| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20260206174910.4066255-5-anthony.l.nguyen@intel.com>
Date: Fri, 6 Feb 2026 09:49:01 -0800
From: Tony Nguyen <anthony.l.nguyen@...el.com>
To: davem@...emloft.net,
kuba@...nel.org,
pabeni@...hat.com,
edumazet@...gle.com,
andrew+netdev@...n.ch,
netdev@...r.kernel.org
Cc: Alexander Lobakin <aleksander.lobakin@...el.com>,
anthony.l.nguyen@...el.com,
jacob.e.keller@...el.com,
nxne.cnse.osdt.itp.upstreaming@...el.com,
horms@...nel.org,
maciej.fijalkowski@...el.com,
magnus.karlsson@...el.com,
ast@...nel.org,
daniel@...earbox.net,
hawk@...nel.org,
john.fastabend@...il.com,
sdf@...ichev.me,
bpf@...r.kernel.org,
Aleksandr Loktionov <aleksandr.loktionov@...el.com>,
Kohei Enju <kohei@...uk.jp>,
Alexander Nowlin <alexander.nowlin@...el.com>
Subject: [PATCH net-next 4/9] ice: implement Rx queue management ops
From: Alexander Lobakin <aleksander.lobakin@...el.com>
Now ice is ready to get queue_mgmt_ops support. It already has API
to disable/reconfig/enable one particular queue (for XSk). Reuse as
much of its code as possible to implement Rx queue management
callbacks and vice versa -- ice_queue_mem_{alloc,free}() can be
reused during ifup/ifdown to elide code duplication.
With this, ice passes the io_uring zcrx selftests, meaning the Rx
part of netmem/MP support is done.
Reviewed-by: Jacob Keller <jacob.e.keller@...el.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@...el.com>
Co-developed-by: Kohei Enju <kohei@...uk.jp>
Signed-off-by: Kohei Enju <kohei@...uk.jp>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@...el.com>
Tested-by: Alexander Nowlin <alexander.nowlin@...el.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@...el.com>
---
drivers/net/ethernet/intel/ice/ice_base.c | 194 +++++++++++++------
drivers/net/ethernet/intel/ice/ice_ethtool.c | 1 +
drivers/net/ethernet/intel/ice/ice_lib.h | 5 +
drivers/net/ethernet/intel/ice/ice_main.c | 2 +-
drivers/net/ethernet/intel/ice/ice_sf_eth.c | 2 +-
drivers/net/ethernet/intel/ice/ice_txrx.c | 26 ++-
drivers/net/ethernet/intel/ice/ice_txrx.h | 2 +
7 files changed, 166 insertions(+), 66 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index f084b1c48e5d..052a6fae50fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -651,6 +651,43 @@ static int ice_rxq_pp_create(struct ice_rx_ring *rq)
return err;
}
+static int ice_queue_mem_alloc(struct net_device *dev,
+ struct netdev_queue_config *qcfg,
+ void *per_queue_mem, int idx)
+{
+ const struct ice_netdev_priv *priv = netdev_priv(dev);
+ const struct ice_rx_ring *real = priv->vsi->rx_rings[idx];
+ struct ice_rx_ring *new = per_queue_mem;
+ int ret;
+
+ new->count = real->count;
+ new->netdev = real->netdev;
+ new->q_index = real->q_index;
+ new->q_vector = real->q_vector;
+ new->vsi = real->vsi;
+
+ ret = ice_rxq_pp_create(new);
+ if (ret)
+ return ret;
+
+ if (!netif_running(dev))
+ return 0;
+
+ ret = __xdp_rxq_info_reg(&new->xdp_rxq, new->netdev, new->q_index,
+ new->q_vector->napi.napi_id, new->rx_buf_len);
+ if (ret)
+ goto err_destroy_fq;
+
+ xdp_rxq_info_attach_page_pool(&new->xdp_rxq, new->pp);
+
+ return 0;
+
+err_destroy_fq:
+ ice_rxq_pp_destroy(new);
+
+ return ret;
+}
+
/**
* ice_vsi_cfg_rxq - Configure an Rx queue
* @ring: the ring being configured
@@ -665,23 +702,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
int err;
if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) {
- if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
- err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
- ring->q_index,
- ring->q_vector->napi.napi_id,
- ring->rx_buf_len);
- if (err)
- return err;
- }
-
ice_rx_xsk_pool(ring);
err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool);
if (err)
return err;
if (ring->xsk_pool) {
- xdp_rxq_info_unreg(&ring->xdp_rxq);
-
rx_buf_len =
xsk_pool_get_rx_frame_size(ring->xsk_pool);
err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
@@ -700,20 +726,10 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
ring->q_index);
} else {
- err = ice_rxq_pp_create(ring);
+ err = ice_queue_mem_alloc(ring->netdev, NULL, ring,
+ ring->q_index);
if (err)
return err;
-
- if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
- err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
- ring->q_index,
- ring->q_vector->napi.napi_id,
- ring->rx_buf_len);
- if (err)
- goto err_destroy_fq;
- }
- xdp_rxq_info_attach_page_pool(&ring->xdp_rxq,
- ring->pp);
}
}
@@ -722,7 +738,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
if (err) {
dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
ring->q_index, err);
- goto err_destroy_fq;
+ goto err_clean_rq;
}
if (ring->xsk_pool) {
@@ -753,12 +769,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
err = ice_alloc_rx_bufs(ring, num_bufs);
if (err)
- goto err_destroy_fq;
+ goto err_clean_rq;
return 0;
-err_destroy_fq:
- ice_rxq_pp_destroy(ring);
+err_clean_rq:
+ ice_clean_rx_ring(ring);
return err;
}
@@ -1470,27 +1486,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats));
}
-/**
- * ice_qp_clean_rings - Cleans all the rings of a given index
- * @vsi: VSI that contains rings of interest
- * @q_idx: ring index in array
- */
-static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
-{
- ice_clean_tx_ring(vsi->tx_rings[q_idx]);
- if (vsi->xdp_rings)
- ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
- ice_clean_rx_ring(vsi->rx_rings[q_idx]);
-}
-
-/**
- * ice_qp_dis - Disables a queue pair
- * @vsi: VSI of interest
- * @q_idx: ring index in array
- *
- * Returns 0 on success, negative on failure.
