- 09 9月, 2010 3 次提交
-
-
由 Alexander Duyck 提交于
The ordering of operations was messed up in the init and as a result when VMDQ was enabled we were trying to enable TX rings before setting the VFTE bits. This resulted in a ring that appeared to fail to enable when in fact it was blocked because the VFTE bits were cleared after the reset. Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Jesse Brandeburg 提交于
Several users report issues with 32-bit adapters when plugged into PCI slots in machines with >= 4GB ram. In particular AMD systems with HyperTransport to PCI bridges seem to trigger the issue, but it isn't limited to only them. This issue is not easily reproducible here, yet still continues to occur in the field. For e1000 on PCI devices, just disable DMA addresses over the 4GB boundary when in PCI (not PCI-X) mode, to prevent the issue from continuing to pop up. The performance impact for this is negligible. The code was refactored to move the init of the hw struct to its own function. This allows the init to be called very early in probe, which then allows using hw-> members for this fix. A slight refactor to the DMA mask code was done for minor correctness based on the instructions in DMA-API-HOWTO. Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Ondrej Zary 提交于
This patch introduces cx82310_eth driver - driver for USB ethernet port of ADSL routers based on Conexant CX82310 chips. Such routers usually have ethernet port(s) too which are bridged together with the USB ethernet port, allowing the USB-connected machine to communicate to the network (and also internet through the ADSL, of course). This is my first driver, so please check thoroughly. As there's no protocol documentation, it was done with usbsnoop dumps from Windows driver, some parts (the commands) inspired by cxacru driver and also other usbnet drivers. The driver passed my testing - some real work and also pings sized from 0 to 65507 B. The only problem I found is the ifconfig error counter. When I return 0 (or 1 but empty skb) from rx_fixup(), usbnet increases the error counter although it's not an error condition (because packets can cross URB boundaries). Maybe the usbnet should be fixed to allow rx_fixup() to return empty skbs (or some other value, e.g. 2)? The USB ID of my device is 0x0572:0xcb01 which conflicts with some ADSL modems using cxacru driver (they probably use the same chipset but simpler firmware). The modems seem to use bDeviceClass 0 and iProduct "ADSL USB MODEM", my router uses bDeviceClass 255 and iProduct "USB NET CARD". The driver matches only devices with class 255 and checks for the iProduct string during init. I already posted a patch for the cxacru driver to ignore these devices. Signed-off-by: NOndrej Zary <linux@rainbow-software.org> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 08 9月, 2010 11 次提交
-
-
由 Eric Dumazet 提交于
- Use napi_gro_receive() and vlan_gro_receive() - Enable GRO by default Tested on a RTL8111/8168 adapter Signed-off-by: NEric Dumazet <eric.dumazet@gmail.com> Acked-by: NFrancois Romieu <romieu@fr.zoreil.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Note that the date format was fixed. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Change LED scheme for dual-media Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Add required changes in order to support dual-media boards. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Group all PHY specific functions together to have an organized code Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Make the needed changes for the new scheme especially around PHY initialization, and link detection. - The get_emac_base function was changed to enable setting different MAC access setting for each PHY based of external configuration. - As a part of the dual-media preparation, the save_spirom_version was modified to accept a PHY specific version address to be saved in the shmem. This will enable to save more than single spirom version in different locations. - The test_link function was changed also as a preparation for the dual-media upcoming changes - Duplicate initialization logic was removed from the link_setting_status and link_initialize functions Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Move all PHY specific logic from bnx2x_main into bnx2x_link. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Flow control implementation is split to be done in each PHY function. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
In previous patch, common PHY functions were split in simple way to allow easy diff. This patch comes to align code in the new functions. In addition, the non-production BCM8072 PHY was removed. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Move the code into PHY oriented functions, and for that a new structure is defines for each PHY which contain PHY properties and its own functions. This also enables to encapsulate all PHY specific operations into the PHY functions. During initialization, the PHYs will be probed by the "bnx2x_phy_probe" function to detect which PHYs exist on-board, and configure them accordingly. Note that the ext_phy_reset implementation was incorporated in the ext_phy_init since it is actually part of the PHY initialization procedure. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yaniv Rosner 提交于
Start building the infrastructure for dual media by adding new component of PHY which will be used all along the function. Modify function to work with this component instead of the link_params. Signed-off-by: NYaniv Rosner <yanivr@broadcom.com> Signed-off-by: NEilon Greenstein <eilong@broadcom.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 07 9月, 2010 26 次提交
-
-
由 Yevgeny Petrilin 提交于
The values didn't match the title after removing the LRO statistics in commit fa37a958Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Yevgeny Petrilin 提交于
If failed to get skb frags using napi_get_frags(), the packet is dropped. Reported-by: NEric Dumazet <eric.dumazet@gmail.com> Signed-off-by: NYevgeny Petrilin <yevgenyp@mellanox.co.il> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Christian Dietrich 提交于
The CHELSIO_T1_1G ifdef isn't necessary at this point, because it is checked in an outer ifdef level already and has no effect here. Signed-off-by: NChristian Dietrich <qy03fugy@stud.informatik.uni-erlangen.de> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Joe Perches 提交于
