath9k: Remove bogus break after returnVasanthakumar Thiagarajan2009-05-111-2/+0
| | | | | | | | | | Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: default WMM AC parametersWey-Yi Guy2009-05-111-2/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Set the default WMM AC parameters for BK/BE/VI/VO parameters: AC CWmin CW max AIFSN TXOP Limit TXOP Limit (802.11b) (802.11a/g) AC_BK 15 1023 7 0 0 AC_BE 15 1023 3 0 0 AC_VI 7 15 2 188 94 (6.016ms) (3.008ms) AC_VO 3 7 2 102 47 (3.264ms) (1.504ms) Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: show qos AC parametersWey-Yi Guy2009-05-111-1/+21
| | | | | | | | | | | | | | | | Show current qos AC parameters in sysfs Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlagn: show current rate scale data in debugfsWey-Yi Guy2009-05-111-0/+42
| | | | | | | | | | | | | | | | | | Add "rate_scale_data" debugfs file to show current bit rate (HT and Legacy), plus additional information (rssi, noise, tsf, beacon time stamp). Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: use #define instead of hard coded valueWey-Yi Guy2009-05-112-10/+12
| | | | | | | | | | | | | | | | | | | | Instead of hard coded value, use the define in iwl-commands.h for better code maintenance Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwl3945: read rev id in nic configAbhijeet Kolekar2009-05-111-7/+5
| | | | | | | | | | | | | | | | | | | | Read rev id in nic_config instead of nic_init. Nic_config has some checking for rev_id but we actually don't read the rev_id in there. Signed-off-by: Abhijeet Kolekar <abhijeet.kolekar@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: more descriptive unsupported hardware messageReinette Chatre2009-05-111-1/+1
| | | | | | | | | | | | | | | | | | Somehow these pre-production cards are showing up in the community. With this message we hope that it will be clear that the hardware is not supported. Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlagn: improve rate scale table searchMohamed Abbas2009-05-112-9/+40
| | | | | | | | | | | | | | | | | | | | | | | | | | | | iwlagn rate scaling will periodically search other rate scale tables to switch to the best table regarding performance. In the past the number of search tables were 3. Every time the rate scale algorithm goes through these available tables in will stay in current table for some time before start searching again. Recent driver support more feature and antenna, so we have more tables to search. This patch make sure we go through all available tables. Signed-off-by: Mohamed Abbas <mohamed.abbas@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: clean up PS codeJohannes Berg2009-05-117-292/+48
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This removes all the dead code that tries to adjust the power saving level based on the system AC state (inacceptable policy in the kernel) or based on overtemp conditions (unused). Also, pass _all_ policy wrt. enabling PS to mac80211, since we do not use the power_disabled internally I now use that to mirror the mac80211 CONF_PS setting. When mac80211 turns off CONF_PS we follow suit. This means that the user power level (which can currently only be set from sysfs) is not touched for mac80211 powersave changes. This means no "association status" checks are necessary since mac80211 will not allow power save to be enabled when not associated. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Acked-by: Mohamed Abbas <mohamed.abbas@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: fix PS disable status raceJohannes Berg2009-05-111-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | iwlwifi internally needs to keep track of whether PS is enabled in the firmware or not. To do this, it keeps a bit in the status flags, called STATUS_POWER_PMI. The code to set this bit looks as follows: static int iwl_set_power(struct iwl_priv *priv, void *cmd) { return iwl_send_cmd_pdu_async(priv, POWER_TABLE_CMD, sizeof(struct iwl_powertable_cmd), cmd, NULL); } int iwl_power_update_mode(...) { [...] if (final_mode != IWL_POWER_MODE_CAM) set_bit(STATUS_POWER_PMI, &priv->status); iwl_update_power_cmd(priv, &cmd, final_mode); cmd.keep_alive_beacons = 0; if (final_mode == IWL_POWER_INDEX_5) cmd.flags |= IWL_POWER_FAST_PD; ret = iwl_set_power(priv, &cmd); if (final_mode == IWL_POWER_MODE_CAM) clear_bit(STATUS_POWER_PMI, &priv->status); else