* [PATCH iwl-next v5 1/5] libeth: pass Rx queue index to PP when creating a fill queue
From: Alexander Lobakin @ 2026-05-05 15:29 UTC (permalink / raw)
To: intel-wired-lan
Cc: Alexander Lobakin, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Kohei Enju, Jacob Keller, Aleksandr Loktionov,
nxne.cnse.osdt.itp.upstreaming, netdev, linux-kernel
In-Reply-To: <20260505152923.1040589-1-aleksander.lobakin@intel.com>
Since recently, page_pool_create() accepts optional stack index of
the Rx queue which the pool will be created for. It can then be
used on control path for stuff like memory providers.
Add the same field to libeth_fq and pass the index from all the
drivers using libeth for managing Rx to simplify implementing MP
support later.
idpf has one libeth_fq per buffer/fill queue and each Rx queue has
two fill queues, but since fill queues can never be shared, we can
store the corresponding Rx queue index there during the
initialization to pass it to libeth.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
drivers/net/ethernet/intel/idpf/idpf_txrx.h | 2 ++
include/net/libeth/rx.h | 2 ++
drivers/net/ethernet/intel/iavf/iavf_txrx.c | 1 +
drivers/net/ethernet/intel/ice/ice_base.c | 2 ++
drivers/net/ethernet/intel/idpf/idpf_txrx.c | 13 +++++++++++++
drivers/net/ethernet/intel/libeth/rx.c | 1 +
6 files changed, 21 insertions(+)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 4be5b3b6d3ed..a0d92adf11c4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -748,6 +748,7 @@ libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
* @size: Length of descriptor ring in bytes
* @dma: Physical address of ring
* @q_vector: Backreference to associated vector
+ * @rxq_idx: stack index of the corresponding Rx queue
* @rx_buffer_low_watermark: RX buffer low watermark
* @rx_hbuf_size: Header buffer size
* @rx_buf_size: Buffer size
@@ -791,6 +792,7 @@ struct idpf_buf_queue {
dma_addr_t dma;
struct idpf_q_vector *q_vector;
+ u16 rxq_idx;
u16 rx_buffer_low_watermark;
u16 rx_hbuf_size;
diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h
index 5d991404845e..3b3d7acd13c9 100644
--- a/include/net/libeth/rx.h
+++ b/include/net/libeth/rx.h
@@ -71,6 +71,7 @@ enum libeth_fqe_type {
* @xdp: flag indicating whether XDP is enabled
* @buf_len: HW-writeable length per each buffer
* @nid: ID of the closest NUMA node with memory
+ * @idx: stack index of the corresponding Rx queue
*/
struct libeth_fq {
struct_group_tagged(libeth_fq_fp, fp,
@@ -88,6 +89,7 @@ struct libeth_fq {
u32 buf_len;
int nid;
+ u32 idx;
};
int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 363c42bf3dcf..d3c68659162b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -771,6 +771,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
.count = rx_ring->count,
.buf_len = LIBIE_MAX_RX_BUF_LEN,
.nid = NUMA_NO_NODE,
+ .idx = rx_ring->queue_index,
};
int ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1667f686ff75..f162cdfc62a7 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -609,6 +609,7 @@ static int ice_rxq_pp_create(struct ice_rx_ring *rq)
struct libeth_fq fq = {
.count = rq->count,
.nid = NUMA_NO_NODE,
+ .idx = rq->q_index,
.hsplit = rq->vsi->hsplit,
.xdp = ice_is_xdp_ena_vsi(rq->vsi),
.buf_len = LIBIE_MAX_RX_BUF_LEN,
@@ -631,6 +632,7 @@ static int ice_rxq_pp_create(struct ice_rx_ring *rq)
.count = rq->count,
.type = LIBETH_FQE_HDR,
.nid = NUMA_NO_NODE,
+ .idx = rq->q_index,
.xdp = ice_is_xdp_ena_vsi(rq->vsi),
};
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index f6b3b15364ff..95930edc566f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -557,6 +557,7 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
.type = LIBETH_FQE_HDR,
.xdp = idpf_xdp_enabled(bufq->q_vector->vport),
.nid = idpf_q_vector_to_mem(bufq->q_vector),
+ .idx = bufq->rxq_idx,
};
int ret;
@@ -699,6 +700,7 @@ static int idpf_rx_bufs_init_singleq(struct idpf_rx_queue *rxq)
.type = LIBETH_FQE_MTU,
.buf_len = IDPF_RX_MAX_BUF_SZ,
.nid = idpf_q_vector_to_mem(rxq->q_vector),
+ .idx = rxq->idx,
};
int ret;
@@ -759,6 +761,7 @@ static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq,
.hsplit = idpf_queue_has(HSPLIT_EN, bufq),
.xdp = idpf_xdp_enabled(bufq->q_vector->vport),
.nid = idpf_q_vector_to_mem(bufq->q_vector),
+ .idx = bufq->rxq_idx,
};
int ret;
@@ -1913,6 +1916,16 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport,
LIBETH_RX_LL_LEN;
idpf_rxq_set_descids(rsrc, q);
}
+
+ if (!idpf_is_queue_model_split(rsrc->rxq_model))
+ continue;
+
+ for (u32 j = 0; j < rsrc->num_bufqs_per_qgrp; j++) {
+ struct idpf_buf_queue *bufq;
+
+ bufq = &rx_qgrp->splitq.bufq_sets[j].bufq;
+ bufq->rxq_idx = rx_qgrp->splitq.rxq_sets[0]->rxq.idx;
+ }
}
err_alloc:
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
index 62521a1f4ec9..8874b714cdcc 100644
--- a/drivers/net/ethernet/intel/libeth/rx.c
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -156,6 +156,7 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi)
.order = LIBETH_RX_PAGE_ORDER,
.pool_size = fq->count,
.nid = fq->nid,
+ .queue_idx = fq->idx,
.dev = napi->dev->dev.parent,
.netdev = napi->dev,
.napi = napi,
--
2.54.0
^ permalink raw reply related
* [PATCH iwl-next v5 2/5] libeth: handle creating pools with unreadable buffers
From: Alexander Lobakin @ 2026-05-05 15:29 UTC (permalink / raw)
To: intel-wired-lan
Cc: Alexander Lobakin, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Kohei Enju, Jacob Keller, Aleksandr Loktionov,
nxne.cnse.osdt.itp.upstreaming, netdev, linux-kernel
In-Reply-To: <20260505152923.1040589-1-aleksander.lobakin@intel.com>
libeth uses netmems for quite some time already, so in order to
support unreadable frags / memory providers, it only needs to set
PP_FLAG_ALLOW_UNREADABLE_NETMEM when needed.
Also add a couple sanity checks to make sure the driver didn't mess
up the configuration options and, in case when an MP is installed,
return the truesize always equal to PAGE_SIZE, so that
libeth_rx_alloc() will never try to allocate frags. Memory providers
manage buffers on their own and expect 1:1 buffer / HW Rx descriptor
association.
Bonus: mention in the libeth_sqe_type description that
LIBETH_SQE_EMPTY should also be used for netmem Tx SQEs -- they
don't need DMA unmapping.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
include/net/libeth/tx.h | 2 +-
drivers/net/ethernet/intel/libeth/rx.c | 42 ++++++++++++++++++++++++++
2 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h
index c3db5c6f1641..a66fc2b3a114 100644
--- a/include/net/libeth/tx.h
+++ b/include/net/libeth/tx.h
@@ -12,7 +12,7 @@
/**
* enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion
- * @LIBETH_SQE_EMPTY: unused/empty OR XDP_TX/XSk frame, no action required
+ * @LIBETH_SQE_EMPTY: empty OR netmem/XDP_TX/XSk frame, no action required
* @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required
* @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree()
* @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA
diff --git a/drivers/net/ethernet/intel/libeth/rx.c b/drivers/net/ethernet/intel/libeth/rx.c
index 8874b714cdcc..11e6e8f353ef 100644
--- a/drivers/net/ethernet/intel/libeth/rx.c
+++ b/drivers/net/ethernet/intel/libeth/rx.c
@@ -6,6 +6,7 @@
#include <linux/export.h>
#include <net/libeth/rx.h>
+#include <net/netdev_queues.h>
/* Rx buffer management */
@@ -139,9 +140,47 @@ static bool libeth_rx_page_pool_params_zc(struct libeth_fq *fq,
fq->buf_len = clamp(mtu, LIBETH_RX_BUF_STRIDE, max);
fq->truesize = fq->buf_len;
+ /*
+ * Allow frags only for kernel pages. `fq->truesize == pp->max_len`
+ * will always fall back to regular page_pool_alloc_netmems()
+ * regardless of the MTU / FQ buffer size.
+ */
+ if (pp->flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM)
+ fq->truesize = pp->max_len;
+
return true;
}
+/**
+ * libeth_rx_page_pool_check_unread - check input params for unreadable MPs
+ * @fq: buffer queue to check
+ * @pp: &page_pool_params for the queue
+ *
+ * Make sure we don't create an invalid pool with full-frame unreadable
+ * buffers, bidirectional unreadable buffers or so, and configure the
+ * ZC payload pool accordingly.
+ *
+ * Return: true on success, false on invalid input params.
+ */
+static bool libeth_rx_page_pool_check_unread(const struct libeth_fq *fq,
+ struct page_pool_params *pp)
+{
+ if (!netif_rxq_has_unreadable_mp(pp->netdev, pp->queue_idx))
+ return true;
+
+ /* For now, the core stack doesn't allow XDP with unreadable frags */
+ if (fq->xdp)
+ return false;
+
+ /* It should be either a header pool or a ZC payload pool */
+ if (fq->type == LIBETH_FQE_HDR)
+ return !fq->hsplit;
+
+ pp->flags |= PP_FLAG_ALLOW_UNREADABLE_NETMEM;
+
+ return fq->hsplit;
+}
+
/**
* libeth_rx_fq_create - create a PP with the default libeth settings
* @fq: buffer queue struct to fill
@@ -165,6 +204,9 @@ int libeth_rx_fq_create(struct libeth_fq *fq, struct napi_struct *napi)
struct page_pool *pool;
int ret;
+ if (!libeth_rx_page_pool_check_unread(fq, &pp))
+ return -EINVAL;
+
pp.dma_dir = fq->xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
if (!fq->hsplit)
--
2.54.0
^ permalink raw reply related
* [PATCH iwl-next v5 3/5] ice: migrate to netdev ops lock
From: Alexander Lobakin @ 2026-05-05 15:29 UTC (permalink / raw)
To: intel-wired-lan
Cc: Alexander Lobakin, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Kohei Enju, Jacob Keller, Aleksandr Loktionov,
nxne.cnse.osdt.itp.upstreaming, netdev, linux-kernel
In-Reply-To: <20260505152923.1040589-1-aleksander.lobakin@intel.com>
Queue management ops unconditionally enable netdev locking. The same
lock is taken by default by several NAPI configuration functions,
such as napi_enable() and netif_napi_set_irq().
Request ops locking in advance and make sure we use the _locked
counterparts of those functions to avoid deadlocks, taking the lock
manually where needed (suspend/resume, queue rebuild and resets).
Co-developed-by: Kohei Enju <kohei@enjuk.jp> # ice_xdp_setup_prog(), safe mode
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
drivers/net/ethernet/intel/ice/ice_base.h | 2 +
drivers/net/ethernet/intel/ice/ice_lib.h | 13 +-
drivers/net/ethernet/intel/ice/ice_base.c | 63 ++++-
drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 15 +-
drivers/net/ethernet/intel/ice/ice_eswitch.c | 26 ++-
drivers/net/ethernet/intel/ice/ice_lib.c | 227 +++++++++++++++----
drivers/net/ethernet/intel/ice/ice_main.c | 78 ++++---
drivers/net/ethernet/intel/ice/ice_sf_eth.c | 3 +
drivers/net/ethernet/intel/ice/ice_xsk.c | 4 +-
9 files changed, 324 insertions(+), 107 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h
index d28294247599..99b2c7232829 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.h
+++ b/drivers/net/ethernet/intel/ice/ice_base.h
@@ -12,8 +12,10 @@ int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg);
int
ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait);
int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx);
+int ice_vsi_alloc_q_vectors_locked(struct ice_vsi *vsi);
int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi);
void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi);
+void ice_vsi_free_q_vectors_locked(struct ice_vsi *vsi);
void ice_vsi_free_q_vectors(struct ice_vsi *vsi);
int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings,
u16 q_idx);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 49454d98dcfe..476fa54ec4e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -53,19 +53,24 @@ struct ice_vsi *
ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
-void ice_napi_add(struct ice_vsi *vsi);
-
+void ice_vsi_set_napi_queues_locked(struct ice_vsi *vsi);
void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);
+void ice_vsi_clear_napi_queues_locked(struct ice_vsi *vsi);
+
+void ice_napi_add(struct ice_vsi *vsi);
int ice_vsi_release(struct ice_vsi *vsi);
void ice_vsi_close(struct ice_vsi *vsi);
-int ice_ena_vsi(struct ice_vsi *vsi, bool locked);
+int ice_ena_vsi_locked(struct ice_vsi *vsi);
+int ice_ena_vsi(struct ice_vsi *vsi);
void ice_vsi_decfg(struct ice_vsi *vsi);
-void ice_dis_vsi(struct ice_vsi *vsi, bool locked);
+void ice_dis_vsi_locked(struct ice_vsi *vsi);
+void ice_dis_vsi(struct ice_vsi *vsi);
+int ice_vsi_rebuild_locked(struct ice_vsi *vsi, u32 vsi_flags);
int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags);
int ice_vsi_cfg(struct ice_vsi *vsi);
struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index f162cdfc62a7..1add82d894bb 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -155,8 +155,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
* handler here (i.e. resume, reset/rebuild, etc.)
*/
if (vsi->netdev)
- netif_napi_add_config(vsi->netdev, &q_vector->napi,
- ice_napi_poll, v_idx);
+ netif_napi_add_config_locked(vsi->netdev, &q_vector->napi,
+ ice_napi_poll, v_idx);
out:
/* tie q_vector and VSI together */
@@ -198,7 +198,7 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
/* only VSI with an associated netdev is set up with NAPI */
if (vsi->netdev)
- netif_napi_del(&q_vector->napi);
+ netif_napi_del_locked(&q_vector->napi);
/* release MSIX interrupt if q_vector had interrupt allocated */
if (q_vector->irq.index < 0)
@@ -886,13 +886,15 @@ int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx)
}
/**
- * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
+ * ice_vsi_alloc_q_vectors_locked - Allocate memory for interrupt vectors
* @vsi: the VSI being configured
*
- * We allocate one q_vector per queue interrupt. If allocation fails we
- * return -ENOMEM.
+ * Should be called only under the netdev lock.
+ * We allocate one q_vector per queue interrupt.
+ *
+ * Return: 0 on success, -ENOMEM if allocation fails.
*/
-int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
+int ice_vsi_alloc_q_vectors_locked(struct ice_vsi *vsi)
{
struct device *dev = ice_pf_to_dev(vsi->back);
u16 v_idx;
@@ -919,6 +921,30 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
return v_idx ? 0 : err;
}
+/**
+ * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
+ * @vsi: the VSI being configured
+ *
+ * We allocate one q_vector per queue interrupt.
+ *
+ * Return: 0 on success, -ENOMEM if allocation fails.
+ */
+int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+ int ret;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ret = ice_vsi_alloc_q_vectors_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+
+ return ret;
+}
+
/**
* ice_vsi_map_rings_to_vectors - Map VSI rings to interrupt vectors
* @vsi: the VSI being configured
@@ -982,10 +1008,12 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
}
/**
- * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors
+ * ice_vsi_free_q_vectors_locked - Free memory allocated for interrupt vectors
* @vsi: the VSI having memory freed
+ *
+ * Should be called only under the netdev lock.
