The RX buffer layout depends on the MTU - see mana_get_rxbuf_cfg() - so changing it rebuilds the queues. Convert mana_change_mtu() to the pre-allocate and swap helpers.
The MTU becomes part of the queue-set configuration: - struct mana_qset gains mtu, so it is swapped atomically with the queues it describes and restored by the rollback path. - mana_port_context gains configured_mtu, the MTU the current RX queues were built for. mana_create_rxq() now sizes buffers from it rather than ndev->mtu, so a new set can be built for a different MTU while ndev->mtu still advertises the old one. - mana_publish_qset() commits ndev->mtu once the new set is serving traffic. It is a no-op for callers that do not change the MTU. Previously ndev->mtu was written before mana_attach() and rolled back on failure, so a failed change was briefly visible to the stack. mana_pre_alloc_rxbufs() is no longer needed here; de-risking allocation after teardown is pointless when there is no teardown. Signed-off-by: Long Li <[email protected]> --- drivers/net/ethernet/microsoft/mana/mana_en.c | 75 ++++++++++++++----- .../ethernet/microsoft/mana/mana_ethtool.c | 8 +- include/net/mana/mana.h | 14 +++- 3 files changed, 74 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 5f682e3d5a706149954764d083b70f25906f28df..4c79d6e82d9a93786ea877fbcef2b3f9d4093a6c 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -889,35 +889,54 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu return -ENOMEM; } +/* mana_change_mtu - resize RX buffers for a new MTU + * + * Uses the pre-allocate + swap path: the new queue set is built for + * @new_mtu while the current one keeps serving traffic at the old MTU. + * ndev->mtu is only updated once the new set is live (see + * mana_publish_qset), so a failed allocation leaves both the queues and + * the advertised MTU untouched. + */ 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; + /* Port is down: no queues to rebuild, just record the new MTU. + * mana_open() will size the RX buffers accordingly. + */ + 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; - } + scratch = mana_qset_scratch_alloc(mpc); + if (!scratch) + return -ENOMEM; - WRITE_ONCE(ndev->mtu, new_mtu); + err = mana_alloc_qset(scratch, mpc->num_queues, mpc->rx_queue_size, + mpc->tx_queue_size, mpc->priv_flags, new_mtu, + &newq); + if (err) + goto free_scratch; /* current qset and ndev->mtu untouched */ - 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: + /* After the caller-side cleanup above, so the EQ pool outlives the + * CQs that reference it. + */ + mana_publish_close_if_needed(mpc); + mana_qset_scratch_free(scratch); return err; } @@ -3097,7 +3116,8 @@ 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); @@ -3965,6 +3985,7 @@ 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; out->mana_eqs_debugfs = ctx->mana_eqs_debugfs; } @@ -3986,6 +4007,7 @@ 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; ctx->mana_eqs_debugfs = qset->mana_eqs_debugfs; } @@ -4049,6 +4071,7 @@ void mana_qset_scratch_free(struct mana_port_context *scratch) * @rx_queue_size: new RX ring size * @tx_queue_size: new TX ring size * @priv_flags: new priv-flag word (affects full-page RX) + * @mtu: MTU the new set is sized for * @out: output qset, populated on success * * The live port context is not referenced at all, so the currently @@ -4057,7 +4080,7 @@ void mana_qset_scratch_free(struct mana_port_context *scratch) */ int mana_alloc_qset(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; @@ -4069,6 +4092,12 @@ int mana_alloc_qset(struct mana_port_context *scratch, unsigned int num_queues, scratch->tx_queue_size = tx_queue_size; scratch->priv_flags = priv_flags; + /* mana_get_rxbuf_cfg() reads this when sizing RX buffers, so the + * new set is built for the requested MTU without disturbing the + * running set. + */ + scratch->configured_mtu = mtu; + err = mana_init_port_context(scratch); if (err) goto out_err; @@ -4361,6 +4390,11 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq, if (err) goto rollback; + /* The new set is serving traffic: advertise its MTU. A no-op for + * callers that are not changing the MTU. + */ + WRITE_ONCE(ndev->mtu, apc->configured_mtu); + /* Pair with the queue-state stores above: a datapath reader that sees * the gate open must also see the queue set it is about to index. */ @@ -4413,6 +4447,8 @@ int mana_publish_qset(struct mana_port_context *apc, struct mana_qset *newq, return err; } + WRITE_ONCE(ndev->mtu, apc->configured_mtu); + /* Same pairing as the success path: the restored queue set has to be * visible before the gate reopens on it. */ @@ -4658,6 +4694,7 @@ 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 9392b82d3d48a2638512a53f9c004629b0c679e5..2a6325256fad3edf1aafbc72f0cd5dc18d61384e 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -737,7 +737,8 @@ static int mana_set_channels(struct net_device *ndev, } err = mana_alloc_qset(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; /* current qset untouched, nothing to undo */ @@ -839,7 +840,7 @@ static int mana_set_ringparam(struct net_device *ndev, } err = mana_alloc_qset(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); @@ -940,7 +941,8 @@ static int mana_set_priv_flags(struct net_device *ndev, u32 priv_flags) } err = mana_alloc_qset(scratch, apc->num_queues, apc->rx_queue_size, - apc->tx_queue_size, priv_flags, &newq); + apc->tx_queue_size, priv_flags, + apc->configured_mtu, &newq); if (err) goto free_scratch; /* current qset and priv_flags untouched */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index e4aaad7bec34297cf406181560a1839d3e6a73df..2fc75e6cd41a63878788182cd099379c8c698b33 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -621,6 +621,12 @@ struct mana_port_context { unsigned int rx_queue_size; unsigned int tx_queue_size; + /* MTU the current RX queues were built for. Normally equal to + * ndev->mtu, but during a queue-set swap the new set is built for + * the new MTU while ndev->mtu still advertises the old one. + */ + int configured_mtu; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -714,6 +720,12 @@ struct mana_qset { unsigned int tx_queue_size; u32 priv_flags; + /* MTU the RX buffers of this set were sized for. It feeds + * mana_get_rxbuf_cfg(), so it is part of the queue-set + * configuration and must be swapped atomically with the queues. + */ + int mtu; + /* Per-queue-set debugfs root ("EQs"). Owned by the qset: it is * recreated by mana_create_eq() for each new set and torn down * with that set, so it must travel with the qset rather than @@ -739,7 +751,7 @@ struct mana_port_context *mana_qset_scratch_alloc(struct mana_port_context *apc) void mana_qset_scratch_free(struct mana_port_context *scratch); int mana_alloc_qset(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); -- 2.43.0
