- 17 Jan, 2006 40 commits
-
-
Jeff Kirsher authored
Improves small packet performance with large amounts of reassembly being done in the stack. Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by:
John Ronciak <john.ronciak@intel.com> Signed-off-by:
Jeff Garzik <jgarzik@pobox.com>
-
Jeff Kirsher authored
This was to fix compilation warnings. Also added log messages when pci_enable_* functions return with an error. Signed-off-by:
-
Jeff Kirsher authored
This is two patches, the first is adding additional bus information for the 8257{1|2|3} controllers. The second patch was orginally a community patch to print bus type/speed/width, and enhanced by us. Signed-off-by: -
Jeff Kirsher authored
The EEPROM image version is reported as a firmware version for these controllers. Signed-off-by:
-
Jeff Kirsher authored
Added 82571 fiber to WOL fix for dual port adapters. Added support for 82546GB (Quad Copper). Added PCIe typedef for x2, igp cable length 115, and extended TX CTRL registers. Added parity error detection and PCIe CTRL registers. Added EEPROM config registers. Signed-off-by:
-
Jeff Kirsher authored
Signed-off-by:
-
Jeff Kirsher authored
Signed-off-by:
-
Jeff Kirsher authored
Fixed an issue netpoll would error out during communication, generating the following error: --netdump[14973]: Got toomany timeouts in handshaking, ... Even after a kernel panic, netpoll requires two way communication to successfully transfer the crash log to the remote server. Signed-off-by:
-
Jeff Kirsher authored
Simplified the logic used to assign the frame_size. Signed-off-by:
-
Jeff Kirsher authored
Fixed VLAN support by switching control over to the firmware. Signed-off-by:
-
Jeff Kirsher authored
Fixed by moving code to correct location (for 82572 and 82571 controllers). Signed-off-by:
-
Jeff Kirsher authored
Fixed the collision distance for 82543 controllers and newer. Signed-off-by:
-
Jeff Kirsher authored
Removed duplicate code, TXDCTL and TXDCTL_COUNT_DESC are the same bit and there is no need to set it twice. Signed-off-by:
-
Jeff Kirsher authored
These were two separate community submitted patches. Signed-off-by:
-
Jeff Kirsher authored
Fixed the TX timeout logic to use "end of packet" rather than "next to clean". Updated message log. Signed-off-by:
-
Jeff Kirsher authored
This patch contains two fixes. The first fix is to the tx and rx descriptor rings clean up process. The second fix is to jumbo frames, which cleans up the code logic and removes most of the fifo related limitations on jumbo frames. This is because the driver code now supports splitting a packet across multiple descriptors. Signed-off-by:
-
Jeff Kirsher authored
10/100 speeds seem to have some problems reporting false tx timeouts especially at half duplex. Fixed by using a timeout factor to attempt to mitigate the false timeouts. Signed-off-by:
-
Jeff Kirsher authored
Fixed flow control water marks based on PBA size. Store flow control state in original_fc in addition to fc. Signed-off-by:
-
Jeff Kirsher authored
Fixed read_eeprom logic to test use_eerd instead of testing for 82573 controllers. Signed-off-by:
-
Jeff Kirsher authored
Signed-off-by:
-
Jeff Kirsher authored
Fixed the loopback logic to work for the PCI express adapters. Signed-off-by:
-
Jeff Kirsher authored
Fixed stats when using multiple queues. When multiple queues are enabled, log a message in syslog. Fixed memory allocation for multiple queues. Signed-off-by:
-
Jeff Kirsher authored
Fix adapter structure to handle multiple queues and prepping the driver for full multiple queue support, some changes are ifdef'd our unless you define CONFIG_E1000_MQ. Signed-off-by:
-
Jeff Kirsher authored
Fixed adapter identification issue. Signed-off-by:
-
Jeff Kirsher authored
Updated the e1000_stats structure and removed mpx for rx_errors and rx_dropped. Signed-off-by:
-
Jeff Kirsher authored
Added a delay to allow PHY configuration to complete before accessing NVM. Signed-off-by:
-
Jeff Kirsher authored
The 82573 controller required different logic than 82571|2 controllers. Corrected the reset logic for 8257{1|2|3} controllers. Signed-off-by: -
Jeff Kirsher authored
Fix so that if a SoL/IDER session is active, do not allow operations which require a PHY reset and instead log a message. Signed-off-by:
-
Jeff Kirsher authored
These fixes update the TX and RX ring structures. Prepare driver for up-coming fixes. Signed-off-by:
-
Jeff Kirsher authored
Fixed the TSO workaround for 82571/2 controllers. Fixed TSO issue where a non-tso packet in a linear SKB which followed a TSO packet would get written back prematurely. Signed-off-by:
-
Jeff Kirsher authored
Partition PBA for Jumbo frames based on MTU size. Signed-off-by:
-
Arnd Bergmann authored
This is now required to avoid drivers/net/spider_net.c:844: error: 'IPPROTO_TCP' undeclared Signed-off-by:
Arnd Bergmann <arndb@de.ibm.com> Signed-off-by:
-
Arnd Bergmann authored
Performance optimizations, changes in these areas: - RX and TX checksum offload - correct maximum MTU - don't use TX interrupts anymore, use a timer instead - remove some superfluous barriers - improve RX RAM full handling From: Utz Bacher <utz.bacher@de.ibm.com> Signed-off-by:
Jens Osterkamp <jens.osterkamp@de.ibm.com> Signed-off-by:
-
Arnd Bergmann authored
The driver incorrectly used dma_addr_t to describe HW structures and consequently broke when that type was changed in 2.6.15-rc. This changed spidernet to use u32 for 32 bit HW defined structure elements. From: Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Signed-off-by:
-
Arnd Bergmann authored
request_firmware() is sometimes problematic, especially in initramfs, reading the firmware from Open Firmware is much preferrable. We still try to get the firmware from the file system first, in order to support old SLOF releases and to allow updates of the spidernet firmware without reflashing the system. From: Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Signed-off-by:
-
Arnd Bergmann authored
Uploading the device firmware may fail if wrong input data was provided by the user. This checks for the condition. From: Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Signed-off-by:
-
Dale Farnsworth authored
All interrupts controlled by the extended mask register are also masked by a bit in the main mask register, so there is no need to directly manipulate the extended mask register. Signed-off-by:
Dale Farnsworth <dale@farnsworth.org> mv643xx_eth.c | 81 ++++++++++++++++++---------------------------------------- 1 file changed, 26 insertions(+), 55 deletions(-) Signed-off-by:
-
Dale Farnsworth authored
Move code from helper functions mv643xx_eth_real_open and mv643xx_eth_real_stop as they are no longer needed. Signed-off-by Dale Farnsworth <dale@farnsworth.org> mv643xx_eth.c | 109 +++++++++++++++++++++++----------------------------------- 1 file changed, 45 insertions(+), 64 deletions(-) Signed-off-by: -
Dale Farnsworth authored
Signed-off-by:
-
Wolfram Joost authored
This patch removes the NETIF_F_HW_CSUM flag to be able to use other protocols than IPv4. Hardware checksums for IPv4 should continue to work because NETIF_F_IP_CSUM is still set. The sanity-check has been enhanced to check the used protocol and to not access skb->iph for non-ipv4-packets. Signed-off-by:
Wolfram Joost <pegasos@frokaschwei.de> Signed-off-by:
-
