mirror of
https://github.com/torvalds/linux.git
synced 2026-05-05 15:02:40 -04:00
93f53db9f9
This patch completes the transition of the ice driver to use the Page Pool
and libeth APIs, following the same direction as commit 5fa4caff59
("iavf: switch to Page Pool"). With the legacy page splitting and recycling
logic already removed, the driver is now in a clean state to adopt the
modern memory model.
The Page Pool integration simplifies buffer management by offloading
DMA mapping and recycling to the core infrastructure. This eliminates
the need for driver-specific handling of headroom, buffer sizing, and
page order. The libeth helper is used for CPU-side processing, while
DMA-for-device is handled by the Page Pool core.
Additionally, this patch extends the conversion to cover XDP support.
The driver now uses libeth_xdp helpers for Rx buffer processing,
and optimizes XDP_TX by skipping per-frame DMA mapping. Instead, all
buffers are mapped as bi-directional up front, leveraging Page Pool's
lifecycle management. This significantly reduces overhead in virtualized
environments.
Performance observations:
- In typical scenarios (netperf, XDP_PASS, XDP_DROP), performance remains
on par with the previous implementation.
- In XDP_TX mode:
* With IOMMU enabled, performance improves dramatically - over 5x
increase - due to reduced DMA mapping overhead and better memory reuse.
* With IOMMU disabled, performance remains comparable to the previous
implementation, with no significant changes observed.
- In XDP_DROP mode:
* For small MTUs, (where multiple buffers can be allocated on a single
memory page), a performance drop of approximately 20% is observed.
According to 'perf top' analysis, the bottleneck is caused by atomic
reference counter increments in the Page Pool.
* For normal MTUs, (where only one buffer can be allocated within a
single memory page), performance remains comparable to baseline
levels.
This change is also a step toward a more modular and unified XDP
implementation across Intel Ethernet drivers, aligning with ongoing
efforts to consolidate and streamline feature support.
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Tested-by: Alexander Nowlin <alexander.nowlin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
102 lines
3.0 KiB
C
102 lines
3.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright (c) 2019, Intel Corporation. */
|
|
|
|
#ifndef _ICE_XSK_H_
|
|
#define _ICE_XSK_H_
|
|
#include "ice_txrx.h"
|
|
|
|
#define PKTS_PER_BATCH 8
|
|
|
|
struct ice_vsi;
|
|
|
|
#ifdef CONFIG_XDP_SOCKETS
|
|
int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
|
|
u16 qid);
|
|
int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
|
|
struct xsk_buff_pool *xsk_pool,
|
|
int budget);
|
|
int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
|
|
bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
|
|
struct xsk_buff_pool *xsk_pool, u16 count);
|
|
bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
|
|
void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
|
|
void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
|
|
bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
|
|
int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present);
|
|
void ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
|
|
u16 qid);
|
|
void ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
|
|
bool enable);
|
|
void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector);
|
|
void ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
|
|
struct ice_q_vector *q_vector);
|
|
#else
|
|
static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
|
|
struct xsk_buff_pool __always_unused *xsk_pool)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int
|
|
ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
|
|
struct xsk_buff_pool __always_unused *pool,
|
|
u16 __always_unused qid)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static inline int
|
|
ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
|
|
struct xsk_buff_pool __always_unused *xsk_pool,
|
|
int __always_unused budget)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool
|
|
ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
|
|
struct xsk_buff_pool __always_unused *xsk_pool,
|
|
u16 __always_unused count)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool ice_xsk_any_rx_ring_ena(struct ice_vsi __always_unused *vsi)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int
|
|
ice_xsk_wakeup(struct net_device __always_unused *netdev,
|
|
u32 __always_unused queue_id, u32 __always_unused flags)
|
|
{
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { }
|
|
static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { }
|
|
|
|
static inline int
|
|
ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring,
|
|
bool __always_unused pool_present)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void
|
|
ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
|
|
u16 qid) { }
|
|
|
|
static inline void
|
|
ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
|
|
bool enable) { }
|
|
|
|
static inline void
|
|
ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector) { }
|
|
|
|
static inline void
|
|
ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
|
|
struct ice_q_vector *q_vector) { }
|
|
#endif /* CONFIG_XDP_SOCKETS */
|
|
#endif /* !_ICE_XSK_H_ */
|