From efd90b64ce25697da8131708bd30b90b5758d22f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= Date: Fri, 25 Sep 2026 15:59:34 +0200 Subject: [PATCH 1/3] net: macb: never give hardware a NULL RX buffer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The refill logic is simple: iterate over all pending rx slots, allocate SKB (& DMA map) if needed and hand it off to the hardware by clearing the RX_USED flag. If the refill operation fails mid-way, it early returns leaving the remaining slots untouched. In an initialised ring that is safe: a slot is either owned by the hardware holding a valid buffer, or software-owned (RX_USED set) waiting for refill to hand it a new one. When slots have never been initialised however, we are in trouble. After dma_alloc_coherent() of the rx ring buffer, all slots have NULL pointers and RX_USED cleared meaning HW will try using them. Ensure this does not happen by setting the RX_USED flag on all slots before calling refill at buffer alloc, in gem_init_rx_ring(). That way even if refill fails on an alloc/dma_map, the HW won't try using NULL pointers as buffers. Note we tweak gem_rx() and macb_rx_pending(): their previous stop condition was only if desc was RX_USED. Now it must be either RX_USED or we got out of the range of successfully allocated descriptors (detected using the rx_tail and rx_prepared_head cursors). Otherwise gem_rx() could consume unallocated buffers. Theoretical bugfix, never encountered in practice. To reproduce, introduce memory pressure (less than 512 SKBs of free memory) and open the interface. Note that this codepath also hits at resume, on HRESP errors and on set_ringparam (while interface is running). Reviewed-by: Nicolai Buchwitz Signed-off-by: Théo Lebrun Link: https://patch.msgid.link/20260925-macb-close-v2-1-360efa565914@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c26ffcf73562..ab19221d5bea 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1615,6 +1615,13 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi, dma_addr_t addr; bool rxused; + /* Only descriptors in [rx_tail, rx_prepared_head) were armed + * for hardware. Outside, we might have RX_USED descriptors for + * alloc failures. + */ + if (queue->rx_tail == queue->rx_prepared_head) + break; + entry = macb_rx_ring_wrap(bp, queue->rx_tail); desc = macb_rx_desc(queue, entry); @@ -1878,6 +1885,10 @@ static bool macb_rx_pending(struct macb_queue *queue) struct macb_dma_desc *desc; unsigned int entry; + /* No armed descriptor left: nothing can be pending. */ + if (macb_is_gem(bp) && queue->rx_tail == queue->rx_prepared_head) + return false; + entry = macb_rx_ring_wrap(bp, queue->rx_tail); desc = macb_rx_desc(queue, entry); @@ -2814,9 +2825,14 @@ static int macb_alloc(struct macb *bp) static void gem_init_rx_ring(struct macb_queue *queue) { + unsigned int i; + queue->rx_tail = 0; queue->rx_prepared_head = 0; + for (i = 0; i < queue->bp->rx_ring_size; i++) + macb_rx_desc(queue, i)->addr |= MACB_BIT(RX_USED); + gem_rx_refill(queue); } From 9ea465c4fbaf4c77bd86a0e91e610a713592a1c8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= Date: Fri, 25 Sep 2026 15:59:35 +0200 Subject: [PATCH 2/3] net: macb: propagate RX ring refill errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gem_rx_refill() is responsible for Rx SKB allocation, including at open, but its prototype indicates a void return value. Therefore we change the code to propagate allocation and DMA mapping errors back up the stack, making sure the open fails if no descriptors were allocated. Change all those to return errno-style ints: - gem_rx_refill() - its parent gem_init_rx_ring() - its grand-parent gem_init_rings() - the macbgem_ops.mog_init_rings function pointer - its grand-uncle macb_init_rings() We tolerate some allocation failures: we accept running with the rx ring only partially filled with successful descriptors. It is important we refuse the zero-valid-descriptor case: nothing would ever trigger a refill, which only happens