This is a note to let you know that I've just added the patch titled net: systemport: Rewrite __bcm_sysport_tx_reclaim() to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: net-systemport-rewrite-__bcm_sysport_tx_reclaim.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Wed Mar 28 20:16:33 CEST 2018 From: Florian Fainelli <f.fainelli@xxxxxxxxx> Date: Tue, 13 Mar 2018 14:45:07 -0700 Subject: net: systemport: Rewrite __bcm_sysport_tx_reclaim() From: Florian Fainelli <f.fainelli@xxxxxxxxx> [ Upstream commit 484d802d0f2f29c335563fcac2a8facf174a1bbc ] There is no need for complex checking between the last consumed index and current consumed index, a simple subtraction will do. This also eliminates the possibility of a permanent transmit queue stall under the following conditions: - one CPU bursts ring->size worth of traffic (up to 256 buffers), to the point where we run out of free descriptors, so we stop the transmit queue at the end of bcm_sysport_xmit() - because of our locking, we have the transmit process disable interrupts which means we can be blocking the TX reclamation process - when TX reclamation finally runs, we will be computing the difference between ring->c_index (last consumed index by SW) and what the HW reports through its register - this register is masked with (ring->size - 1) = 0xff, which will lead to stripping the upper bits of the index (register is 16-bits wide) - we will be computing last_tx_cn as 0, which means there is no work to be done, and we never wake-up the transmit queue, leaving it permanently disabled A practical example is e.g: ring->c_index aka last_c_index = 12, we pushed 256 entries, HW consumer index = 268, we mask it with 0xff = 12, so last_tx_cn == 0, nothing happens. Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by: Florian Fainelli <f.fainelli@xxxxxxxxx> Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/net/ethernet/broadcom/bcmsysport.c | 33 +++++++++++++---------------- drivers/net/ethernet/broadcom/bcmsysport.h | 2 - 2 files changed, 16 insertions(+), 19 deletions(-) --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -707,37 +707,33 @@ static unsigned int __bcm_sysport_tx_rec struct bcm_sysport_tx_ring *ring) { struct net_device *ndev = priv->netdev; - unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; + unsigned int txbds_processed = 0; struct bcm_sysport_cb *cb; + unsigned int txbds_ready; + unsigned int c_index; u32 hw_ind; /* Compute how many descriptors have been processed since last call */ hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index)); c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK; - ring->p_index = (hw_ind & RING_PROD_INDEX_MASK); - - last_c_index = ring->c_index; - num_tx_cbs = ring->size; - - c_index &= (num_tx_cbs - 1); - - if (c_index >= last_c_index) - last_tx_cn = c_index - last_c_index; - else - last_tx_cn = num_tx_cbs - last_c_index + c_index; + txbds_ready = (c_index - ring->c_index) & RING_CONS_INDEX_MASK; netif_dbg(priv, tx_done, ndev, - "ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n", - ring->index, c_index, last_tx_cn, last_c_index); + "ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n", + ring->index, ring->c_index, c_index, txbds_ready); - while (last_tx_cn-- > 0) { - cb = ring->cbs + last_c_index; + while (txbds_processed < txbds_ready) { + cb = &ring->cbs[ring->clean_index]; bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl); ring->desc_count++; - last_c_index++; - last_c_index &= (num_tx_cbs - 1); + txbds_processed++; + + if (likely(ring->clean_index < ring->size - 1)) + ring->clean_index++; + else + ring->clean_index = 0; } ring->c_index = c_index; @@ -1207,6 +1203,7 @@ static int bcm_sysport_init_tx_ring(stru netif_tx_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64); ring->index = index; ring->size = size; + ring->clean_index = 0; ring->alloc_size = ring->size; ring->desc_cpu = p; ring->desc_count = ring->size; --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -638,7 +638,7 @@ struct bcm_sysport_tx_ring { unsigned int desc_count; /* Number of descriptors */ unsigned int curr_desc; /* Current descriptor */ unsigned int c_index; /* Last consumer index */ - unsigned int p_index; /* Current producer index */ + unsigned int clean_index; /* Current clean index */ struct bcm_sysport_cb *cbs; /* Transmit control blocks */ struct dma_desc *desc_cpu; /* CPU view of the descriptor */ struct bcm_sysport_priv *priv; /* private context backpointer */ Patches currently in stable-queue which might be from f.fainelli@xxxxxxxxx are queue-4.9/net-systemport-rewrite-__bcm_sysport_tx_reclaim.patch queue-4.9/net-fec-fix-unbalanced-pm-runtime-calls.patch