Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 08 3月, 2013 1 次提交
  3. 07 3月, 2013 1 次提交
  5. 05 2月, 2013 1 次提交
  7. 30 1月, 2013 1 次提交
  9. 13 1月, 2013 1 次提交
    • S
      be2net: fix unconditionally returning IRQ_HANDLED in INTx · d0b9cec3
      由 Sathya Perla 提交于 
      commit e49cc34f introduced an unconditional IRQ_HANDLED return in be_intx()
to workaround Lancer and BE2 HW issues. This is bad as it prevents the kernel
from detecting interrupt storms due to broken HW.

The BE2/Lancer HW issues are:
1) In Lancer, there is no means for the driver to detect if the interrupt
belonged to device, other than counting and notifying events.
2) In Lancer de-asserting INTx takes a while, causing the INTx irq handler
to be called multiple times till the de-assert happens.
3) In BE2, we see an occasional interrupt even when EQs are unarmed.

Issue (1) can cause the notified events to be orphaned, if NAPI was already
running.
This patch fixes this issue by scheduling NAPI only if it is not scheduled
already. Doing this also takes care of possible events_get() race that may be
caused due to issue (2) and (3). Also, IRQ_HANDLED is returned only the first
time zero events are detected.
(Thanks Ben H. for the feedback and suggestions.)
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d0b9cec3
  11. 19 12月, 2012 1 次提交
    • S
      be2net: fix wrong frag_idx reported by RX CQ · d23e946c
      由 Sathya Perla 提交于 
      The RX CQ can report completions with invalid frag_idx when the RXQ that
was *previously* using it, was not cleaned up properly. This hits
a BUG_ON() in be2net.

When completion coalescing is enabled on a CQ, an explicit CQ-notify
(with rearm) is needed for each compl, to flush partially coalesced CQ
entries that are pending DMA.

In be_close(), this fix now notifies CQ for each compl, waits explicitly
for the flush compl to arrive and complains if it doesn't arrive.

Also renaming be_crit_error() to be_hw_error() as it's the more
appropriate name and to convey that we don't wait for the flush compl
only when a HW error has occurred.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      d23e946c
  13. 08 11月, 2012 5 次提交
  15. 22 10月, 2012 6 次提交
  17. 30 9月, 2012 1 次提交
  19. 31 8月, 2012 1 次提交
  21. 17 7月, 2012 1 次提交
  23. 12 7月, 2012 3 次提交
  25. 09 7月, 2012 1 次提交
  27. 27 6月, 2012 1 次提交
  29. 07 6月, 2012 1 次提交
  31. 19 5月, 2012 1 次提交
  33. 11 5月, 2012 1 次提交
  35. 09 5月, 2012 1 次提交
  37. 27 4月, 2012 1 次提交
  39. 26 4月, 2012 1 次提交
  41. 24 4月, 2012 1 次提交
  43. 20 3月, 2012 3 次提交
  45. 02 3月, 2012 1 次提交
  47. 24 2月, 2012 2 次提交
  49. 13 2月, 2012 1 次提交
    • S
      be2net: event queue re-design · 10ef9ab4
      由 Sathya Perla 提交于 
      v2: Fixed up the bad typecasting pointed out by David...

In the current design 8 TXQs are serviced by 1 EQ, while each RSS queue
is serviced by a separate EQ. This is being changed as follows:

- Upto 8 EQs will be used (based on the availabilty of msix vectors).
Each EQ will handle 1 RSS and 1 TX ring. The default non-RSS RX queue and
MCC queue are handled by the last EQ.

- On cards which provide support, upto 8 RSS rings will be used, instead
of the current limit of 4.

The new design allows spreading the TX multi-queue completion processing
across multiple CPUs unlike the previous design.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      10ef9ab4
  51. 02 2月, 2012 1 次提交