Add #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt Convert jeprintk to pr_err Remove jeprintk macro define Remove periods from end of logging messages Coalesce format strings Signed-off-by: NJoe Perches <joe@perches.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Jiri Slaby 提交于
bnad_set_rx_mode omit to unlock bna_lock on one fail path. Fix that. Signed-off-by: NJiri Slaby <jslaby@suse.cz> Cc: Debashis Dutt <ddutt@brocade.com> Cc: Rasesh Mody <rmody@brocade.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Julia Lawall 提交于
In this case, a device_node structure is stored in another structure that is then freed without first decrementing the reference count of the device_node structure. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // <smpl> @r exists@ expression x; identifier f; position p1,p2; @@ x@p1->f = \(of_find_node_by_path\|of_find_node_by_name\|of_find_node_by_phandle\|of_get_parent\|of_get_next_parent\|of_get_next_child\|of_find_compatible_node\|of_match_node\|of_find_node_by_type\|of_find_node_with_property\|of_find_matching_node\|of_parse_phandle\|of_node_get\)(...); ... when != of_node_put(x) kfree@p2(x) @script:python@ p1 << r.p1; p2 << r.p2; @@ cocci.print_main("call",p1) cocci.print_secs("free",p2) // </smpl> Signed-off-by: NJulia Lawall <julia@diku.dk> Acked-by: NWolfram Sang <w.sang@pengutronix.de> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Add an entry to the MAINTAINERS file for ibmveth, clean up the copyright and add all authors. Change the name of the module to reflect the product name over the last number of years. Considering all the changes we have made, bump the driver version. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
These files probably came across from the skeleton driver. Remove them. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
We had a driver specific assert function which wasn't enabled most of the time. Convert them to BUG_ON and enable them all the time. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
We had a few cases where we returned success on error. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Fix most of the kernel coding style issues in ibmveth. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
IbmVethNumBufferPools -> IBMVETH_NUM_BUFF_POOLS Also change IBMVETH_MAX_MTU -> IBMVETH_MIN_MTU, it refers to the minimum size not the maximum. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Use netdev_err to standardise the error output. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Use netdev_dbg to standardise the debug output. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
These functions appear before their use, so we can remove the redundant prototypes. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
We were using alloc_skb which doesn't create any headroom. Change it to use netdev_alloc_skb to match most other drivers. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
We export all the driver specific statistics via ethtool, so there is no need to duplicate this in procfs. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
This patch enables TCP checksum offload support for IPv6 on ibmveth. This completely eliminates the generation and checking of the checksum for IPv6 packets that are completely virtual and never touch a physical network. A basic TCPIPV6_STREAM netperf run showed a ~30% throughput improvement when an MTU of 64000 was used. This featured is enabled by default, as is the case for IPv4 checksum offload. When checksum offload is enabled the driver will negotiate IPv4 and IPv6 offload with the firmware separately and enable what is available. As long as either IPv4 or IPv6 offload is supported and enabled the device will report that checksum offload is enabled. The device stats, available through ethtool, will display which checksum offload features are supported/enabled by firmware. Performance testing against a stock kernel shows no regression for IPv4 or IPv6 in terms of throughput or processor utilization with checksum disabled or enabled. Signed-off-by: NRobert Jennings <rcj@linux.vnet.ibm.com> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Remove code in the device probe function where we set up the checksum offload feature and replace it with a call to an existing function that is doing the same. This is done to clean up the driver in preparation of adding IPv6 checksum offload support. Signed-off-by: NRobert Jennings <rcj@linux.vnet.ibm.com> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
On some machines we can improve the bandwidth by ensuring rx buffers are not in the cache. Add a module option that is disabled by default that flushes rx buffers on insertion. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
ibmveth can scatter gather up to 6 segments. If we go over this then we have no option but to call skb_linearize, like other drivers with similar limitations do. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Anton Blanchard 提交于
We want to order the read in ibmveth_rxq_pending_buffer and the read of ibmveth_rxq_buffer_valid which are both cacheable memory. smp_rmb() is good enough for this. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
For small packets, create a new skb and copy the packet into it so we avoid tearing down and creating a TCE entry. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
Use the existing bounce buffer if we send a buffer under a certain size. This saves the overhead of a TCE map/unmap. I can't see any reason for the wmb() in the bounce buffer case, if we need a barrier it will be before we call h_send_logical_lan but we have nothing in the common case. Remove it. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
The ibmveth adapter needs locking in the transmit routine to protect the bounce_buffer but it sets LLTX and forgets to add any of its own locking. Just remove the deprecated LLTX option. Remove the stats lock in the process. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Santiago Leon 提交于
At the moment we try and replenish the receive ring on every rx interrupt. We even have a pool->threshold but aren't using it. To limit the maximum latency incurred when refilling, change the threshold from 1/2 to 7/8 and reduce the largest rx pool from 768 buffers to 512 which should be more than enough. Signed-off-by: NAnton Blanchard <anton@samba.org> Signed-off-by: NSantiago Leon <santil@linux.vnet.ibm.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-