*/
-void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
+void ice_vsi_free_q_vectors_locked(struct ice_vsi *vsi)
{
int v_idx;
@@ -995,6 +1023,23 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
vsi->num_q_vectors = 0;
}
+/**
+ * ice_vsi_free_q_vectors - Free memory allocated for interrupt vectors
+ * @vsi: the VSI having memory freed
+ */
+void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ice_vsi_free_q_vectors_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+}
+
/**
* ice_cfg_tstamp - Configure Tx time stamp queue
* @tx_ring: Tx ring to be configured with timestamping
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 16aa25535152..7d89c0acc5d8 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -273,14 +273,13 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
* ice_dcb_ena_dis_vsi - disable certain VSIs for DCB config/reconfig
* @pf: pointer to the PF instance
* @ena: true to enable VSIs, false to disable
- * @locked: true if caller holds RTNL lock, false otherwise
*
* Before a new DCB configuration can be applied, VSIs of type PF, SWITCHDEV
* and CHNL need to be brought down. Following completion of DCB configuration
* the VSIs that were downed need to be brought up again. This helper function
* does both.
*/
-static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked)
+static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena)
{
int i;
@@ -294,9 +293,9 @@ static void ice_dcb_ena_dis_vsi(struct ice_pf *pf, bool ena, bool locked)
case ICE_VSI_CHNL:
case ICE_VSI_PF:
if (ena)
- ice_ena_vsi(vsi, locked);
+ ice_ena_vsi(vsi);
else
- ice_dis_vsi(vsi, locked);
+ ice_dis_vsi(vsi);
break;
default:
continue;
@@ -416,7 +415,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
rtnl_lock();
/* disable VSIs affected by DCB changes */
- ice_dcb_ena_dis_vsi(pf, false, true);
+ ice_dcb_ena_dis_vsi(pf, false);
memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg));
memcpy(&curr_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec));
@@ -445,7 +444,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
out:
/* enable previously downed VSIs */
- ice_dcb_ena_dis_vsi(pf, true, true);
+ ice_dcb_ena_dis_vsi(pf, true);
if (!locked)
rtnl_unlock();
free_cfg:
@@ -1107,7 +1106,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
rtnl_lock();
/* disable VSIs affected by DCB changes */
- ice_dcb_ena_dis_vsi(pf, false, true);
+ ice_dcb_ena_dis_vsi(pf, false);
ret = ice_query_port_ets(pi, &buf, sizeof(buf), NULL);
if (ret) {
@@ -1119,7 +1118,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
ice_pf_dcb_recfg(pf, false);
/* enable previously downed VSIs */
- ice_dcb_ena_dis_vsi(pf, true, true);
+ ice_dcb_ena_dis_vsi(pf, true);
unlock_rtnl:
rtnl_unlock();
out:
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 2e4f0969035f..af0cc77fbf71 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -23,10 +23,16 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
struct net_device *netdev = uplink_vsi->netdev;
bool if_running = netif_running(netdev);
struct ice_vsi_vlan_ops *vlan_ops;
+ int ret;
+
+ if (if_running && !test_and_set_bit(ICE_VSI_DOWN, uplink_vsi->state)) {
+ netdev_lock(netdev);
+ ret = ice_down(uplink_vsi);
+ netdev_unlock(netdev);
- if (if_running && !test_and_set_bit(ICE_VSI_DOWN, uplink_vsi->state))
- if (ice_down(uplink_vsi))
+ if (ret)
return -ENODEV;
+ }
ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx);
ice_vsi_cfg_sw_lldp(uplink_vsi, true, false);
@@ -53,8 +59,14 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
if (ice_vsi_update_local_lb(uplink_vsi, true))
goto err_override_local_lb;
- if (if_running && ice_up(uplink_vsi))
- goto err_up;
+ if (if_running) {
+ netdev_lock(netdev);
+ ret = ice_up(uplink_vsi);
+ netdev_unlock(netdev);
+
+ if (ret)
+ goto err_up;
+ }
return 0;
@@ -74,8 +86,12 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
ice_fltr_add_mac_and_broadcast(uplink_vsi,
uplink_vsi->port_info->mac.perm_addr,
ICE_FWD_TO_VSI);
- if (if_running)
+
+ if (if_running) {
+ netdev_lock(netdev);
ice_up(uplink_vsi);
+ netdev_unlock(netdev);
+ }
return -ENODEV;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 837b71b7b2b7..6760aac609f2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2304,10 +2304,14 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi)
}
/**
- * ice_vsi_cfg_def - configure default VSI based on the type
+ * ice_vsi_cfg_def_locked - configure default VSI based on the type
* @vsi: pointer to VSI
+ *
+ * Should be called only with the netdev lock taken.
+ *
+ * Return: 0 on success, -errno on failure.
*/
-static int ice_vsi_cfg_def(struct ice_vsi *vsi)
+static int ice_vsi_cfg_def_locked(struct ice_vsi *vsi)
{
struct device *dev = ice_pf_to_dev(vsi->back);
struct ice_pf *pf = vsi->back;
@@ -2350,7 +2354,7 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
case ICE_VSI_CTRL:
case ICE_VSI_SF:
case ICE_VSI_PF:
- ret = ice_vsi_alloc_q_vectors(vsi);
+ ret = ice_vsi_alloc_q_vectors_locked(vsi);
if (ret)
goto unroll_vsi_init;
@@ -2400,7 +2404,7 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
* creates a VSI and corresponding structures for bookkeeping
* purpose
*/
- ret = ice_vsi_alloc_q_vectors(vsi);
+ ret = ice_vsi_alloc_q_vectors_locked(vsi);
if (ret)
goto unroll_vsi_init;
@@ -2424,7 +2428,7 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
}
break;
case ICE_VSI_LB:
- ret = ice_vsi_alloc_q_vectors(vsi);
+ ret = ice_vsi_alloc_q_vectors_locked(vsi);
if (ret)
goto unroll_vsi_init;
@@ -2451,7 +2455,7 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
unroll_vector_base:
/* reclaim SW interrupts back to the common pool */
unroll_alloc_q_vector:
- ice_vsi_free_q_vectors(vsi);
+ ice_vsi_free_q_vectors_locked(vsi);
unroll_vsi_init:
ice_vsi_delete_from_hw(vsi);
unroll_get_qs:
@@ -2463,6 +2467,28 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
return ret;
}
+/**
+ * ice_vsi_cfg_def - configure default VSI based on the type
+ * @vsi: pointer to VSI
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static int ice_vsi_cfg_def(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+ int ret;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ret = ice_vsi_cfg_def_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+
+ return ret;
+}
+
/**
* ice_vsi_cfg - configure a previously allocated VSI
* @vsi: pointer to VSI
@@ -2497,10 +2523,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
}
/**
- * ice_vsi_decfg - remove all VSI configuration
+ * ice_vsi_decfg_locked - remove all VSI configuration
* @vsi: pointer to VSI
+ *
+ * Should be called only under the netdev lock.
*/
-void ice_vsi_decfg(struct ice_vsi *vsi)
+static void ice_vsi_decfg_locked(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
int err;
@@ -2518,7 +2546,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART);
ice_vsi_clear_rings(vsi);
- ice_vsi_free_q_vectors(vsi);
+ ice_vsi_free_q_vectors_locked(vsi);
ice_vsi_put_qs(vsi);
ice_vsi_free_arrays(vsi);
@@ -2533,6 +2561,23 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
vsi->agg_node->num_vsis--;
}
+/**
+ * ice_vsi_decfg - remove all VSI configuration
+ * @vsi: pointer to VSI
+ */
+void ice_vsi_decfg(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ice_vsi_decfg_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+}
+
/**
* ice_vsi_setup - Set up a VSI by a given type
* @pf: board private structure
@@ -2706,18 +2751,19 @@ void ice_vsi_close(struct ice_vsi *vsi)
if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state))
ice_down(vsi);
- ice_vsi_clear_napi_queues(vsi);
+ ice_vsi_clear_napi_queues_locked(vsi);
ice_vsi_free_irq(vsi);
ice_vsi_free_tx_rings(vsi);
ice_vsi_free_rx_rings(vsi);
}
/**
- * ice_ena_vsi - resume a VSI
- * @vsi: the VSI being resume
- * @locked: is the rtnl_lock already held
+ * ice_ena_vsi_locked - resume a VSI (without taking the netdev lock)
+ * @vsi: VSI to resume
+ *
+ * Return: 0 on success, -errno on failure.
*/
-int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
+int ice_ena_vsi_locked(struct ice_vsi *vsi)
{
int err = 0;
@@ -2728,15 +2774,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
if (vsi->netdev && (vsi->type == ICE_VSI_PF ||
vsi->type == ICE_VSI_SF)) {
- if (netif_running(vsi->netdev)) {
- if (!locked)
- rtnl_lock();
-
+ if (netif_running(vsi->netdev))
err = ice_open_internal(vsi->netdev);
-
- if (!locked)
- rtnl_unlock();
- }
} else if (vsi->type == ICE_VSI_CTRL) {
err = ice_vsi_open_ctrl(vsi);
}
@@ -2745,11 +2784,34 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
}
/**
- * ice_dis_vsi - pause a VSI
+ * ice_ena_vsi - resume a VSI
+ * @vsi: VSI to resume
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int ice_ena_vsi(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+ int ret;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ret = ice_ena_vsi_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+
+ return ret;
+}
+
+/**
+ * ice_dis_vsi_locked - pause a VSI
* @vsi: the VSI being paused
- * @locked: is the rtnl_lock already held
+ *
+ * The caller must always hold the netdev lock.
*/
-void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+void ice_dis_vsi_locked(struct ice_vsi *vsi)
{
bool already_down = test_bit(ICE_VSI_DOWN, vsi->state);
@@ -2758,14 +2820,9 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
if (vsi->netdev && (vsi->type == ICE_VSI_PF ||
vsi->type == ICE_VSI_SF)) {
if (netif_running(vsi->netdev)) {
- if (!locked)
- rtnl_lock();
already_down = test_bit(ICE_VSI_DOWN, vsi->state);
if (!already_down)
ice_vsi_close(vsi);
-
- if (!locked)
- rtnl_unlock();
} else if (!already_down) {
ice_vsi_close(vsi);
}
@@ -2775,12 +2832,30 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
}
/**
- * ice_vsi_set_napi_queues - associate netdev queues with napi
+ * ice_dis_vsi - pause a VSI
+ * @vsi: the VSI being paused
+ */
+void ice_dis_vsi(struct ice_vsi *vsi)
+{
+ struct net_device *dev = vsi->netdev;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ice_dis_vsi_locked(vsi);
+
+ if (dev)
+ netdev_unlock(dev);
+}
+
+/**
+ * ice_vsi_set_napi_queues_locked - associate netdev queues with napi
* @vsi: VSI pointer
*
* Associate queue[s] with napi for all vectors.
+ * Must be called only with the netdev_lock taken.
*/
-void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
+void ice_vsi_set_napi_queues_locked(struct ice_vsi *vsi)
{
struct net_device *netdev = vsi->netdev;
int q_idx, v_idx;
@@ -2788,7 +2863,6 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
if (!netdev)
return;
- ASSERT_RTNL();
ice_for_each_rxq(vsi, q_idx)
if (vsi->rx_rings[q_idx] && vsi->rx_rings[q_idx]->q_vector)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
@@ -2802,17 +2876,37 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
ice_for_each_q_vector(vsi, v_idx) {
struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
- netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+ netif_napi_set_irq_locked(&q_vector->napi, q_vector->irq.virq);
}
}
/**
- * ice_vsi_clear_napi_queues - dissociate netdev queues from napi
+ * ice_vsi_set_napi_queues - associate VSI queues with NAPIs
* @vsi: VSI pointer
*
+ * Version of ice_vsi_set_napi_queues_locked() that takes the netdev_lock,
+ * to use it outside of the net_device_ops context.
+ */
+void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
+{
+ struct net_device *netdev = vsi->netdev;
+
+ if (!netdev)
+ return;
+
+ netdev_lock(netdev);
+ ice_vsi_set_napi_queues_locked(vsi);
+ netdev_unlock(netdev);
+}
+
+/**
+ * ice_vsi_clear_napi_queues_locked - dissociate netdev queues from napi
+ * @vsi: VSI to process
+ *
* Clear the association between all VSI queues queue[s] and napi.
+ * Must be called only with the netdev_lock taken.
*/
-void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
+void ice_vsi_clear_napi_queues_locked(struct ice_vsi *vsi)
{
struct net_device *netdev = vsi->netdev;
int q_idx, v_idx;
@@ -2820,12 +2914,11 @@ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
if (!netdev)
return;
- ASSERT_RTNL();
/* Clear the NAPI's interrupt number */
ice_for_each_q_vector(vsi, v_idx) {
struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
- netif_napi_set_irq(&q_vector->napi, -1);
+ netif_napi_set_irq_locked(&q_vector->napi, -1);
}
ice_for_each_txq(vsi, q_idx)
@@ -2835,6 +2928,25 @@ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
}
+/**
+ * ice_vsi_clear_napi_queues - dissociate VSI queues from NAPIs
+ * @vsi: VSI to process
+ *
+ * Version of ice_vsi_clear_napi_queues_locked() that takes the netdev lock,
+ * to use it outside of the net_device_ops context.
+ */
+void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
+{
+ struct net_device *netdev = vsi->netdev;
+
+ if (!netdev)
+ return;
+
+ netdev_lock(netdev);
+ ice_vsi_clear_napi_queues_locked(vsi);
+ netdev_unlock(netdev);
+}
+
/**
* ice_napi_add - register NAPI handler for the VSI
* @vsi: VSI for which NAPI handler is to be registered
@@ -3072,16 +3184,17 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi)
}
/**
- * ice_vsi_rebuild - Rebuild VSI after reset
+ * ice_vsi_rebuild_locked - Rebuild VSI after reset
* @vsi: VSI to be rebuild
* @vsi_flags: flags used for VSI rebuild flow
*
* Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or
* ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware.
+ * Should be called only under the netdev lock.
*
- * Returns 0 on success and negative value on failure
+ * Return: 0 on success, -errno on failure.
