kernel/drivers/net/ethernet/sfc/tx.c, branch linux-4.3.y

sfc: push partner queue for skb->xmit_more

2015-12-09T19:34:08Z

[ Upstream commit b2663a4f30e85ec606b806f5135413e6d5c78d1e ] When the IP stack passes SKBs the sfc driver puts them in 2 different TX queues (called partners), one for checksummed and one for not checksummed. If the SKB has xmit_more set the driver will delay pushing the work to the NIC. When later it does decide to push the buffers this patch ensures it also pushes the partner queue, if that also has any delayed work. Before this fix the work in the partner queue would be left for a long time and cause a netdev watchdog. Fixes: 70b33fb ("sfc: add support for skb->xmit_more") Reported-by: Jianlin Shi Signed-off-by: Martin Habets Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman

sfc: Report TX completions to BQL after all TX events in interrupt

2015-07-09T07:00:40Z

The limit for BQL is updated each time we call netdev_tx_completed_queue. Without this patch the BQL limit was updated for every TX event we see. The issue was that this only updated the limit to handle the data we complete in two events as the first event wouldn't show that enough traffic had been processed between them. This was OK when interrupt moderation was off but not when it was on as more data had to be completed in a single interrupt. The patch changes this so that we do report the completion to BQL only when all the TX events in the interrupt have been processed. Signed-off-by: Shradha Shah Signed-off-by: David S. Miller

sfc: remove incorrect EFX_BUG_ON_PARANOID check

2014-10-22T16:51:16Z

write_count and insert_count can wrap around, making > check invalid. Fixes: 70b33fb0ddec827cbbd14cdc664fc27b2ef4a6b6 ("sfc: add support for skb->xmit_more"). Signed-off-by: Edward Cree Signed-off-by: David S. Miller

sfc: add support for skb->xmit_more

2014-10-18T03:47:32Z

Don't ring the doorbell, and don't do PIO. This will also prevent TX Push, because there will be more than one buffer waiting when the doorbell is rung. Signed-off-by: Edward Cree Signed-off-by: David S. Miller

sfc: Convert the normal transmit complete path to dev_consume_skb_any()

2014-09-10T00:33:56Z

Convert the normal transmit completion path from dev_kfree_skb_any() to dev_consume_skb_any() to help keep dropped packet profiling meaningful. Signed-off-by: Rick Jones Signed-off-by: David S. Miller

sfc: Use __iowrite64_copy instead of a slightly different local function

2014-07-29T22:30:29Z

__iowrite64_copy() isn't quite the same as efx_memcpy_64(), but it looks close enough: - The length is in units of qwords not bytes - It never byte-swaps, but that doesn't make a difference now as PIO is only enabled for x86_64 - It doesn't include any memory barriers, but that's OK as there is a barrier just before pushing the doorbell - mlx4_en uses it for the same purpose Compile-tested only. Signed-off-by: Ben Hutchings Acked-by: Edward Cree Signed-off-by: David S. Miller

sfc: Add per-queue statistics in ethtool

2014-07-17T23:48:36Z

Implement per channel software TX and RX packet counters accessed as ethtool statistics. This allows confirmation with MAC statistics. Signed-off-by: Shradha Shah Signed-off-by: David S. Miller

sfc: PIO:Restrict to 64bit arch and use 64-bit writes.

2014-06-11T22:36:21Z

Fixes:ee45fd92c739 ("sfc: Use TX PIO for sufficiently small packets") The linux net driver uses memcpy_toio() in order to copy into the PIO buffers. Even on a 64bit machine this causes 32bit accesses to a write- combined memory region. There are hardware limitations that mean that only 64bit naturally aligned accesses are safe in all cases. Due to being write-combined memory region two 32bit accesses may be coalesced to form a 64bit non 64bit aligned access. Solution was to open-code the memory copy routines using pointers and to only enable PIO for x86_64 machines. Not tested on platforms other than x86_64 because this patch disables the PIO feature on other platforms. Compile-tested on x86 to ensure that works. The WARN_ON_ONCE() code in the previous version of this patch has been moved into the internal sfc debug driver as the assertion was unnecessary in the upstream kernel code. This bug fix applies to v3.13 and v3.14 stable branches. Signed-off-by: Shradha Shah Signed-off-by: David S. Miller

sfc: Rename 'use_options' variable in tso_start() to clearer 'use_opt_desc'

2014-02-12T22:53:35Z

Signed-off-by: Ben Hutchings Signed-off-by: Shradha Shah Signed-off-by: David S. Miller

sfc: Replace TSOH_OFFSET with the equivalent NET_IP_ALIGN

2014-02-12T22:53:34Z

If CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is defined then NET_IP_ALIGN will be defined as 0, so this macro is redundant. Signed-off-by: Ben Hutchings Signed-off-by: Shradha Shah Signed-off-by: David S. Miller