- 24 Sep, 2008 40 commits
-
-
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 <jesse.brandeburg@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
Jeff Garzik <jgarzik@redhat.com>
-
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:
-
Ben Hutchings authored
Match pci_request_region() with pci_release_region(), not release_mem_region(). From: Steve Hodgson <shodgson@solarflare.com> Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
-
Mats Erik Andersson authored
I would like to submit a correction to the driver drivers/net/8139too.c, which in no way changes the compiled driver, but does change the value of a previously incorrect value for the configuration register address of Flash PROM on the network processor rtl8139C. This corrected value is in accordance with the datasheet for rtl8139C, and in addition this new value is indeed used in other functional drivers that use this adapter for programming a Flash memory chip in situ. But as said, the two new constants are never referenced in the driver maintained by you: they are only informational and correct! Mats Erik Andersson, meand@users.sourceforge.net Signed-off-by: -
Breno Leitao authored
VLAN doesn't work except if you'd opened the interface in promiscuous mode before. This happens because VLAN tag stripping is not correctly marked as enabled at device startup Also, the vlan_strip_flag field was moved to the private network structure. Signed-off-by:
Breno Leitao <leitao@linux.vnet.ibm.com> Signed-off-by:
Jay Vosburgh <fubar@us.ibm.com> Signed-off-by:
-
Yoichi Yuasa authored
release_irq label is only used when ALLOW_DMA is defined. drivers/net/cs89x0.c: In function 'net_open': drivers/net/cs89x0.c:1401: warning: label 'release_irq' defined but not used Signed-off-by:
Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp> Signed-off-by:
-
Adrian Bunk authored
hso_serial_common_free() mustn't be called if hso_serial_common_create() fails. Reported-by:
Adrian Bunk <bunk@kernel.org> Signed-off-by:
-
Krzysztof Halasa authored
WAN: fixes a NULL dereference in hdlc_x25. Reported-by: Adrian Bunk <bunk@kernel.org>. Signed-off-by:
Krzysztof Halasa <khc@pm.waw.pl> Signed-off-by:
-
Vlad Yasevich authored
IPv6 all-node-multicasts and DAD probes should not be tx-balanced on ALB/TLB bonds. The all-node-multicast is an equivalent to IPv4 broadcasts. DAD probes have to be sent only on the primary so that we don't get false-positive detections. Signed-off-by: -
Matthew Wilcox authored
Lockdep warns about the mdio_lock taken with interrupts enabled then later taken from interrupt context. Initially, I considered changing these to spin_lock_irq/spin_unlock_irq, but then I looked at atl1e_phy_init() and saw that it calls msleep(). Sleeping while holding a spinlock is not allowed either. In the probe path, we haven't registered the interrupt handler, so it can't poke at this card yet. It's before we call register_netdev(), so I don't think any other threads can reach this card either. If I'm right, we don't need a spinlock at all. Signed-off-by:
Matthew Wilcox <willy@linux.intel.com> Signed-off-by:
-
Hannes Hering authored
The ehea busmap must be allocated only once in the first of many calls of the ehea_create_busmap_callback. Signed-off-by:
Hannes Hering <hering2@de.ibm.com> Signed-off-by:
-
David Fries authored
A call to pnp_stop_dev and pnp_start_dev now shuts down and initializes plug and play devices for suspend and resume. Signed-off-by:
David Fries <david@fries.net> Cc: Atsushi Nemoto <anemo@mba.ocn.ne.jp> Cc: Paul Gortmaker <p_gortmaker@yahoo.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Jeff Garzik <jeff@garzik.org> Signed-off-by:
-