*/
-int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
+int ice_vsi_rebuild_locked(struct ice_vsi *vsi, u32 vsi_flags)
{
struct ice_coalesce_stored *coalesce;
int prev_num_q_vectors;
@@ -3102,8 +3215,8 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
if (ret)
goto unlock;
- ice_vsi_decfg(vsi);
- ret = ice_vsi_cfg_def(vsi);
+ ice_vsi_decfg_locked(vsi);
+ ret = ice_vsi_cfg_def_locked(vsi);
if (ret)
goto unlock;
@@ -3133,12 +3246,38 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
kfree(coalesce);
decfg:
if (ret)
- ice_vsi_decfg(vsi);
+ ice_vsi_decfg_locked(vsi);
unlock:
mutex_unlock(&vsi->xdp_state_lock);
return ret;
}
+/**
+ * ice_vsi_rebuild - Rebuild VSI after reset
+ * @vsi: VSI to be rebuild
+ * @vsi_flags: flags used for VSI rebuild flow
+ *
+ * Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or
+ * ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
+{
+ struct net_device *dev = vsi->netdev;
+ int ret;
+
+ if (dev)
+ netdev_lock(dev);
+
+ ret = ice_vsi_rebuild_locked(vsi, vsi_flags);
+
+ if (dev)
+ netdev_unlock(dev);
+
+ return ret;
+}
+
/**
* ice_is_reset_in_progress - check for a reset in progress
* @state: PF state field
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 1d1947a7fe11..50975fe7cab7 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -507,16 +507,15 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
/**
* ice_pf_dis_all_vsi - Pause all VSIs on a PF
* @pf: the PF
- * @locked: is the rtnl_lock already held
*/
-static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+static void ice_pf_dis_all_vsi(struct ice_pf *pf)
{
int node;
int v;
ice_for_each_vsi(pf, v)
if (pf->vsi[v])
- ice_dis_vsi(pf->vsi[v], locked);
+ ice_dis_vsi(pf->vsi[v]);
for (node = 0; node < ICE_MAX_PF_AGG_NODES; node++)
pf->pf_agg_node[node].num_vsis = 0;
@@ -605,7 +604,7 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
ice_clear_hw_tbls(hw);
/* disable the VSIs and their queues that are not already DOWN */
set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state);
- ice_pf_dis_all_vsi(pf, false);
+ ice_pf_dis_all_vsi(pf);
if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
ice_ptp_prepare_for_reset(pf, reset_type);
@@ -2943,9 +2942,9 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
goto resume_if;
}
}
- xdp_features_set_redirect_target(vsi->netdev, true);
+ xdp_features_set_redirect_target_locked(vsi->netdev, true);
} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
- xdp_features_clear_redirect_target(vsi->netdev);
+ xdp_features_clear_redirect_target_locked(vsi->netdev);
xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
@@ -3447,11 +3446,13 @@ static void ice_set_ops(struct ice_vsi *vsi)
if (ice_is_safe_mode(pf)) {
netdev->netdev_ops = &ice_netdev_safe_mode_ops;
+ netdev->request_ops_lock = true;
ice_set_ethtool_safe_mode_ops(netdev);
return;
}
netdev->netdev_ops = &ice_netdev_ops;
+ netdev->request_ops_lock = true;
netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
netdev->xdp_metadata_ops = &ice_xdp_md_ops;
ice_set_ethtool_ops(netdev);
@@ -4058,6 +4059,7 @@ bool ice_is_wol_supported(struct ice_hw *hw)
* @locked: is adev device_lock held
*
* Only change the number of queues if new_tx, or new_rx is non-0.
+ * Note that it should be called only with the netdev lock taken.
*
* Returns 0 on success.
*/
@@ -4083,7 +4085,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
/* set for the next time the netdev is started */
if (!netif_running(vsi->netdev)) {
- err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ err = ice_vsi_rebuild_locked(vsi, ICE_VSI_FLAG_NO_INIT);
if (err)
goto rebuild_err;
dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
@@ -4091,7 +4093,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
}
ice_vsi_close(vsi);
- err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ err = ice_vsi_rebuild_locked(vsi, ICE_VSI_FLAG_NO_INIT);
if (err)
goto rebuild_err;
@@ -5437,7 +5439,7 @@ static void ice_prepare_for_shutdown(struct ice_pf *pf)
dev_dbg(ice_pf_to_dev(pf), "Tearing down internal switch for shutdown\n");
/* disable the VSIs and their queues that are not already DOWN */
- ice_pf_dis_all_vsi(pf, false);
+ ice_pf_dis_all_vsi(pf);
ice_for_each_vsi(pf, v)
if (pf->vsi[v])
@@ -5473,16 +5475,17 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
/* Remap vectors and rings, after successful re-init interrupts */
ice_for_each_vsi(pf, v) {
- if (!pf->vsi[v])
+ struct ice_vsi *vsi = pf->vsi[v];
+
+ if (!vsi)
continue;
- ret = ice_vsi_alloc_q_vectors(pf->vsi[v]);
+ ret = ice_vsi_alloc_q_vectors(vsi);
if (ret)
goto err_reinit;
- ice_vsi_map_rings_to_vectors(pf->vsi[v]);
- rtnl_lock();
- ice_vsi_set_napi_queues(pf->vsi[v]);
- rtnl_unlock();
+
+ ice_vsi_map_rings_to_vectors(vsi);
+ ice_vsi_set_napi_queues(vsi);
}
ret = ice_req_irq_msix_misc(pf);
@@ -5495,13 +5498,15 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
return 0;
err_reinit:
- while (v--)
- if (pf->vsi[v]) {
- rtnl_lock();
- ice_vsi_clear_napi_queues(pf->vsi[v]);
- rtnl_unlock();
- ice_vsi_free_q_vectors(pf->vsi[v]);
- }
+ while (v--) {
+ struct ice_vsi *vsi = pf->vsi[v];
+
+ if (!vsi)
+ continue;
+
+ ice_vsi_clear_napi_queues(vsi);
+ ice_vsi_free_q_vectors(vsi);
+ }
return ret;
}
@@ -5564,14 +5569,17 @@ static int ice_suspend(struct device *dev)
* to CPU0.
*/
ice_free_irq_msix_misc(pf);
+
ice_for_each_vsi(pf, v) {
- if (!pf->vsi[v])
+ struct ice_vsi *vsi = pf->vsi[v];
+
+ if (!vsi)
continue;
- rtnl_lock();
- ice_vsi_clear_napi_queues(pf->vsi[v]);
- rtnl_unlock();
- ice_vsi_free_q_vectors(pf->vsi[v]);
+
+ ice_vsi_clear_napi_queues(vsi);
+ ice_vsi_free_q_vectors(vsi);
}
+
ice_clear_interrupt_scheme(pf);
pci_save_state(pdev);
@@ -6699,7 +6707,7 @@ static void ice_napi_enable_all(struct ice_vsi *vsi)
ice_init_moderation(q_vector);
if (q_vector->rx.rx_ring || q_vector->tx.tx_ring)
- napi_enable(&q_vector->napi);
+ napi_enable_locked(&q_vector->napi);
}
}
@@ -7198,7 +7206,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
if (q_vector->rx.rx_ring || q_vector->tx.tx_ring)
- napi_disable(&q_vector->napi);
+ napi_disable_locked(&q_vector->napi);
cancel_work_sync(&q_vector->tx.dim.work);
cancel_work_sync(&q_vector->rx.dim.work);
@@ -7498,7 +7506,7 @@ int ice_vsi_open(struct ice_vsi *vsi)
if (err)
goto err_set_qs;
- ice_vsi_set_napi_queues(vsi);
+ ice_vsi_set_napi_queues_locked(vsi);
}
err = ice_up_complete(vsi);
@@ -7584,7 +7592,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type)
vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx);
/* enable the VSI */
- err = ice_ena_vsi(vsi, false);
+ err = ice_ena_vsi(vsi);
if (err) {
dev_err(dev, "enable VSI failed, err %d, VSI index %d, type %s\n",
err, vsi->idx, ice_vsi_type_str(type));
@@ -9190,7 +9198,7 @@ static int ice_setup_tc_mqprio_qdisc(struct net_device *netdev, void *type_data)
return 0;
/* Pause VSI queues */
- ice_dis_vsi(vsi, true);
+ ice_dis_vsi_locked(vsi);
if (!hw && !test_bit(ICE_FLAG_TC_MQPRIO, pf->flags))
ice_remove_q_channels(vsi, true);
@@ -9229,14 +9237,14 @@ static int ice_setup_tc_mqprio_qdisc(struct net_device *netdev, void *type_data)
cur_rxq = vsi->num_rxq;
/* proceed with rebuild main VSI using correct number of queues */
- ret = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ ret = ice_vsi_rebuild_locked(vsi, ICE_VSI_FLAG_NO_INIT);
if (ret) {
/* fallback to current number of queues */
dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n");
vsi->req_txq = cur_txq;
vsi->req_rxq = cur_rxq;
clear_bit(ICE_RESET_FAILED, pf->state);
- if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) {
+ if (ice_vsi_rebuild_locked(vsi, ICE_VSI_FLAG_NO_INIT)) {
dev_err(dev, "Rebuild of main VSI failed again\n");
return ret;
}
@@ -9292,7 +9300,7 @@ static int ice_setup_tc_mqprio_qdisc(struct net_device *netdev, void *type_data)
vsi->all_enatc = 0;
}
/* resume VSI */
- ice_ena_vsi(vsi, true);
+ ice_ena_vsi_locked(vsi);
return ret;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index a730aa368c92..cd6ba53a873b 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -58,6 +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;
SET_NETDEV_DEVLINK_PORT(netdev, devlink_port);
err = register_netdev(netdev);
@@ -183,7 +184,9 @@ static void ice_sf_dev_remove(struct auxiliary_device *adev)
devlink = priv_to_devlink(sf_dev->priv);
devl_lock(devlink);
+ netdev_lock(vsi->netdev);
ice_vsi_close(vsi);
+ netdev_unlock(vsi->netdev);
ice_sf_decfg_netdev(vsi);
ice_devlink_destroy_sf_dev_port(sf_dev);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 0643017541c3..be0cb548487a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -33,9 +33,9 @@ ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector,
return;
if (enable)
- napi_enable(&q_vector->napi);
+ napi_enable_locked(&q_vector->napi);
else
- napi_disable(&q_vector->napi);
+ napi_disable_locked(&q_vector->napi);
}
/**
--
2.54.0
^ permalink raw reply related
* [PATCH iwl-next v5 4/5] ice: implement Rx queue management ops
From: Alexander Lobakin @ 2026-05-05 15:29 UTC (permalink / raw)
To: intel-wired-lan
Cc: Alexander Lobakin, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Kohei Enju, Jacob Keller, Aleksandr Loktionov,
nxne.cnse.osdt.itp.upstreaming, netdev, linux-kernel
In-Reply-To: <20260505152923.1040589-1-aleksander.lobakin@intel.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@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
drivers/net/ethernet/intel/ice/ice_lib.h | 5 +
drivers/net/ethernet/intel/ice/ice_txrx.h | 2 +
drivers/net/ethernet/intel/ice/ice_base.c | 182 +++++++++++++++-----
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 ++-
6 files changed, 165 insertions(+), 54 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 476fa54ec4e8..e1e85976e523 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"
@@ -135,4 +137,7 @@ 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_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 5e517f219379..7c22b2015067 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -462,6 +462,8 @@ 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);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1add82d894bb..4e0b8895c303 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -653,6 +653,43 @@ 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->truesize);
+ 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
@@ -691,19 +728,10 @@ 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;
-
- err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
- ring->q_index,
- ring->q_vector->napi.napi_id,
- ring->truesize);
- if (err)
- goto err_destroy_fq;
-
- xdp_rxq_info_attach_page_pool(&ring->xdp_rxq,
- ring->pp);
}
}
@@ -712,7 +740,7 @@ 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) {
@@ -743,12 +771,12 @@ 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;
}
@@ -1460,27 +1488,7 @@ 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;
@@ -1519,23 +1527,35 @@ 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;
@@ -1553,10 +1573,6 @@ 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);
@@ -1577,3 +1593,81 @@ 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_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 50975fe7cab7..a88f9e3c0077 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3452,7 +3452,7 @@ 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 cd6ba53a873b..8d1541712abc 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 4ca1a0602307..43b467076027 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -531,17 +531,13 @@ 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 */
@@ -570,8 +566,12 @@ 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);
@@ -581,6 +581,16 @@ 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
--
2.54.0
^ permalink raw reply related
* [PATCH iwl-next v5 5/5] ice: add support for transmitting unreadable frags
From: Alexander Lobakin @ 2026-05-05 15:29 UTC (permalink / raw)
To: intel-wired-lan
Cc: Alexander Lobakin, Tony Nguyen, Przemek Kitszel, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Kohei Enju, Jacob Keller, Aleksandr Loktionov,
nxne.cnse.osdt.itp.upstreaming, netdev, linux-kernel
In-Reply-To: <20260505152923.1040589-1-aleksander.lobakin@intel.com>
Advertise netmem Tx support in ice. The only change needed is to set
ICE_TX_BUF_FRAG conditionally, only when skb_frag_is_net_iov() is
false. Otherwise, the Tx buffer type will be ICE_TX_BUF_EMPTY and
the driver will skip the DMA unmapping operation.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
drivers/net/ethernet/intel/ice/ice_main.c | 1 +
drivers/net/ethernet/intel/ice/ice_sf_eth.c | 1 +
drivers/net/ethernet/intel/ice/ice_txrx.c | 17 +++++++++++++----
3 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a88f9e3c0077..0e61b38e53a5 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3453,6 +3453,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
netdev->netdev_ops = &ice_netdev_ops;
netdev->queue_mgmt_ops = &ice_queue_mgmt_ops;
+ netdev->netmem_tx = true;
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 8d1541712abc..fdf98aa431ba 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -59,6 +59,7 @@ static int ice_sf_cfg_netdev(struct ice_dynamic_port *dyn_port,
ether_addr_copy(netdev->perm_addr, dyn_port->hw_addr);
netdev->netdev_ops = &ice_sf_netdev_ops;
netdev->queue_mgmt_ops = &ice_queue_mgmt_ops;
+ netdev->netmem_tx = true;
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 43b467076027..1d97e2cc2ade 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -113,11 +113,17 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc,
static void
ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
{
- if (tx_buf->type != ICE_TX_BUF_XDP_TX && dma_unmap_len(tx_buf, len))
+ switch (tx_buf->type) {
+ case ICE_TX_BUF_DUMMY:
+ case ICE_TX_BUF_FRAG:
+ case ICE_TX_BUF_SKB:
+ case ICE_TX_BUF_XDP_XMIT:
dma_unmap_page(ring->dev,
dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len),
DMA_TO_DEVICE);
+ break;
+ }
switch (tx_buf->type) {
case ICE_TX_BUF_DUMMY:
@@ -338,12 +344,14 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget)
}
/* unmap any remaining paged data */
- if (dma_unmap_len(tx_buf, len)) {
+ if (tx_buf->type != ICE_TX_BUF_EMPTY) {
dma_unmap_page(tx_ring->dev,
dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len),
DMA_TO_DEVICE);
+
dma_unmap_len_set(tx_buf, len, 0);
+ tx_buf->type = ICE_TX_BUF_EMPTY;
}
}
ice_trace(clean_tx_irq_unmap_eop, tx_ring, tx_desc, tx_buf);
@@ -1495,7 +1503,8 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
DMA_TO_DEVICE);
tx_buf = &tx_ring->tx_buf[i];
- tx_buf->type = ICE_TX_BUF_FRAG;
+ if (!skb_frag_is_net_iov(frag))
+ tx_buf->type = ICE_TX_BUF_FRAG;
}
/* record SW timestamp if HW timestamp is not available */
@@ -2377,7 +2386,7 @@ void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring)
}
/* unmap the data header */
- if (dma_unmap_len(tx_buf, len))
+ if (tx_buf->type != ICE_TX_BUF_EMPTY)
dma_unmap_single(tx_ring->dev,
dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len),
--
2.54.0
^ permalink raw reply related
* Re: [PATCH net 2/5] net: dsa: mt7530: preserve VLAN tags on trapped link-local frames
From: Chester A. Unal @ 2026-05-05 15:37 UTC (permalink / raw)
To: Daniel Golle, Andrew Lunn, Vladimir Oltean, David S. Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Matthias Brugger,
AngeloGioacchino Del Regno, DENG Qingfang, Florian Fainelli,
Arınç ÜNAL, Sean Wang, netdev, linux-kernel,
linux-arm-kernel, linux-mediatek
In-Reply-To: <3ad4b724d7ae6250b8429d50fe913d2dca07a3f9.1777986341.git.daniel@makrotopia.org>
Hey Daniel.
On 05/05/2026 15:16, Daniel Golle wrote:
> The BPC, RGAC1 and RGAC2 registers control the handling of link-local
> frames with reserved MAC DAs (01:80:C2:00:00:0x). These frames are
> correctly trapped to the CPU port, but the egress VLAN tag attribute was
> set to MT7530_VLAN_EG_UNTAGGED which causes the switch to strip any
> VLAN tags from trapped frames before they reach the CPU.
>
> This causes VLAN-tagged link-local frames (STP BPDUs, LLDP, PTP Peer
> Delay Requests) to arrive at the CPU without their VLAN tag, so they
> are delivered to the base network interface instead of the VLAN
> sub-interface. The DSA local_termination selftest confirms this: all
> link-local protocol tests on VLAN upper interfaces fail.
