UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'bpf-af-xdp-mlx5e' 

Tariq Toukan says:

====================
This series contains improvements to the AF_XDP kernel infrastructure
and AF_XDP support in mlx5e. The infrastructure improvements are
required for mlx5e, but also some of them benefit to all drivers, and
some can be useful for other drivers that want to implement AF_XDP.

The performance testing was performed on a machine with the following
configuration:

- 24 cores of Intel Xeon E5-2620 v3 @ 2.40 GHz
- Mellanox ConnectX-5 Ex with 100 Gbit/s link

The results with retpoline disabled, single stream:

txonly: 33.3 Mpps (21.5 Mpps with queue and app pinned to the same CPU)
rxdrop: 12.2 Mpps
l2fwd: 9.4 Mpps

The results with retpoline enabled, single stream:

txonly: 21.3 Mpps (14.1 Mpps with queue and app pinned to the same CPU)
rxdrop: 9.9 Mpps
l2fwd: 6.8 Mpps

v2 changes:

Added patches for mlx5e and addressed the comments for v1. Rebased for
bpf-next.

v3 changes:

Rebased for the newer bpf-next, resolved conflicts in libbpf. Addressed
Björn's comments for coding style. Fixed a bug in error handling flow in
mlx5e_open_xsk.

v4 changes:

UAPI is not changed, XSK RX queues are exposed to the kernel. The lower
half of the available amount of RX queues are regular queues, and the
upper half are XSK RX queues. The patch "xsk: Extend channels to support
combined XSK/non-XSK traffic" was dropped. The final patch was reworked
accordingly.

Added "net/mlx5e: Attach/detach XDP program safely", as the changes
introduced in the XSK patch base on the stuff from this one.

Added "libbpf: Support drivers with non-combined channels", which aligns
the condition in libbpf with the condition in the kernel.

Rebased over the newer bpf-next.

v5 changes:

In v4, ethtool reports the number of channels as 'combined' and the
number of XSK RX queues as 'rx' for mlx5e. It was changed, so that 'rx'
is 0, and 'combined' reports the double amount of channels if there is
an active UMEM - to make libbpf happy.

The patch for libbpf was dropped. Although it's still useful and fixes
things, it raises some disagreement, so I'm dropping it - it's no longer
useful for mlx5e anymore after the change above.

v6 changes:

As Maxim is out of office, I rebased the series on behalf of him,
solved some conflicts, and re-spinned.
====================

Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit is contained in:
Daniel Borkmann 2019-06-27 22:53:29 +02:00
parent e5c891a349 db05815b36
commit 3b1c667e47
35 changed files with 2359 additions and 512 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
drivers/net/ethernet/intel/i40e/i40e_xsk.c
View File

@ -641,8 +641,8 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
struct i40e_tx_desc *tx_desc = NULL;
struct i40e_tx_buffer *tx_bi;
bool work_done = true;
struct xdp_desc desc;
dma_addr_t dma;
u32 len;
while (budget-- > 0) {
if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
@ -651,21 +651,23 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
break;
}
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len))
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
break;
dma_sync_single_for_device(xdp_ring->dev, dma, len,
dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
DMA_BIDIRECTIONAL);
tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
tx_bi->bytecount = len;
tx_bi->bytecount = desc.len;
tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
tx_desc->buffer_addr = cpu_to_le64(dma);
tx_desc->cmd_type_offset_bsz =
build_ctob(I40E_TX_DESC_CMD_ICRC
| I40E_TX_DESC_CMD_EOP,
0, len, 0);
0, desc.len, 0);
xdp_ring->next_to_use++;
if (xdp_ring->next_to_use == xdp_ring->count)

15
drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
View File

@ -571,8 +571,9 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
union ixgbe_adv_tx_desc *tx_desc = NULL;
struct ixgbe_tx_buffer *tx_bi;
bool work_done = true;
u32 len, cmd_type;
struct xdp_desc desc;
dma_addr_t dma;
u32 cmd_type;
while (budget-- > 0) {
if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
@ -581,14 +582,16 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
break;
}
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len))
if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
break;
dma_sync_single_for_device(xdp_ring->dev, dma, len,
dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
DMA_BIDIRECTIONAL);
tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
tx_bi->bytecount = len;
tx_bi->bytecount = desc.len;
tx_bi->xdpf = NULL;
tx_bi->gso_segs = 1;
@ -599,10 +602,10 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
cmd_type = IXGBE_ADVTXD_DTYP_DATA |
IXGBE_ADVTXD_DCMD_DEXT |
IXGBE_ADVTXD_DCMD_IFCS;
cmd_type |= len | IXGBE_TXD_CMD;
cmd_type |= desc.len | IXGBE_TXD_CMD;
tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
tx_desc->read.olinfo_status =
cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);
cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT);
xdp_ring->next_to_use++;
if (xdp_ring->next_to_use == xdp_ring->count)

2
drivers/net/ethernet/mellanox/mlx5/core/Makefile
View File

@ -24,7 +24,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \
en/params.o
en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
#
# Netdev extra

155
drivers/net/ethernet/mellanox/mlx5/core/en.h
View File

@ -137,6 +137,7 @@ struct page_pool;
#define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1)
#define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
#define MLX5E_TX_CQ_POLL_BUDGET 128
#define MLX5E_TX_XSK_POLL_BUDGET 64
#define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */
#define MLX5E_UMR_WQE_INLINE_SZ \
@ -155,6 +156,11 @@ do { \
##__VA_ARGS__); \
} while (0)
enum mlx5e_rq_group {
MLX5E_RQ_GROUP_REGULAR,
MLX5E_RQ_GROUP_XSK,
MLX5E_NUM_RQ_GROUPS /* Keep last. */
};
static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
{
@ -179,7 +185,8 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
/* Use this function to get max num channels after netdev was created */
static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev)
{
return min_t(unsigned int, netdev->num_rx_queues,
return min_t(unsigned int,
netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS,
netdev->num_tx_queues);
}
@ -250,6 +257,7 @@ struct mlx5e_params {
u32 lro_timeout;
u32 pflags;
struct bpf_prog *xdp_prog;
struct mlx5e_xsk *xsk;
unsigned int sw_mtu;
int hard_mtu;
};
@ -348,6 +356,13 @@ enum {
struct mlx5e_sq_wqe_info {
u8 opcode;
/* Auxiliary data for different opcodes. */
union {
struct {
struct mlx5e_rq *rq;
} umr;
};
};
struct mlx5e_txqsq {
@ -392,14 +407,55 @@ struct mlx5e_txqsq {
} ____cacheline_aligned_in_smp;
struct mlx5e_dma_info {
struct page *page;
dma_addr_t addr;
dma_addr_t addr;
union {
struct page *page;
struct {
u64 handle;
void *data;
} xsk;
};
};
/* XDP packets can be transmitted in different ways. On completion, we need to
* distinguish between them to clean up things in a proper way.
*/
enum mlx5e_xdp_xmit_mode {
/* An xdp_frame was transmitted due to either XDP_REDIRECT from another
* device or XDP_TX from an XSK RQ. The frame has to be unmapped and
* returned.
*/
MLX5E_XDP_XMIT_MODE_FRAME,
/* The xdp_frame was created in place as a result of XDP_TX from a
* regular RQ. No DMA remapping happened, and the page belongs to us.
*/
MLX5E_XDP_XMIT_MODE_PAGE,
/* No xdp_frame was created at all, the transmit happened from a UMEM
* page. The UMEM Completion Ring producer pointer has to be increased.
*/
MLX5E_XDP_XMIT_MODE_XSK,
};
struct mlx5e_xdp_info {
struct xdp_frame *xdpf;
dma_addr_t dma_addr;
struct mlx5e_dma_info di;
enum mlx5e_xdp_xmit_mode mode;
union {
struct {
struct xdp_frame *xdpf;
dma_addr_t dma_addr;
} frame;
struct {
struct mlx5e_rq *rq;
struct mlx5e_dma_info di;
} page;
};
};
struct mlx5e_xdp_xmit_data {
dma_addr_t dma_addr;
void *data;
u32 len;
};
struct mlx5e_xdp_info_fifo {
@ -425,8 +481,12 @@ struct mlx5e_xdp_mpwqe {
};
struct mlx5e_xdpsq;
typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
struct mlx5e_xdp_info*);
typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
struct mlx5e_xdp_xmit_data *,
struct mlx5e_xdp_info *,
int);
struct mlx5e_xdpsq {
/* data path */
@ -443,8 +503,10 @@ struct mlx5e_xdpsq {
struct mlx5e_cq cq;
/* read only */
struct xdp_umem *umem;
struct mlx5_wq_cyc wq;
struct mlx5e_xdpsq_stats *stats;
mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check;
mlx5e_fp_xmit_xdp_frame xmit_xdp_frame;
struct {
struct mlx5e_xdp_wqe_info *wqe_info;
@ -571,9 +633,11 @@ struct mlx5e_rq {
u8 log_stride_sz;
u8 umr_in_progress;
u8 umr_last_bulk;
u8 umr_completed;
} mpwqe;
};
struct {
u16 umem_headroom;
u16 headroom;
u8 map_dir; /* dma map direction */
} buff;
@ -600,10 +664,14 @@ struct mlx5e_rq {
/* XDP */
struct bpf_prog *xdp_prog;
struct mlx5e_xdpsq xdpsq;
struct mlx5e_xdpsq *xdpsq;
DECLARE_BITMAP(flags, 8);
struct page_pool *page_pool;
/* AF_XDP zero-copy */
struct zero_copy_allocator zca;
struct xdp_umem *umem;
/* control */
struct mlx5_wq_ctrl wq_ctrl;
__be32 mkey_be;
@ -616,9 +684,15 @@ struct mlx5e_rq {
struct xdp_rxq_info xdp_rxq;
} ____cacheline_aligned_in_smp;
enum mlx5e_channel_state {
MLX5E_CHANNEL_STATE_XSK,
MLX5E_CHANNEL_NUM_STATES
};
struct mlx5e_channel {
/* data path */
struct mlx5e_rq rq;
struct mlx5e_xdpsq rq_xdpsq;
struct mlx5e_txqsq sq[MLX5E_MAX_NUM_TC];
struct mlx5e_icosq icosq; /* internal control operations */
bool xdp;
@ -631,6 +705,13 @@ struct mlx5e_channel {
/* XDP_REDIRECT */
struct mlx5e_xdpsq xdpsq;
/* AF_XDP zero-copy */
struct mlx5e_rq xskrq;
struct mlx5e_xdpsq xsksq;
struct mlx5e_icosq xskicosq;
/* xskicosq can be accessed from any CPU - the spinlock protects it. */
spinlock_t xskicosq_lock;
/* data path - accessed per napi poll */
struct irq_desc *irq_desc;
struct mlx5e_ch_stats *stats;
@ -639,6 +720,7 @@ struct mlx5e_channel {
struct mlx5e_priv *priv;
struct mlx5_core_dev *mdev;
struct hwtstamp_config *tstamp;
DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
int ix;
int cpu;
cpumask_var_t xps_cpumask;
@ -654,14 +736,17 @@ struct mlx5e_channel_stats {
struct mlx5e_ch_stats ch;
struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
struct mlx5e_rq_stats rq;
struct mlx5e_rq_stats xskrq;
struct mlx5e_xdpsq_stats rq_xdpsq;
struct mlx5e_xdpsq_stats xdpsq;
struct mlx5e_xdpsq_stats xsksq;
} ____cacheline_aligned_in_smp;
enum {
MLX5E_STATE_OPENED,
MLX5E_STATE_DESTROYING,
MLX5E_STATE_XDP_TX_ENABLED,
MLX5E_STATE_XDP_OPEN,
};
struct mlx5e_rqt {
@ -694,6 +779,17 @@ struct mlx5e_modify_sq_param {
int rl_index;
};
struct mlx5e_xsk {
/* UMEMs are stored separately from channels, because we don't want to
* lose them when channels are recreated. The kernel also stores UMEMs,
* but it doesn't distinguish between zero-copy and non-zero-copy UMEMs,
* so rely on our mechanism.
*/
struct xdp_umem **umems;
u16 refcnt;
bool ever_used;
};
struct mlx5e_priv {
/* priv data path fields - start */
struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@ -714,6 +810,7 @@ struct mlx5e_priv {
struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS];
struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS];
struct mlx5e_tir xsk_tir[MLX5E_MAX_NUM_CHANNELS];
struct mlx5e_rss_params rss_params;
u32 tx_rates[MLX5E_MAX_NUM_SQS];
@ -750,6 +847,7 @@ struct mlx5e_priv {
struct mlx5e_tls *tls;
#endif
struct devlink_health_reporter *tx_reporter;
struct mlx5e_xsk xsk;
};
struct mlx5e_profile {
@ -793,11 +891,13 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
bool recycle);
void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info,
bool recycle);
void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
void mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
@ -853,6 +953,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
struct mlx5e_xsk_param;
struct mlx5e_rq_param;
int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
struct xdp_umem *umem, struct mlx5e_rq *rq);
int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
void mlx5e_close_rq(struct mlx5e_rq *rq);
struct mlx5e_sq_param;
int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
void mlx5e_close_icosq(struct mlx5e_icosq *sq);
int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
struct mlx5e_sq_param *param, struct xdp_umem *umem,
struct mlx5e_xdpsq *sq, bool is_redirect);
void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq);
struct mlx5e_cq_param;
int mlx5e_open_cq(struct mlx5e_channel *c, struct net_dim_cq_moder moder,
struct mlx5e_cq_param *param, struct mlx5e_cq *cq);
void mlx5e_close_cq(struct mlx5e_cq *cq);
int mlx5e_open_locked(struct net_device *netdev);
int mlx5e_close_locked(struct net_device *netdev);
@ -1023,10 +1147,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv);
int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
@ -1095,6 +1219,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv);
void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
struct mlx5e_xsk *xsk,
struct mlx5e_rss_params *rss_params,
struct mlx5e_params *params,
u16 max_channels, u16 mtu);