once a frame has been received. Theoretical bugfix, never encountered in practice. To reproduce, introduce memory pressure (less than 512 SKBs of free memory) and open the interface. I expect the last queue to be unusable because it has zero usable rx buffers. Note that other callers of refill (resume, HRESP error task, NAPI) cannot do anything useful with that error and keep their best-effort refill, hoping it will improve. Signed-off-by: Théo Lebrun Reviewed-by: Nicolai Buchwitz Link: https://patch.msgid.link/20260925-macb-close-v2-2-360efa565914@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb.h | 2 +- drivers/net/ethernet/cadence/macb_main.c | 33 +++++++++++++++++++----- 2 files changed, 27 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d6931c41f39d..cfaa0ca49f1a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1197,7 +1197,7 @@ struct macb_queue; struct macb_or_gem_ops { int (*mog_alloc_rx_buffers)(struct macb *bp); void (*mog_free_rx_buffers)(struct macb *bp); - void (*mog_init_rings)(struct macb *bp); + int (*mog_init_rings)(struct macb *bp); int (*mog_rx)(struct macb_queue *queue, struct napi_struct *napi, int budget); }; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ab19221d5bea..db86f5370a05 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1505,7 +1505,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) return packets; } -static void gem_rx_refill(struct macb_queue *queue) +static int gem_rx_refill(struct macb_queue *queue) { struct macb *bp = queue->bp; struct macb_dma_desc *desc; @@ -1577,6 +1577,14 @@ static void gem_rx_refill(struct macb_queue *queue) netdev_vdbg(bp->netdev, "rx ring: queue: %p, prepared head %d, tail %d\n", queue, queue->rx_prepared_head, queue->rx_tail); + + /* Fail if queue has zero prepared descriptors. This is critical because + * nothing will ever trigger a refill again. + */ + if (queue->rx_prepared_head == queue->rx_tail) + return -ENOMEM; + + return 0; } /* Mark DMA descriptors from begin up to and not including end as unused */ @@ -2823,7 +2831,7 @@ static int macb_alloc(struct macb *bp) return -ENOMEM; } -static void gem_init_rx_ring(struct macb_queue *queue) +static int gem_init_rx_ring(struct macb_queue *queue) { unsigned int i; @@ -2833,14 +2841,16 @@ static void gem_init_rx_ring(struct macb_queue *queue) for (i = 0; i < queue->bp->rx_ring_size; i++) macb_rx_desc(queue, i)->addr |= MACB_BIT(RX_USED); - gem_rx_refill(queue); + return gem_rx_refill(queue); } -static void gem_init_rings(struct macb *bp) +static int gem_init_rings(struct macb *bp) { struct macb_queue *queue; struct macb_dma_desc *desc = NULL; + int last_err = 0; unsigned int q; + int err; int i; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { @@ -2853,11 +2863,15 @@ static void gem_init_rings(struct macb *bp) queue->tx_head = 0; queue->tx_tail = 0; - gem_init_rx_ring(queue); + err = gem_init_rx_ring(queue); + if (err) + last_err = err; } + + return last_err; } -static void macb_init_rings(struct macb *bp) +static int macb_init_rings(struct macb *bp) { int i; struct macb_dma_desc *desc = NULL; @@ -2872,6 +2886,8 @@ static void macb_init_rings(struct macb *bp) bp->queues[0].tx_head = 0; bp->queues[0].tx_tail = 0; desc->ctrl |= MACB_BIT(TX_WRAP); + + return 0; } static void macb_reset_hw(struct macb *bp) @@ -3202,7 +3218,9 @@ static int macb_open(struct net_device *netdev) goto pm_exit; } - bp->macbgem_ops.mog_init_rings(bp); + err = bp->macbgem_ops.mog_init_rings(bp); + if (err) + goto free_rings; macb_init_buffers(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { @@ -3240,6 +3258,7 @@ static int macb_open(struct net_device *netdev) napi_disable(&queue->napi_rx); napi_disable(&queue->napi_tx); } +free_rings: macb_free(bp); pm_exit: pm_runtime_put_sync(&bp->pdev->dev); From 4fcaed2cb1d8fc66b93920cef25da242d5051867 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Th=C3=A9o=20Lebrun?