>
> Set the EG_TAG attribute to MT7530_VLAN_EG_DISABLED (system default)
> so that the switch does not modify VLAN tags in trapped frames. This
> way VLAN-tagged frames retain their original tag and are delivered to
> the correct VLAN sub-interface, matching the behavior of non-trapped
> frames which pass through without VLAN tag modification.
>
> Fixes: 69ddba9d170b ("net: dsa: mt7530: fix handling of all link-local frames")
> Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Thank you for this patch. Could you please confirm that it conforms to the
findings documented on this patch log?
https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=e8bf353577f382c7066c661fed41b2adc0fc7c40
Cheers.
Chester A.
^ permalink raw reply
* [PATCH net] tcp: tcp_child_process() related UAF
From: Eric Dumazet @ 2026-05-05 15:39 UTC (permalink / raw)
To: David S . Miller, Jakub Kicinski, Paolo Abeni
Cc: Simon Horman, Neal Cardwell, Kuniyuki Iwashima, netdev,
eric.dumazet, Eric Dumazet, Damiano Melotti
tcp_child_process( .. child ...) currently calls sock_put(child).
Unfortunately @child (named @nsk in callers) can be used after
this point to send a RST packet.
To fix this UAF, I remove the sock_put() from tcp_child_process()
and let the callers handle this after it is safe.
Remove @rsk variable in tcp_v4_do_rcv() and change tcp_v6_do_rcv()
so that both functions look the same.
Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Reported-by: Damiano Melotti <melotti@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_ipv4.c | 14 ++++++--------
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv6/tcp_ipv6.c | 13 ++++++++-----
3 files changed, 15 insertions(+), 14 deletions(-)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8fc24c3743c5f905f8e07a26fb0edb40fb6ab767..c0526cc0398049fb34b5de20a1175d54942e80cd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1827,7 +1827,6 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
enum skb_drop_reason reason;
- struct sock *rsk;
reason = psp_sk_rx_policy_check(sk, skb);
if (reason)
@@ -1863,24 +1862,21 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
if (nsk != sk) {
reason = tcp_child_process(sk, nsk, skb);
- if (reason) {
- rsk = nsk;
+ sock_put(nsk);
+ if (reason)
goto reset;
- }
return 0;
}
} else
sock_rps_save_rxhash(sk, skb);
reason = tcp_rcv_state_process(sk, skb);
- if (reason) {
- rsk = sk;
+ if (reason)
goto reset;
- }
return 0;
reset:
- tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason));
+ tcp_v4_send_reset(sk, skb, sk_rst_convert_drop_reason(reason));
discard:
sk_skb_reason_drop(sk, skb, reason);
/* Be careful here. If this function gets more complicated and
@@ -2193,8 +2189,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
rst_reason = sk_rst_convert_drop_reason(drop_reason);
tcp_v4_send_reset(nsk, skb, rst_reason);
+ sock_put(nsk);
goto discard_and_relse;
}
+ sock_put(nsk);
sock_put(sk);
return 0;
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 199f0b579e89cf25689e74a8d37bb0c022a6c92d..e6092c3ac840bdc1f62d4435c414e7f79edc10c2 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -1012,6 +1012,6 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
}
bh_unlock_sock(child);
- sock_put(child);
+
return reason;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2c3f7a739709d7b89f376f79b71173e5f2d8e64e..51583aef0643e92c961fc00f48f1192184d087ed 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1617,12 +1617,13 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (sk->sk_state == TCP_LISTEN) {
struct sock *nsk = tcp_v6_cookie_check(sk, skb);
+ if (!nsk)
+ return 0;
if (nsk != sk) {
- if (nsk) {
- reason = tcp_child_process(sk, nsk, skb);
- if (reason)
- goto reset;
- }
+ reason = tcp_child_process(sk, nsk, skb);
+ sock_put(nsk);
+ if (reason)
+ goto reset;
return 0;
}
} else
@@ -1827,8 +1828,10 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
rst_reason = sk_rst_convert_drop_reason(drop_reason);
tcp_v6_send_reset(nsk, skb, rst_reason);
+ sock_put(nsk);
goto discard_and_relse;
}
+ sock_put(nsk);
sock_put(sk);
return 0;
}
--
2.54.0.545.g6539524ca2-goog
^ permalink raw reply related
* Re: [PATCH net v2] net: mana: Optimize irq affinity for low vcpu configs
From: Yury Norov @ 2026-05-05 15:43 UTC (permalink / raw)
To: Shradha Gupta
Cc: Dexuan Cui, Wei Liu, Haiyang Zhang, K. Y. Srinivasan, Andrew Lunn,
David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Konstantin Taranov, Simon Horman, Erni Sri Satya Vennela,
Dipayaan Roy, Shiraz Saleem, Michael Kelley, Long Li, Yury Norov,
linux-hyperv, linux-kernel, netdev, Paul Rosswurm, Shradha Gupta,
Saurabh Singh Sengar, stable
In-Reply-To: <afmK531eRcPCecKm@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net>
On Mon, May 04, 2026 at 11:15:03PM -0700, Shradha Gupta wrote:
> On Sat, May 02, 2026 at 01:15:36PM -0400, Yury Norov wrote:
> > On Sat, May 02, 2026 at 07:37:43AM -0700, Shradha Gupta wrote:
> > > On Fri, May 01, 2026 at 12:22:20PM -0400, Yury Norov wrote:
> > > > On Wed, Apr 29, 2026 at 02:06:37AM -0700, Shradha Gupta wrote:
> > > > > In mana driver, the number of IRQs allocated is capped by the
> > > > > min(num_cpu + 1, queue count). In cases, where the IRQ count is greater
> > > > > than the vcpu count, we want to utilize all the vCPUs, irrespective of
> > > > > their NUMA/core bindings.
> > > > >
> > > > > This is important, especially in the envs where number of vCPUs are so
> > > > > few that the softIRQ handling overhead on two IRQs on the same vCPU is
> > > > > much more than their overheads if they were spread across sibling vCPUs.
> > > > >
> > > > > This behaviour is more evident with dynamic IRQ allocation. Since MANA
> > > > > IRQs are assigned at a later stage compared to static allocation, other
> > > > > device IRQs may already be affinitized to the vCPUs. As a result, IRQ
> > > > > weights become imbalanced, causing multiple MANA IRQs to land on the
> > > > > same vCPU, while some vCPUs have none.
> > > > >
> > > > > In such cases when many parallel TCP connections are tested, the
> > > > > throughput drops significantly.
> > > > >
> > > > > Test envs:
> > > > > =======================================================
> > > > > Case 1: without this patch
> > > > > =======================================================
> > > > > 4 vcpu(2 cores), 5 MANA IRQs (1 HWC + 4 Queue)
> > > > >
> > > > > TYPE effective vCPU aff
> > > > > =======================================================
> > > > > IRQ0: HWC 0
> > > > > IRQ1: mana_q1 0
> > > > > IRQ2: mana_q2 2
> > > > > IRQ3: mana_q3 0
> > > > > IRQ4: mana_q4 3
> > > > >
> > > > > %soft on each vCPU(mpstat -P ALL 1) on receiver
> > > > > vCPU 0 1 2 3
> > > > > =======================================================
> > > > > pass 1: 38.85 0.03 24.89 24.65
> > > > > pass 2: 39.15 0.03 24.57 25.28
> > > > > pass 3: 40.36 0.03 23.20 23.17
> > > > >
> > > > > =======================================================
> > > > > Case 2: with this patch
> > > > > =======================================================
> > > > > 4 vcpu(2 cores), 5 MANA IRQs (1 HWC + 4 Queue)
> > > > >
> > > > > TYPE effective vCPU aff
> > > > > =======================================================
> > > > > IRQ0: HWC 0
> > > > > IRQ1: mana_q1 0
> > > > > IRQ2: mana_q2 1
> > > > > IRQ3: mana_q3 2
> > > > > IRQ4: mana_q4 3
> > > > >
> > > > > %soft on each vCPU(mpstat -P ALL 1) on receiver
> > > > > vCPU 0 1 2 3
> > > > > =======================================================
> > > > > pass 1: 15.42 15.85 14.99 14.51
> > > > > pass 2: 15.53 15.94 15.81 15.93
> > > > > pass 3: 16.41 16.35 16.40 16.36
> > > > >
> > > > > =======================================================
> > > > > Throughput Impact(in Gbps, same env)
> > > > > =======================================================
> > > > > TCP conn with patch w/o patch
> > > > > 20480 15.65 7.73
> > > > > 10240 15.63 8.93
> > > > > 8192 15.64 9.69
> > > > > 6144 15.64 13.16
> > > > > 4096 15.69 15.75
> > > > > 2048 15.69 15.83
> > > > > 1024 15.71 15.28
> > > > >
> > > > > Fixes: 755391121038 ("net: mana: Allocate MSI-X vectors dynamically")
> > > > > Cc: stable@vger.kernel.org
> > > > > Co-developed-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
> > > > > Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
> > > > > Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
> > > > > Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
> > > > > ---
> > > > > Changes in v2
> > > > > * Removed the unused skip_first_cpu variable
> > > > > * fixed exit condition in irq_setup_linear() with len == 0
> > > > > * changed return type of irq_setup_linear() as it will always be 0
> > > > > * removed the unnecessary rcu_read_lock() in irq_setup_linear()
> > > > > * added appropriate comments to indicate expected behaviour when
> > > > > IRQs are more than or equal to num_online_cpus()
> > > > > ---
> > > > > .../net/ethernet/microsoft/mana/gdma_main.c | 47 ++++++++++++++++---
> > > > > 1 file changed, 40 insertions(+), 7 deletions(-)
> > > > >
> > > > > diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > > > > index 098fbda0d128..d740d1dc43da 100644
> > > > > --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > > > > +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> > > > > @@ -167,6 +167,8 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
> > > > > } else {
> > > > > /* If dynamic allocation is enabled we have already allocated
> > > > > * hwc msi
> > > > > + * Also, we make sure in this case the following is always true
> > > > > + * (num_msix_usable - 1 HWC) <= num_online_cpus()
> > > > > */
> > > > > gc->num_msix_usable = min(resp.max_msix, num_online_cpus() + 1);
> > > > > }
> > > > > @@ -1672,11 +1674,24 @@ static int irq_setup(unsigned int *irqs, unsigned int len, int node,
> > > > > return 0;
> > > > > }
> > > > >
> > > > > +/* should be called with cpus_read_lock() held */
> > > > > +static void irq_setup_linear(unsigned int *irqs, unsigned int len)
> > > > > +{
> > > > > + int cpu;
> > > > > +
> > > > > + for_each_online_cpu(cpu) {
> > > > > + if (len == 0)
> > > > > + break;
> > > > > +
> > > > > + irq_set_affinity_and_hint(*irqs++, cpumask_of(cpu));
> > > > > + len--;
> > > > > + }
> > > > > +}
> > > > > +
> > > > > static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
> > > > > {
> > > > > struct gdma_context *gc = pci_get_drvdata(pdev);
> > > > > struct gdma_irq_context *gic;
> > > > > - bool skip_first_cpu = false;
> > > > > int *irqs, irq, err, i;
> > > > >
> > > > > irqs = kmalloc_objs(int, nvec);
> > > >
> > > > So what about WARN_ON() and nvec adjustment before kmalloc?
> > > Hey Yury,
> > >
> > > I am still a bit unsure about the WARN_ON() before kmalloc, as after
> > > that also, in the same function till we take the cpus_read_lock() the
> > > num_online_cpus() can change(or reduce). That's why I introduced the
> > > dev_dbg() to capture hot-remove edge case.
> >
> > OK.
> >
> > > Do you still think it adds more value?
> >
> > It's your driver, so you know better. I just wonder because you said
> > it's good to add WARN_ON(), and then didn't do that.
> >
> > > >
> > > > > @@ -1722,13 +1737,31 @@ static int mana_gd_setup_dyn_irqs(struct pci_dev *pdev, int nvec)
> > > > > * first CPU sibling group since they are already affinitized to HWC IRQ
> > > > > */
> > > > > cpus_read_lock();
> > > > > - if (gc->num_msix_usable <= num_online_cpus())
> > > > > - skip_first_cpu = true;
> > > > > + if (gc->num_msix_usable <= num_online_cpus()) {
> > > > > + err = irq_setup(irqs, nvec, gc->numa_node, true);
> > > > > + if (err) {
> > > > > + cpus_read_unlock();
> > > > > + goto free_irq;
> > > >
> > > > One thing puzzles me: if you skip first CPU with this 'true', and the
> > > > gc->num_msix_usable == num_online_cpus(), it's one more than you can
> > > > distribute. What do I miss?
> > > >
> > >
> > > Let me explain this case a bit better then,
> > >
> > > - num_msix_usable = HWC IRQ + Queue IRQ
> > > - nvec in this functions is only Queue IRQ (HWC already setup)
> > >
> > > When num_online_cpus == num_msix_usable:
> > > - nvec = num_online_cpus - 1
> > > - first CPU is already assigned to HWC IRQ, so skip it
> > > - Queue IRQs fit in the remaining CPUs
> > >
> > > please let me know if I did not get your question right
> >
> > Can you put that in a comment?
>
> Sure I will. thanks
>
> >
> > > > > + }
> > > > > + } else {
> > > > > + /*
> > > > > + * When num_msix_usable are more than num_online_cpus, we try to
> > > > > + * make sure we are using all vcpus. In such a case NUMA or
> > > > > + * CPU core affinity does not matter.
> > > >
> > > > If it doesn't matter, why don't you assign each IRQ to all CPUs then?
> > > > In theory, the system would have most of flexibility to balance them.
> > > >
> > >
> > > Okay, let me fix the comment and elaborate on this. It doesn't matter
> > > because in such a case we want to anyway exhaust and distribute the
> > > Queue IRQs to all vCPUs.
> > > We don't want to rely on the system's balancer in this case as it could
> > > be skewed by other devices' IRQ weights
> >
> > I don't understand this. If I want to reserve some CPUs to solely
> > handle IRQs from my high-priority hardware, then I configure my system
> > accordingly. For example, assign all non-networking IRQs on CPU0, and
> > all networking IRQs to all CPUs.
> >
> > In your case, you distribute IRQs evenly, which means you've no
> > preferred CPUs. So, assuming the system is only running your IRQ
> > driver, it's at max is as good as all-CPU distribution. In case of
> > heavy loading some particular CPU, your scheme could cause
> > corresponding IRQs to starve.
> >
> > I recall, when we was working on irq_setup(), the original idea was to
> > distribute IRQs one-to-one, but than I suggested the
> >
> > irq_set_affinity_and_hint(*irqs++, topology_sibling_cpumask(cpu));
> >
> > and after experiments, you agreed on that.
> >
> > Can you please run your throughput test for my suggested distribution
> > too? Would be also nice to see how each distribution works when some
> > CPUs are under stress.
> >
> > Thanks,
> > Yury
>
> The design of irq_setup() works exactly how we want it for our IRQs for
> almost all of our usecases, so we want to keep that as is. The only
> scenarios where this is an issue in terms of significant throughput drop
> is when we are working with low vCPU VMs (vCPU <= 4 with high TCP
> connection counts) and where there are additional NVMe devices attached
> to the VM.
>
> The current patch about utilizing all the vCPUs helps in that case and
> doesn't cause any regression for other cases.
>
> This linear path is only taken when num_msix_usable > num_online_cpus(),
> which is limited to low-vCPU VMs. Larger VMs continue using irq_setup()
> as before.
>
> We can definately get our throughput run results on other suggestions
> you have. And about that, I just needed a bit more clarity on what to
> test against. Are you suggesting, with irq_setup() intact and in use, we
> configure the non-mana IRQs to say CPU0 and capture the numbers?
Can you try this:
while(len--)
// Or cpu_online_mask or cpu_all_mask?
irq_set_affinity_and_hint(*irqs++, NULL);
And compare it to the linear version under your vCPU scenario?