108
drivers/net/ethernet/mellanox/mlx5/core/en/params.c
View File

@ -3,65 +3,102 @@
#include "en/params.h"
u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
u16 linear_rq_headroom = params->xdp_prog ?
XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
u32 frag_sz;
return params->xdp_prog || xsk;
}
linear_rq_headroom += NET_IP_ALIGN;
u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u16 headroom = NET_IP_ALIGN;
frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
if (mlx5e_rx_is_xdp(params, xsk)) {
headroom += XDP_PACKET_HEADROOM;
if (xsk)
headroom += xsk->headroom;
} else {
headroom += MLX5_RX_HEADROOM;
}
if (params->xdp_prog && frag_sz < PAGE_SIZE)
frag_sz = PAGE_SIZE;
return headroom;
}
u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
u16 linear_rq_headroom = mlx5e_get_linear_rq_headroom(params, xsk);
u32 frag_sz = linear_rq_headroom + hw_mtu;
/* AF_XDP doesn't build SKBs in place. */
if (!xsk)
frag_sz = MLX5_SKB_FRAG_SZ(frag_sz);
/* XDP in mlx5e doesn't support multiple packets per page. */
if (mlx5e_rx_is_xdp(params, xsk))
frag_sz = max_t(u32, frag_sz, PAGE_SIZE);
/* Even if we can go with a smaller fragment size, we must not put
* multiple packets into a single frame.
*/
if (xsk)
frag_sz = max_t(u32, frag_sz, xsk->chunk_size);
return frag_sz;
}
u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params);
u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk);
return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
}
bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params)
bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
/* AF_XDP allocates SKBs on XDP_PASS - ensure they don't occupy more
* than one page. For this, check both with and without xsk.
*/
u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk),
mlx5e_rx_get_linear_frag_sz(params, NULL));
return !params->lro_en && frag_sz <= PAGE_SIZE;
return !params->lro_en && linear_frag_sz <= PAGE_SIZE;
}
#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk);
s8 signed_log_num_strides_param;
u8 log_num_strides;
if (!mlx5e_rx_is_linear_skb(params))
if (!mlx5e_rx_is_linear_skb(params, xsk))
return false;
if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
if (order_base_2(linear_frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
return false;
if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
return true;
log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
signed_log_num_strides_param =
(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
return signed_log_num_strides_param >= 0;
}
u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params);
u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params, xsk);
/* Numbers are unsigned, don't subtract to avoid underflow. */
if (params->log_rq_mtu_frames <
@ -72,33 +109,30 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
}
u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk))
return order_base_2(mlx5e_rx_get_linear_frag_sz(params, xsk));
return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
}
u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
return MLX5_MPWRQ_LOG_WQE_SZ -
mlx5e_mpwqe_get_log_stride_size(mdev, params);
mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
}
u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
struct mlx5e_params *params)
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk)
{
u16 linear_rq_headroom = params->xdp_prog ?
XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
bool is_linear_skb;
bool is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
mlx5e_rx_is_linear_skb(params, xsk) :
mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
linear_rq_headroom += NET_IP_ALIGN;
is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
mlx5e_rx_is_linear_skb(params) :
mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
return is_linear_skb ? linear_rq_headroom : 0;
return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
}

118
drivers/net/ethernet/mellanox/mlx5/core/en/params.h
View File

@ -6,17 +6,119 @@
#include "en.h"
u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params);
u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params);
bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params);
struct mlx5e_xsk_param {
u16 headroom;
u16 chunk_size;
};
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
struct mlx5_wq_param wq;
struct mlx5e_rq_frags_info frags_info;
};
struct mlx5e_sq_param {
u32 sqc[MLX5_ST_SZ_DW(sqc)];
struct mlx5_wq_param wq;
bool is_mpw;
};
struct mlx5e_cq_param {
u32 cqc[MLX5_ST_SZ_DW(cqc)];
struct mlx5_wq_param wq;
u16 eq_ix;
u8 cq_period_mode;
};
struct mlx5e_channel_param {
struct mlx5e_rq_param rq;
struct mlx5e_sq_param sq;
struct mlx5e_sq_param xdp_sq;
struct mlx5e_sq_param icosq;
struct mlx5e_cq_param rx_cq;
struct mlx5e_cq_param tx_cq;
struct mlx5e_cq_param icosq_cq;
};
static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params,
u16 qid,
enum mlx5e_rq_group group,
u16 *ix)
{
int nch = params->num_channels;
int ch = qid - nch * group;
if (ch < 0 || ch >= nch)
return false;
*ix = ch;
return true;
}
static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params,
u16 qid,
u16 *ix,
enum mlx5e_rq_group *group)
{
u16 nch = params->num_channels;
*ix = qid % nch;
*group = qid / nch;
}
static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid)
{
return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS;
}
/* Parameter calculations */
u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params);
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
struct mlx5e_params *params);
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk);
/* Build queue parameters */
void mlx5e_build_rq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
struct mlx5e_rq_param *param);
void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
struct mlx5e_sq_param *param);
void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
struct mlx5e_cq_param *param);
void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_cq_param *param);
void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
u8 log_wq_size,
struct mlx5e_cq_param *param);
void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
u8 log_wq_size,
struct mlx5e_sq_param *param);
void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_sq_param *param);
#endif /* __MLX5_EN_PARAMS_H__ */