set_bit(STATUS_POWER_PMI, &priv->status); if (priv->cfg->ops->lib->update_chain_flags && update_chains) priv->cfg->ops->lib->update_chain_flags(priv); [...] } Now, this bit really needs to track what the _firmware_ thinks, not what the driver thinks. Therefore, there is a race condition here -- the driver sets the bit before it knows that the async command sent to the card in the iwl_set_power function has been processed. As a result, the call to update_chain_flags() may think that the card has been woken up (PMI bit cleared) while in reality it hasn't processed the async POWER_TABLE_CMD yet. This leads to bugs -- any commands the update_chain_flags function sends can get stuck and subsequent commands also fail. The fix is almost trivial: since there's no reason to send an async command here (in fact, there almost never should be since many mac80211 callbacks can sleep) just make the function wait for the card to process the command and then return and clear the PMI bit. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Acked-by: Mohamed Abbas <mohamed.abbas@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: do proper hw restartJohannes Berg2009-05-114-61/+24
| | | | | | | | | | | | | | | | | | When the microcode fails for any reason, ask mac80211 to recover instead of trying ourselves and failing at it. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * mac80211: move HT operation mode BSS infoJohannes Berg2009-05-113-4/+4
| | | | | | | | | | | | | | | | | | There really is no need to have a separate struct for a single variable. The fact that it exists is due to the code legacy, but we can remove that now. Very simple. Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * rt2x00: Fix chipset detection for rt73usbIvo van Doorn2009-05-111-1/+1
| | | | | | | | | | | | | | | | | | The lower 4 bytes of the chipset revision must contain a non-zero value. This bug was introduced by "rt2x00: Simplify rt2x00_check_rev". Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * iwlwifi: make iwl_set_rate staticJohannes Berg2009-05-112-4/+1
| | | | | | | | | | | | | | | | It's not needed outside iwl-core.c Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Acked-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
| * wireless: WL12XX should depend on GENERIC_HARDIRQSGeert Uytterhoeven2009-05-111-1/+1
| | | | | | | | | | | | | | | | | | | | | | m68k allmodconfig: | drivers/net/wireless/wl12xx/main.c: In function 'wl12xx_probe': | drivers/net/wireless/wl12xx/main.c:1273: error: implicit declaration of function 'set_irq_type' | make[1]: *** [drivers/net/wireless/wl12xx/main.o] Error 1 Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Kalle Valo <kalle.valo@nokia.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
* | ixgbe: Don't reset the hardware when switching between LFC and PFCPeter P Waskiewicz Jr2009-05-171-17/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | When running in DCB mode, switching between link flow control and priority flow control shouldn't need to reset the hardware. This removes that reset. This also extends the set_all() dcbnl callback to return a value indicating that the HW config changed, however a reset was not required. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: When in DCB mode with PFC enabled, show LFC is disabledPeter P Waskiewicz Jr2009-05-171-0/+7
| | | | | | | | | | | | | | | | | | Ethtool should report that link flow control is disabled when in priority flow control mode. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Allow link flow control in DCB mode for 82599 adaptersPeter P Waskiewicz Jr2009-05-177-7/+66
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 82599 supports using either link flow control or priority flow control when in DCB mode. The dcbnl interface already supports sending down configurations through rtnetlink that can enable LFC when DCB is enabled, so the driver should take advantage of this. 82598 does not support using LFC when DCB is enabled, so explicitly disable it when we're in DCB mode. This means we always run in PFC mode when DCB is enabled. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Set Priority Flow Control low water threshhold for DCBPeter P Waskiewicz Jr2009-05-171-11/+37
