@@ -771,12 +771,12 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
* Returns a pointer to xsk_buff_pool structure if there is a buffer pool
* present, NULL otherwise.
*/
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_xsk_pool(struct ice_rx_ring *ring)
{
struct ice_vsi *vsi = ring->vsi;
u16 qid = ring->q_index;
- return ice_get_xp_from_qid(vsi, qid);
+ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
}
/**
@@ -801,7 +801,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
if (!ring)
return;
- ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
}
/**
@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
return err;
}
- ring->xsk_pool = ice_xsk_pool(ring);
+ ice_xsk_pool(ring);
if (ring->xsk_pool) {
xdp_rxq_info_unreg(&ring->xdp_rxq);
@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
return 0;
}
- ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+ ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
if (!ok) {
u16 pf_q = ring->vsi->rxq_map[ring->q_index];
@@ -2946,7 +2946,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
ice_for_each_rxq(vsi, i) {
struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
- if (rx_ring->xsk_pool)
+ if (READ_ONCE(rx_ring->xsk_pool))
napi_schedule(&rx_ring->q_vector->napi);
}
}
@@ -1523,7 +1523,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
ice_for_each_tx_ring(tx_ring, q_vector->tx) {
bool wd;
- if (tx_ring->xsk_pool)
+ if (READ_ONCE(tx_ring->xsk_pool))
wd = ice_xmit_zc(tx_ring);
else if (ice_ring_is_xdp(tx_ring))
wd = true;
@@ -1556,7 +1556,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
* comparison in the irq context instead of many inside the
* ice_clean_rx_irq function and makes the codebase cleaner.
*/
- cleaned = rx_ring->xsk_pool ?
+ cleaned = READ_ONCE(rx_ring->xsk_pool) ?
ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
ice_clean_rx_irq(rx_ring, budget_per_ring);
work_done += cleaned;
@@ -250,6 +250,8 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
ice_qvec_toggle_napi(vsi, q_vector, true);
ice_qvec_ena_irq(vsi, q_vector);
+ /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+ synchronize_net();
netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
netif_carrier_on(vsi->netdev);
clear_bit(ICE_CFG_BUSY, vsi->state);
@@ -469,7 +471,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
*
* Returns true if all allocations were successful, false if any fail.
*/
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count)
{
u32 nb_buffs_extra = 0, nb_buffs = 0;
union ice_32b_rx_flex_desc *rx_desc;
@@ -481,8 +484,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
xdp = ice_xdp_buf(rx_ring, ntu);
if (ntu + count >= rx_ring->count) {
- nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
- rx_desc,
+ nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
rx_ring->count - ntu);
if (nb_buffs_extra != rx_ring->count - ntu) {
ntu += nb_buffs_extra;
@@ -495,7 +497,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
ice_release_rx_desc(rx_ring, 0);
}
- nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+ nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
ntu += nb_buffs;
if (ntu == rx_ring->count)
@@ -518,7 +520,8 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
*
* Returns true if all calls to internal alloc routine succeeded
*/
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count)
{
u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
u16 leftover, i, tail_bumps;
@@ -527,9 +530,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
leftover = count - (tail_bumps * rx_thresh);
for (i = 0; i < tail_bumps; i++)
- if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+ if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
return false;
- return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+ return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
}
/**
@@ -650,7 +653,7 @@ static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
if (xdp_ring->next_to_clean >= cnt)
xdp_ring->next_to_clean -= cnt;
if (xsk_frames)
- xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+ xsk_tx_completed(READ_ONCE(xdp_ring->xsk_pool), xsk_frames);
return completed_frames;
}
@@ -702,7 +705,8 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
dma_addr_t dma;
dma = xsk_buff_xdp_get_dma(xdp);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+ xsk_buff_raw_dma_sync_for_device(READ_ONCE(xdp_ring->xsk_pool),
+ dma, size);
tx_buf->xdp = xdp;
tx_buf->type = ICE_TX_BUF_XSK_TX;
@@ -760,7 +764,8 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
if (!err)
return ICE_XDP_REDIR;
- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+ if (xsk_uses_need_wakeup(READ_ONCE(rx_ring->xsk_pool)) &&
+ err == -ENOBUFS)
result = ICE_XDP_EXIT;
else
result = ICE_XDP_CONSUMED;
@@ -829,8 +834,8 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
*/
int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
{
+ struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
- struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