237
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
View File

@ -31,11 +31,13 @@
*/
#include <linux/bpf_trace.h>
#include <net/xdp_sock.h>
#include "en/xdp.h"
#include "en/params.h"
int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
{
int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
int hr = mlx5e_get_linear_rq_headroom(params, xsk);
/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
* The condition checked in mlx5e_rx_is_linear_skb is:
@ -54,25 +56,70 @@ int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
}
static inline bool
mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
struct xdp_buff *xdp)
mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
struct mlx5e_dma_info *di, struct xdp_buff *xdp)
{
struct mlx5e_xdp_xmit_data xdptxd;
struct mlx5e_xdp_info xdpi;
struct xdp_frame *xdpf;
dma_addr_t dma_addr;
xdpi.xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpi.xdpf))
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return false;
xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf);
dma_sync_single_for_device(sq->pdev, xdpi.dma_addr,
xdpi.xdpf->len, PCI_DMA_TODEVICE);
xdpi.di = *di;
return sq->xmit_xdp_frame(sq, &xdpi);
xdptxd.data = xdpf->data;
xdptxd.len = xdpf->len;
if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) {
/* The xdp_buff was in the UMEM and was copied into a newly
* allocated page. The UMEM page was returned via the ZCA, and
* this new page has to be mapped at this point and has to be
* unmapped and returned via xdp_return_frame on completion.
*/
/* Prevent double recycling of the UMEM page. Even in case this
* function returns false, the xdp_buff shouldn't be recycled,
* as it was already done in xdp_convert_zc_to_xdp_frame.
*/
__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME;
dma_addr = dma_map_single(sq->pdev, xdptxd.data, xdptxd.len,
DMA_TO_DEVICE);
if (dma_mapping_error(sq->pdev, dma_addr)) {
xdp_return_frame(xdpf);
return false;
}
xdptxd.dma_addr = dma_addr;
xdpi.frame.xdpf = xdpf;
xdpi.frame.dma_addr = dma_addr;
} else {
/* Driver assumes that convert_to_xdp_frame returns an xdp_frame
* that points to the same memory region as the original
* xdp_buff. It allows to map the memory only once and to use
* the DMA_BIDIRECTIONAL mode.
*/
xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE;
dma_addr = di->addr + (xdpf->data - (void *)xdpf);
dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len,
DMA_TO_DEVICE);
xdptxd.dma_addr = dma_addr;
xdpi.page.rq = rq;
xdpi.page.di = *di;
}
return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0);
}
/* returns true if packet was consumed by xdp */
bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
void *va, u16 *rx_headroom, u32 *len)
void *va, u16 *rx_headroom, u32 *len, bool xsk)
{
struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
struct xdp_buff xdp;
@ -86,16 +133,20 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + *len;
xdp.data_hard_start = va;
if (xsk)
xdp.handle = di->xsk.handle;
xdp.rxq = &rq->xdp_rxq;
act = bpf_prog_run_xdp(prog, &xdp);
if (xsk)
xdp.handle += xdp.data - xdp.data_hard_start;
switch (act) {
case XDP_PASS:
*rx_headroom = xdp.data - xdp.data_hard_start;
*len = xdp.data_end - xdp.data;
return false;
case XDP_TX:
if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp)))
if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, &xdp)))
goto xdp_abort;
__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
return true;
@ -106,7 +157,8 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
goto xdp_abort;
__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
__set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
mlx5e_page_dma_unmap(rq, di);
if (!xsk)
mlx5e_page_dma_unmap(rq, di);
rq->stats->xdp_redirect++;
return true;
default:
@ -160,7 +212,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
stats->mpwqe++;
}
static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
{
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
@ -183,32 +235,55 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
session->wqe = NULL; /* Close session */
}
static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_info *xdpi)
enum {
MLX5E_XDP_CHECK_OK = 1,
MLX5E_XDP_CHECK_START_MPWQE = 2,
};
static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
{
struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
struct mlx5e_xdpsq_stats *stats = sq->stats;
struct xdp_frame *xdpf = xdpi->xdpf;
if (unlikely(sq->hw_mtu < xdpf->len)) {
stats->err++;
return false;
}
if (unlikely(!session->wqe)) {
if (unlikely(!sq->mpwqe.wqe)) {
if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
MLX5_SEND_WQE_MAX_WQEBBS))) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
stats->full++;
return false;
sq->stats->full++;
return -EBUSY;
}
return MLX5E_XDP_CHECK_START_MPWQE;
}
return MLX5E_XDP_CHECK_OK;
}
static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_xmit_data *xdptxd,
struct mlx5e_xdp_info *xdpi,
int check_result)
{
struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
struct mlx5e_xdpsq_stats *stats = sq->stats;
if (unlikely(xdptxd->len > sq->hw_mtu)) {
stats->err++;
return false;
}
if (!check_result)
check_result = mlx5e_xmit_xdp_frame_check_mpwqe(sq);
if (unlikely(check_result < 0))
return false;
if (check_result == MLX5E_XDP_CHECK_START_MPWQE) {
/* Start the session when nothing can fail, so it's guaranteed
* that if there is an active session, it has at least one dseg,
* and it's safe to complete it at any time.
*/
mlx5e_xdp_mpwqe_session_start(sq);
}
mlx5e_xdp_mpwqe_add_dseg(sq, xdpi, stats);
mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
if (unlikely(session->complete ||
session->ds_count == session->max_ds_count))
@ -219,7 +294,22 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
return true;
}
static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
{
if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
sq->stats->full++;
return -EBUSY;
}
return MLX5E_XDP_CHECK_OK;
}
static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_xmit_data *xdptxd,
struct mlx5e_xdp_info *xdpi,
int check_result)
{
struct mlx5_wq_cyc *wq = &sq->wq;
u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@ -229,9 +319,8 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
struct mlx5_wqe_data_seg *dseg = wqe->data;
struct xdp_frame *xdpf = xdpi->xdpf;
dma_addr_t dma_addr = xdpi->dma_addr;
unsigned int dma_len = xdpf->len;
dma_addr_t dma_addr = xdptxd->dma_addr;
u32 dma_len = xdptxd->len;
struct mlx5e_xdpsq_stats *stats = sq->stats;
@ -242,18 +331,16 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
return false;
}
if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
stats->full++;
if (!check_result)
check_result = mlx5e_xmit_xdp_frame_check(sq);
if (unlikely(check_result < 0))
return false;
}
cseg->fm_ce_se = 0;
/* copy the inline part if required */
if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE);
memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE);
eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
dma_len -= MLX5E_XDP_MIN_INLINE;
dma_addr += MLX5E_XDP_MIN_INLINE;
@ -277,7 +364,7 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_wqe_info *wi,
struct mlx5e_rq *rq,
u32 *xsk_frames,
bool recycle)
{
struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
@ -286,22 +373,32 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
for (i = 0; i < wi->num_pkts; i++) {
struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
if (rq) {
/* XDP_TX */
mlx5e_page_release(rq, &xdpi.di, recycle);
} else {
/* XDP_REDIRECT */
dma_unmap_single(sq->pdev, xdpi.dma_addr,
xdpi.xdpf->len, DMA_TO_DEVICE);
xdp_return_frame(xdpi.xdpf);
switch (xdpi.mode) {
case MLX5E_XDP_XMIT_MODE_FRAME:
/* XDP_TX from the XSK RQ and XDP_REDIRECT */
dma_unmap_single(sq->pdev, xdpi.frame.dma_addr,
xdpi.frame.xdpf->len, DMA_TO_DEVICE);
xdp_return_frame(xdpi.frame.xdpf);
break;
case MLX5E_XDP_XMIT_MODE_PAGE:
/* XDP_TX from the regular RQ */
mlx5e_page_release_dynamic(xdpi.page.rq, &xdpi.page.di, recycle);
break;
case MLX5E_XDP_XMIT_MODE_XSK:
/* AF_XDP send */
(*xsk_frames)++;
break;
default:
WARN_ON_ONCE(true);
}
}
}
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
{
struct mlx5e_xdpsq *sq;
struct mlx5_cqe64 *cqe;
u32 xsk_frames = 0;
u16 sqcc;
int i;
@ -343,10 +440,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
sqcc += wi->num_wqebbs;
mlx5e_free_xdpsq_desc(sq, wi, rq, true);
mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true);
} while (!last_wqe);
} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
if (xsk_frames)
xsk_umem_complete_tx(sq->umem, xsk_frames);
sq->stats->cqes += i;
mlx5_cqwq_update_db_record(&cq->wq);
@ -358,8 +458,10 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
return (i == MLX5E_TX_CQ_POLL_BUDGET);
}
void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
{
u32 xsk_frames = 0;
while (sq->cc != sq->pc) {
struct mlx5e_xdp_wqe_info *wi;
u16 ci;
@ -369,8 +471,11 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
sq->cc += wi->num_wqebbs;
mlx5e_free_xdpsq_desc(sq, wi, rq, false);
mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false);
}
if (xsk_frames)
xsk_umem_complete_tx(sq->umem, xsk_frames);
}
int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
@ -398,21 +503,27 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
struct mlx5e_xdp_xmit_data xdptxd;
struct mlx5e_xdp_info xdpi;
xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
xdptxd.data = xdpf->data;
xdptxd.len = xdpf->len;
xdptxd.dma_addr = dma_map_single(sq->pdev, xdptxd.data,
xdptxd.len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(sq->pdev, xdptxd.dma_addr))) {
xdp_return_frame_rx_napi(xdpf);
drops++;
continue;
}
xdpi.xdpf = xdpf;
xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME;
xdpi.frame.xdpf = xdpf;
xdpi.frame.dma_addr = xdptxd.dma_addr;
if (unlikely(!sq->xmit_xdp_frame(sq, &xdpi))) {
dma_unmap_single(sq->pdev, xdpi.dma_addr,
xdpf->len, DMA_TO_DEVICE);
if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0))) {
dma_unmap_single(sq->pdev, xdptxd.dma_addr,
xdptxd.len, DMA_TO_DEVICE);
xdp_return_frame_rx_napi(xdpf);
drops++;
}
@ -429,7 +540,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
{
struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
struct mlx5e_xdpsq *xdpsq = rq->xdpsq;
if (xdpsq->mpwqe.wqe)
mlx5e_xdp_mpwqe_complete(xdpsq);
@ -444,6 +555,8 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw)
{
sq->xmit_xdp_frame_check = is_mpw ?
mlx5e_xmit_xdp_frame_check_mpwqe : mlx5e_xmit_xdp_frame_check;
sq->xmit_xdp_frame = is_mpw ?
mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame;
}

36
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
View File

@ -39,11 +39,13 @@
(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
struct mlx5e_xsk_param;
int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
void *va, u16 *rx_headroom, u32 *len);
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq);
void *va, u16 *rx_headroom, u32 *len, bool xsk);
void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq);
bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw);
void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
@ -66,6 +68,21 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
}
static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv)
{
set_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
}
static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv)
{
clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
}
static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv)
{
return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
}
static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
{
if (sq->doorbell_cseg) {
@ -97,15 +114,14 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
}
static inline void
mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi,
mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_xmit_data *xdptxd,
struct mlx5e_xdpsq_stats *stats)
{
struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
dma_addr_t dma_addr = xdpi->dma_addr;
struct xdp_frame *xdpf = xdpi->xdpf;
struct mlx5_wqe_data_seg *dseg =
(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
u16 dma_len = xdpf->len;
u32 dma_len = xdptxd->len;
session->pkt_count++;
@ -124,7 +140,7 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi,
}
inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
memcpy(inline_dseg->data, xdpf->data, dma_len);
memcpy(inline_dseg->data, xdptxd->data, dma_len);
session->ds_count += ds_cnt;
stats->inlnw++;
@ -132,7 +148,7 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi,
}
no_inline:
dseg->addr = cpu_to_be64(dma_addr);
dseg->addr = cpu_to_be64(xdptxd->dma_addr);
dseg->byte_count = cpu_to_be32(dma_len);
dseg->lkey = sq->mkey_be;
session->ds_count++;

1
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile Normal file
View File

@ -0,0 +1 @@
subdir-ccflags-y += -I$(src)/../..