| | | | | | | | | | | | | | | | | | This sets the low water threshhold for priority flow control for 82598 and 82599 controllers in DCB mode. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Enable jumbo frame for FCoE feature in 82599Yi Zou2009-05-172-0/+26
| | | | | | | | | | | | | | | | | | | | | | Enable jumbo frame when FCoE feature is enabled in 82599. Use 3K as the receive queue buffer size for receive queues used by FCoE to address for max Fiber Channel frame size as 2148 bytes (with max 2112 bytes of payload). Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Enable FCoE redirection table feature in 82599Yi Zou2009-05-171-4/+24
| | | | | | | | | | | | | | | | | | | | | | | | Enable using FCoE redirection table feature in 82599. The FCoE redirection table has maximum of eight entries, corresponding to maximum of eight receive queues to be used for distributing incoming FCoE packets. This patch sets up the FCoE redirection table when multiple receive queues are available for FCoE. Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Add RING_F_FCOE for FCoE feature in 82599Yi Zou2009-05-172-0/+102
| | | | | | | | | | | | | | | | | | | | | | | | Add ring feature for FCoE to make use of the FCoE redirection table in 82599. The FCoE redirection table is a receive side scaling feature for Fiber Channel over Ethernet feature in 82599, enabling distributing FCoE packets to different receive queues based on the exchange id. Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Add SAN MAC address to the RAR, return the address to DCBWaskiewicz Jr, Peter P2009-05-174-7/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After acquiring the SAN MAC address from the EEPROM, we need to program it into one of the RARs. Also, DCB will use this MAC address to run DCBX commands, so it doesn't have to play musical MAC addresses when things like bonding enter the picture. So we need to return the MAC address through the netlink interface to userspace. This also moves the init_rx_addrs() call out of start_hw() and into reset_hw(). We shouldn't try to read any of the RAR information before initializing our internal accounting of the RAR table, which was what was happening. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Add FCoE Storage MAC Address supportPJ Waskiewicz2009-05-173-0/+126
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements the Storage Address entrypoint from the net device. It will read the SAN MAC addresses from the EEPROM of the 82599 hardware, and make them available to the FCoE stack through the net device. Also, add/del the SAN MAC address to the netdev dev_addr_list via the kernel api dev_addr_add()/dev_addr_del() when there is a valid SAN MAC supported by the HW. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | skfddi: convert PRINTK() to pr_debug()Alexander Beregalov2009-05-171-81/+75
| | | | | | | | | | Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | mac89x0: remove PRINTK()Alexander Beregalov2009-05-171-2/+0
| | | | | | | | | | | | | | There are no users of it. Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | de620: convert PRINTK() to pr_debug() and cleanupAlexander Beregalov2009-05-171-41/+18
| | | | | | | | | | | | | | Also remove DE620_DEBUG and de620_debug. Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | de600: convert PRINTK() to pr_debug()Alexander Beregalov2009-05-171-16/+3
| | | | | | | | | | | | | | Also remove de600_debug as it is not needed. Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | de620: fix forgotten semicolonAlexander Beregalov2009-05-171-1/+1
| | | | | | | | | | | | | | It seems it always was here. Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | drivers/net: Convert #ifdef DEBUG printk(KERN_DEBUG to pr_debug(Joe Perches2009-05-171-8/+5
| | | | | | | | | | Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | sfc: Use generic XENPAK register definitionsBen Hutchings2009-05-173-73/+4
| | | | | | | | | | Signed-off-by: Ben Hutchings <bhutchings@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | smsc95xx: strip ethernet fcs (crc) on receive pathPeter Korsgaard2009-05-171-2/+2
| | | | | | | | | | | | | | | | | | | | The smsc95xx driver was forwarding the trailing fcs on received frames up the stack leading to confusion in tcpdump. Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk> Tested-by: Steve Glendinning <steve.glendinning@smsc.com> Acked-by: Steve Glendinning <steve.glendinning@smsc.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | dm9601: trivial comment fixesPeter Korsgaard2009-05-171-6/+6
