diff options
| author | Magnus Karlsson <magnus.karlsson@intel.com> | 2020-11-16 12:12:47 +0100 |
|---|---|---|
| committer | Daniel Borkmann <daniel@iogearbox.net> | 2020-11-17 22:07:40 +0100 |
| commit | 3106c580fb7cf26691c1ce3aba2223f3ae56d846 (patch) | |
| tree | fd8b06d91a34b79b6f9b456ed2d6509033f39e1b /drivers/net/ethernet/intel/i40e/i40e_txrx.c | |
| parent | 9349eb3a9d2ae0151510dd98b6640dfaeebee9cc (diff) | |
i40e: Use batched xsk Tx interfaces to increase performance
Use the new batched xsk interfaces for the Tx path in the i40e driver
to improve performance. On my machine, this yields a throughput
increase of 4% for the l2fwd sample app in xdpsock. If we instead just
look at the Tx part, this patch set increases throughput with above
20% for Tx.
Note that I had to explicitly loop unroll the inner loop to get to
this performance level, by using a pragma. It is honored by both clang
and gcc and should be ignored by versions that do not support
it. Using the -funroll-loops compiler command line switch on the
source file resulted in a loop unrolling on a higher level that
lead to a performance decrease instead of an increase.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/1605525167-14450-6-git-send-email-magnus.karlsson@gmail.com
Diffstat (limited to 'drivers/net/ethernet/intel/i40e/i40e_txrx.c')
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_txrx.c | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d43ce13a93c9..c21548c71bb1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -676,6 +676,8 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) i40e_clean_tx_ring(tx_ring); kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; + kfree(tx_ring->xsk_descs); + tx_ring->xsk_descs = NULL; if (tx_ring->desc) { dma_free_coherent(tx_ring->dev, tx_ring->size, @@ -1277,6 +1279,13 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) if (!tx_ring->tx_bi) goto err; + if (ring_is_xdp(tx_ring)) { + tx_ring->xsk_descs = kcalloc(I40E_MAX_NUM_DESCRIPTORS, sizeof(*tx_ring->xsk_descs), + GFP_KERNEL); + if (!tx_ring->xsk_descs) + goto err; + } + u64_stats_init(&tx_ring->syncp); /* round up to nearest 4K */ @@ -1300,6 +1309,8 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) return 0; err: + kfree(tx_ring->xsk_descs); + tx_ring->xsk_descs = NULL; kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; return -ENOMEM; |