192
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c Normal file
View File

@ -0,0 +1,192 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */
#include "rx.h"
#include "en/xdp.h"
#include <net/xdp_sock.h>
/* RX data path */
bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count)
{
/* Check in advance that we have enough frames, instead of allocating
* one-by-one, failing and moving frames to the Reuse Ring.
*/
return xsk_umem_has_addrs_rq(rq->umem, count);
}
int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
struct xdp_umem *umem = rq->umem;
u64 handle;
if (!xsk_umem_peek_addr_rq(umem, &handle))
return -ENOMEM;
dma_info->xsk.handle = handle + rq->buff.umem_headroom;
dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle);
/* No need to add headroom to the DMA address. In striding RQ case, we
* just provide pages for UMR, and headroom is counted at the setup
* stage when creating a WQE. In non-striding RQ case, headroom is
* accounted in mlx5e_alloc_rx_wqe.
*/
dma_info->addr = xdp_umem_get_dma(umem, handle);
xsk_umem_discard_addr_rq(umem);
dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE,
DMA_BIDIRECTIONAL);
return 0;
}
static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle)
{
xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask);
}
/* XSKRQ uses pages from UMEM, they must not be released. They are returned to
* the userspace if possible, and if not, this function is called to reuse them
* in the driver.
*/
void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle);
}
/* Return a frame back to the hardware to fill in again. It is used by XDP when
* the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP.
*/
void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
{
struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca);
mlx5e_xsk_recycle_frame(rq, handle);
}
static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
u32 cqe_bcnt)
{
struct sk_buff *skb;
skb = napi_alloc_skb(rq->cq.napi, cqe_bcnt);
if (unlikely(!skb)) {
rq->stats->buff_alloc_err++;
return NULL;
}
skb_put_data(skb, data, cqe_bcnt);
return skb;
}
struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
struct mlx5e_mpw_info *wi,
u16 cqe_bcnt,
u32 head_offset,
u32 page_idx)
{
struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
u32 cqe_bcnt32 = cqe_bcnt;
void *va, *data;
u32 frag_size;
bool consumed;
/* Check packet size. Note LRO doesn't use linear SKB */
if (unlikely(cqe_bcnt > rq->hw_mtu)) {
rq->stats->oversize_pkts_sw_drop++;
return NULL;
}
/* head_offset is not used in this function, because di->xsk.data and
* di->addr point directly to the necessary place. Furthermore, in the
* current implementation, one page = one packet = one frame, so
* head_offset should always be 0.
*/
WARN_ON_ONCE(head_offset);
va = di->xsk.data;
data = va + rx_headroom;
frag_size = rq->buff.headroom + cqe_bcnt32;
dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
prefetch(data);
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true);
rcu_read_unlock();
/* Possible flows:
* - XDP_REDIRECT to XSKMAP:
* The page is owned by the userspace from now.
* - XDP_TX and other XDP_REDIRECTs:
* The page was returned by ZCA and recycled.
* - XDP_DROP:
* Recycle the page.
* - XDP_PASS:
* Allocate an SKB, copy the data and recycle the page.
*
* Pages to be recycled go to the Reuse Ring on MPWQE deallocation. Its
* size is the same as the Driver RX Ring's size, and pages for WQEs are
* allocated first from the Reuse Ring, so it has enough space.
*/
if (likely(consumed)) {
if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
return NULL; /* page/packet was consumed by XDP */
}
/* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the
* frame. On SKB allocation failure, NULL is returned.
*/
return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32);
}
struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
struct mlx5e_wqe_frag_info *wi,
u32 cqe_bcnt)
{
struct mlx5e_dma_info *di = wi->di;
u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
void *va, *data;
bool consumed;
u32 frag_size;
/* wi->offset is not used in this function, because di->xsk.data and
* di->addr point directly to the necessary place. Furthermore, in the
* current implementation, one page = one packet = one frame, so
* wi->offset should always be 0.
*/
WARN_ON_ONCE(wi->offset);
va = di->xsk.data;
data = va + rx_headroom;
frag_size = rq->buff.headroom + cqe_bcnt;
dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
prefetch(data);
if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
rq->stats->wqe_err++;
return NULL;
}
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true);
rcu_read_unlock();
if (likely(consumed))
return NULL; /* page/packet was consumed by XDP */
/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
* will be handled by mlx5e_put_rx_frag.
* On SKB allocation failure, NULL is returned.
*/
return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt);
}

27
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h Normal file
View File

@ -0,0 +1,27 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/* Copyright (c) 2019 Mellanox Technologies. */
#ifndef __MLX5_EN_XSK_RX_H__
#define __MLX5_EN_XSK_RX_H__
#include "en.h"
/* RX data path */
bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count);
int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info);
void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info);
void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle);
struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
struct mlx5e_mpw_info *wi,
u16 cqe_bcnt,
u32 head_offset,
u32 page_idx);
struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
struct mlx5e_wqe_frag_info *wi,
u32 cqe_bcnt);
#endif /* __MLX5_EN_XSK_RX_H__ */

223
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c Normal file
View File

@ -0,0 +1,223 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */
#include "setup.h"
#include "en/params.h"
bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
struct mlx5_core_dev *mdev)
{
/* AF_XDP doesn't support frames larger than PAGE_SIZE, and the current
* mlx5e XDP implementation doesn't support multiple packets per page.
*/
if (xsk->chunk_size != PAGE_SIZE)
return false;
/* Current MTU and XSK headroom don't allow packets to fit the frames. */
if (mlx5e_rx_get_linear_frag_sz(params, xsk) > xsk->chunk_size)
return false;
/* frag_sz is different for regular and XSK RQs, so ensure that linear
* SKB mode is possible.
*/
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
return mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
default: /* MLX5_WQ_TYPE_CYCLIC */
return mlx5e_rx_is_linear_skb(params, xsk);
}
}
static void mlx5e_build_xskicosq_param(struct mlx5e_priv *priv,
u8 log_wq_size,
struct mlx5e_sq_param *param)
{
void *sqc = param->sqc;
void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
mlx5e_build_sq_param_common(priv, param);
MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
}
static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
struct mlx5e_channel_param *cparam)
{
const u8 xskicosq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
mlx5e_build_rq_param(priv, params, xsk, &cparam->rq);
mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
mlx5e_build_xskicosq_param(priv, xskicosq_size, &cparam->icosq);
mlx5e_build_rx_cq_param(priv, params, xsk, &cparam->rx_cq);
mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
mlx5e_build_ico_cq_param(priv, xskicosq_size, &cparam->icosq_cq);
}
int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
struct mlx5e_channel *c)
{
struct mlx5e_channel_param cparam = {};
struct net_dim_cq_moder icocq_moder = {};
int err;
if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev))
return -EINVAL;
mlx5e_build_xsk_cparam(priv, params, xsk, &cparam);
err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam.rx_cq, &c->xskrq.cq);
if (unlikely(err))
return err;
err = mlx5e_open_rq(c, params, &cparam.rq, xsk, umem, &c->xskrq);
if (unlikely(err))
goto err_close_rx_cq;
err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam.tx_cq, &c->xsksq.cq);
if (unlikely(err))
goto err_close_rq;
/* Create a separate SQ, so that when the UMEM is disabled, we could
* close this SQ safely and stop receiving CQEs. In other case, e.g., if
* the XDPSQ was used instead, we might run into trouble when the UMEM
* is disabled and then reenabled, but the SQ continues receiving CQEs
* from the old UMEM.
*/
err = mlx5e_open_xdpsq(c, params, &cparam.xdp_sq, umem, &c->xsksq, true);
if (unlikely(err))
goto err_close_tx_cq;
err = mlx5e_open_cq(c, icocq_moder, &cparam.icosq_cq, &c->xskicosq.cq);
if (unlikely(err))
goto err_close_sq;
/* Create a dedicated SQ for posting NOPs whenever we need an IRQ to be
* triggered and NAPI to be called on the correct CPU.
*/
err = mlx5e_open_icosq(c, params, &cparam.icosq, &c->xskicosq);
if (unlikely(err))
goto err_close_icocq;
spin_lock_init(&c->xskicosq_lock);
set_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
return 0;
err_close_icocq:
mlx5e_close_cq(&c->xskicosq.cq);
err_close_sq:
mlx5e_close_xdpsq(&c->xsksq);
err_close_tx_cq:
mlx5e_close_cq(&c->xsksq.cq);
err_close_rq:
mlx5e_close_rq(&c->xskrq);
err_close_rx_cq:
mlx5e_close_cq(&c->xskrq.cq);
return err;
}
void mlx5e_close_xsk(struct mlx5e_channel *c)
{
clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
napi_synchronize(&c->napi);
mlx5e_close_rq(&c->xskrq);
mlx5e_close_cq(&c->xskrq.cq);
mlx5e_close_icosq(&c->xskicosq);
mlx5e_close_cq(&c->xskicosq.cq);
mlx5e_close_xdpsq(&c->xsksq);
mlx5e_close_cq(&c->xsksq.cq);
}
void mlx5e_activate_xsk(struct mlx5e_channel *c)
{
set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
/* TX queue is created active. */
mlx5e_trigger_irq(&c->xskicosq);
}
void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
{
mlx5e_deactivate_rq(&c->xskrq);
/* TX queue is disabled on close. */
}
static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn)
{
struct mlx5e_redirect_rqt_param direct_rrp = {
.is_rss = false,
{
.rqn = rqn,
},
};
u32 rqtn = priv->xsk_tir[ix].rqt.rqtn;
return mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
}
int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c)
{
return mlx5e_redirect_xsk_rqt(priv, c->ix, c->xskrq.rqn);
}
int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix)
{
return mlx5e_redirect_xsk_rqt(priv, ix, priv->drop_rq.rqn);
}
int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
{
int err, i;
if (!priv->xsk.refcnt)
return 0;
for (i = 0; i < chs->num; i++) {
struct mlx5e_channel *c = chs->c[i];
if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
continue;
err = mlx5e_xsk_redirect_rqt_to_channel(priv, c);
if (unlikely(err))
goto err_stop;
}
return 0;
err_stop:
for (i--; i >= 0; i--) {
if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
continue;
mlx5e_xsk_redirect_rqt_to_drop(priv, i);
}
return err;
}
void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
{
int i;
if (!priv->xsk.refcnt)
return;
for (i = 0; i < chs->num; i++) {
if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
continue;
mlx5e_xsk_redirect_rqt_to_drop(priv, i);
}
}