u32 ntc = rx_ring->next_to_clean;
u32 ntu = rx_ring->next_to_use;
struct xdp_buff *first = NULL;
@@ -942,7 +947,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
rx_ring->next_to_clean = ntc;
entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
- failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+ failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+ entries_to_alloc);
ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -968,14 +974,15 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
* @desc: AF_XDP descriptor to pull the DMA address and length from
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
unsigned int *total_bytes)
{
struct ice_tx_desc *tx_desc;
dma_addr_t dma;
- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+ dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
tx_desc->buf_addr = cpu_to_le64(dma);
@@ -991,7 +998,9 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
* @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool,
+ struct xdp_desc *descs,
unsigned int *total_bytes)
{
u16 ntu = xdp_ring->next_to_use;
@@ -1001,8 +1010,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
dma_addr_t dma;
- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+ dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
tx_desc->buf_addr = cpu_to_le64(dma);
@@ -1022,17 +1031,19 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
* @nb_pkts: count of packets to be send
* @total_bytes: bytes accumulator that will be used for stats update
*/
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
- u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+ struct xsk_buff_pool *xsk_pool,
+ struct xdp_desc *descs, u32 nb_pkts,
+ unsigned int *total_bytes)
{
u32 batched, leftover, i;
batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
leftover = nb_pkts & (PKTS_PER_BATCH - 1);
for (i = 0; i < batched; i += PKTS_PER_BATCH)
- ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+ ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
for (; i < batched + leftover; i++)
- ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+ ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
}
/**
@@ -1043,7 +1054,8 @@ static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *d
*/
bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
{
- struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+ struct xsk_buff_pool *xsk_pool = READ_ONCE(xdp_ring->xsk_pool);
+ struct xdp_desc *descs = xsk_pool->tx_descs;
u32 nb_pkts, nb_processed = 0;
unsigned int total_bytes = 0;
int budget;
@@ -1057,25 +1069,26 @@ bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
budget = ICE_DESC_UNUSED(xdp_ring);
budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
- nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+ nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
if (!nb_pkts)
return true;
if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
nb_processed = xdp_ring->count - xdp_ring->next_to_use;
- ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+ &total_bytes);
xdp_ring->next_to_use = 0;
}
- ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
- &total_bytes);
+ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+ nb_pkts - nb_processed, &total_bytes);
ice_set_rs_bit(xdp_ring);
ice_xdp_ring_update_tail(xdp_ring);
ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
- if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
- xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+ if (xsk_uses_need_wakeup(xsk_pool))
+ xsk_set_tx_need_wakeup(xsk_pool);
return nb_pkts < budget;
}
@@ -1108,7 +1121,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
ring = vsi->rx_rings[queue_id]->xdp_ring;
- if (!ring->xsk_pool)
+ if (!READ_ONCE(ring->xsk_pool))
return -EINVAL;
/* The idea here is that if NAPI is running, mark a miss, so
@@ -22,7 +22,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
u16 qid);
int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+ struct xsk_buff_pool *xsk_pool, u16 count);
bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
@@ -51,6 +52,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
static inline bool
ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+ struct xsk_buff_pool __always_unused *xsk_pool,
u16 __always_unused count)
{
return false;
xsk_buff_pool pointers that ice ring structs hold are updated via ndo_bpf that is executed in process context while it can be read by remote CPU at the same time within NAPI poll. Use synchronize_net() after pointer update and {READ,WRITE}_ONCE() when working with mentioned pointer. Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> --- drivers/net/ethernet/intel/ice/ice.h | 6 +- drivers/net/ethernet/intel/ice/ice_base.c | 4 +- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 4 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 73 +++++++++++++---------- drivers/net/ethernet/intel/ice/ice_xsk.h | 4 +- 6 files changed, 54 insertions(+), 39 deletions(-)