= Date: Fri, 25 Sep 2026 15:59:36 +0200 Subject: [PATCH 3/3] net: macb: quiesce IRQs and drain BH on interface close MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The macb_close() operation is facing races as it disables IRQs late in its sequence and keeps BH primitives alive while shutdown. Non exhaustive list of races that could occur: - macb_tx_error_task() could be scheduled and access the buffers freed by macb_close(). - macb_tx_error_task() or macb_hresp_error_task() might re-enable interrupts after the IDR write in macb_close(). - macb_close() calls napi_disable() meaning that if macb_tx_error_task() occurs later, it will deadlock on napi_disable() that shouldn't be called if NAPI is already disabled. - macb_hresp_error_task() might reinit every RX/TX ring under macb_close()'s foot. - macb_interrupt() might re-enable NAPI just after it has been disabled by macb_close(). Instead, disable all our primitives one by one: - (1) mask and sync on IRQ handlers, - (2) drain any scheduled bp->hresp_err_bh_work, - (3) drain any scheduled queue->tx_error_task, - (4) drain queue->napi_rx/napi_tx, - (5) drain bp->tx_lpi_work. Careful! Ordering is important because our scheduling primitives can wake each other up. Recap table: | | enable/disable | schedule | | |----|-------|-------|------|----|----|--------|-----| | |IRQs|napi_tx|napi_rx|tx_lpi|napi|napi|tx_error|hresp| | Context | | | | task | rx | tx | task |task | |===============|====|=======|=======|======|====|====|========|=====| | open | X | X | X | | | | | | | link_up | X | | | | | | | | | link_down | X | | | | | | | | | close | X | X | X | | | | | | | enable_tx_lpi | | | | X | | | | | | swap | X | X | X | X | | | | | | suspend | X | X | X | | | | | | | resume | X | X | X | | | | | | |---------------|----|-------|-------|------|----|----|--------|-----| | irq & netpoll | X | | | | X | X | X | X | |---------------|----|-------|-------|------|----|----|--------|-----| | napi_rx | X | | | | X | | | | | napi_tx | X | | | X | | X | | | |---------------|----|-------|-------|------|----|----|--------|-----| | tx_error_task | X | X | | | | | | | | hresp task | X | | | | | | | | As example, one ordering constraint that can be deduced from the table: napi_tx can schedule tx_lpi_task meaning napi_tx must be disabled before tx_lpi_task, else we risk napi_tx re-enabling tx_lpi_task after it has been disabled by macb_close(). We do *not* use IDR masking to shutdown IRQs because that risks conflicting with BH primitives we have not disabled yet. For example if we writel(IDR) in macb_close() and napi_rx is pending then IRQs might be unmasked by the NAPI poll. As for why we do not use disable_irq(): we will have situations where we are quiesced but want to listen to some IRQs and (minor reason) we register shared IRQ handlers so we shouldn't disable the full IRQ line. Instead we introduce a bool that tells macb_interrupt() to self-disarm. Its default value is true as we start closed. It gets set to false while interface is active. Reading into my crystal ball, we'll reuse that flag in suspend/WOL, set_ringparam and change_mtu (context swap). Note that old IRQ handler tried preventing a race with close by self-disarming based on netif_running(). This might work, but it does not prevent a race with the error codepath of macb_open() which needs to run with IRQs dis-armed but netif_running() returns true during that time. Reviewed-by: Nicolai Buchwitz Signed-off-by: Théo Lebrun Link: https://patch.msgid.link/20260925-macb-close-v2-3-360efa565914@bootlin.