Can you run your throughput test alone and on parallel with some
IRQ torture test?
stress-ng --timer 4 --timeout 60s
And maybe pin the stress test to the default CPU. Assuming it's 0:
taskset -c 0 stress-ng --timer 4 --timeout 60s
Unless the 'linear' version is significantly faster, I'd stick to the
above.
Thanks,
Yury
^ permalink raw reply
* Re: [PATCH 05/11] selftests: Add additional kernel functions to tools/include/
From: Jason Gunthorpe @ 2026-05-05 15:43 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches
In-Reply-To: <afkUO56H6KPy5afA@google.com>
On Mon, May 04, 2026 at 09:48:43PM +0000, David Matlack wrote:
> On 2026-04-30 09:08 PM, Jason Gunthorpe wrote:
> > These are needed by the VFIO mlx5 selftest in the following patches,
> > which includes some headers from mlx5 and also needs a few more
> > MMIO-related features.
> >
> > - DECLARE_FLEX_ARRAY in new tools/include/linux/stddef.h (wraps
> > existing __DECLARE_FLEX_ARRAY from uapi/linux/stddef.h)
>
> Is this needed? I don't see it used anywhere.
>
> $ git grep DECLARE_FLEX_ARRAY tools/testing/selftests/vfio
I think it was used in an earlier version, I can drop it
Jason
^ permalink raw reply
* Re: [PATCH net v5 0/8] xsk: fix bugs around xsk skb allocation
From: Alexander Lobakin @ 2026-05-05 15:44 UTC (permalink / raw)
To: Jason Xing
Cc: davem, edumazet, kuba, pabeni, bjorn, magnus.karlsson,
maciej.fijalkowski, jonathan.lemon, sdf, ast, daniel, hawk,
john.fastabend, horms, andrew+netdev, bpf, netdev, Jason Xing
In-Reply-To: <20260502200722.53960-1-kerneljasonxing@gmail.com>
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Sat, 2 May 2026 23:07:14 +0300
> From: Jason Xing <kernelxing@tencent.com>
>
> There are rare issues around xsk_build_skb(). Some of them
> were founded by Sashiko[1][2].
For the series:
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Just don't forget to look at Sashiko's replies, I haven't looked deep
into them, so can't say whether anything there makes sense.
>
> [1]: https://lore.kernel.org/all/20260415082654.21026-1-kerneljasonxing@gmail.com/
> [2]: https://lore.kernel.org/all/20260418045644.28612-1-kerneljasonxing@gmail.com/
>
> ---
> v5
> Link: https://lore.kernel.org/all/20260424053816.27965-1-kerneljasonxing@gmail.com/
> 1. reword patch 3
> 2. adjust the order of patch 6 that is now moved up to be patch 2)
> 3. use helper in patch (Stan)
>
> v4
> Link: https://lore.kernel.org/all/20260422033650.68457-1-kerneljasonxing@gmail.com/
> 1. fix 32-bit arch issue in patch 8 (Alexander && Maciej)
> 2. add acked-by tags (Stan)
>
> v3
> Link: https://lore.kernel.org/all/20260420082805.14844-1-kerneljasonxing@gmail.com/
> 1. use !xs->skb as the indicator of first frag in patch 3 (Stan)
> 2. move init skb after it's allocated successfully, so patch 4,5,6 have
> been adjusted accordingly (Stan)
> 3. do not support 32-bit arch (Stan)
> 4. add acked-by tags (Stan)
>
> v2
> Link: https://lore.kernel.org/all/20260418045644.28612-1-kerneljasonxing@gmail.com/#t
> 1. add four patches spotted by sashiko to fix buggy pre-existing
> behavior
> 2. adjust the order of 8 patches.
>
>
>
> Jason Xing (8):
> xsk: reject sw-csum UMEM binding to IFF_TX_SKB_NO_LINEAR devices
> xsk: free the skb when hitting the upper bound MAX_SKB_FRAGS
> xsk: handle NULL dereference of the skb without frags issue
> xsk: fix use-after-free of xs->skb in xsk_build_skb() free_err path
> xsk: prevent CQ desync when freeing half-built skbs in xsk_build_skb()
> xsk: avoid skb leak in XDP_TX_METADATA case
> xsk: fix xsk_addrs slab leak on multi-buffer error path
> xsk: fix u64 descriptor address truncation on 32-bit architectures
>
> net/xdp/xsk.c | 115 ++++++++++++++++++++++++++--------------
> net/xdp/xsk_buff_pool.c | 3 ++
> 2 files changed, 77 insertions(+), 41 deletions(-)
Thanks,
Olek
^ permalink raw reply
* Re: [PATCH 09/11] vfio: selftests: Add mlx5 driver - HW init and command interface
From: Jason Gunthorpe @ 2026-05-05 15:45 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches
In-Reply-To: <afkfP-8UHaoyLd5Y@google.com>
On Mon, May 04, 2026 at 10:35:43PM +0000, David Matlack wrote:
> On 2026-04-30 09:08 PM, Jason Gunthorpe wrote:
>
> > +/*
> > + * Driver state — overlaid on device->driver.region.vaddr.
> > + *
> > + * Contains both software-only state and HW-visible DMA buffers. HW buffers need
> > + * strict IOVA alignment.
> > + */
> > +struct mlx5st_device {
>
> Can we do s/mlx5st/mlx5/ on the series?
No, I don't want to do this. Since it is in tree I want to reserve the
mlx5_ prefix only for the main driver. The driver is huge, I do not
want to harm or confuse grep - that team will get mad.
Jason
^ permalink raw reply
* Re: [PATCH 10/11] vfio: selftests: Add mlx5 driver - data path and memcpy ops
From: Jason Gunthorpe @ 2026-05-05 15:49 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches
In-Reply-To: <afkghFm9Vo-SfF5c@google.com>
On Mon, May 04, 2026 at 10:41:08PM +0000, David Matlack wrote:
> On 2026-04-30 09:08 PM, Jason Gunthorpe wrote:
>
> > @@ -1368,6 +1716,11 @@ static void mlx5st_init(struct vfio_pci_device *device)
> > mlx5st_alloc_pd(dev);
> > mlx5st_create_mkey(dev);
> >
> > + mlx5st_setup_datapath(dev);
> > +
> > + device->driver.max_memcpy_size = 1 << 20;
> > + device->driver.max_memcpy_count = SQ_WQE_CNT - 1;
>
> What are these limits a function of? e.g. Is the 1MB size a hardware
> limit? Can we change SQ_WQE_CNT in the future to increase max count?
I have to check, I don't think there is a small limit on RDMA WRITE,
and SQ_WQE_CNT is just a number it could be somewhat bigger.
This may be a hold over from an ealier version where it was trying to
make a PAS array, and the PAS array was capped. I removed that but
would have missed this.
Jason
^ permalink raw reply
* Re: [PATCH 00/11] mlx5 support for VFIO self test
From: Jason Gunthorpe @ 2026-05-05 15:50 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches, Josh Hilke
In-Reply-To: <afkjkBq8B-4KjhS_@google.com>
On Mon, May 04, 2026 at 10:54:08PM +0000, David Matlack wrote:
> > The PF support flow requires a bunch more complicated stuff.
>
> Do you think it's worth supporting PFs? If anyone with a CX NIC can
> enable SR-IOV and run selftests on a VF then we can keep the driver
> somewhat simpler.
It turns out my test system cannot enable SR-IOV due to iommu_group
problems so I rather prefer to have this :) I had to hack a kernel up
to do the initial testing and it was very annoying.
Jason
^ permalink raw reply
* Re: [PATCH 07/11] vfio: selftests: Allow drivers to specify required region size
From: Jason Gunthorpe @ 2026-05-05 15:52 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches
In-Reply-To: <afkH3pMJKkIbElhI@google.com>
On Mon, May 04, 2026 at 08:55:58PM +0000, David Matlack wrote:
> On 2026-04-30 09:08 PM, Jason Gunthorpe wrote:
> > Add a region_size field to struct vfio_pci_driver_ops so drivers can
> > declare how much DMA-mapped region they need. The mlx5 driver will
> > need ~18MB for firmware pages. Existing drivers leave region_size as
> > 0 and get the current default of SZ_2M.
>
> I would like to get rid of the magic SZ_2M to make it easier for other
> tests to use the driver framework. Can you make this commit update all
> the drivers to set region_size? They can all use the same approach:
>
> struct vfio_pci_driver_ops foo_driver = {
> ...
> .region_size = roundup_pow_of_two(sizeof(struct foo)),
> ...
> };
Sure, lets put the roundup in the core code?
Jason
^ permalink raw reply
* Re: [PATCH 08/11] vfio: selftests: Add dev_dbg
From: Jason Gunthorpe @ 2026-05-05 15:53 UTC (permalink / raw)
To: David Matlack
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches
In-Reply-To: <afkMenQ_gfmLUJIy@google.com>
On Mon, May 04, 2026 at 09:15:38PM +0000, David Matlack wrote:
> On 2026-04-30 09:08 PM, Jason Gunthorpe wrote:
> > Enable it with a #define DEBUG at the top of the file. Allows leaving
> > behind debugging prints that are useful in case future changes are
> > required.
> >
> > Assisted-by: Claude:claude-opus-4.6
> > Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> > ---
> > .../selftests/vfio/lib/include/libvfio/vfio_pci_device.h | 6 ++++++
> > 1 file changed, 6 insertions(+)
> >
> > diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h b/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h
> > index bb4525abd01a22..2d587b988c09fa 100644
> > --- a/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h
> > +++ b/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h
> > @@ -38,6 +38,12 @@ struct vfio_pci_device {
> > #define dev_info(_dev, _fmt, ...) printf("%s: " _fmt, (_dev)->bdf, ##__VA_ARGS__)
> > #define dev_err(_dev, _fmt, ...) fprintf(stderr, "%s: " _fmt, (_dev)->bdf, ##__VA_ARGS__)
> >
> > +#ifdef DEBUG
> > +#define dev_dbg dev_info
> > +#else
> > +#define dev_dbg(_dev, _fmt, ...) do { } while (0)
>
> Can you add something to make sure the format strings are still
> validated by the compiler even if DEBUG is not defined? (since it
> will almost never be defined). e.g.
Yeah, I did this with the usual "if (false) printk()" technique
Jason
^ permalink raw reply
* Re: [PATCH net-next v3 2/3] r8152: Add support for the RTL8159 chip
From: Birger Koblitz @ 2026-05-05 15:54 UTC (permalink / raw)
To: Jakub Kicinski
Cc: andrew+netdev, davem, edumazet, pabeni, linux-usb, netdev,
linux-kernel, hsu.chih.kai, olek2
In-Reply-To: <20260505023022.877676-1-kuba@kernel.org>
On 05/05/2026 4:30 am, Jakub Kicinski wrote:
> This is an AI-generated review of your patch. The human sending this
> email has considered the AI review valid, or at least plausible.
> ---
> r8152: Add support for the RTL8159 chip
>
> This patch adds support for the RTL8159 chip as RTL_VER_17, reusing the
> RTL8157 initialization and USB power management paths. The bulk of the
> new code lives in r8157_hw_phy_cfg() to configure the RTL8159 PHY, and
> the USB product ID 0x815a is added to the device table.
> Is the leading space before ocp_byte_clr_bits here intentional? The rest
> of the switch statement uses a single tab for indentation. checkpatch.pl
> should catch this.
No, will fix in v4. Interesting, that checkpatch does not find this. I
am very sure I ran b4 prep --check before, it is near impossible to omit
that step before sending.
>
> Small typo, "nomal" -> "normal".
Will fix.
>> + /* close Sparse NEC, improve connect 5EUU calble performace */
> ^^^^^ ^^^^^^^^^
>
> Two typos here, "calble" -> "cable" and "performace" -> "performance".
Will fix.
> Is this "will include in v10" comment a reference to an internal Realtek
> source-tree revision? It does not appear to have meaning in the upstream
> tree and could be dropped or rephrased.
I will drop this.
>> @@ -8201,6 +8407,11 @@ static void r8156_init(struct r8152 *tp)
>> return;
>> }
>>
>> + if (tp->version == RTL_VER_17 && r8159_wait_backup_restore(tp)) {
>> + dev_err(&tp->intf->dev, "init failed, backup-restore timed out\n");
>> + return;
>> + }
>> +
>
> Should this path also set RTL8152_INACCESSIBLE on tp->flags, or should the
> init callback be changed to return an error that probe can honor, so that
> a half-initialized device is not exposed to userspace?
I'll set RTL8152_INACCESSIBLE in line with what is done already in the
rest of r8156_init()
>> @@ -8274,7 +8485,10 @@ static void r8156_init(struct r8152 *tp)
>> set_bit(GREEN_ETHERNET, &tp->flags);
>>
>> /* rx aggregation / 16 bytes Rx descriptor */
>> - if (tp->version == RTL_VER_16)
>> + if (tp->version == RTL_VER_17)
>> + ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL,
>> + RX_AGG_DISABLE | RX_DESC_16B | BIT(11));
> ^^^^^^
>
> What does BIT(11) in USB_USB_CTRL correspond to here, and is it
> RTL8159-specific?
>
> The commit message says the RTL8159 "reuses hardware features of the
> RTL8157 (RTL_VER_16)", but this path clears an extra bit that the
> RTL_VER_16 path does not. Since there is no symbolic name or comment,
> it is hard to tell whether RTL_VER_16 is missing this clear, whether
> RTL_VER_17 should not be clearing it, or whether it really is an
> RTL8159-only quirk.
>
> Could a named define and/or a short comment be added to describe what
> this bit does?
This was brought up before, and unfortunately, there is no documentation
whatsoever for this bit. Any guess at a name may turn out to be misleading.
But I will change the comment to read:
/* RX aggregation / 16 bytes RX descriptor
* BIT(11) is specific to RTL8159, with unknown meaning
*/
if (tp->version == RTL_VER_17)
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL,
RX_AGG_DISABLE | RX_DESC_16B | BIT(11));
else if (tp->version == RTL_VER_16)
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL, RX_AGG_DISABLE |
RX_DESC_16B);
else ...
Birger
^ permalink raw reply
* Re: [PATCH net-next 1/5] ionic: Small improvements in devcmd retry logic
From: Eric Joyner @ 2026-05-05 15:54 UTC (permalink / raw)
To: Jakub Kicinski
Cc: netdev, Brett Creeley, Andrew Lunn, David S. Miller, Eric Dumazet,
Paolo Abeni
In-Reply-To: <20260501163740.0f775e67@kernel.org>
On 5/1/2026 4:37 PM, Jakub Kicinski wrote:
> Caution: This message originated from an External Source. Use proper caution when opening attachments, clicking links, or responding.
>
>
> On Thu, 30 Apr 2026 20:15:51 -0700 Eric Joyner wrote:
>> If the timeout time is hit when the last attempt returned EAGAIN, the
>> driver returns -ETIMEDOUT. This causes the -EAGAIN result to be lost.
>> Fix this by returning -EAGAIN if the timeout time is hit and the
>> previous result matches.
>>
>> Also, reduce the sleep between the write to done and doorbell
>> registers. The msleep(1000) was initially added in an arbitrary
>> manner. However, this long of a sleep is problematic because
>> it reduces the number of retries when -EAGAIN is returned, which
>> may result in the devmcd giving up early due to the timeout. Fix
>> this by reducing the sleep to msleep(50).
>
> It would be useful to explain the significance of the return value
> to the callers. Are you trying to return EAGAIN to user space?
> Or some kernel-internal function catches this?
It looks like the -EAGAIN return value used here would have been used by
"[PATCH net 1/7] ionic: Allow the first devcmd to trigger deferred probe" [1];
this change got put in this series because we decided it was more of a net-next
change rather than a net change, but didn't realize these two were more
connected than what we saw at first glance.
