From: Long Li <[email protected]> Carry the MTU in the queue set and size replacement RX buffers from it. Publish ndev->mtu after RSS configuration succeeds; allocation failure leaves the live queues and advertised MTU unchanged.
This full rebuild temporarily keeps both sets of SQ/RQ/CQ objects, RX buffers and page pools live. The port-owned EQ pool is shared, not doubled. Device resource limits may reject this temporary peak; allocation failure preserves the live queues and configuration. Reserve RAW-QP admission under vport_mutex for the entire live replacement, including unpublished queues, fail-close and scratch cleanup. Preserve validation, no-op and down-port behavior. Signed-off-by: Long Li <[email protected]> Signed-off-by: Wei Hu <[email protected]> --- drivers/net/ethernet/microsoft/mana/mana_en.c | 66 ++++++++++++++----- .../ethernet/microsoft/mana/mana_ethtool.c | 10 +-- include/net/mana/mana.h | 7 +- 3 files changed, 60 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 10225c09f5b7..4577a473ff42 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -927,32 +927,52 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu static int mana_change_mtu(struct net_device *ndev, int new_mtu) { struct mana_port_context *mpc = netdev_priv(ndev); - unsigned int old_mtu = ndev->mtu; + struct mana_port_context *scratch; + struct mana_qset newq, oldq; int err; - /* Pre-allocate buffers to prevent failure in mana_attach later */ - err = mana_pre_alloc_rxbufs(mpc, new_mtu, mpc->num_queues); - if (err) { - netdev_err(ndev, "Insufficient memory for new MTU\n"); - return err; + if (!mpc->port_is_up) { + mpc->configured_mtu = new_mtu; + WRITE_ONCE(ndev->mtu, new_mtu); + return 0; } - err = mana_detach(ndev, false); - if (err) { - netdev_err(ndev, "mana_detach failed: %d\n", err); - goto out; + /* Fail-close may release the Ethernet vport reference. */ + mutex_lock(&mpc->vport_mutex); + if (mpc->channel_changing) { + mutex_unlock(&mpc->vport_mutex); + return -EBUSY; + } + mpc->channel_changing = true; + mutex_unlock(&mpc->vport_mutex); + + scratch = mana_qset_scratch_alloc(mpc); + if (!scratch) { + err = -ENOMEM; + goto clear_flag; } - WRITE_ONCE(ndev->mtu, new_mtu); + err = mana_alloc_qset(mpc, scratch, mpc->num_queues, + mpc->rx_queue_size, mpc->tx_queue_size, + mpc->priv_flags, new_mtu, &newq); + if (err) + goto free_scratch; - err = mana_attach(ndev); + err = mana_publish_qset(mpc, &newq, &oldq); if (err) { - netdev_err(ndev, "mana_attach failed: %d\n", err); - WRITE_ONCE(ndev->mtu, old_mtu); + mana_free_qset(scratch, &newq); + goto free_scratch; } -out: - mana_pre_dealloc_rxbufs(mpc); + mana_free_qset(scratch, &oldq); + +free_scratch: + mana_publish_close_if_needed(mpc); + mana_qset_scratch_free(scratch); +clear_flag: + mutex_lock(&mpc->vport_mutex); + mpc->channel_changing = false; + mutex_unlock(&mpc->vport_mutex); return err; } @@ -3306,7 +3326,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->rxq_idx = rxq_idx; rxq->rxobj = INVALID_MANA_HANDLE; - mana_get_rxbuf_cfg(apc, ndev->mtu, &rxq->datasize, &rxq->alloc_size, + mana_get_rxbuf_cfg(apc, apc->configured_mtu, &rxq->datasize, + &rxq->alloc_size, &rxq->headroom, &rxq->frag_count); /* Create page pool for RX queue */ err = mana_create_page_pool(rxq, gc); @@ -4017,6 +4038,7 @@ static void mana_qset_snapshot(const struct mana_port_context *ctx, out->rx_queue_size = ctx->rx_queue_size; out->tx_queue_size = ctx->tx_queue_size; out->priv_flags = ctx->priv_flags; + out->mtu = ctx->configured_mtu; } /* Vport identity and port debugfs outlive queue sets. */ @@ -4033,6 +4055,7 @@ static void mana_qset_install(struct mana_port_context *ctx, ctx->rx_queue_size = qset->rx_queue_size; ctx->tx_queue_size = qset->tx_queue_size; ctx->priv_flags = qset->priv_flags; + ctx->configured_mtu = qset->mtu; } /* Scratch starts without SQs/RQs and borrows the port's EQ pool. Never call @@ -4073,7 +4096,7 @@ void mana_qset_scratch_free(struct mana_port_context *scratch) int mana_alloc_qset(struct mana_port_context *apc, struct mana_port_context *scratch, unsigned int num_queues, unsigned int rx_queue_size, unsigned int tx_queue_size, - u32 priv_flags, struct mana_qset *out) + u32 priv_flags, int mtu, struct mana_qset *out) { struct net_device *ndev = scratch->ndev; int err; @@ -4085,6 +4108,8 @@ int mana_alloc_qset(struct mana_port_context *apc, scratch->tx_queue_size = tx_queue_size; scratch->priv_flags = priv_flags; + scratch->configured_mtu = mtu; + err = mana_init_port_context(scratch); if (err) goto out_err; @@ -4337,6 +4362,8 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq, if (err) goto rollback; + WRITE_ONCE(ndev->mtu, apc->configured_mtu); + /* Publish fields before opening the gate; pair with TX/XDP read * barriers. The post-gate full barrier cannot replace this. */ @@ -4392,6 +4419,8 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq, synchronize_net(); mana_fold_qset_rx_stats(apc, out_old); + WRITE_ONCE(ndev->mtu, apc->configured_mtu); + /* Publish restored fields before reopening the gate, as on success. */ smp_wmb(); @@ -4544,6 +4573,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->port_handle = INVALID_MANA_HANDLE; apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; + apc->configured_mtu = ndev->mtu; apc->link_cfg_error = 1; apc->cqe_coalescing_enable = 0; apc->cqe8_coalescing_enable = 0; diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 7a1120342208..2ad0fb4d5008 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -738,7 +738,8 @@ static int mana_set_channels(struct net_device *ndev, } err = mana_alloc_qset(apc, scratch, new_count, apc->rx_queue_size, - apc->tx_queue_size, apc->priv_flags, &newq); + apc->tx_queue_size, apc->priv_flags, + apc->configured_mtu, &newq); if (err) goto free_scratch; @@ -827,7 +828,7 @@ static int mana_set_ringparam(struct net_device *ndev, } err = mana_alloc_qset(apc, scratch, apc->num_queues, new_rx, new_tx, - apc->priv_flags, &newq); + apc->priv_flags, apc->configured_mtu, &newq); if (err) { NL_SET_ERR_MSG_FMT(extack, "failed to change ring params: %d", err); @@ -917,8 +918,9 @@ static int mana_set_priv_flags(struct net_device *ndev, u32 priv_flags) goto clear_flag; } - err = mana_alloc_qset(apc, scratch, apc->num_queues, apc->rx_queue_size, - apc->tx_queue_size, priv_flags, &newq); + err = mana_alloc_qset(apc, scratch, apc->num_queues, + apc->rx_queue_size, apc->tx_queue_size, + priv_flags, apc->configured_mtu, &newq); if (err) goto free_scratch; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index c66f9dcab407..3faad257e97e 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -626,6 +626,10 @@ struct mana_port_context { unsigned int rx_queue_size; unsigned int tx_queue_size; + /* MTU used to size RX buffers, independent of ndev->mtu during a swap. + */ + int configured_mtu; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -702,6 +706,7 @@ struct mana_qset { unsigned int tx_queue_size; u32 priv_flags; + int mtu; }; netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); @@ -724,7 +729,7 @@ static inline struct mana_stats_rx *mana_rxq_stats(struct mana_rxq *rxq) int mana_alloc_qset(struct mana_port_context *apc, struct mana_port_context *scratch, unsigned int num_queues, unsigned int rx_queue_size, unsigned int tx_queue_size, - u32 priv_flags, struct mana_qset *out); + u32 priv_flags, int mtu, struct mana_qset *out); int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq, struct mana_qset *out_old); void mana_publish_close_if_needed(struct mana_port_context *apc);