25
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h Normal file
View File

@ -0,0 +1,25 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/* Copyright (c) 2019 Mellanox Technologies. */
#ifndef __MLX5_EN_XSK_SETUP_H__
#define __MLX5_EN_XSK_SETUP_H__
#include "en.h"
struct mlx5e_xsk_param;
bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
struct mlx5_core_dev *mdev);
int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
struct mlx5e_channel *c);
void mlx5e_close_xsk(struct mlx5e_channel *c);
void mlx5e_activate_xsk(struct mlx5e_channel *c);
void mlx5e_deactivate_xsk(struct mlx5e_channel *c);
int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c);
int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix);
int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
#endif /* __MLX5_EN_XSK_SETUP_H__ */

111
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c Normal file
View File

@ -0,0 +1,111 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */
#include "tx.h"
#include "umem.h"
#include "en/xdp.h"
#include "en/params.h"
#include <net/xdp_sock.h>
int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_params *params = &priv->channels.params;
struct mlx5e_channel *c;
u16 ix;
if (unlikely(!mlx5e_xdp_is_open(priv)))
return -ENETDOWN;
if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
return -EINVAL;
c = priv->channels.c[ix];
if (unlikely(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)))
return -ENXIO;
if (!napi_if_scheduled_mark_missed(&c->napi)) {
spin_lock(&c->xskicosq_lock);
mlx5e_trigger_irq(&c->xskicosq);
spin_unlock(&c->xskicosq_lock);
}
return 0;
}
/* When TX fails (because of the size of the packet), we need to get completions
* in order, so post a NOP to get a CQE. Since AF_XDP doesn't distinguish
* between successful TX and errors, handling in mlx5e_poll_xdpsq_cq is the
* same.
*/
static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
struct mlx5e_xdp_info *xdpi)
{
u16 pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
struct mlx5e_xdp_wqe_info *wi = &sq->db.wqe_info[pi];
struct mlx5e_tx_wqe *nopwqe;
wi->num_wqebbs = 1;
wi->num_pkts = 1;
nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
sq->doorbell_cseg = &nopwqe->ctrl;
}
bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
{
struct xdp_umem *umem = sq->umem;
struct mlx5e_xdp_info xdpi;
struct mlx5e_xdp_xmit_data xdptxd;
bool work_done = true;
bool flush = false;
xdpi.mode = MLX5E_XDP_XMIT_MODE_XSK;
for (; budget; budget--) {
int check_result = sq->xmit_xdp_frame_check(sq);
struct xdp_desc desc;
if (unlikely(check_result < 0)) {
work_done = false;
break;
}
if (!xsk_umem_consume_tx(umem, &desc)) {
/* TX will get stuck until something wakes it up by
* triggering NAPI. Currently it's expected that the
* application calls sendto() if there are consumed, but
* not completed frames.
*/
break;
}
xdptxd.dma_addr = xdp_umem_get_dma(umem, desc.addr);
xdptxd.data = xdp_umem_get_data(umem, desc.addr);
xdptxd.len = desc.len;
dma_sync_single_for_device(sq->pdev, xdptxd.dma_addr,
xdptxd.len, DMA_BIDIRECTIONAL);
if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) {
if (sq->mpwqe.wqe)
mlx5e_xdp_mpwqe_complete(sq);
mlx5e_xsk_tx_post_err(sq, &xdpi);
}
flush = true;
}
if (flush) {
if (sq->mpwqe.wqe)
mlx5e_xdp_mpwqe_complete(sq);
mlx5e_xmit_xdp_doorbell(sq);
xsk_umem_consume_tx_done(umem);
}
return !(budget && work_done);
}

15
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h Normal file
View File

@ -0,0 +1,15 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/* Copyright (c) 2019 Mellanox Technologies. */
#ifndef __MLX5_EN_XSK_TX_H__
#define __MLX5_EN_XSK_TX_H__
#include "en.h"
/* TX data path */
int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid);
bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget);
#endif /* __MLX5_EN_XSK_TX_H__ */

267
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c Normal file
View File

@ -0,0 +1,267 @@
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */
#include <net/xdp_sock.h>
#include "umem.h"
#include "setup.h"
#include "en/params.h"
static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv,
struct xdp_umem *umem)
{
struct device *dev = priv->mdev->device;
u32 i;
for (i = 0; i < umem->npgs; i++) {
dma_addr_t dma = dma_map_page(dev, umem->pgs[i], 0, PAGE_SIZE,
DMA_BIDIRECTIONAL);
if (unlikely(dma_mapping_error(dev, dma)))
goto err_unmap;
umem->pages[i].dma = dma;
}
return 0;
err_unmap:
while (i--) {
dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
DMA_BIDIRECTIONAL);
umem->pages[i].dma = 0;
}
return -ENOMEM;
}
static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv,
struct xdp_umem *umem)
{
struct device *dev = priv->mdev->device;
u32 i;
for (i = 0; i < umem->npgs; i++) {
dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
DMA_BIDIRECTIONAL);
umem->pages[i].dma = 0;
}
}
static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk)
{
if (!xsk->umems) {
xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS,
sizeof(*xsk->umems), GFP_KERNEL);
if (unlikely(!xsk->umems))
return -ENOMEM;
}
xsk->refcnt++;
xsk->ever_used = true;
return 0;
}
static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk)
{
if (!--xsk->refcnt) {
kfree(xsk->umems);
xsk->umems = NULL;
}
}
static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix)
{
int err;
err = mlx5e_xsk_get_umems(xsk);
if (unlikely(err))
return err;
xsk->umems[ix] = umem;
return 0;
}
static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix)
{
xsk->umems[ix] = NULL;
mlx5e_xsk_put_umems(xsk);
}
static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem)
{
return umem->headroom <= 0xffff && umem->chunk_size_nohr <= 0xffff;
}
void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk)
{
xsk->headroom = umem->headroom;
xsk->chunk_size = umem->chunk_size_nohr + umem->headroom;
}
static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
struct xdp_umem *umem, u16 ix)
{
struct mlx5e_params *params = &priv->channels.params;
struct mlx5e_xsk_param xsk;
struct mlx5e_channel *c;
int err;
if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix)))
return -EBUSY;
if (unlikely(!mlx5e_xsk_is_umem_sane(umem)))
return -EINVAL;
err = mlx5e_xsk_map_umem(priv, umem);
if (unlikely(err))
return err;
err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix);
if (unlikely(err))
goto err_unmap_umem;
mlx5e_build_xsk_param(umem, &xsk);
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
/* XSK objects will be created on open. */
goto validate_closed;
}
if (!params->xdp_prog) {
/* XSK objects will be created when an XDP program is set,
* and the channels are reopened.
*/
goto validate_closed;
}
c = priv->channels.c[ix];
err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
if (unlikely(err))
goto err_remove_umem;
mlx5e_activate_xsk(c);
/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
* any Fill Ring entries at the setup stage.
*/
err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]);
if (unlikely(err))
goto err_deactivate;
return 0;
err_deactivate:
mlx5e_deactivate_xsk(c);
mlx5e_close_xsk(c);
err_remove_umem:
mlx5e_xsk_remove_umem(&priv->xsk, ix);
err_unmap_umem:
mlx5e_xsk_unmap_umem(priv, umem);
return err;
validate_closed:
/* Check the configuration in advance, rather than fail at a later stage
* (in mlx5e_xdp_set or on open) and end up with no channels.
*/
if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) {
err = -EINVAL;
goto err_remove_umem;
}
return 0;
}
static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
{
struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params,
&priv->xsk, ix);
struct mlx5e_channel *c;
if (unlikely(!umem))
return -EINVAL;
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
goto remove_umem;
/* XSK RQ and SQ are only created if XDP program is set. */
if (!priv->channels.params.xdp_prog)
goto remove_umem;
c = priv->channels.c[ix];
mlx5e_xsk_redirect_rqt_to_drop(priv, ix);
mlx5e_deactivate_xsk(c);
mlx5e_close_xsk(c);
remove_umem:
mlx5e_xsk_remove_umem(&priv->xsk, ix);
mlx5e_xsk_unmap_umem(priv, umem);
return 0;
}
static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem,
u16 ix)
{
int err;
mutex_lock(&priv->state_lock);
err = mlx5e_xsk_enable_locked(priv, umem, ix);
mutex_unlock(&priv->state_lock);
return err;
}
static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix)
{
int err;
mutex_lock(&priv->state_lock);
err = mlx5e_xsk_disable_locked(priv, ix);
mutex_unlock(&priv->state_lock);
return err;
}
int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid)
{
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_params *params = &priv->channels.params;
u16 ix;
if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
return -EINVAL;
return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) :
mlx5e_xsk_disable_umem(priv, ix);
}
int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries)
{
struct xdp_umem_fq_reuse *reuseq;
reuseq = xsk_reuseq_prepare(nentries);
if (unlikely(!reuseq))
return -ENOMEM;
xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
return 0;
}
u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk)
{
u16 res = xsk->refcnt ? params->num_channels : 0;
while (res) {
if (mlx5e_xsk_get_umem(params, xsk, res - 1))
break;
--res;
}
return res;
}

31
drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h Normal file
View File

@ -0,0 +1,31 @@
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
/* Copyright (c) 2019 Mellanox Technologies. */
#ifndef __MLX5_EN_XSK_UMEM_H__
#define __MLX5_EN_XSK_UMEM_H__
#include "en.h"
static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params,
struct mlx5e_xsk *xsk, u16 ix)
{
if (!xsk || !xsk->umems)
return NULL;
if (unlikely(ix >= params->num_channels))
return NULL;
return xsk->umems[ix];
}
struct mlx5e_xsk_param;
void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk);
/* .ndo_bpf callback. */
int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid);
int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries);
u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk);
#endif /* __MLX5_EN_XSK_UMEM_H__ */