1: https://lore.kernel.org/netdev/20260429210007.40015-2-eric.joyner@amd.com/
- Eric
^ permalink raw reply
* [PATCH net-next v4 0/3] r8152: Add support for the RTL8159 10Gbit USB Ethernet chip
From: Birger Koblitz @ 2026-05-05 15:56 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni
Cc: linux-usb, netdev, linux-kernel, Chih Kai Hsu, Birger Koblitz,
Andrew Lunn, Aleksander Jan Bajkowski
Add support for the RTL8159, which is a 10GBit USB-Ethernet adapter
chip in the RTL815x family of chips.
The RTL8159 re-uses the frame descriptor format and SRAM2 access introduced
with the RTL8157 as well as most of the setup and PM logic of the RTL8157.
The module was tested with a Lekuo DR59R11 USB-C 10GbE Ethernet Adapter:
[ 2502.906947] usb 2-1: new SuperSpeed USB device number 3 using xhci_hcd
[ 2502.927859] usb 2-1: New USB device found, idVendor=0bda, idProduct=815a, bcdDevice=30.00
[ 2502.927867] usb 2-1: New USB device strings: Mfr=1, Product=2, SerialNumber=7
[ 2502.927871] usb 2-1: Product: USB 10/100/1G/2.5G/5G/10G LAN
[ 2502.927873] usb 2-1: Manufacturer: Realtek
[ 2502.927875] usb 2-1: SerialNumber: 000388C9B3B5XXXX
[ 2503.063745] r8152-cfgselector 2-1: reset SuperSpeed USB device number 3 using xhci_hcd
[ 2503.123876] r8152 2-1:1.0: Requesting firmware: rtl_nic/rtl8159-1.fw
[ 2503.126267] r8152 2-1:1.0: PHY firmware installed 0 to be loaded: 20
[ 2503.156265] r8152 2-1:1.0: load rtl8159-1 v1 2026/01/01 successfully
[ 2503.270729] r8152 2-1:1.0 eth0: v1.12.13
[ 2503.289349] r8152 2-1:1.0 enx88c9b3b5xxxx: renamed from eth0
[ 2507.777055] r8152 2-1:1.0 enx88c9b3b5xxxx: carrier on
The RTL8159 adapter was tested against an AQC107 PCIe-card supporting
10GBit/s and an RTL8157 5Gbit USB-Ethernet adapter supporting 5GBit/s for
performance, link speed and EEE negotiation. Using USB3.2 Gen 2 (20GBit) with
the RTL8159 USB adapter and running iperf3 against the AQC107 PCIe
card resulted in 8.96 Gbits/sec transfer speed.
The code is based on the out-of-tree r8152 driver published by Realtek under
the GPL.
The RTL8159 requires firmware for the PHY in order to achieve a 10GBit link
speed. Without firmware, only 5GBit were achieved. The firmware can be
extracted from the out-of-tree r8152 driver-code where it is stored in the
ram17 u8-array. Code is added to use the existing firmware upload mechanism
of the driver for the RTL8157/9 PHY firmware code. The firmware will be
submitted separately to linux-firmware.
Signed-off-by: Birger Koblitz <mail@birger-koblitz.de>
---
Changes in v4:
- Fix formatting and spelling in r8157_hw_phy_cfg()
- Set RTL8152_INACCESSIBLE when r8159_wait_backup_restore() times out
- More documentation on RX aggregation/descriptor settings
- Link to v3: https://lore.kernel.org/r/20260502-rtl8159_net_next-v3-0-12c895d46cd6@birger-koblitz.de
Changes in v3:
- Various references to RTL8157 in the commit description changed
to RTL8159
- Fix incorrect use of OCP_EEE_ADV2 register for 10GBit
- Fix various instances where a gate on RTL_VER_16 was not extended
to RTL_VER_17, although RTL8159 needs the same code-path as RTL8157
- Explain use of 0x815a device-ID for RTL8159 in commit message
- Extend poll-timeout for backup-restore to 20ms
- Drop patch for IRQ mitigation
- Link to v2: https://lore.kernel.org/r/20260429-rtl8159_net_next-v2-0-bab3cd4e4c66@birger-koblitz.de
Changes in v2:
- Correct formatting of comments
- Order case statement values correctly
- Add error message when backup-restore fails
- Correct commit message of support for firmware upload
- Link to v1: https://lore.kernel.org/r/20260428-rtl8159_net_next-v1-0-52d03927b46f@birger-koblitz.de
---
Birger Koblitz (3):
r8152: Add support for 10Gbit Link Speeds and EEE
r8152: Add support for the RTL8159 chip
r8152: Add firmware upload capability for RTL8157/RTL8159
drivers/net/usb/r8152.c | 345 +++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 325 insertions(+), 20 deletions(-)
---
base-commit: 0f19519fdd22bc0f5429377da3a52327c5eee166
change-id: 20260427-rtl8159_net_next-4f778a614fa7
Best regards,
--
Birger Koblitz <mail@birger-koblitz.de>
^ permalink raw reply
* [PATCH net-next v4 1/3] r8152: Add support for 10Gbit Link Speeds and EEE
From: Birger Koblitz @ 2026-05-05 15:56 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni
Cc: linux-usb, netdev, linux-kernel, Chih Kai Hsu, Birger Koblitz,
Andrew Lunn, Aleksander Jan Bajkowski
In-Reply-To: <20260505-rtl8159_net_next-v4-0-1a648a9c4d8d@birger-koblitz.de>
The RTL8159 supports 10GBit Link speeds. Add support for this speed
in the setup and setting/getting through ethtool. Also add 10GBit EEE.
Add functionality for setup and ethtool get/set methods.
Signed-off-by: Birger Koblitz <mail@birger-koblitz.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Aleksander Jan Bajkowski <olek2@wp.pl>
---
drivers/net/usb/r8152.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 50 insertions(+), 3 deletions(-)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ae834876aa1acc7a9af08a4c01b7a984c4ab8433..05abfab1df94a571347196bfce7c232865e1058e 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -621,6 +621,7 @@ enum spd_duplex {
FORCE_1000M_FULL,
NWAY_2500M_FULL,
NWAY_5000M_FULL,
+ NWAY_10000M_FULL,
};
/* OCP_ALDPS_CONFIG */
@@ -742,6 +743,7 @@ enum spd_duplex {
#define BP4_SUPER_ONLY 0x1578 /* RTL_VER_04 only */
enum rtl_register_content {
+ _10000bps = BIT(14),
_5000bps = BIT(12),
_2500bps = BIT(10),
_1250bps = BIT(9),
@@ -757,6 +759,8 @@ enum rtl_register_content {
#define is_speed_2500(_speed) (((_speed) & (_2500bps | LINK_STATUS)) == (_2500bps | LINK_STATUS))
#define is_speed_5000(_speed) (((_speed) & (_5000bps | LINK_STATUS)) == (_5000bps | LINK_STATUS))
+#define is_speed_10000(_speed) (((_speed) & (_10000bps | LINK_STATUS)) \
+ == (_10000bps | LINK_STATUS))
#define is_flow_control(_speed) (((_speed) & (_tx_flow | _rx_flow)) == (_tx_flow | _rx_flow))
#define RTL8152_MAX_TX 4
@@ -1008,6 +1012,7 @@ struct r8152 {
u32 support_2500full:1;
u32 support_5000full:1;
+ u32 support_10000full:1;
u32 lenovo_macpassthru:1;
u32 dell_tb_rx_agg_bug:1;
u16 ocp_base;
@@ -1260,6 +1265,7 @@ enum tx_csum_stat {
#define RTL_ADVERTISED_1000_FULL BIT(5)
#define RTL_ADVERTISED_2500_FULL BIT(6)
#define RTL_ADVERTISED_5000_FULL BIT(7)
+#define RTL_ADVERTISED_10000_FULL BIT(8)
/* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
* The RTL chips use a 64 element hash table based on the Ethernet CRC.
@@ -6513,6 +6519,9 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
if (tp->support_5000full)
support |= RTL_ADVERTISED_5000_FULL;
+
+ if (tp->support_10000full)
+ support |= RTL_ADVERTISED_10000_FULL;
}
advertising &= support;
@@ -6559,9 +6568,10 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
r8152_mdio_write(tp, MII_CTRL1000, new1);
}
- if (tp->support_2500full || tp->support_5000full) {
+ if (tp->support_2500full || tp->support_5000full || tp->support_10000full) {
orig = ocp_reg_read(tp, OCP_10GBT_CTRL);
- new1 = orig & ~(MDIO_AN_10GBT_CTRL_ADV2_5G | MDIO_AN_10GBT_CTRL_ADV5G);
+ new1 = orig & ~(MDIO_AN_10GBT_CTRL_ADV2_5G | MDIO_AN_10GBT_CTRL_ADV5G
+ | MDIO_AN_10GBT_CTRL_ADV10G);
if (advertising & RTL_ADVERTISED_2500_FULL) {
new1 |= MDIO_AN_10GBT_CTRL_ADV2_5G;
@@ -6573,6 +6583,11 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
tp->ups_info.speed_duplex = NWAY_5000M_FULL;
}
+ if (advertising & RTL_ADVERTISED_10000_FULL) {
+ new1 |= MDIO_AN_10GBT_CTRL_ADV10G;
+ tp->ups_info.speed_duplex = NWAY_10000M_FULL;
+ }
+
if (orig != new1)
ocp_reg_write(tp, OCP_10GBT_CTRL, new1);
}
@@ -8708,7 +8723,10 @@ int rtl8152_get_link_ksettings(struct net_device *netdev,
linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
cmd->link_modes.supported, tp->support_5000full);
- if (tp->support_2500full || tp->support_5000full) {
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+ cmd->link_modes.supported, tp->support_10000full);
+
+ if (tp->support_2500full || tp->support_5000full || tp->support_10000full) {
u16 ocp_10gbt_ctrl = ocp_reg_read(tp, OCP_10GBT_CTRL);
u16 ocp_10gbt_stat = ocp_reg_read(tp, OCP_10GBT_STAT);
@@ -8737,6 +8755,19 @@ int rtl8152_get_link_ksettings(struct net_device *netdev,
if (is_speed_5000(rtl8152_get_speed(tp)))
cmd->base.speed = SPEED_5000;
}
+
+ if (tp->support_10000full) {
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+ cmd->link_modes.advertising,
+ ocp_10gbt_ctrl & MDIO_AN_10GBT_CTRL_ADV10G);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+ cmd->link_modes.lp_advertising,
+ ocp_10gbt_stat & MDIO_AN_10GBT_STAT_LP10G);
+
+ if (is_speed_10000(rtl8152_get_speed(tp)))
+ cmd->base.speed = SPEED_10000;
+ }
}
mutex_unlock(&tp->control);
@@ -8790,6 +8821,10 @@ static int rtl8152_set_link_ksettings(struct net_device *dev,
cmd->link_modes.advertising))
advertising |= RTL_ADVERTISED_5000_FULL;
+ if (test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+ cmd->link_modes.advertising))
+ advertising |= RTL_ADVERTISED_10000_FULL;
+
mutex_lock(&tp->control);
ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed,
@@ -8953,6 +8988,13 @@ static int r8153_get_eee(struct r8152 *tp, struct ethtool_keee *eee)
linkmode_set_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, common);
}
+ if (tp->support_10000full) {
+ linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, eee->supported);
+
+ if (speed & _10000bps)
+ linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common);
+ }
+
eee->eee_enabled = tp->eee_en;
if (speed & _1000bps)
@@ -9967,6 +10009,11 @@ static int rtl8152_probe_once(struct usb_interface *intf,
tp->speed = SPEED_5000;
tp->advertising |= RTL_ADVERTISED_5000_FULL;
}
+ if (tp->support_10000full &&
+ tp->udev->speed >= USB_SPEED_SUPER) {
+ tp->speed = SPEED_10000;
+ tp->advertising |= RTL_ADVERTISED_10000_FULL;
+ }
tp->advertising |= RTL_ADVERTISED_1000_FULL;
}
tp->duplex = DUPLEX_FULL;
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v4 3/3] r8152: Add firmware upload capability for RTL8157/RTL8159
From: Birger Koblitz @ 2026-05-05 15:56 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni
Cc: linux-usb, netdev, linux-kernel, Chih Kai Hsu, Birger Koblitz,
Aleksander Jan Bajkowski
In-Reply-To: <20260505-rtl8159_net_next-v4-0-1a648a9c4d8d@birger-koblitz.de>
The RTL8159 (RTL_VER_17) requires firmware for its PHY in order to work
at connection speeds > 5GBit. Add support for uploading firmware for
the PHY using the existing rtl8152_apply_firmware() function
in r8157_hw_phy_cfg() and set up the correct names for the firmware
files.
This also adds support for uploading firmware for the RTL8157
(RTL_VER_16) PHY, for which firmware is however not strictly necessary
to work. Still, this allows to upload newer versions of the firmware used
by this chip, e.g. to improve interoperability.
If no firmware is found, both the RTL8157 and the RTL8159 will continue
to work.
Signed-off-by: Birger Koblitz <mail@birger-koblitz.de>
Tested-by: Aleksander Jan Bajkowski <olek2@wp.pl>
---
drivers/net/usb/r8152.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 1e7f20348ac6def85106f1e8bab93a377980c77d..d281ad5ed78eded01876c6064aed95e1f78cfc05 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -4663,10 +4663,11 @@ static bool rtl8152_is_fw_phy_speed_up_ok(struct r8152 *tp, struct fw_phy_speed_
case RTL_VER_11:
case RTL_VER_12:
case RTL_VER_14:
- case RTL_VER_16:
goto out;
case RTL_VER_13:
case RTL_VER_15:
+ case RTL_VER_16:
+ case RTL_VER_17:
default:
break;
}
@@ -7982,12 +7983,14 @@ static void r8157_hw_phy_cfg(struct r8152 *tp)
data = r8153_phy_status(tp, 0);
switch (data) {
case PHY_STAT_EXT_INIT:
+ rtl8152_apply_firmware(tp, true);
ocp_reg_clr_bits(tp, 0xa466, BIT(0));
ocp_reg_clr_bits(tp, 0xa468, BIT(3) | BIT(1));
break;
case PHY_STAT_LAN_ON:
case PHY_STAT_PWRDN:
default:
+ rtl8152_apply_firmware(tp, false);
break;
}
@@ -9926,6 +9929,8 @@ static int rtl_ops_init(struct r8152 *tp)
#define FIRMWARE_8153C_1 "rtl_nic/rtl8153c-1.fw"
#define FIRMWARE_8156A_2 "rtl_nic/rtl8156a-2.fw"
#define FIRMWARE_8156B_2 "rtl_nic/rtl8156b-2.fw"
+#define FIRMWARE_8157_1 "rtl_nic/rtl8157-1.fw"
+#define FIRMWARE_8159_1 "rtl_nic/rtl8159-1.fw"
MODULE_FIRMWARE(FIRMWARE_8153A_2);
MODULE_FIRMWARE(FIRMWARE_8153A_3);
@@ -9934,6 +9939,8 @@ MODULE_FIRMWARE(FIRMWARE_8153B_2);
MODULE_FIRMWARE(FIRMWARE_8153C_1);
MODULE_FIRMWARE(FIRMWARE_8156A_2);
MODULE_FIRMWARE(FIRMWARE_8156B_2);
+MODULE_FIRMWARE(FIRMWARE_8157_1);
+MODULE_FIRMWARE(FIRMWARE_8159_1);
static int rtl_fw_init(struct r8152 *tp)
{
@@ -9972,6 +9979,12 @@ static int rtl_fw_init(struct r8152 *tp)
rtl_fw->pre_fw = r8153b_pre_firmware_1;
rtl_fw->post_fw = r8153c_post_firmware_1;
break;
+ case RTL_VER_16:
+ rtl_fw->fw_name = FIRMWARE_8157_1;
+ break;
+ case RTL_VER_17:
+ rtl_fw->fw_name = FIRMWARE_8159_1;
+ break;
default:
break;
}
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v4 2/3] r8152: Add support for the RTL8159 chip
From: Birger Koblitz @ 2026-05-05 15:56 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni
Cc: linux-usb, netdev, linux-kernel, Chih Kai Hsu, Birger Koblitz,
Aleksander Jan Bajkowski
In-Reply-To: <20260505-rtl8159_net_next-v4-0-1a648a9c4d8d@birger-koblitz.de>
The RTL8159 re-uses the packet descriptor format introduced with the
RTL8157 and other hardware features of the RTL8157 (RTL_VER_16) such
as the SRAM access. The support therefore consists in expanding the
existing RTL8157 code for initialization and USB power management
to also be used for the RTL8159 (RTL_VER_17).