| | | | | | | | | | | | | | | | The comments describing the rx/tx headers used a combination of zero- and 1-based indexing, leading to confusion. Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: tx scalability works : trans_startEric Dumazet2009-05-171-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | bnx2: bnx2_tx_int() optimizationsEric Dumazet2009-05-172-7/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When using bnx2 in a high transmit load, bnx2_tx_int() cost is pretty high. There are two reasons. One is an expensive call to bnx2_get_hw_tx_cons(bnapi) for each freed skb One is cpu stalls when accessing skb_is_gso(skb) / skb_shinfo(skb)->nr_frags because of two cache line misses. (One to get skb->end/head to compute skb_shinfo(skb), one to get is_gso/nr_frags) This patch : 1) avoids calling bnx2_get_hw_tx_cons(bnapi) too many times. 2) makes bnx2_start_xmit() cache is_gso & nr_frags into sw_tx_bd descriptor. This uses a litle bit more ram (256 longs per device on x86), but helps a lot. 3) uses a prefetch(&skb->end) to speedup dev_kfree_skb(), bringing cache line that will be needed in skb_release_data() result is 5 % bandwidth increase in benchmarks, involving UDP or TCP receive & transmits, when a cpu is dedicated to ksoftirqd for bnx2. bnx2_tx_int going from 3.33 % cpu to 0.5 % cpu in oprofile Note : skb_dma_unmap() still very expensive but this is for another patch, not related to bnx2 (2.9 % of cpu, while it does nothing on x86_32) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net/ibmveth: fix panic in probeStephen Rothwell2009-05-171-1/+1
| | | | | | | | | | | | | | | | | | netdev->dev_addr changed from being an array to being a pointer, so we should not take its address for memcpy(). Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Add FCoE related statistics to 82599Yi Zou2009-05-173-0/+22
| | | | | | | | | | | | | | | | | | | | | | | | This adds FCoE related statistics to 82599, including number Rx-ed and Tx-ed FCoE packets, number of Rx-ed and Tx-ed FCoE packets in dwords, number of bad Fiber Channel CRCs detected in FCoE packets, and number of FCoE packets dropped on the Rx side. Signed-off-by: Yi Zou <yi.zou@intel.com> Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Implement FCoE Rx side large receive offload feature to 82599Yi Zou2009-05-172-0/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements the FCoE Rx side offload feature in ixgbe_main.c to 82599 using the Rx offload infrastructure code added in the previous patch. The large receive offload by Direct Data Placement (DDP) for FCoE is achieved by implementing the ndo_fcoe_ddp_setup and ndo_fcoe_ddp_done in net_device_ops via netdev. It is up to the ULD, i.e., fcoe and libfc to query and setup large receive offload accordingly through the corresponding netdev upon creating fcoe instances. Signed-off-by: Yi Zou <yi.zou@intel.com> Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Add infrastructure code for FCoE large receive offload to 82599Yi Zou2009-05-173-1/+344
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds infrastructure code for FCoE Rx side offload feature to 82599, which provides large receive offload for FCoE by Direct Data Placement (DDP). The ixgbe_fcoe_ddp_get() and ixgbe_fcoe_ddp_put() pair corresponds to the netdev support to FCoE by the function pointers provided in net_device_ops as ndo_fcoe_ddp_setup and ndo_fcoe_ddp_done. The implementation of these in ixgbe is shown in the next patch. Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Chris Leech <christopher.leech@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ixgbe: Implement FCoE Tx side offload features in base driver of 82599Yi Zou2009-05-175-20/+101
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implements the FCoE Tx side offload features in ixgbe_main.c to 82599 using the Tx offload infrastructure code added in the previous patch. This is achieved by the calling the FCoE Sequence Offload (FSO) function ixgbe_fso() on the transmit path of ixgbe. This patch also includes an EEPROM check to make sure the NIC we're loading on is an offload-enabled SKU. Signed-off-by: Yi Zou <yi.zou@intel.com> Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
OpenPOWER on IntegriCloud