25
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
View File

@ -32,6 +32,7 @@
#include "en.h"
#include "en/port.h"
#include "en/xsk/umem.h"
#include "lib/clock.h"
void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
@ -388,8 +389,17 @@ static int mlx5e_set_ringparam(struct net_device *dev,
void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv,
struct ethtool_channels *ch)
{
mutex_lock(&priv->state_lock);
ch->max_combined = mlx5e_get_netdev_max_channels(priv->netdev);
ch->combined_count = priv->channels.params.num_channels;
if (priv->xsk.refcnt) {
/* The upper half are XSK queues. */
ch->max_combined *= 2;
ch->combined_count *= 2;
}
mutex_unlock(&priv->state_lock);
}
static void mlx5e_get_channels(struct net_device *dev,
@ -403,6 +413,7 @@ static void mlx5e_get_channels(struct net_device *dev,
int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
struct ethtool_channels *ch)
{
struct mlx5e_params *cur_params = &priv->channels.params;
unsigned int count = ch->combined_count;
struct mlx5e_channels new_channels = {};
bool arfs_enabled;
@ -414,16 +425,26 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
return -EINVAL;
}
if (priv->channels.params.num_channels == count)
if (cur_params->num_channels == count)
return 0;
mutex_lock(&priv->state_lock);
/* Don't allow changing the number of channels if there is an active
* XSK, because the numeration of the XSK and regular RQs will change.
*/
if (priv->xsk.refcnt) {
err = -EINVAL;
netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n",
__func__);
goto out;
}
new_channels.params = priv->channels.params;
new_channels.params.num_channels = count;
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
priv->channels.params = new_channels.params;
*cur_params = new_channels.params;
if (!netif_is_rxfh_configured(priv->netdev))
mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
MLX5E_INDIR_RQT_SIZE, count);

18
drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
View File

@ -32,6 +32,8 @@
#include <linux/mlx5/fs.h>
#include "en.h"
#include "en/params.h"
#include "en/xsk/umem.h"
struct mlx5e_ethtool_rule {
struct list_head list;
@ -414,6 +416,14 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
} else {
struct mlx5e_params *params = &priv->channels.params;
enum mlx5e_rq_group group;
struct mlx5e_tir *tir;
u16 ix;
mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group);
tir = group == MLX5E_RQ_GROUP_XSK ? priv->xsk_tir : priv->direct_tir;
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (!dst) {
err = -ENOMEM;
@ -421,7 +431,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
}
dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn;
dst->tir_num = tir[ix].tirn;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
}
@ -600,9 +610,9 @@ static int validate_flow(struct mlx5e_priv *priv,
if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
return -ENOSPC;
if (fs->ring_cookie >= priv->channels.params.num_channels &&
fs->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
if (fs->ring_cookie != RX_CLS_FLOW_DISC)
if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie))
return -EINVAL;
switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
case ETHER_FLOW:

780
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
View File

File diff suppressed because it is too large Load Diff

12
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
View File

@ -1519,7 +1519,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
if (err)
goto err_close_drop_rq;
err = mlx5e_create_direct_rqts(priv);
err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_rqts;
@ -1527,7 +1527,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
if (err)
goto err_destroy_direct_rqts;
err = mlx5e_create_direct_tirs(priv);
err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_tirs;
@ -1544,11 +1544,11 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
err_destroy_ttc_table:
mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
err_destroy_indirect_tirs:
mlx5e_destroy_indirect_tirs(priv, false);
err_destroy_direct_rqts:
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
err_close_drop_rq:
@ -1562,9 +1562,9 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
mlx5_del_flow_rules(rpriv->vport_rx_rule);
mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
mlx5e_destroy_indirect_tirs(priv, false);
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
mlx5e_close_drop_rq(&priv->drop_rq);
}

104
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
View File

@ -47,6 +47,7 @@
#include "en_accel/tls_rxtx.h"
#include "lib/clock.h"
#include "en/xdp.h"
#include "en/xsk/rx.h"
static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
{
@ -235,8 +236,8 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
return true;
}
static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
if (mlx5e_rx_cache_get(rq, dma_info))
return 0;
@ -256,13 +257,23 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
return 0;
}
static inline int mlx5e_page_alloc(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
if (rq->umem)
return mlx5e_xsk_page_alloc_umem(rq, dma_info);
else
return mlx5e_page_alloc_pool(rq, dma_info);
}
void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
{
dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
}
void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
bool recycle)
void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info,
bool recycle)
{
if (likely(recycle)) {
if (mlx5e_rx_cache_put(rq, dma_info))
@ -277,6 +288,20 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
}
}
static inline void mlx5e_page_release(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info,
bool recycle)
{
if (rq->umem)
/* The `recycle` parameter is ignored, and the page is always
* put into the Reuse Ring, because there is no way to return
* the page to the userspace when the interface goes down.
*/
mlx5e_xsk_page_release(rq, dma_info);
else
mlx5e_page_release_dynamic(rq, dma_info, recycle);
}
static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
struct mlx5e_wqe_frag_info *frag)
{
@ -288,7 +313,7 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
* offset) should just use the new one without replenishing again
* by themselves.
*/
err = mlx5e_page_alloc_mapped(rq, frag->di);
err = mlx5e_page_alloc(rq, frag->di);
return err;
}
@ -354,6 +379,13 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
int err;
int i;
if (rq->umem) {
int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired)))
return -ENOMEM;
}
for (i = 0; i < wqe_bulk; i++) {
struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i);
@ -401,11 +433,17 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
static void
mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
{
const bool no_xdp_xmit =
bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
bool no_xdp_xmit;
struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
int i;
/* A common case for AF_XDP. */
if (bitmap_full(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE))
return;
no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap,
MLX5_MPWRQ_PAGES_PER_WQE);
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
mlx5e_page_release(rq, &dma_info[i], recycle);
@ -427,11 +465,6 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n)
mlx5_wq_ll_update_db_record(wq);
}
static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
{
return mlx5_wq_cyc_get_ctr_wrap_cnt(&sq->wq, sq->pc);
}
static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
struct mlx5_wq_cyc *wq,
u16 pi, u16 nnops)
@ -459,6 +492,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
int err;
int i;
if (rq->umem &&
unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) {
err = -ENOMEM;
goto err;
}
pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) {
@ -467,12 +506,10 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
}
umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2))
memcpy(umr_wqe, &rq->mpwqe.umr_wqe,
offsetof(struct mlx5e_umr_wqe, inline_mtts));
memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts));
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
err = mlx5e_page_alloc_mapped(rq, dma_info);
err = mlx5e_page_alloc(rq, dma_info);
if (unlikely(err))
goto err_unmap;
umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
@ -487,6 +524,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->db.ico_wqe[pi].umr.rq = rq;
sq->pc += MLX5E_UMR_WQEBBS;
sq->doorbell_cseg = &umr_wqe->ctrl;
@ -498,6 +536,8 @@ err_unmap:
dma_info--;
mlx5e_page_release(rq, dma_info, true);
}
err:
rq->stats->buff_alloc_err++;
return err;
@ -544,11 +584,10 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
return !!err;
}
static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
struct mlx5_cqe64 *cqe;
u8 completed_umr = 0;
u16 sqcc;
int i;
@ -589,7 +628,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
sqcc += MLX5E_UMR_WQEBBS;
completed_umr++;
wi->umr.rq->mpwqe.umr_completed++;
} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
sqcc++;
} else {
@ -605,24 +644,25 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
sq->cc = sqcc;
mlx5_cqwq_update_db_record(&cq->wq);
if (likely(completed_umr)) {
mlx5e_post_rx_mpwqe(rq, completed_umr);
rq->mpwqe.umr_in_progress -= completed_umr;
}
}
bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
{
struct mlx5e_icosq *sq = &rq->channel->icosq;
struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
u8 umr_completed = rq->mpwqe.umr_completed;
int alloc_err = 0;
u8 missing, i;
u16 head;
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return false;
mlx5e_poll_ico_cq(&sq->cq, rq);
if (umr_completed) {
mlx5e_post_rx_mpwqe(rq, umr_completed);
rq->mpwqe.umr_in_progress -= umr_completed;
rq->mpwqe.umr_completed = 0;
}
missing = mlx5_wq_ll_missing(wq) - rq->mpwqe.umr_in_progress;
@ -636,7 +676,9 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
head = rq->mpwqe.actual_wq_head;
i = missing;
do {
if (unlikely(mlx5e_alloc_rx_mpwqe(rq, head)))
alloc_err = mlx5e_alloc_rx_mpwqe(rq, head);
if (unlikely(alloc_err))
break;
head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
} while (--i);
@ -650,6 +692,12 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk;
rq->mpwqe.actual_wq_head = head;
/* If XSK Fill Ring doesn't have enough frames, busy poll by
* rescheduling the NAPI poll.
*/
if (unlikely(alloc_err == -ENOMEM && rq->umem))
return true;
return false;
}
@ -1018,7 +1066,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
}
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt);
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
rcu_read_unlock();
if (consumed)
return NULL; /* page/packet was consumed by XDP */
@ -1235,7 +1283,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
prefetch(data);
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32);
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false);
rcu_read_unlock();
if (consumed) {
if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))