Most of the additional code is added in r8157_hw_phy_cfg() to configure
the RTL8159 PHY.
Add support for the USB device ID of Realtek RTL8159-based adapters,
for which the product ID is 0x815a. Detect the RTL8159 as RTL_VER_17
and set it up.
Signed-off-by: Birger Koblitz <mail@birger-koblitz.de>
Tested-by: Aleksander Jan Bajkowski <olek2@wp.pl>
---
drivers/net/usb/r8152.c | 277 +++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 261 insertions(+), 16 deletions(-)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 05abfab1df94a571347196bfce7c232865e1058e..1e7f20348ac6def85106f1e8bab93a377980c77d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1247,6 +1247,7 @@ enum rtl_version {
RTL_VER_14,
RTL_VER_15,
RTL_VER_16,
+ RTL_VER_17,
RTL_VER_MAX
};
@@ -3432,6 +3433,7 @@ static void rtl8152_nic_reset(struct r8152 *tp)
break;
case RTL_VER_16:
+ case RTL_VER_17:
ocp_byte_clr_bits(tp, MCU_TYPE_PLA, PLA_CR, CR_RE | CR_TE);
break;
@@ -3471,6 +3473,9 @@ static void rtl_eee_plus_en(struct r8152 *tp, bool enable)
static void rtl_set_eee_plus(struct r8152 *tp)
{
+ if (tp->version == RTL_VER_17)
+ return rtl_eee_plus_en(tp, false);
+
if (rtl8152_get_speed(tp) & _10bps)
rtl_eee_plus_en(tp, true);
else
@@ -3656,6 +3661,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp)
case RTL_VER_13:
case RTL_VER_15:
case RTL_VER_16:
+ case RTL_VER_17:
ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_TIMEOUT,
640 / 8);
ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EXTRA_AGGR_TMR,
@@ -3700,6 +3706,7 @@ static void r8153_set_rx_early_size(struct r8152 *tp)
ocp_data / 8);
break;
case RTL_VER_16:
+ case RTL_VER_17:
ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE,
ocp_data / 16);
break;
@@ -4548,6 +4555,7 @@ static void rtl_clear_bp(struct r8152 *tp, u16 type)
break;
case RTL_VER_14:
case RTL_VER_16:
+ case RTL_VER_17:
default:
ocp_write_word(tp, type, USB_BP2_EN, 0);
bp_num = 16;
@@ -5818,6 +5826,7 @@ static void rtl_eee_enable(struct r8152 *tp, bool enable)
case RTL_VER_13:
case RTL_VER_15:
case RTL_VER_16:
+ case RTL_VER_17:
if (enable) {
r8156_eee_en(tp, true);
ocp_reg_write(tp, OCP_EEE_ADV, tp->eee_adv);
@@ -6408,7 +6417,7 @@ static int rtl8156_enable(struct r8152 *tp)
set_tx_qlen(tp);
rtl_set_eee_plus(tp);
- if (tp->version >= RTL_VER_12 && tp->version <= RTL_VER_16)
+ if (tp->version >= RTL_VER_12 && tp->version <= RTL_VER_17)
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_RX_AGGR_NUM, RX_AGGR_NUM_MASK);
r8153_set_rx_early_timeout(tp);
@@ -6817,7 +6826,7 @@ static void rtl8156_up(struct r8152 *tp)
return;
r8153b_u1u2en(tp, false);
- if (tp->version != RTL_VER_16)
+ if (tp->version < RTL_VER_16)
r8153_u2p3en(tp, false);
r8153_aldps_en(tp, false);
@@ -6831,7 +6840,7 @@ static void rtl8156_up(struct r8152 *tp)
ocp_byte_clr_bits(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, NOW_IS_OOB);
- if (tp->version == RTL_VER_16)
+ if (tp->version >= RTL_VER_16)
ocp_word_clr_bits(tp, MCU_TYPE_PLA, PLA_RCR1, BIT(3));
ocp_word_clr_bits(tp, MCU_TYPE_PLA, PLA_SFF_STS_7, MCU_BORW_EN);
@@ -6856,7 +6865,7 @@ static void rtl8156_up(struct r8152 *tp)
ocp_word_clr_bits(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, PLA_MCU_SPDWN_EN);
- if (tp->version != RTL_VER_16)
+ if (tp->version < RTL_VER_16)
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_SPEED_OPTION,
RG_PWRDN_EN | ALL_SPEED_OFF);
@@ -6868,10 +6877,10 @@ static void rtl8156_up(struct r8152 *tp)
}
r8153_aldps_en(tp, true);
- if (tp->version != RTL_VER_16)
+ if (tp->version < RTL_VER_16)
r8153_u2p3en(tp, true);
- if (tp->version != RTL_VER_16 && tp->udev->speed >= USB_SPEED_SUPER)
+ if (tp->version < RTL_VER_16 && tp->udev->speed >= USB_SPEED_SUPER)
r8153b_u1u2en(tp, true);
}
@@ -6886,7 +6895,7 @@ static void rtl8156_down(struct r8152 *tp)
PLA_MCU_SPDWN_EN);
r8153b_u1u2en(tp, false);
- if (tp->version != RTL_VER_16) {
+ if (tp->version < RTL_VER_16) {
r8153_u2p3en(tp, false);
r8153b_power_cut_en(tp, false);
}
@@ -7996,7 +8005,7 @@ static void r8157_hw_phy_cfg(struct r8152 *tp)
/* Advanced Power Saving parameter */
ocp_reg_set_bits(tp, 0xa430, BIT(0) | BIT(1));
- /* aldpsce force mode */
+ /* Disable ALDPS force mode */
ocp_reg_clr_bits(tp, 0xa44a, BIT(2));
switch (tp->version) {
@@ -8120,6 +8129,190 @@ static void r8157_hw_phy_cfg(struct r8152 *tp)
sram2_write_w0w1(tp, 0x807c, 0xff00, 0x5000);
sram2_write_w0w1(tp, 0x809d, 0xff00, 0x5000);
break;
+
+ case RTL_VER_17:
+ /* Disable bypass turn off clk in ALDPS */
+ ocp_byte_clr_bits(tp, MCU_TYPE_PLA, 0xd3c8, BIT(0));
+
+ /* Power level tuning
+ * test mode power level
+ */
+ sram_write_w0w1(tp, 0x8415, 0xff00, 0x9300);
+ /* normal link power level 10G, 5G, 2.5G */
+ sram_write_w0w1(tp, 0x81a3, 0xff00, 0x0f00);
+ sram_write_w0w1(tp, 0x81ae, 0xff00, 0x0f00);
+ sram_write_w0w1(tp, 0x81b9, 0xff00, 0xb900);
+ /* normal link TX filter */
+ sram2_write_w0w1(tp, 0x83b0, 0x0e00, 0);
+ sram2_write_w0w1(tp, 0x83c5, 0x0e00, 0);
+ sram2_write_w0w1(tp, 0x83da, 0x0e00, 0);
+ sram2_write_w0w1(tp, 0x83ef, 0x0e00, 0);
+
+ /* AFE power saving for 2.5G & 5G */
+ sram_write(tp, 0x8173, 0x8620);
+ sram_write(tp, 0x8175, 0x8671);
+
+ sram_write_w0w1(tp, 0x817c, 0, BIT(13));
+ sram_write_w0w1(tp, 0x8187, 0, BIT(13));
+ sram_write_w0w1(tp, 0x8192, 0, BIT(13));
+ sram_write_w0w1(tp, 0x819d, 0, BIT(13));
+ sram_write_w0w1(tp, 0x81a8, BIT(13), 0);
+ sram_write_w0w1(tp, 0x81b3, BIT(13), 0);
+ sram_write_w0w1(tp, 0x81be, 0, BIT(13));
+
+ sram_write_w0w1(tp, 0x817d, 0xff00, 0xa600);
+ sram_write_w0w1(tp, 0x8188, 0xff00, 0xa600);
+ sram_write_w0w1(tp, 0x8193, 0xff00, 0xa600);
+ sram_write_w0w1(tp, 0x819e, 0xff00, 0xa600);
+ sram_write_w0w1(tp, 0x81a9, 0xff00, 0x1400);
+ sram_write_w0w1(tp, 0x81b4, 0xff00, 0x1400);
+ sram_write_w0w1(tp, 0x81bf, 0xff00, 0xa600);
+
+ /* RFI parameter
+ * disable preset FBE
+ */
+ ocp_reg_clr_bits(tp, 0xaeaa, BIT(5) | BIT(3));
+ /* modify PGA for 5G&10G */
+ sram2_write(tp, 0x84f0, 0x201c);
+ sram2_write(tp, 0x84f2, 0x3117);
+ /* RFI parameter */
+ ocp_reg_write(tp, 0xaec6, 0x0000);
+ ocp_reg_write(tp, 0xae20, 0xffff);
+ ocp_reg_write(tp, 0xaece, 0xffff);
+ ocp_reg_write(tp, 0xaed2, 0xffff);
+ ocp_reg_write(tp, 0xaec8, 0x0000);
+ ocp_reg_clr_bits(tp, 0xaed0, BIT(0));
+ ocp_reg_write(tp, 0xadb8, 0x0150);
+ sram2_write_w0w1(tp, 0x8197, 0xff00, 0x5000);
+ sram2_write_w0w1(tp, 0x8231, 0xff00, 0x5000);
+ sram2_write_w0w1(tp, 0x82cb, 0xff00, 0x5000);
+ sram2_write_w0w1(tp, 0x82cd, 0xff00, 0x5700);
+ sram2_write_w0w1(tp, 0x8233, 0xff00, 0x5700);
+ sram2_write_w0w1(tp, 0x8199, 0xff00, 0x5700);
+
+ sram2_write(tp, 0x815a, 0x0150);
+ sram2_write(tp, 0x81f4, 0x0150);
+ sram2_write(tp, 0x828e, 0x0150);
+ sram2_write(tp, 0x81b1, 0x0000);
+ sram2_write(tp, 0x824b, 0x0000);
+ sram2_write(tp, 0x82e5, 0x0000);
+
+ sram2_write_w0w1(tp, 0x84f7, 0xff00, 0x2800);
+ ocp_reg_set_bits(tp, 0xaec2, BIT(12));
+ sram2_write_w0w1(tp, 0x81b3, 0xff00, 0xad00);
+ sram2_write_w0w1(tp, 0x824d, 0xff00, 0xad00);
+ sram2_write_w0w1(tp, 0x82e7, 0xff00, 0xad00);
+ ocp_reg_w0w1(tp, 0xae4e, 0x000f, 0x0001);
+ sram2_write_w0w1(tp, 0x82ce, 0xf000, 0x4000);
+
+ /* 5G shift sel, default = '04'
+ * 10G shift sel, default = '03'
+ */
+ sram2_write_w0w1(tp, 0x83a5, 0xff00, 0x0400);
+ sram2_write_w0w1(tp, 0x83a6, 0xff00, 0x0400);
+ sram2_write_w0w1(tp, 0x83a7, 0xff00, 0x0400);
+ sram2_write_w0w1(tp, 0x83a8, 0xff00, 0x0400);
+
+ /* XG INRX parameters
+ * RC coefficients
+ */
+ sram2_write(tp, 0x84ac, 0x0000);
+ sram2_write(tp, 0x84ae, 0x0000);
+ sram2_write(tp, 0x84b0, 0xf818);
+ sram2_write_w0w1(tp, 0x84b2, 0xff00, 0x6000);
+ /* Training AAGC PAR (with uc2 patch) */
+ sram2_write(tp, 0x8ffc, 0x6008);
+ sram2_write(tp, 0x8ffe, 0xf450);
+ /* DAC BGK */
+ sram2_write_w0w1(tp, 0x8015, 0, BIT(9));
+ sram2_write_w0w1(tp, 0x8016, 0, BIT(11));
+ sram2_write_w0w1(tp, 0x8fe6, 0xff00, 0x0800);
+ sram2_write(tp, 0x8fe4, 0x2114);
+ /* 10G PBO table */
+ sram2_write(tp, 0x8647, 0xa7b1);
+ sram2_write(tp, 0x8649, 0xbbca);
+ sram2_write_w0w1(tp, 0x864b, 0xff00, 0xdc00);
+ /* 2.5G ado power window size */
+ sram2_write_w0w1(tp, 0x8154, 0xc000, 0x4000);
+ sram2_write_w0w1(tp, 0x8158, 0xc000, 0);
+ /* 10G lock far */
+ sram2_write(tp, 0x826c, 0xffff);
+ sram2_write(tp, 0x826e, 0xffff);
+ /* XG INRX parameter */
+ sram2_write_w0w1(tp, 0x8872, 0xff00, 0x0e00);
+ sram_write_w0w1(tp, 0x8012, 0, BIT(11));
+ sram_write_w0w1(tp, 0x8012, 0, BIT(14));
+ ocp_reg_set_bits(tp, 0xb576, BIT(0));
+ sram_write_w0w1(tp, 0x834a, 0xff00, 0x0700);
+ sram2_write_w0w1(tp, 0x8217, 0x3f00, 0x2a00);
+ sram_write_w0w1(tp, 0x81b1, 0xff00, 0x0b00);
+ sram2_write_w0w1(tp, 0x8fed, 0xff00, 0x4e00);
+ /* Slave about EC mu of datamode AAGC and DAC BG */
+ sram2_write_w0w1(tp, 0x88ac, 0xff00, 0x2300);
+ /* improve UBE */
+ ocp_reg_set_bits(tp, 0xbf0c, 0x7 << 11);
+ /* close Sparse NEC, improve connect 5EUU cable performance */
+ sram2_write_w0w1(tp, 0x88de, 0xff00, 0);
+ /* 5G slave compatibility issue */
+ sram2_write(tp, 0x80b4, 0x5195);
+
+ /* XG Test Mode
+ * xgtstm_map_tbl for mdi_cap_sel
+ */
+ sram_write(tp, 0x8370, 0x8671);
+ sram_write(tp, 0x8372, 0x86c8);
+ /* xgtstm_amp_map_tbl for REG_IBX_UP_SHIFT_L */
+ sram_write(tp, 0x8401, 0x86c8);
+ sram_write(tp, 0x8403, 0x86da);
+ sram_write_w0w1(tp, 0x8406, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x8408, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x840a, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x840c, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x840e, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x8410, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x8412, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x8414, 0x1800, 0x1000);
+ sram_write_w0w1(tp, 0x8416, 0x1800, 0x1000);
+
+ /* Cable Test Patch */
+ sram_write(tp, 0x82bd, 0x1f40);
+
+ /* Thermal sensor parameters */
+ ocp_reg_w0w1(tp, 0xbfb4, 0x07ff, 0x0328);
+ ocp_reg_write(tp, 0xbfb6, 0x3e14);
+
+ /* spdchg_gtx_shape_100M */
+ ocp_reg_write(tp, OCP_SRAM_ADDR, 0x81c4);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x003b);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x0086);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00b7);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00db);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00fe);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00fe);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00fe);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00fe);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x00c3);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x0078);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x0047);
+ ocp_reg_write(tp, OCP_SRAM_DATA, 0x0023);
+
+ /* lsbmsk_parameters
+ * RL6961_lsbmsk_parameter_250207
+ */
+ sram2_write(tp, 0x88d7, 0x01a0);
+ sram2_write(tp, 0x88d9, 0x01a0);
+ sram2_write(tp, 0x8ffa, 0x002a);
+
+ sram2_write(tp, 0x8fee, 0xffdf);
+ sram2_write(tp, 0x8ff0, 0xffff);
+ sram2_write(tp, 0x8ff2, 0x0a4a);
+ sram2_write(tp, 0x8ff4, 0xaa5a);
+ sram2_write(tp, 0x8ff6, 0x0a4a);
+ sram2_write(tp, 0x8ff8, 0xaa5a);
+
+ sram2_write_w0w1(tp, 0x88d5, 0xff00, 0x0200);
+ break;
+
default:
break;
}
@@ -8155,6 +8348,18 @@ static void r8157_hw_phy_cfg(struct r8152 *tp)
set_bit(PHY_RESET, &tp->flags);
}
+static int r8159_wait_backup_restore(struct r8152 *tp)
+{
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+ if (!(ocp_data & PCUT_STATUS))
+ return 0;
+
+ return poll_timeout_us(ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_GPHY_CTRL),
+ ocp_data & BACKUP_RESTRORE, 200, 20000, false);
+}
+
static void r8156_init(struct r8152 *tp)
{
u32 ocp_data;