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb.h | 5 ++ drivers/net/ethernet/cadence/macb_main.c | 84 ++++++++++++++++++------ 2 files changed, 69 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index cfaa0ca49f1a..1cb2778fe49e 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1382,6 +1382,11 @@ struct macb { struct delayed_work tx_lpi_work; u32 tx_lpi_timer; + /* ISR must not drive NAPI & BH mechanisms. True when the interface + * is closed. Protected by bp->lock. + */ + bool irq_quiesced; + int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index db86f5370a05..20fe30789834 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2028,6 +2028,53 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) return work_done; } +static void macb_quiesce_start(struct macb *bp) +{ + struct macb_queue *queue; + unsigned long flags; + unsigned int q; + + spin_lock_irqsave(&bp->lock, flags); + bp->irq_quiesced = true; + spin_unlock_irqrestore(&bp->lock, flags); + + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + synchronize_irq(queue->irq); + + cancel_work_sync(&bp->hresp_err_bh_work); + + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { + /* Must be done before NAPI is disabled: the task ends with a + * napi_enable() call. + */ + cancel_work_sync(&queue->tx_error_task); + + napi_disable(&queue->napi_rx); + napi_disable(&queue->napi_tx); + } + + /* Must be done after napi_tx is disabled: its completion re-arms + * the LPI timer. + */ + cancel_delayed_work_sync(&bp->tx_lpi_work); +} + +static void macb_quiesce_end(struct macb *bp) +{ + struct macb_queue *queue; + unsigned long flags; + unsigned int q; + + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { + napi_enable(&queue->napi_rx); + napi_enable(&queue->napi_tx); + } + + spin_lock_irqsave(&bp->lock, flags); + bp->irq_quiesced = false; + spin_unlock_irqrestore(&bp->lock, flags); +} + static void macb_hresp_error_task(struct work_struct *work) { struct macb *bp = from_work(bp, work, hresp_err_bh_work); @@ -2170,8 +2217,8 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) spin_lock(&bp->lock); while (status) { - /* close possible race with dev_close */ - if (unlikely(!netif_running(netdev))) { + /* self-disarm while the netdev is closed */ + if (unlikely(bp->irq_quiesced)) { queue_writel(queue, IDR, -1); macb_queue_isr_clear(bp, queue, -1); break; @@ -3198,8 +3245,6 @@ static int macb_open(struct net_device *netdev) { size_t bufsz = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN; struct macb *bp = netdev_priv(netdev); - struct macb_queue *queue; - unsigned int q; int err; netdev_dbg(bp->netdev, "open\n"); @@ -3223,10 +3268,7 @@ static int macb_open(struct net_device *netdev) goto free_rings; macb_init_buffers(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - napi_enable(&queue->napi_rx); - napi_enable(&queue->napi_tx); - } + macb_quiesce_end(bp); macb_init_hw(bp); @@ -3253,11 +3295,10 @@ static int macb_open(struct net_device *netdev) phy_power_off(bp->phy); reset_hw: + /* The netdev stays down: quiesce and drain, as macb_close() does. */ + macb_quiesce_start(bp); + macb_reset_hw(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - napi_disable(&queue->napi_rx); - napi_disable(&queue->napi_tx); - } free_rings: macb_free(bp); pm_exit: @@ -3268,19 +3309,17 @@ static int macb_open(struct net_device *netdev) static int macb_close(struct net_device *netdev) { struct macb *bp = netdev_priv(netdev); - struct macb_queue *queue; unsigned long flags; unsigned int q; + macb_quiesce_start(bp); + + /* Drain the BH contexts before stopping the queues: NAPI completion + * and tx_error_task wake them up. + */ netif_tx_stop_all_queues(netdev); - - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - napi_disable(&queue->napi_rx); - napi_disable(&queue->napi_tx); + for (q = 0; q < bp->num_queues; ++q) netdev_tx_reset_queue(netdev_get_tx_queue(netdev, q)); - } - - cancel_delayed_work_sync(&bp->tx_lpi_work); phylink_stop(bp->phylink); phylink_disconnect_phy(bp->phylink); @@ -4802,6 +4841,11 @@ static int macb_init_dflt(struct platform_device *pdev) bp->tx_ring_size = DEFAULT_TX_RING_SIZE; bp->rx_ring_size = DEFAULT_RX_RING_SIZE; + /* No locking needed because the IRQs are not requested yet. The + * flag is cleared by macb_open() and re-armed by macb_close(). + */ + bp->irq_quiesced = true; + /* set the queue register mapping once for all: queue0 has a special * register mapping but we don't want to test the queue index then * compute the corresponding register offset at run time.