115
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
View File

@ -104,7 +104,33 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_force_irq) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_bytes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_complete) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary_inner) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_none) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_ecn_mark) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_removed_vlan_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_drop) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_redirect) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_wqe_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_cqes) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_strides) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_oversize_pkts_sw_drop) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_buff_alloc_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_blks) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_pkts) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_congst_umr) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_arfs_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_xmit) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_mpwqe) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_inlnw) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_full) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_cqes) },
};
#define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc)
@ -144,6 +170,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
&priv->channel_stats[i];
struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
struct mlx5e_xdpsq_stats *xsksq_stats = &channel_stats->xsksq;
struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
int j;
@ -186,6 +214,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->ch_poll += ch_stats->poll;
s->ch_arm += ch_stats->arm;
s->ch_aff_change += ch_stats->aff_change;
s->ch_force_irq += ch_stats->force_irq;
s->ch_eq_rearm += ch_stats->eq_rearm;
/* xdp redirect */
s->tx_xdp_xmit += xdpsq_red_stats->xmit;
@ -194,6 +223,32 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->tx_xdp_full += xdpsq_red_stats->full;
s->tx_xdp_err += xdpsq_red_stats->err;
s->tx_xdp_cqes += xdpsq_red_stats->cqes;
/* AF_XDP zero-copy */
s->rx_xsk_packets += xskrq_stats->packets;
s->rx_xsk_bytes += xskrq_stats->bytes;
s->rx_xsk_csum_complete += xskrq_stats->csum_complete;
s->rx_xsk_csum_unnecessary += xskrq_stats->csum_unnecessary;
s->rx_xsk_csum_unnecessary_inner += xskrq_stats->csum_unnecessary_inner;
s->rx_xsk_csum_none += xskrq_stats->csum_none;
s->rx_xsk_ecn_mark += xskrq_stats->ecn_mark;
s->rx_xsk_removed_vlan_packets += xskrq_stats->removed_vlan_packets;
s->rx_xsk_xdp_drop += xskrq_stats->xdp_drop;
s->rx_xsk_xdp_redirect += xskrq_stats->xdp_redirect;
s->rx_xsk_wqe_err += xskrq_stats->wqe_err;
s->rx_xsk_mpwqe_filler_cqes += xskrq_stats->mpwqe_filler_cqes;
s->rx_xsk_mpwqe_filler_strides += xskrq_stats->mpwqe_filler_strides;
s->rx_xsk_oversize_pkts_sw_drop += xskrq_stats->oversize_pkts_sw_drop;
s->rx_xsk_buff_alloc_err += xskrq_stats->buff_alloc_err;
s->rx_xsk_cqe_compress_blks += xskrq_stats->cqe_compress_blks;
s->rx_xsk_cqe_compress_pkts += xskrq_stats->cqe_compress_pkts;
s->rx_xsk_congst_umr += xskrq_stats->congst_umr;
s->rx_xsk_arfs_err += xskrq_stats->arfs_err;
s->tx_xsk_xmit += xsksq_stats->xmit;
s->tx_xsk_mpwqe += xsksq_stats->mpwqe;
s->tx_xsk_inlnw += xsksq_stats->inlnw;
s->tx_xsk_full += xsksq_stats->full;
s->tx_xsk_err += xsksq_stats->err;
s->tx_xsk_cqes += xsksq_stats->cqes;
for (j = 0; j < priv->max_opened_tc; j++) {
struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@ -1266,11 +1321,43 @@ static const struct counter_desc xdpsq_stats_desc[] = {
{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
};
static const struct counter_desc xskrq_stats_desc[] = {
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, packets) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, bytes) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_complete) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_none) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, ecn_mark) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_drop) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_redirect) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, wqe_err) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, congst_umr) },
{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, arfs_err) },
};
static const struct counter_desc xsksq_stats_desc[] = {
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, full) },
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, err) },
{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
};
static const struct counter_desc ch_stats_desc[] = {
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, force_irq) },
{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
};
@ -1278,6 +1365,8 @@ static const struct counter_desc ch_stats_desc[] = {
#define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc)
#define NUM_XDPSQ_STATS ARRAY_SIZE(xdpsq_stats_desc)
#define NUM_RQ_XDPSQ_STATS ARRAY_SIZE(rq_xdpsq_stats_desc)
#define NUM_XSKRQ_STATS ARRAY_SIZE(xskrq_stats_desc)
#define NUM_XSKSQ_STATS ARRAY_SIZE(xsksq_stats_desc)
#define NUM_CH_STATS ARRAY_SIZE(ch_stats_desc)
static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
@ -1288,13 +1377,16 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
(NUM_CH_STATS * max_nch) +
(NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
(NUM_RQ_XDPSQ_STATS * max_nch) +
(NUM_XDPSQ_STATS * max_nch);
(NUM_XDPSQ_STATS * max_nch) +
(NUM_XSKRQ_STATS * max_nch * priv->xsk.ever_used) +
(NUM_XSKSQ_STATS * max_nch * priv->xsk.ever_used);
}
static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
int idx)
{
int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
bool is_xsk = priv->xsk.ever_used;
int i, j, tc;
for (i = 0; i < max_nch; i++)
@ -1306,6 +1398,9 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
for (j = 0; j < NUM_RQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
rq_stats_desc[j].format, i);
for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
xskrq_stats_desc[j].format, i);
for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
rq_xdpsq_stats_desc[j].format, i);
@ -1318,10 +1413,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
sq_stats_desc[j].format,
priv->channel_tc2txq[i][tc]);
for (i = 0; i < max_nch; i++)
for (i = 0; i < max_nch; i++) {
for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
xsksq_stats_desc[j].format, i);
for (j = 0; j < NUM_XDPSQ_STATS; j++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
xdpsq_stats_desc[j].format, i);
}
return idx;
}
@ -1330,6 +1429,7 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
int idx)
{
int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
bool is_xsk = priv->xsk.ever_used;
int i, j, tc;
for (i = 0; i < max_nch; i++)
@ -1343,6 +1443,10 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
data[idx++] =
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
rq_stats_desc, j);
for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
data[idx++] =
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xskrq,
xskrq_stats_desc, j);
for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
data[idx++] =
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
@ -1356,11 +1460,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
sq_stats_desc, j);
for (i = 0; i < max_nch; i++)
for (i = 0; i < max_nch; i++) {
for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
data[idx++] =
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xsksq,
xsksq_stats_desc, j);
for (j = 0; j < NUM_XDPSQ_STATS; j++)
data[idx++] =
MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
xdpsq_stats_desc, j);
}
return idx;
}

30
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
View File

@ -46,6 +46,8 @@
#define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
#define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld)
#define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
#define MLX5E_DECLARE_XSKRQ_STAT(type, fld) "rx%d_xsk_"#fld, offsetof(type, fld)
#define MLX5E_DECLARE_XSKSQ_STAT(type, fld) "tx%d_xsk_"#fld, offsetof(type, fld)
#define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
struct counter_desc {
@ -116,12 +118,39 @@ struct mlx5e_sw_stats {
u64 ch_poll;
u64 ch_arm;
u64 ch_aff_change;
u64 ch_force_irq;
u64 ch_eq_rearm;
#ifdef CONFIG_MLX5_EN_TLS
u64 tx_tls_ooo;
u64 tx_tls_resync_bytes;
#endif
u64 rx_xsk_packets;
u64 rx_xsk_bytes;
u64 rx_xsk_csum_complete;
u64 rx_xsk_csum_unnecessary;
u64 rx_xsk_csum_unnecessary_inner;
u64 rx_xsk_csum_none;
u64 rx_xsk_ecn_mark;
u64 rx_xsk_removed_vlan_packets;
u64 rx_xsk_xdp_drop;
u64 rx_xsk_xdp_redirect;
u64 rx_xsk_wqe_err;
u64 rx_xsk_mpwqe_filler_cqes;
u64 rx_xsk_mpwqe_filler_strides;
u64 rx_xsk_oversize_pkts_sw_drop;
u64 rx_xsk_buff_alloc_err;
u64 rx_xsk_cqe_compress_blks;
u64 rx_xsk_cqe_compress_pkts;
u64 rx_xsk_congst_umr;
u64 rx_xsk_arfs_err;
u64 tx_xsk_xmit;
u64 tx_xsk_mpwqe;
u64 tx_xsk_inlnw;
u64 tx_xsk_full;
u64 tx_xsk_err;
u64 tx_xsk_cqes;
};
struct mlx5e_qcounter_stats {
@ -256,6 +285,7 @@ struct mlx5e_ch_stats {
u64 poll;
u64 arm;
u64 aff_change;
u64 force_irq;
u64 eq_rearm;
};

42
drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
View File

@ -33,6 +33,7 @@
#include <linux/irq.h>
#include "en.h"
#include "en/xdp.h"
#include "en/xsk/tx.h"
static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
{
@ -87,7 +88,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
napi);
struct mlx5e_ch_stats *ch_stats = c->stats;
struct mlx5e_xdpsq *xsksq = &c->xsksq;
struct mlx5e_rq *xskrq = &c->xskrq;
struct mlx5e_rq *rq = &c->rq;
bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
bool aff_change = false;
bool busy_xsk = false;
bool busy = false;
int work_done = 0;
int i;
@ -97,22 +103,38 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
for (i = 0; i < c->num_tc; i++)
busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq, NULL);
busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
if (c->xdp)
busy |= mlx5e_poll_xdpsq_cq(&rq->xdpsq.cq, rq);
busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq);
if (likely(budget)) { /* budget=0 means: don't poll rx rings */
work_done = mlx5e_poll_rx_cq(&rq->cq, budget);
if (xsk_open)
work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget);
if (likely(budget - work_done))
work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done);
busy |= work_done == budget;
}
busy |= c->rq.post_wqes(rq);
mlx5e_poll_ico_cq(&c->icosq.cq);
busy |= rq->post_wqes(rq);
if (xsk_open) {
mlx5e_poll_ico_cq(&c->xskicosq.cq);
busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq);
busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET);
busy_xsk |= xskrq->post_wqes(xskrq);
}
busy |= busy_xsk;
if (busy) {
if (likely(mlx5e_channel_no_affinity_change(c)))
return budget;
ch_stats->aff_change++;
aff_change = true;
if (budget && work_done == budget)
work_done--;
}
@ -133,6 +155,18 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
mlx5e_cq_arm(&c->icosq.cq);
mlx5e_cq_arm(&c->xdpsq.cq);
if (xsk_open) {
mlx5e_handle_rx_dim(xskrq);
mlx5e_cq_arm(&c->xskicosq.cq);
mlx5e_cq_arm(&xsksq->cq);
mlx5e_cq_arm(&xskrq->cq);
}
if (unlikely(aff_change && busy_xsk)) {
mlx5e_trigger_irq(&c->icosq);
ch_stats->force_irq++;
}
return work_done;
}

14
drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
View File

@ -87,7 +87,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
mlx5e_set_netdev_mtu_boundaries(priv);
netdev->mtu = netdev->max_mtu;
mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params,
mlx5e_get_netdev_max_channels(netdev),
netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
@ -365,7 +365,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
if (err)
goto err_close_drop_rq;
err = mlx5e_create_direct_rqts(priv);
err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_rqts;
@ -373,7 +373,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
if (err)
goto err_destroy_direct_rqts;
err = mlx5e_create_direct_tirs(priv);
err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
if (err)
goto err_destroy_indirect_tirs;
@ -384,11 +384,11 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
return 0;
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
err_destroy_indirect_tirs:
mlx5e_destroy_indirect_tirs(priv, true);
err_destroy_direct_rqts:
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
err_close_drop_rq:
@ -401,9 +401,9 @@ err_destroy_q_counters:
static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
{
mlx5i_destroy_flow_steering(priv);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
mlx5e_destroy_indirect_tirs(priv, true);
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
mlx5e_close_drop_rq(&priv->drop_rq);
mlx5e_destroy_q_counters(priv);