- */
-int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+static int __ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
{
struct ice_txq_meta txq_meta = { };
struct ice_q_vector *q_vector;
@@ -1529,23 +1525,35 @@ int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
}
ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
- ice_qp_clean_rings(vsi, q_idx);
ice_qp_reset_stats(vsi, q_idx);
+ ice_clean_tx_ring(vsi->tx_rings[q_idx]);
+ if (vsi->xdp_rings)
+ ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+
return fail;
}
/**
- * ice_qp_ena - Enables a queue pair
+ * ice_qp_dis - Disables a queue pair
* @vsi: VSI of interest
* @q_idx: ring index in array
*
* Returns 0 on success, negative on failure.
*/
-int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
+int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+{
+ int ret;
+
+ ret = __ice_qp_dis(vsi, q_idx);
+ ice_clean_rx_ring(vsi->rx_rings[q_idx]);
+
+ return ret;
+}
+
+static int __ice_qp_ena(struct ice_vsi *vsi, u16 q_idx, int fail)
{
struct ice_q_vector *q_vector;
- int fail = 0;
bool link_up;
int err;
@@ -1563,10 +1571,6 @@ int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
ice_tx_xsk_pool(vsi, q_idx);
}
- err = ice_vsi_cfg_single_rxq(vsi, q_idx);
- if (!fail)
- fail = err;
-
q_vector = vsi->rx_rings[q_idx]->q_vector;
ice_qvec_cfg_msix(vsi, q_vector, q_idx);
@@ -1587,3 +1591,81 @@ int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
return fail;
}
+
+/**
+ * ice_qp_ena - Enables a queue pair
+ * @vsi: VSI of interest
+ * @q_idx: ring index in array
+ *
+ * Returns 0 on success, negative on failure.
+ */
+int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
+{
+ return __ice_qp_ena(vsi, q_idx, ice_vsi_cfg_single_rxq(vsi, q_idx));
+}
+
+static int ice_queue_start(struct net_device *dev,
+ struct netdev_queue_config *qcfg,
+ void *per_queue_mem, int idx)
+{
+ const struct ice_netdev_priv *priv = netdev_priv(dev);
+ struct ice_rx_ring *real = priv->vsi->rx_rings[idx];
+ struct ice_rx_ring *new = per_queue_mem;
+ struct napi_struct *napi;
+ int ret;
+
+ real->pp = new->pp;
+ real->rx_fqes = new->rx_fqes;
+ real->hdr_fqes = new->hdr_fqes;
+ real->hdr_pp = new->hdr_pp;
+
+ real->hdr_truesize = new->hdr_truesize;
+ real->truesize = new->truesize;
+ real->rx_hdr_len = new->rx_hdr_len;
+ real->rx_buf_len = new->rx_buf_len;
+
+ memcpy(&real->xdp_rxq, &new->xdp_rxq, sizeof(new->xdp_rxq));
+
+ ret = ice_setup_rx_ctx(real);
+ if (ret)
+ return ret;
+
+ napi = &real->q_vector->napi;
+
+ page_pool_enable_direct_recycling(real->pp, napi);
+ if (real->hdr_pp)
+ page_pool_enable_direct_recycling(real->hdr_pp, napi);
+
+ ret = ice_alloc_rx_bufs(real, ICE_DESC_UNUSED(real));
+
+ return __ice_qp_ena(priv->vsi, idx, ret);
+}
+
+static int ice_queue_stop(struct net_device *dev, void *per_queue_mem,
+ int idx)
+{
+ const struct ice_netdev_priv *priv = netdev_priv(dev);
+ struct ice_rx_ring *real = priv->vsi->rx_rings[idx];
+ int ret;
+
+ ret = __ice_qp_dis(priv->vsi, idx);
+ if (ret)
+ return ret;
+
+ page_pool_disable_direct_recycling(real->pp);
+ if (real->hdr_pp)
+ page_pool_disable_direct_recycling(real->hdr_pp);
+
+ ice_zero_rx_ring(real);
+ memcpy(per_queue_mem, real, sizeof(*real));
+
+ return 0;
+}
+
+const struct netdev_queue_mgmt_ops ice_queue_mgmt_ops = {
+ .ndo_queue_mem_alloc = ice_queue_mem_alloc,
+ .ndo_queue_mem_free = ice_queue_mem_free,
+ .ndo_queue_mem_size = sizeof(struct ice_rx_ring),
+ .ndo_queue_start = ice_queue_start,
+ .ndo_queue_stop = ice_queue_stop,
+};
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index c6bc29cfb8e6..8df07e92187f 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3338,6 +3338,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
