linux/drivers/net/ethernet/intel/i40e/i40e_xsk.h
Magnus Karlsson 3106c580fb 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
2020-11-17 22:07:40 +01:00

40 lines
1.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2018 Intel Corporation. */
#ifndef _I40E_XSK_H_
#define _I40E_XSK_H_
/* This value should match the pragma in the loop_unrolled_for
* macro. Why 4? It is strictly empirical. It seems to be a good
* compromise between the advantage of having simultaneous outstanding
* reads to the DMA array that can hide each others latency and the
* disadvantage of having a larger code path.
*/
#define PKTS_PER_BATCH 4
#ifdef __clang__
#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
#elif __GNUC__ >= 8
#define loop_unrolled_for _Pragma("GCC unroll 4") for
#else
#define loop_unrolled_for for
#endif
struct i40e_vsi;
struct xsk_buff_pool;
struct zero_copy_allocator;
int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
int i40e_xsk_pool_setup(struct i40e_vsi *vsi, struct xsk_buff_pool *pool,
u16 qid);
bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count);
int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring);
int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring);
void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring);
#endif /* _I40E_XSK_H_ */