5
drivers/net/ethernet/mellanox/mlx5/core/wq.h
View File

@ -134,11 +134,6 @@ static inline void mlx5_wq_cyc_update_db_record(struct mlx5_wq_cyc *wq)
*wq->db = cpu_to_be32(wq->wqe_ctr);
}
static inline u16 mlx5_wq_cyc_get_ctr_wrap_cnt(struct mlx5_wq_cyc *wq, u16 ctr)
{
return ctr >> wq->fbc.log_sz;
}
static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
{
return ctr & wq->fbc.sz_m1;

27
include/net/xdp_sock.h
View File

@ -77,10 +77,11 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
void xsk_flush(struct xdp_sock *xs);
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
/* Used from netdev driver */
bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt);
u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr);
void xsk_umem_discard_addr(struct xdp_umem *umem);
void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len);
bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
void xsk_umem_consume_tx_done(struct xdp_umem *umem);
struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries);
struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
@ -99,6 +100,16 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
}
/* Reuse-queue aware version of FILL queue helpers */
static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
{
struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
if (rq->length >= cnt)
return true;
return xsk_umem_has_addrs(umem, cnt - rq->length);
}
static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
struct xdp_umem_fq_reuse *rq = umem->fq_reuse;
@ -146,6 +157,11 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
return false;
}
static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
{
return false;
}
static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
return NULL;
@ -159,8 +175,8 @@ static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
{
}
static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma,
u32 *len)
static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
struct xdp_desc *desc)
{
return false;
}
@ -200,6 +216,11 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
return 0;
}
static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt)
{
return false;
}
static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr)
{
return NULL;

8
include/uapi/linux/if_xdp.h
View File

@ -46,6 +46,7 @@ struct xdp_mmap_offsets {
#define XDP_UMEM_FILL_RING 5
#define XDP_UMEM_COMPLETION_RING 6
#define XDP_STATISTICS 7
#define XDP_OPTIONS 8
struct xdp_umem_reg {
__u64 addr; /* Start of packet data area */
@ -60,6 +61,13 @@ struct xdp_statistics {
__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
};
struct xdp_options {
__u32 flags;
};
/* Flags for the flags field of struct xdp_options */
#define XDP_OPTIONS_ZEROCOPY (1 << 0)
/* Pgoff for mmaping the rings */
#define XDP_PGOFF_RX_RING 0
#define XDP_PGOFF_TX_RING 0x80000000

36
net/xdp/xsk.c
View File

@ -37,6 +37,12 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
READ_ONCE(xs->umem->fq);
}
bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
{
return xskq_has_addrs(umem->fq, cnt);
}
EXPORT_SYMBOL(xsk_umem_has_addrs);
u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
return xskq_peek_addr(umem->fq, addr);
@ -166,22 +172,18 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem)
}
EXPORT_SYMBOL(xsk_umem_consume_tx_done);
bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len)
bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
{
struct xdp_desc desc;
struct xdp_sock *xs;
rcu_read_lock();
list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
if (!xskq_peek_desc(xs->tx, &desc))
if (!xskq_peek_desc(xs->tx, desc))
continue;
if (xskq_produce_addr_lazy(umem->cq, desc.addr))
if (xskq_produce_addr_lazy(umem->cq, desc->addr))
goto out;
*dma = xdp_umem_get_dma(umem, desc.addr);
*len = desc.len;
xskq_discard_desc(xs->tx);
rcu_read_unlock();
return true;
@ -644,6 +646,26 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
return 0;
}
case XDP_OPTIONS:
{
struct xdp_options opts = {};
if (len < sizeof(opts))
return -EINVAL;
mutex_lock(&xs->mutex);
if (xs->zc)
opts.flags |= XDP_OPTIONS_ZEROCOPY;
mutex_unlock(&xs->mutex);
len = sizeof(opts);
if (copy_to_user(optval, &opts, len))
return -EFAULT;
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
default:
break;
}

14
net/xdp/xsk_queue.h
View File

@ -117,6 +117,20 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
return q->nentries - (producer - q->cons_tail);
}
static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt)
{
u32 entries = q->prod_tail - q->cons_tail;
if (entries >= cnt)
return true;
/* Refresh the local pointer. */
q->prod_tail = READ_ONCE(q->ring->producer);
entries = q->prod_tail - q->cons_tail;
return entries >= cnt;
}
/* UMEM queue */
static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr)

44
samples/bpf/xdpsock_user.c
View File

@ -68,6 +68,7 @@ static int opt_queue;
static int opt_poll;
static int opt_interval = 1;
static u32 opt_xdp_bind_flags;
static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
static __u32 prog_id;
struct xsk_umem_info {
@ -276,6 +277,12 @@ static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
{
struct xsk_umem_info *umem;
struct xsk_umem_config cfg = {
.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
.frame_size = opt_xsk_frame_size,
.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
};
int ret;
umem = calloc(1, sizeof(*umem));
@ -283,7 +290,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
exit_with_error(errno);
ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
NULL);
&cfg);
if (ret)
exit_with_error(-ret);
@ -323,11 +330,9 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
&idx);
if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
exit_with_error(-ret);
for (i = 0;
i < XSK_RING_PROD__DEFAULT_NUM_DESCS *
XSK_UMEM__DEFAULT_FRAME_SIZE;
i += XSK_UMEM__DEFAULT_FRAME_SIZE)
*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = i;
for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
i * opt_xsk_frame_size;
xsk_ring_prod__submit(&xsk->umem->fq,
XSK_RING_PROD__DEFAULT_NUM_DESCS);
@ -346,6 +351,7 @@ static struct option long_options[] = {
{"interval", required_argument, 0, 'n'},
{"zero-copy", no_argument, 0, 'z'},
{"copy", no_argument, 0, 'c'},
{"frame-size", required_argument, 0, 'f'},
{0, 0, 0, 0}
};
@ -365,8 +371,9 @@ static void usage(const char *prog)
" -n, --interval=n Specify statistics update interval (default 1 sec).\n"
" -z, --zero-copy Force zero-copy mode.\n"
" -c, --copy Force copy mode.\n"
" -f, --frame-size=n Set the frame size (must be a power of two, default is %d).\n"
"\n";
fprintf(stderr, str, prog);
fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
exit(EXIT_FAILURE);
}
@ -377,7 +384,7 @@ static void parse_command_line(int argc, char **argv)
opterr = 0;
for (;;) {
c = getopt_long(argc, argv, "Frtli:q:psSNn:cz", long_options,
c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:", long_options,
&option_index);
if (c == -1)
break;
@ -420,6 +427,9 @@ static void parse_command_line(int argc, char **argv)
case 'F':
opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
break;
case 'f':
opt_xsk_frame_size = atoi(optarg);
break;
default:
usage(basename(argv[0]));
}
@ -432,6 +442,11 @@ static void parse_command_line(int argc, char **argv)
usage(basename(argv[0]));
}
if (opt_xsk_frame_size & (opt_xsk_frame_size - 1)) {
fprintf(stderr, "--frame-size=%d is not a power of two\n",
opt_xsk_frame_size);
usage(basename(argv[0]));
}
}
static void kick_tx(struct xsk_socket_info *xsk)
@ -583,8 +598,7 @@ static void tx_only(struct xsk_socket_info *xsk)
for (i = 0; i < BATCH_SIZE; i++) {
xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr
= (frame_nb + i) <<
XSK_UMEM__DEFAULT_FRAME_SHIFT;
= (frame_nb + i) * opt_xsk_frame_size;
xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len =
sizeof(pkt_data) - 1;
}
@ -661,21 +675,19 @@ int main(int argc, char **argv)
}
ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE);
NUM_FRAMES * opt_xsk_frame_size);
if (ret)
exit_with_error(ret);
/* Create sockets... */
umem = xsk_configure_umem(bufs,
NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE);
umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
xsks[num_socks++] = xsk_configure_socket(umem);
if (opt_bench == BENCH_TXONLY) {
int i;
for (i = 0; i < NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE;
i += XSK_UMEM__DEFAULT_FRAME_SIZE)
(void)gen_eth_frame(umem, i);
for (i = 0; i < NUM_FRAMES; i++)
(void)gen_eth_frame(umem, i * opt_xsk_frame_size);
}
signal(SIGINT, int_exit);

8
tools/include/uapi/linux/if_xdp.h
View File

@ -46,6 +46,7 @@ struct xdp_mmap_offsets {
#define XDP_UMEM_FILL_RING 5
#define XDP_UMEM_COMPLETION_RING 6
#define XDP_STATISTICS 7
#define XDP_OPTIONS 8
struct xdp_umem_reg {
__u64 addr; /* Start of packet data area */
@ -60,6 +61,13 @@ struct xdp_statistics {
__u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
};
struct xdp_options {
__u32 flags;
};
/* Flags for the flags field of struct xdp_options */
#define XDP_OPTIONS_ZEROCOPY (1 << 0)
/* Pgoff for mmaping the rings */
#define XDP_PGOFF_RX_RING 0
#define XDP_PGOFF_TX_RING 0x80000000

12
tools/lib/bpf/xsk.c
View File

@ -65,6 +65,7 @@ struct xsk_socket {
int xsks_map_fd;
__u32 queue_id;
char ifname[IFNAMSIZ];
bool zc;
};
struct xsk_nl_info {
@ -480,6 +481,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
void *rx_map = NULL, *tx_map = NULL;
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
struct xdp_options opts;
struct xsk_socket *xsk;
socklen_t optlen;
int err;
@ -597,6 +599,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
}
xsk->prog_fd = -1;
optlen = sizeof(opts);
err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen);
if (err) {
err = -errno;
goto out_mmap_tx;
}
xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY;
if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
err = xsk_setup_xdp_prog(xsk);
if (err)

2
tools/lib/bpf/xsk.h
View File

@ -167,7 +167,7 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
#define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048
#define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048
#define XSK_UMEM__DEFAULT_FRAME_SHIFT 11 /* 2048 bytes */
#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */
#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT)
#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0