rx_rings[i].desc = NULL;
rx_rings[i].xdp_buf = NULL;
+ memset(&rx_rings[i].xdp_rxq, 0, sizeof(rx_rings[i].xdp_rxq));
/* this is to allow wr32 to have something to write to
* during early allocation of Rx buffers
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index e55b72db72c4..bccf173959be 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -4,6 +4,8 @@
#ifndef _ICE_LIB_H_
#define _ICE_LIB_H_
+#include <net/netdev_queues.h>
+
#include "ice.h"
#include "ice_vlan.h"
@@ -133,4 +135,7 @@ void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f);
void ice_init_feature_support(struct ice_pf *pf);
bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi);
void ice_vsi_update_l2tsel(struct ice_vsi *vsi, enum ice_l2tsel l2tsel);
+
+extern const struct netdev_queue_mgmt_ops ice_queue_mgmt_ops;
+
#endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 27ee7c1ee19c..d4480698f917 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3525,7 +3525,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
}
netdev->netdev_ops = &ice_netdev_ops;
- netdev->request_ops_lock = true;
+ netdev->queue_mgmt_ops = &ice_queue_mgmt_ops;
netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
netdev->xdp_metadata_ops = &ice_xdp_md_ops;
ice_set_ethtool_ops(netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index 2c3db1b03055..41e1606a8222 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -58,7 +58,7 @@ static int ice_sf_cfg_netdev(struct ice_dynamic_port *dyn_port,
eth_hw_addr_set(netdev, dyn_port->hw_addr);
ether_addr_copy(netdev->perm_addr, dyn_port->hw_addr);
netdev->netdev_ops = &ice_sf_netdev_ops;
- netdev->request_ops_lock = true;
+ netdev->queue_mgmt_ops = &ice_queue_mgmt_ops;
SET_NETDEV_DEVLINK_PORT(netdev, devlink_port);
err = register_netdev(netdev);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 396326a6d5be..d2cddb24ea05 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -530,17 +530,13 @@ void ice_rxq_pp_destroy(struct ice_rx_ring *rq)
rq->hdr_pp = NULL;
}
-/**
- * ice_clean_rx_ring - Free Rx buffers
- * @rx_ring: ring to be cleaned
- */
-void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
+void ice_queue_mem_free(struct net_device *dev, void *per_queue_mem)
{
- u32 size;
+ struct ice_rx_ring *rx_ring = per_queue_mem;
if (rx_ring->xsk_pool) {
ice_xsk_clean_rx_ring(rx_ring);
- goto rx_skip_free;
+ return;
}
/* ring already cleared, nothing to do */
@@ -567,8 +563,12 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
}
ice_rxq_pp_destroy(rx_ring);
+}
+
+void ice_zero_rx_ring(struct ice_rx_ring *rx_ring)
+{
+ size_t size;
-rx_skip_free:
/* Zero out the descriptor ring */
size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
PAGE_SIZE);
@@ -578,6 +578,16 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
rx_ring->next_to_use = 0;
}
+/**
+ * ice_clean_rx_ring - Free Rx buffers
+ * @rx_ring: ring to be cleaned
+ */
+void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
+{
+ ice_queue_mem_free(rx_ring->netdev, rx_ring);
+ ice_zero_rx_ring(rx_ring);
+}
+
/**
* ice_free_rx_ring - Free Rx resources
* @rx_ring: ring to clean the resources from
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index b6547e1b7c42..557b5e656bb0 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -458,6 +458,8 @@ u16
ice_select_queue(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
void ice_clean_tx_ring(struct ice_tx_ring *tx_ring);
+void ice_queue_mem_free(struct net_device *dev, void *per_queue_mem);
+void ice_zero_rx_ring(struct ice_rx_ring *rx_ring);
void ice_clean_rx_ring(struct ice_rx_ring *rx_ring);
int ice_setup_tx_ring(struct ice_tx_ring *tx_ring);
int ice_setup_rx_ring(struct ice_rx_ring *rx_ring);
--
2.47.1
Powered by blists - more mailing lists