- 24 Sep, 2008 40 commits
-
-
Jeff Kirsher authored
Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by:
Jeff Garzik <jgarzik@redhat.com>
-
Jesse Brandeburg authored
ixgbe_xmit_frame can be refactored to use fewer locals and better utilize common kernel macros. also fixed minor buglet with internal to driver vlan flag variable being passed incorrectly. Signed-off-by:
-
Jesse Brandeburg authored
some functions were un-necessarily using local variables. Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Jesse Brandeburg authored
This is partial preparation for a future patch which will extend ixgbe_set_num_queues Signed-off-by:
-
Jesse Brandeburg authored
clean up the hardware shutdown sequence to prevent hardware from continuing to send when resetting or unloading. Signed-off-by:
-
Jesse Brandeburg authored
This is a massive update that includes infrastructure for further patches where we will add support for more phy types and eeprom types. This code is shared as much as possible with other drivers, so the code may seem a little obtuse at times but wherever possible we keep to the linux style and methods. Signed-off-by:
-
Jesse Brandeburg authored
in some configurations there can be more than one rx queue per vector in msi-x mode. Add functionality to be able to clean this without changing the performance path single-rx-queue cleanup. Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Jesse Brandeburg authored
changing ring sizes in ethtool needs to be robust. If an allocation fails the driver must continue operation, with the previous settings. Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Jesse Brandeburg authored
most of the time we only need 1500 bytes for a packet which means we don't need a whole 4k page for each packet. Share the allocation by using a reference count to the page and giving half to two receive descriptors. This can enable us to use packet split mode all the time due to the performance increase of allocating half the pages. Signed-off-by:
-
Jesse Brandeburg authored
when using more than 8 tx queues you can overrun the 8 bit v_idx field, so change it to 16 bits to represent the maximum number of queues (one for each bit) Signed-off-by:
-
Jesse Brandeburg authored
ixgbe was incorrectly setting the throttle rate setting for all tx queues and the driver has been refreshed to better handle a dynamic interrupt mode as well as multiple queues. Signed-off-by:
-
Jesse Brandeburg authored
ethtool was not disabling the correct netif flags when setting checksum disable. Signed-off-by:
-
Jeff Kirsher authored
Form: Jesse Brandeburg <jesse.brandeburg@intel.com> Signed-off-by:
-
Jesse Brandeburg authored
1) reading some of the registers in our hardware causes them to clear, so don't read ICR in the ethtool register dump function. 2) several register iterators were not iterating Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Jesse Brandeburg authored
fix ixgbe bug reported with shared legacy interrupts Signed-off-by:
-
Jesse Brandeburg authored
Upon review a buglet was found where link change was not causing an immediate link change event as it should. Signed-off-by:
-
Jesse Brandeburg authored
This patch updates the link_up code and watchdog thread so that link_up doesn't cause stack overflows due to long waits in interrupt context. Signed-off-by:
Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by:
-
Jesse Brandeburg authored
after the most recent patches, the driver was not using the correct iterator for updating the receive address registers (RAR) Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Jesse Brandeburg authored
Signed-off-by:
-
Dhananjay Phadke authored
Define old and new pci vendor and device ids. Signed-off-by:
Dhananjay Phadke <dhananjay@netxen.com> Signed-off-by:
-
Brice Goglin authored
Rename the cryptic "dca_capable" to "dca_capable_firmware" and "dca_enabled" to "dca_device_present" in the firmware counters. Signed-off-by:
Brice Goglin <brice@myri.com> Signed-off-by:
-
Brice Goglin authored
Stop scaring people with what looks like a fatal message when DCA support is compiled into their kernel, but the DCA device is not present. Signed-off-by:
-
Magnus Damm authored
Remove duplicated debug printout. Signed-off-by:
Magnus Damm <damm@igel.co.jp> Signed-off-by:
-
Florian Fainelli authored
This patch fixes the bad usage of udelay(5000), which in turns is a mdelay(5). It causes compilation for ARM where udelay maximum value is checked. Reported-by:
Martin Michlmayr <tbm@cyrius.com> Signed-off-by:
Florian Fainelli <florian.fainelli@telecomint.eu> Signed-off-by:
-
Ben Hutchings authored
FALCON_SPI_MAX_LEN has type size_t while other SPI lengths have type unsigned int. This results in warnings from min() on 64-bit architectures where they are different. Add a cast to make it match. From: Steve Hodgson <shodgson@solarflare.com> Signed-off-by:
Ben Hutchings <bhutchings@solarflare.com> Signed-off-by:
-
Ben Hutchings authored
For some buffers we use a starting offset of either NET_IP_ALIGN or 0 depending on whether we believe the architecture supports efficient access to unaligned words. There is now a config macro specifying whether this is the case, so check that rather than checking for specific architectures. Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
-
Ben Hutchings authored
This should avoid an interrupt storm, which has been observed in the field with one faulty board. Signed-off-by:
-
Ben Hutchings authored
This prevents speculative reading of the statistics before the completion flag. From: Neil Turton <nturton@solarflare.com> Signed-off-by:
-
Ben Hutchings authored
mdio_clause45_links_ok() correctly checks efx_phy_mode_disabled(), so tenxpress_link_ok() doesn't need to. From: Steve Hodgson <shodgson@solarflare.com> Signed-off-by:
-
Steve Hodgson authored
Signed-off-by:
-
Ben Hutchings authored
Increase the potential retry count for RX flushes from 5 to 100. Stop polling the RX_DESC_PTR_TBL to infer that a flush might have happened. Instead absolutely rely on the flush events, unless bug 7803 applies (Falcon rev A only). To keep things quick, request flushes for every TX and RX queue up front, and match up the events to requests. Signed-off-by:
-
Steve Hodgson authored
Signed-off-by:
-
Ben Hutchings authored
On some boards 10Xpress feeds a 156 MHz clock to the Falcon XMAC. MAC statistics DMA can fail while this clock is stopped during a PHY reset. From: Steve Hodgson <shodgson@solarflare.com> Signed-off-by:
-
Ben Hutchings authored
There was a bug in XAUI synchronisation in early 10Xpress firmware versions. This is fixed in released firmware and we do not need to work around it. Signed-off-by:
-