@@ -8164,14 +8369,14 @@ static void r8156_init(struct r8152 *tp)
if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
return;
- if (tp->version == RTL_VER_16) {
+ if (tp->version == RTL_VER_16 || tp->version == RTL_VER_17) {
ocp_byte_set_bits(tp, MCU_TYPE_USB, 0xcffe, BIT(3));
ocp_byte_clr_bits(tp, MCU_TYPE_USB, 0xd3ca, BIT(0));
}
ocp_byte_clr_bits(tp, MCU_TYPE_USB, USB_ECM_OP, EN_ALL_SPEED);
- if (tp->version != RTL_VER_16)
+ if (tp->version < RTL_VER_16)
ocp_write_word(tp, MCU_TYPE_USB, USB_SPEED_OPTION, 0);
ocp_word_set_bits(tp, MCU_TYPE_USB, USB_ECM_OPTION, BYPASS_MAC_RESET);
@@ -8185,6 +8390,7 @@ static void r8156_init(struct r8152 *tp)
case RTL_VER_13:
case RTL_VER_15:
case RTL_VER_16:
+ case RTL_VER_17:
r8156b_wait_loading_flash(tp);
break;
default:
@@ -8201,6 +8407,12 @@ static void r8156_init(struct r8152 *tp)
return;
}
+ if (tp->version == RTL_VER_17 && r8159_wait_backup_restore(tp)) {
+ rtl_set_inaccessible(tp);
+ dev_err(&tp->intf->dev, "init failed, backup-restore timed out\n");
+ return;
+ }
+
data = r8153_phy_status(tp, 0);
if (data == PHY_STAT_EXT_INIT) {
ocp_reg_clr_bits(tp, 0xa468, BIT(3) | BIT(1));
@@ -8216,7 +8428,7 @@ static void r8156_init(struct r8152 *tp)
data = r8153_phy_status(tp, PHY_STAT_LAN_ON);
- if (tp->version == RTL_VER_16)
+ if (tp->version >= RTL_VER_16)
r8157_u2p3en(tp, false);
else
r8153_u2p3en(tp, false);
@@ -8227,7 +8439,7 @@ static void r8156_init(struct r8152 *tp)
/* U1/U2/L1 idle timer. 500 us */
ocp_write_word(tp, MCU_TYPE_USB, USB_U1U2_TIMER, 500);
- if (tp->version == RTL_VER_16)
+ if (tp->version >= RTL_VER_16)
r8157_power_cut_en(tp, false);
else
r8153b_power_cut_en(tp, false);
@@ -8260,7 +8472,7 @@ static void r8156_init(struct r8152 *tp)
r8156_mac_clk_spd(tp, true);
- if (tp->version != RTL_VER_16)
+ if (tp->version < RTL_VER_16)
ocp_word_clr_bits(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, PLA_MCU_SPDWN_EN);
ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS);
@@ -8273,8 +8485,13 @@ static void r8156_init(struct r8152 *tp)
set_bit(GREEN_ETHERNET, &tp->flags);
- /* rx aggregation / 16 bytes Rx descriptor */
- if (tp->version == RTL_VER_16)
+ /* RX aggregation / 16 bytes RX descriptor
+ * BIT(11) is specific to RTL8159, with unknown meaning
+ */
+ if (tp->version == RTL_VER_17)
+ ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL,
+ RX_AGG_DISABLE | RX_DESC_16B | BIT(11));
+ else if (tp->version == RTL_VER_16)
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL, RX_AGG_DISABLE | RX_DESC_16B);
else
ocp_word_clr_bits(tp, MCU_TYPE_USB, USB_USB_CTRL, RX_AGG_DISABLE | RX_ZERO_EN);
@@ -8282,7 +8499,7 @@ static void r8156_init(struct r8152 *tp)
if (tp->version < RTL_VER_12)
ocp_byte_set_bits(tp, MCU_TYPE_USB, USB_BMU_CONFIG, ACT_ODMA);
- if (tp->version == RTL_VER_16) {
+ if (tp->version >= RTL_VER_16) {
/* Disable Rx Zero Len */
rtl_bmu_clr_bits(tp, 0x2300, BIT(3));
/* TX descriptor Signature */
@@ -9670,6 +9887,29 @@ static int rtl_ops_init(struct r8152 *tp)
r8157_desc_init(tp);
break;
+ case RTL_VER_17:
+ tp->eee_en = true;
+ tp->eee_adv = MDIO_EEE_100TX | MDIO_EEE_1000T | MDIO_EEE_10GT;
+ tp->eee_adv2 = MDIO_EEE_2_5GT | MDIO_EEE_5GT;
+ ops->init = r8156_init;
+ ops->enable = rtl8156_enable;
+ ops->disable = rtl8153_disable;
+ ops->up = rtl8156_up;
+ ops->down = rtl8156_down;
+ ops->unload = rtl8153_unload;
+ ops->eee_get = r8153_get_eee;
+ ops->eee_set = r8152_set_eee;
+ ops->in_nway = rtl8153_in_nway;
+ ops->hw_phy_cfg = r8157_hw_phy_cfg;
+ ops->autosuspend_en = rtl8157_runtime_enable;
+ ops->change_mtu = rtl8156_change_mtu;
+ tp->rx_buf_sz = 48 * 1024;
+ tp->support_2500full = 1;
+ tp->support_5000full = 1;
+ tp->support_10000full = 1;
+ r8157_desc_init(tp);
+ break;
+
default:
ret = -ENODEV;
dev_err(&tp->intf->dev, "Unknown Device\n");
@@ -9823,6 +10063,9 @@ static u8 __rtl_get_hw_ver(struct usb_device *udev)
case 0x1030:
version = RTL_VER_16;
break;
+ case 0x2020:
+ version = RTL_VER_17;
+ break;
default:
version = RTL_VER_UNKNOWN;
dev_info(&udev->dev, "Unknown version 0x%04x\n", ocp_data);
@@ -9975,6 +10218,7 @@ static int rtl8152_probe_once(struct usb_interface *intf,
case RTL_VER_13:
case RTL_VER_15:
case RTL_VER_16:
+ case RTL_VER_17:
netdev->max_mtu = size_to_mtu(16 * 1024);
break;
case RTL_VER_01:
@@ -10140,6 +10384,7 @@ static const struct usb_device_id rtl8152_table[] = {
{ USB_DEVICE(VENDOR_ID_REALTEK, 0x8155) },
{ USB_DEVICE(VENDOR_ID_REALTEK, 0x8156) },
{ USB_DEVICE(VENDOR_ID_REALTEK, 0x8157) },
+ { USB_DEVICE(VENDOR_ID_REALTEK, 0x815a) },
/* Microsoft */
{ USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab) },
--
2.47.3
^ permalink raw reply related
* Re: [PATCH v2] net: dsa: realtek: rtl8365mb: add support for RTL8367SB
From: Alexander Lobakin @ 2026-05-05 15:55 UTC (permalink / raw)
To: Mieczyslaw Nalewaj
Cc: Andrew Lunn, Vladimir Oltean, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Alvin Šipraga,
Yury Norov, Rasmus Villemoes, Russell King, netdev
In-Reply-To: <05921e1f-693b-4322-a762-c8f03c386a78@yahoo.com>
From: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Date: Tue, 5 May 2026 16:17:19 +0200
> Add chip info entry for the Realtek RTL8367SB switch. This device has
> chip ID 0x6367 and version 0x0010. It exposes two external interfaces:
> port 6 supports SGMII and HSGMII, while port 7 supports MII, TMII,
> RMII and RGMII. Use the existing 8365MB-VC jam table for initialization.
>
> Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
> ---
> drivers/net/dsa/realtek/rtl8365mb.c | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
Thanks,
Olek
^ permalink raw reply
* Re: [PATCH 00/11] mlx5 support for VFIO self test
From: David Matlack @ 2026-05-05 15:57 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Alex Williamson, kvm, Leon Romanovsky, linux-kselftest,
linux-rdma, Mark Bloch, netdev, Saeed Mahameed, Shuah Khan,
Tariq Toukan, patches, Josh Hilke
In-Reply-To: <afoR1izCEe9y0MZA@nvidia.com>
On Tue, May 5, 2026 at 8:50 AM Jason Gunthorpe <jgg@nvidia.com> wrote:
>
> On Mon, May 04, 2026 at 10:54:08PM +0000, David Matlack wrote:
> > > The PF support flow requires a bunch more complicated stuff.
> >
> > Do you think it's worth supporting PFs? If anyone with a CX NIC can
> > enable SR-IOV and run selftests on a VF then we can keep the driver
> > somewhat simpler.
>
> It turns out my test system cannot enable SR-IOV due to iommu_group
> problems so I rather prefer to have this :) I had to hack a kernel up
> to do the initial testing and it was very annoying.
Ok sounds good.
^ permalink raw reply
* Re: [PATCH net v7 2/2] ipv6: flowlabel: enforce per-netns limit for unprivileged callers
From: Willem de Bruijn @ 2026-05-05 15:58 UTC (permalink / raw)
To: Maoyi Xie, David S . Miller
Cc: Jakub Kicinski, Paolo Abeni, Eric Dumazet, David Ahern,
Alexey Kuznetsov, Willem de Bruijn, Willem de Bruijn, netdev,
linux-kernel, stable
In-Reply-To: <20260505072015.1672730-3-maoyi.xie@ntu.edu.sg>
Maoyi Xie wrote:
> fl_size, fl_ht and ip6_fl_lock in net/ipv6/ip6_flowlabel.c are
> file scope and shared across netns. mem_check() reads fl_size to
> decide whether to deny non-CAP_NET_ADMIN callers. capable() runs
> against init_user_ns, so an unprivileged user in any non-init
> userns can push fl_size past FL_MAX_SIZE - FL_MAX_SIZE / 4 and
> starve every other unprivileged userns on the host.
>
> Add struct netns_ipv6::flowlabel_count, bumped and decremented
> next to fl_size in fl_intern, ip6_fl_gc and ip6_fl_purge. The new
> field fills the existing 4-byte hole after ipmr_seq, so struct
> netns_ipv6 stays the same size on 64-bit builds.
>
> Bump FL_MAX_SIZE from 4096 to 8192. It has been 4096 since the
> file was added. Machines and connection counts have grown.
>
> mem_check() folds an extra per-netns ceiling into the existing
> non-CAP_NET_ADMIN conditional. The ceiling is half of the total
> budget that unprivileged callers have ever been able to use, i.e.
> (FL_MAX_SIZE - FL_MAX_SIZE / 4) / 2 = 3072 entries. With
> FL_MAX_SIZE doubled, this preserves the original per-user reach
> of 3K (what an unprivileged caller could already obtain before
> this change), while forcing an attacker to spread allocations
> across at least two netns to exhaust the global non-CAP_NET_ADMIN
> budget.
>
> CAP_NET_ADMIN against init_user_ns still bypasses both caps.
>
> The previous patch took ip6_fl_lock across mem_check and
> fl_intern, so the new flowlabel_count read in mem_check and the
> new flowlabel_count++ in fl_intern run under the same critical
> section. flowlabel_count is therefore plain int, like fl_size.
>
> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
> Suggested-by: Willem de Bruijn <willemb@google.com>
> Cc: stable@vger.kernel.org # v5.15+
> Signed-off-by: Maoyi Xie <maoyi.xie@ntu.edu.sg>
Reviewed-by: Willem de Bruijn <willemb@google.com>
^ permalink raw reply
* Re: [PATCH net-next 02/12] net: pcs: pcs-xpcs: select operating mode for 10G-baseR capable PCS
From: Daniel Thompson @ 2026-05-05 15:58 UTC (permalink / raw)
To: Andrew Lunn
Cc: Alex Elder, andrew+netdev, davem, edumazet, kuba, pabeni,
maxime.chevallier, rmk+kernel, andersson, konradybcio, robh,
krzk+dt, conor+dt, linusw, brgl, arnd, gregkh, mohd.anwar,
a0987203069, alexandre.torgue, ast, boon.khai.ng, chenchuangyu,
chenhuacai, daniel, hawk, hkallweit1, inochiama, john.fastabend,
julianbraha, livelycarpet87, matthew.gerlach, mcoquelin.stm32, me,
prabhakar.mahadev-lad.rj, richardcochran, rohan.g.thomas, sdf,
siyanteng, weishangjuan, wens, netdev, bpf, linux-arm-msm,
devicetree, linux-gpio, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <f9a581a2-02ea-4948-8c97-835cb7638b1d@lunn.ch>
On Fri, May 01, 2026 at 06:50:45PM +0200, Andrew Lunn wrote:
> > +static int xpcs_config_operating_mode(struct dw_xpcs *xpcs, int an_mode)
> > +{
> > + int mdio_stat2, ret;
> > +
> > + switch (an_mode) {
> > + case DW_AN_C37_SGMII:
> > + case DW_AN_C37_1000BASEX:
> > + case DW_2500BASEX:
> > + mdio_stat2 = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT2);
> > + if (mdio_stat2 < 0)
> > + return mdio_stat2;
> > +
> > + /*
> > + * If this XPCS supports 10Gbase-R then it will be the default
> > + * which prevents 1000base-X and slower from working correctly.
>
> It would be interesting to know if Toshiba messed up the integration
> of the PCS, or there is an errata for the licensed IP.
I'm afraid I don't know, but it looks like the issue is not unique to
Toshiba!
This is a discovery which, rather to my chagrin, I only made after we
posted the patches (thanks to a hint from Sashiko): there is similar
code in txgbe_xpcs_switch_mode(). I cleary overlooked that when I
originally reviewed the existing XPCS code. I suspect I stopped
scanning that code path due to the PMA related conditional branch...
Regardless of how I missed it, txgbe_xpcs_switch_mode() implements
similar logic to this patch. I think it is using MDIO_PCS_CTRL2_10GBX as
the Reserved value but otherwise looks similar. There are comments that
imply 10Gbase-X isn't implemented by their XPCS which would make
MDIO_PCS_CTRL2_10GBX reserved (but are too vague to be 100% sure).
Right now it looks like xpcs_switch_interface_mode() and my
xpcs_config_operating_mode() are more closely related than I realized
so I plan to move my code into xpcs_switch_interface_mode().
I don't think I can unify the Wangxun and Toshiba code (the waits and
resets in the Wangxun code make that too high risk) but I'm not yet
ready to give up and just make the Toshiba changes into another vendor
quirk!
Daniel.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox