From ac0a230f719b02432d8c7eba7615ebd691da86f4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 8 May 2024 06:45:04 -0700 Subject: eth: sungem: remove .ndo_poll_controller to avoid deadlocks Erhard reports netpoll warnings from sungem: netpoll_send_skb_on_dev(): eth0 enabled interrupts in poll (gem_start_xmit+0x0/0x398) WARNING: CPU: 1 PID: 1 at net/core/netpoll.c:370 netpoll_send_skb+0x1fc/0x20c gem_poll_controller() disables interrupts, which may sleep. We can't sleep in netpoll, it has interrupts disabled completely. Strangely, gem_poll_controller() doesn't even poll the completions, and instead acts as if an interrupt has fired so it just schedules NAPI and exits. None of this has been necessary for years, since netpoll invokes NAPI directly. Fixes: fe09bb619096 ("sungem: Spring cleaning and GRO support") Reported-and-tested-by: Erhard Furtner Link: https://lore.kernel.org/all/20240428125306.2c3080ef@legion Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240508134504.3560956-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/sun/sungem.c | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 9bd1df8308d2..d3a2fbb14140 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -949,17 +949,6 @@ static irqreturn_t gem_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -#ifdef CONFIG_NET_POLL_CONTROLLER -static void gem_poll_controller(struct net_device *dev) -{ - struct gem *gp = netdev_priv(dev); - - disable_irq(gp->pdev->irq); - gem_interrupt(gp->pdev->irq, dev); - enable_irq(gp->pdev->irq); -} -#endif - static void gem_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct gem *gp = netdev_priv(dev); @@ -2839,9 +2828,6 @@ static const struct net_device_ops gem_netdev_ops = { .ndo_change_mtu = gem_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = gem_set_mac_address, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = gem_poll_controller, -#endif }; static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) -- cgit v1.2.3 From ecb51fa37ee22f137a87fa140b1e9f1759949f9a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 8 May 2024 11:43:34 +0100 Subject: net: ethernet: mediatek: split tx and rx fields in mtk_soc_data struct Split tx and rx fields in mtk_soc_data struct. This is a preliminary patch to roll back to ADMAv1 for MT7986 and MT7981 SoC in order to fix a hw hang if the device receives a corrupted packet when using ADMAv2.0. Fixes: 197c9e9b17b1 ("net: ethernet: mtk_eth_soc: introduce support for mt7986 chipset") Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Golle Reviewed-by: Przemek Kitszel Link: https://lore.kernel.org/r/70a799b1f060ec2f57883e88ccb420ac0fb0abb5.1715164770.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 210 ++++++++++++++++------------ drivers/net/ethernet/mediatek/mtk_eth_soc.h | 29 ++-- 2 files changed, 139 insertions(+), 100 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index caa13b9cedff..3eefb735ce19 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1139,7 +1139,7 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) eth->scratch_ring = eth->sram_base; else eth->scratch_ring = dma_alloc_coherent(eth->dma_dev, - cnt * soc->txrx.txd_size, + cnt * soc->tx.desc_size, ð->phy_scratch_ring, GFP_KERNEL); if (unlikely(!eth->scratch_ring)) @@ -1155,17 +1155,17 @@ static int mtk_init_fq_dma(struct mtk_eth *eth) if (unlikely(dma_mapping_error(eth->dma_dev, dma_addr))) return -ENOMEM; - phy_ring_tail = eth->phy_scratch_ring + soc->txrx.txd_size * (cnt - 1); + phy_ring_tail = eth->phy_scratch_ring + soc->tx.desc_size * (cnt - 1); for (i = 0; i < cnt; i++) { dma_addr_t addr = dma_addr + i * MTK_QDMA_PAGE_SIZE; struct mtk_tx_dma_v2 *txd; - txd = eth->scratch_ring + i * soc->txrx.txd_size; + txd = eth->scratch_ring + i * soc->tx.desc_size; txd->txd1 = addr; if (i < cnt - 1) txd->txd2 = eth->phy_scratch_ring + - (i + 1) * soc->txrx.txd_size; + (i + 1) * soc->tx.desc_size; txd->txd3 = TX_DMA_PLEN0(MTK_QDMA_PAGE_SIZE); if (MTK_HAS_CAPS(soc->caps, MTK_36BIT_DMA)) @@ -1416,7 +1416,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, if (itxd == ring->last_free) return -ENOMEM; - itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size); + itx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size); memset(itx_buf, 0, sizeof(*itx_buf)); txd_info.addr = dma_map_single(eth->dma_dev, skb->data, txd_info.size, @@ -1457,7 +1457,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, memset(&txd_info, 0, sizeof(struct mtk_tx_dma_desc_info)); txd_info.size = min_t(unsigned int, frag_size, - soc->txrx.dma_max_len); + soc->tx.dma_max_len); txd_info.qid = queue; txd_info.last = i == skb_shinfo(skb)->nr_frags - 1 && !(frag_size - txd_info.size); @@ -1470,7 +1470,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, mtk_tx_set_dma_desc(dev, txd, &txd_info); tx_buf = mtk_desc_to_tx_buf(ring, txd, - soc->txrx.txd_size); + soc->tx.desc_size); if (new_desc) memset(tx_buf, 0, sizeof(*tx_buf)); tx_buf->data = (void *)MTK_DMA_DUMMY_DESC; @@ -1513,7 +1513,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, } else { int next_idx; - next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->txrx.txd_size), + next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd, soc->tx.desc_size), ring->dma_size); mtk_w32(eth, next_idx, MT7628_TX_CTX_IDX0); } @@ -1522,7 +1522,7 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, err_dma: do { - tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, itxd, soc->tx.desc_size); /* unmap dma */ mtk_tx_unmap(eth, tx_buf, NULL, false); @@ -1547,7 +1547,7 @@ static int mtk_cal_txd_req(struct mtk_eth *eth, struct sk_buff *skb) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; nfrags += DIV_ROUND_UP(skb_frag_size(frag), - eth->soc->txrx.dma_max_len); + eth->soc->tx.dma_max_len); } } else { nfrags += skb_shinfo(skb)->nr_frags; @@ -1654,7 +1654,7 @@ static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth) ring = ð->rx_ring[i]; idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); - rxd = ring->dma + idx * eth->soc->txrx.rxd_size; + rxd = ring->dma + idx * eth->soc->rx.desc_size; if (rxd->rxd2 & RX_DMA_DONE) { ring->calc_idx_update = true; return ring; @@ -1822,7 +1822,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, } htxd = txd; - tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, txd, soc->tx.desc_size); memset(tx_buf, 0, sizeof(*tx_buf)); htx_buf = tx_buf; @@ -1841,7 +1841,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, goto unmap; tx_buf = mtk_desc_to_tx_buf(ring, txd, - soc->txrx.txd_size); + soc->tx.desc_size); memset(tx_buf, 0, sizeof(*tx_buf)); n_desc++; } @@ -1879,7 +1879,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, } else { int idx; - idx = txd_to_idx(ring, txd, soc->txrx.txd_size); + idx = txd_to_idx(ring, txd, soc->tx.desc_size); mtk_w32(eth, NEXT_DESP_IDX(idx, ring->dma_size), MT7628_TX_CTX_IDX0); } @@ -1890,7 +1890,7 @@ static int mtk_xdp_submit_frame(struct mtk_eth *eth, struct xdp_frame *xdpf, unmap: while (htxd != txd) { - tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->txrx.txd_size); + tx_buf = mtk_desc_to_tx_buf(ring, htxd, soc->tx.desc_size); mtk_tx_unmap(eth, tx_buf, NULL, false); htxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; @@ -2021,7 +2021,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, goto rx_done; idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); - rxd = ring->dma + idx * eth->soc->txrx.rxd_size; + rxd = ring->dma + idx * eth->soc->rx.desc_size; data = ring->data[idx]; if (!mtk_rx_get_desc(eth, &trxd, rxd)) @@ -2156,7 +2156,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, rxdcsum = &trxd.rxd4; } - if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid) + if (*rxdcsum & eth->soc->rx.dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -2280,7 +2280,7 @@ static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, break; tx_buf = mtk_desc_to_tx_buf(ring, desc, - eth->soc->txrx.txd_size); + eth->soc->tx.desc_size); if (!tx_buf->data) break; @@ -2331,7 +2331,7 @@ static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, } mtk_tx_unmap(eth, tx_buf, &bq, true); - desc = ring->dma + cpu * eth->soc->txrx.txd_size; + desc = ring->dma + cpu * eth->soc->tx.desc_size; ring->last_free = desc; atomic_inc(&ring->free_count); @@ -2421,7 +2421,7 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget) do { int rx_done; - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->pdma.irq_status); rx_done = mtk_poll_rx(napi, budget - rx_done_total, eth); rx_done_total += rx_done; @@ -2437,10 +2437,10 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget) return budget; } while (mtk_r32(eth, reg_map->pdma.irq_status) & - eth->soc->txrx.rx_irq_done_mask); + eth->soc->rx.irq_done_mask); if (napi_complete_done(napi, rx_done_total)) - mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask); return rx_done_total; } @@ -2449,7 +2449,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth) { const struct mtk_soc_data *soc = eth->soc; struct mtk_tx_ring *ring = ð->tx_ring; - int i, sz = soc->txrx.txd_size; + int i, sz = soc->tx.desc_size; struct mtk_tx_dma_v2 *txd; int ring_size; u32 ofs, val; @@ -2572,14 +2572,14 @@ static void mtk_tx_clean(struct mtk_eth *eth) } if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && ring->dma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * soc->txrx.txd_size, + ring->dma_size * soc->tx.desc_size, ring->dma, ring->phys); ring->dma = NULL; } if (ring->dma_pdma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * soc->txrx.txd_size, + ring->dma_size * soc->tx.desc_size, ring->dma_pdma, ring->phys_pdma); ring->dma_pdma = NULL; } @@ -2634,15 +2634,15 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SRAM) || rx_flag != MTK_RX_FLAGS_NORMAL) { ring->dma = dma_alloc_coherent(eth->dma_dev, - rx_dma_size * eth->soc->txrx.rxd_size, - &ring->phys, GFP_KERNEL); + rx_dma_size * eth->soc->rx.desc_size, + &ring->phys, GFP_KERNEL); } else { struct mtk_tx_ring *tx_ring = ð->tx_ring; ring->dma = tx_ring->dma + tx_ring_size * - eth->soc->txrx.txd_size * (ring_no + 1); + eth->soc->tx.desc_size * (ring_no + 1); ring->phys = tx_ring->phys + tx_ring_size * - eth->soc->txrx.txd_size * (ring_no + 1); + eth->soc->tx.desc_size * (ring_no + 1); } if (!ring->dma) @@ -2653,7 +2653,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) dma_addr_t dma_addr; void *data; - rxd = ring->dma + i * eth->soc->txrx.rxd_size; + rxd = ring->dma + i * eth->soc->rx.desc_size; if (ring->page_pool) { data = mtk_page_pool_get_buff(ring->page_pool, &dma_addr, GFP_KERNEL); @@ -2744,7 +2744,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_ if (!ring->data[i]) continue; - rxd = ring->dma + i * eth->soc->txrx.rxd_size; + rxd = ring->dma + i * eth->soc->rx.desc_size; if (!rxd->rxd1) continue; @@ -2761,7 +2761,7 @@ static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring, bool in_ if (!in_sram && ring->dma) { dma_free_coherent(eth->dma_dev, - ring->dma_size * eth->soc->txrx.rxd_size, + ring->dma_size * eth->soc->rx.desc_size, ring->dma, ring->phys); ring->dma = NULL; } @@ -3124,7 +3124,7 @@ static void mtk_dma_free(struct mtk_eth *eth) netdev_reset_queue(eth->netdev[i]); if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) { dma_free_coherent(eth->dma_dev, - MTK_QDMA_RING_SIZE * soc->txrx.txd_size, + MTK_QDMA_RING_SIZE * soc->tx.desc_size, eth->scratch_ring, eth->phy_scratch_ring); eth->scratch_ring = NULL; eth->phy_scratch_ring = 0; @@ -3174,7 +3174,7 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth) eth->rx_events++; if (likely(napi_schedule_prep(ð->rx_napi))) { - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); __napi_schedule(ð->rx_napi); } @@ -3200,9 +3200,9 @@ static irqreturn_t mtk_handle_irq(int irq, void *_eth) const struct mtk_reg_map *reg_map = eth->soc->reg_map; if (mtk_r32(eth, reg_map->pdma.irq_mask) & - eth->soc->txrx.rx_irq_done_mask) { + eth->soc->rx.irq_done_mask) { if (mtk_r32(eth, reg_map->pdma.irq_status) & - eth->soc->txrx.rx_irq_done_mask) + eth->soc->rx.irq_done_mask) mtk_handle_irq_rx(irq, _eth); } if (mtk_r32(eth, reg_map->tx_irq_mask) & MTK_TX_DONE_INT) { @@ -3220,10 +3220,10 @@ static void mtk_poll_controller(struct net_device *dev) struct mtk_eth *eth = mac->hw; mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); mtk_handle_irq_rx(eth->irq[2], dev); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_enable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, eth->soc->rx.irq_done_mask); } #endif @@ -3387,7 +3387,7 @@ static int mtk_open(struct net_device *dev) napi_enable(ð->tx_napi); napi_enable(ð->rx_napi); mtk_tx_irq_enable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_enable(eth, soc->txrx.rx_irq_done_mask); + mtk_rx_irq_enable(eth, soc->rx.irq_done_mask); refcount_set(ð->dma_refcnt, 1); } else @@ -3471,7 +3471,7 @@ static int mtk_stop(struct net_device *dev) mtk_gdm_config(eth, MTK_GDMA_DROP_ALL); mtk_tx_irq_disable(eth, MTK_TX_DONE_INT); - mtk_rx_irq_disable(eth, eth->soc->txrx.rx_irq_done_mask); + mtk_rx_irq_disable(eth, eth->soc->rx.irq_done_mask); napi_disable(ð->tx_napi); napi_disable(ð->rx_napi); @@ -3947,9 +3947,9 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) /* FE int grouping */ mtk_w32(eth, MTK_TX_DONE_INT, reg_map->pdma.int_grp); - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->pdma.int_grp + 4); + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->pdma.int_grp + 4); mtk_w32(eth, MTK_TX_DONE_INT, reg_map->qdma.int_grp); - mtk_w32(eth, eth->soc->txrx.rx_irq_done_mask, reg_map->qdma.int_grp + 4); + mtk_w32(eth, eth->soc->rx.irq_done_mask, reg_map->qdma.int_grp + 4); mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); if (mtk_is_netsys_v3_or_greater(eth)) { @@ -5039,11 +5039,15 @@ static const struct mtk_soc_data mt2701_data = { .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5059,11 +5063,15 @@ static const struct mtk_soc_data mt7621_data = { .offload_version = 1, .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5081,11 +5089,15 @@ static const struct mtk_soc_data mt7622_data = { .hash_offset = 2, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5102,11 +5114,15 @@ static const struct mtk_soc_data mt7623_data = { .hash_offset = 2, .foe_entry_size = MTK_FOE_ENTRY_V1_SIZE, .disable_pll_modes = true, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5121,11 +5137,15 @@ static const struct mtk_soc_data mt7629_data = { .required_pctl = false, .has_accounting = true, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, @@ -5143,11 +5163,15 @@ static const struct mtk_soc_data mt7981_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), + .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, + .dma_len_offset = 8, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma_v2), + .irq_done_mask = MTK_RX_DONE_INT_V2, + .dma_l4_valid = RX_DMA_L4_VALID_V2, .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, }, @@ -5165,11 +5189,15 @@ static const struct mtk_soc_data mt7986_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V2_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), + .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, + .dma_len_offset = 8, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma_v2), + .irq_done_mask = MTK_RX_DONE_INT_V2, + .dma_l4_valid = RX_DMA_L4_VALID_V2, .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, }, @@ -5187,11 +5215,15 @@ static const struct mtk_soc_data mt7988_data = { .hash_offset = 4, .has_accounting = true, .foe_entry_size = MTK_FOE_ENTRY_V3_SIZE, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma_v2), - .rxd_size = sizeof(struct mtk_rx_dma_v2), - .rx_irq_done_mask = MTK_RX_DONE_INT_V2, - .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma_v2), + .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, + .dma_len_offset = 8, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma_v2), + .irq_done_mask = MTK_RX_DONE_INT_V2, + .dma_l4_valid = RX_DMA_L4_VALID_V2, .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, }, @@ -5204,11 +5236,15 @@ static const struct mtk_soc_data rt5350_data = { .required_clks = MT7628_CLKS_BITMAP, .required_pctl = false, .version = 1, - .txrx = { - .txd_size = sizeof(struct mtk_tx_dma), - .rxd_size = sizeof(struct mtk_rx_dma), - .rx_irq_done_mask = MTK_RX_DONE_INT, - .rx_dma_l4_valid = RX_DMA_L4_VALID_PDMA, + .tx = { + .desc_size = sizeof(struct mtk_tx_dma), + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, + }, + .rx = { + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, + .dma_l4_valid = RX_DMA_L4_VALID_PDMA, .dma_max_len = MTK_TX_DMA_BUF_LEN, .dma_len_offset = 16, }, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 9ae3b8a71d0e..39b50de1decb 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -327,8 +327,8 @@ /* QDMA descriptor txd3 */ #define TX_DMA_OWNER_CPU BIT(31) #define TX_DMA_LS0 BIT(30) -#define TX_DMA_PLEN0(x) (((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset) -#define TX_DMA_PLEN1(x) ((x) & eth->soc->txrx.dma_max_len) +#define TX_DMA_PLEN0(x) (((x) & eth->soc->tx.dma_max_len) << eth->soc->tx.dma_len_offset) +#define TX_DMA_PLEN1(x) ((x) & eth->soc->tx.dma_max_len) #define TX_DMA_SWC BIT(14) #define TX_DMA_PQID GENMASK(3, 0) #define TX_DMA_ADDR64_MASK GENMASK(3, 0) @@ -348,8 +348,8 @@ /* QDMA descriptor rxd2 */ #define RX_DMA_DONE BIT(31) #define RX_DMA_LSO BIT(30) -#define RX_DMA_PREP_PLEN0(x) (((x) & eth->soc->txrx.dma_max_len) << eth->soc->txrx.dma_len_offset) -#define RX_DMA_GET_PLEN0(x) (((x) >> eth->soc->txrx.dma_len_offset) & eth->soc->txrx.dma_max_len) +#define RX_DMA_PREP_PLEN0(x) (((x) & eth->soc->rx.dma_max_len) << eth->soc->rx.dma_len_offset) +#define RX_DMA_GET_PLEN0(x) (((x) >> eth->soc->rx.dma_len_offset) & eth->soc->rx.dma_max_len) #define RX_DMA_VTAG BIT(15) #define RX_DMA_ADDR64_MASK GENMASK(3, 0) #if IS_ENABLED(CONFIG_64BIT) @@ -1153,10 +1153,9 @@ struct mtk_reg_map { * @foe_entry_size Foe table entry size. * @has_accounting Bool indicating support for accounting of * offloaded flows. - * @txd_size Tx DMA descriptor size. - * @rxd_size Rx DMA descriptor size. - * @rx_irq_done_mask Rx irq done register mask. - * @rx_dma_l4_valid Rx DMA valid register mask. + * @desc_size Tx/Rx DMA descriptor size. + * @irq_done_mask Rx irq done register mask. + * @dma_l4_valid Rx DMA valid register mask. * @dma_max_len Max DMA tx/rx buffer length. * @dma_len_offset Tx/Rx DMA length field offset. */ @@ -1174,13 +1173,17 @@ struct mtk_soc_data { bool has_accounting; bool disable_pll_modes; struct { - u32 txd_size; - u32 rxd_size; - u32 rx_irq_done_mask; - u32 rx_dma_l4_valid; + u32 desc_size; u32 dma_max_len; u32 dma_len_offset; - } txrx; + } tx; + struct { + u32 desc_size; + u32 irq_done_mask; + u32 dma_l4_valid; + u32 dma_max_len; + u32 dma_len_offset; + } rx; }; #define MTK_DMA_MONITOR_TIMEOUT msecs_to_jiffies(1000) -- cgit v1.2.3 From 5e69ff84f3e6cc54502a902043847b37ed78afd4 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Wed, 8 May 2024 11:43:56 +0100 Subject: net: ethernet: mediatek: use ADMAv1 instead of ADMAv2.0 on MT7981 and MT7986 ADMAv2.0 is plagued by RX hangs which can't easily detected and happen upon receival of a corrupted Ethernet frame. Use ADMAv1 instead which is also still present and usable, and doesn't suffer from that problem. Fixes: 197c9e9b17b1 ("net: ethernet: mtk_eth_soc: introduce support for mt7986 chipset") Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Golle Link: https://lore.kernel.org/r/57cef74bbd0c243366ad1ff4221e3f72f437ec80.1715164770.git.daniel@makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 46 ++++++++++++++--------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 3eefb735ce19..d7d73295f0dc 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -110,16 +110,16 @@ static const struct mtk_reg_map mt7986_reg_map = { .tx_irq_mask = 0x461c, .tx_irq_status = 0x4618, .pdma = { - .rx_ptr = 0x6100, - .rx_cnt_cfg = 0x6104, - .pcrx_ptr = 0x6108, - .glo_cfg = 0x6204, - .rst_idx = 0x6208, - .delay_irq = 0x620c, - .irq_status = 0x6220, - .irq_mask = 0x6228, - .adma_rx_dbg0 = 0x6238, - .int_grp = 0x6250, + .rx_ptr = 0x4100, + .rx_cnt_cfg = 0x4104, + .pcrx_ptr = 0x4108, + .glo_cfg = 0x4204, + .rst_idx = 0x4208, + .delay_irq = 0x420c, + .irq_status = 0x4220, + .irq_mask = 0x4228, + .adma_rx_dbg0 = 0x4238, + .int_grp = 0x4250, }, .qdma = { .qtx_cfg = 0x4400, @@ -1107,7 +1107,7 @@ static bool mtk_rx_get_desc(struct mtk_eth *eth, struct mtk_rx_dma_v2 *rxd, rxd->rxd1 = READ_ONCE(dma_rxd->rxd1); rxd->rxd3 = READ_ONCE(dma_rxd->rxd3); rxd->rxd4 = READ_ONCE(dma_rxd->rxd4); - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { rxd->rxd5 = READ_ONCE(dma_rxd->rxd5); rxd->rxd6 = READ_ONCE(dma_rxd->rxd6); } @@ -2028,7 +2028,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, break; /* find out which mac the packet come from. values start at 1 */ - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { u32 val = RX_DMA_GET_SPORT_V2(trxd.rxd5); switch (val) { @@ -2140,7 +2140,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb->dev = netdev; bytes += skb->len; - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { reason = FIELD_GET(MTK_RXD5_PPE_CPU_REASON, trxd.rxd5); hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY; if (hash != MTK_RXD5_FOE_ENTRY) @@ -2690,7 +2690,7 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) rxd->rxd3 = 0; rxd->rxd4 = 0; - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { rxd->rxd5 = 0; rxd->rxd6 = 0; rxd->rxd7 = 0; @@ -3893,7 +3893,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) else mtk_hw_reset(eth); - if (mtk_is_netsys_v2_or_greater(eth)) { + if (mtk_is_netsys_v3_or_greater(eth)) { /* Set FE to PDMAv2 if necessary */ val = mtk_r32(eth, MTK_FE_GLO_MISC); mtk_w32(eth, val | BIT(4), MTK_FE_GLO_MISC); @@ -5169,11 +5169,11 @@ static const struct mtk_soc_data mt7981_data = { .dma_len_offset = 8, }, .rx = { - .desc_size = sizeof(struct mtk_rx_dma_v2), - .irq_done_mask = MTK_RX_DONE_INT_V2, + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, .dma_l4_valid = RX_DMA_L4_VALID_V2, - .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, - .dma_len_offset = 8, + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, }, }; @@ -5195,11 +5195,11 @@ static const struct mtk_soc_data mt7986_data = { .dma_len_offset = 8, }, .rx = { - .desc_size = sizeof(struct mtk_rx_dma_v2), - .irq_done_mask = MTK_RX_DONE_INT_V2, + .desc_size = sizeof(struct mtk_rx_dma), + .irq_done_mask = MTK_RX_DONE_INT, .dma_l4_valid = RX_DMA_L4_VALID_V2, - .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, - .dma_len_offset = 8, + .dma_max_len = MTK_TX_DMA_BUF_LEN, + .dma_len_offset = 16, }, }; -- cgit v1.2.3 From 6d51d44ecddb5c2962688ef06e55e4fbc949f04a Mon Sep 17 00:00:00 2001 From: Dan Nowlin Date: Wed, 8 May 2024 10:19:07 -0700 Subject: ice: Fix package download algorithm Previously, the driver assumed that all signature segments would contain one or more buffers to download. In the future, there will be signature segments that will contain no buffers to download. Correct download flow to allow for signature segments that have zero download buffers and skip the download in this case. Fixes: 3cbdb0343022 ("ice: Add support for E830 DDP package segment") Reviewed-by: Przemek Kitszel Signed-off-by: Dan Nowlin Signed-off-by: Paul Greenwalt Reviewed-by: Paul Menzel Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20240508171908.2760776-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_ddp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index fc91c4d41186..4df561d64bc3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1424,14 +1424,14 @@ ice_dwnld_sign_and_cfg_segs(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr, goto exit; } - conf_idx = le32_to_cpu(seg->signed_seg_idx); - start = le32_to_cpu(seg->signed_buf_start); count = le32_to_cpu(seg->signed_buf_count); - state = ice_download_pkg_sig_seg(hw, seg); - if (state) + if (state || !count) goto exit; + conf_idx = le32_to_cpu(seg->signed_seg_idx); + start = le32_to_cpu(seg->signed_buf_start); + state = ice_download_pkg_config_seg(hw, pkg_hdr, conf_idx, start, count); -- cgit v1.2.3 From 812552808f7ff71133fc59768cdc253c5b8ca1bf Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 9 May 2024 09:44:54 +0200 Subject: net: ethernet: cortina: Locking fixes This fixes a probably long standing problem in the Cortina Gemini ethernet driver: there are some paths in the code where the IRQ registers are written without taking the proper locks. Fixes: 4d5ae32f5e1e ("net: ethernet: Add a driver for Gemini gigabit ethernet") Signed-off-by: Linus Walleij Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240509-gemini-ethernet-locking-v1-1-afd00a528b95@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cortina/gemini.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 705c3eb19cd3..d1fbadbf86d4 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1107,10 +1107,13 @@ static void gmac_tx_irq_enable(struct net_device *netdev, { struct gemini_ethernet_port *port = netdev_priv(netdev); struct gemini_ethernet *geth = port->geth; + unsigned long flags; u32 val, mask; netdev_dbg(netdev, "%s device %d\n", __func__, netdev->dev_id); + spin_lock_irqsave(&geth->irq_lock, flags); + mask = GMAC0_IRQ0_TXQ0_INTS << (6 * netdev->dev_id + txq); if (en) @@ -1119,6 +1122,8 @@ static void gmac_tx_irq_enable(struct net_device *netdev, val = readl(geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG); val = en ? val | mask : val & ~mask; writel(val, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG); + + spin_unlock_irqrestore(&geth->irq_lock, flags); } static void gmac_tx_irq(struct net_device *netdev, unsigned int txq_num) @@ -1415,15 +1420,19 @@ static unsigned int gmac_rx(struct net_device *netdev, unsigned int budget) union gmac_rxdesc_3 word3; struct page *page = NULL; unsigned int page_offs; + unsigned long flags; unsigned short r, w; union dma_rwptr rw; dma_addr_t mapping; int frag_nr = 0; + spin_lock_irqsave(&geth->irq_lock, flags); rw.bits32 = readl(ptr_reg); /* Reset interrupt as all packages until here are taken into account */ writel(DEFAULT_Q0_INT_BIT << netdev->dev_id, geth->base + GLOBAL_INTERRUPT_STATUS_1_REG); + spin_unlock_irqrestore(&geth->irq_lock, flags); + r = rw.bits.rptr; w = rw.bits.wptr; @@ -1726,10 +1735,9 @@ static irqreturn_t gmac_irq(int irq, void *data) gmac_update_hw_stats(netdev); if (val & (GMAC0_RX_OVERRUN_INT_BIT << (netdev->dev_id * 8))) { + spin_lock(&geth->irq_lock); writel(GMAC0_RXDERR_INT_BIT << (netdev->dev_id * 8), geth->base + GLOBAL_INTERRUPT_STATUS_4_REG); - - spin_lock(&geth->irq_lock); u64_stats_update_begin(&port->ir_stats_syncp); ++port->stats.rx_fifo_errors; u64_stats_update_end(&port->ir_stats_syncp); -- cgit v1.2.3 From 3d5918477f94e4c2f064567875c475468e264644 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 9 May 2024 14:29:47 +0300 Subject: net/mlx5e: Fix netif state handling mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks: mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :( Hence, clean resources in this case as well. [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]--- Fixes: 2c3b5beec46a ("net/mlx5e: More generic netdev management API") Signed-off-by: Shay Drory Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240509112951.590184-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 319930c04093..64497b6eebd3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6058,7 +6058,7 @@ static int mlx5e_resume(struct auxiliary_device *adev) return 0; } -static int _mlx5e_suspend(struct auxiliary_device *adev) +static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; @@ -6067,7 +6067,7 @@ static int _mlx5e_suspend(struct auxiliary_device *adev) struct mlx5_core_dev *pos; int i; - if (!netif_device_present(netdev)) { + if (!pre_netdev_reg && !netif_device_present(netdev)) { if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) mlx5_sd_for_each_dev(i, mdev, pos) mlx5e_destroy_mdev_resources(pos); @@ -6090,7 +6090,7 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); if (actual_adev) - err = _mlx5e_suspend(actual_adev); + err = _mlx5e_suspend(actual_adev, false); mlx5_sd_cleanup(mdev); return err; @@ -6157,7 +6157,7 @@ static int _mlx5e_probe(struct auxiliary_device *adev) return 0; err_resume: - _mlx5e_suspend(adev); + _mlx5e_suspend(adev, true); err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: @@ -6197,7 +6197,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev) mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); - _mlx5e_suspend(adev); + _mlx5e_suspend(adev, false); priv->profile->cleanup(priv); mlx5e_destroy_netdev(priv); mlx5e_devlink_port_unregister(mlx5e_dev); -- cgit v1.2.3 From 3c453e8cc672de1f9c662948dba43176bc68d7f0 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 9 May 2024 14:29:48 +0300 Subject: net/mlx5: Fix peer devlink set for SF representor devlink port The cited patch change register devlink flow, and neglect to reflect the changes for peer devlink set logic. Peer devlink set is triggering a call trace if done after devl_register.[1] Hence, align peer devlink set logic with register devlink flow. [1] WARNING: CPU: 4 PID: 3394 at net/devlink/core.c:155 devlink_rel_nested_in_add+0x177/0x180 CPU: 4 PID: 3394 Comm: kworker/u40:1 Not tainted 6.9.0-rc4_for_linust_min_debug_2024_04_16_14_08 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: mlx5_vhca_event0 mlx5_vhca_state_work_handler [mlx5_core] RIP: 0010:devlink_rel_nested_in_add+0x177/0x180 Call Trace: ? __warn+0x78/0x120 ? devlink_rel_nested_in_add+0x177/0x180 ? report_bug+0x16d/0x180 ? handle_bug+0x3c/0x60 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? devlink_port_init+0x30/0x30 ? devlink_port_type_clear+0x50/0x50 ? devlink_rel_nested_in_add+0x177/0x180 ? devlink_rel_nested_in_add+0xdd/0x180 mlx5_sf_mdev_event+0x74/0xb0 [mlx5_core] notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_sf_dev_probe+0x185/0x3e0 [mlx5_core] auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc5/0x3a0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x64f/0x860 __auxiliary_device_add+0x3b/0xa0 mlx5_sf_dev_add+0x139/0x330 [mlx5_core] mlx5_sf_dev_state_change_handler+0x1e4/0x250 [mlx5_core] notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_vhca_state_work_handler+0x151/0x200 [mlx5_core] process_one_work+0x13f/0x2e0 worker_thread+0x2bd/0x3c0 ? rescuer_thread+0x410/0x410 kthread+0xc4/0xf0 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x2d/0x50 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork_asm+0x11/0x20 Fixes: bf729988303a ("net/mlx5: Restore mistakenly dropped parts in register devlink flow") Fixes: c6e77aa9dd82 ("net/mlx5: Register devlink first under devlink lock") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240509112951.590184-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 14 +++++--------- .../net/ethernet/mellanox/mlx5/core/sf/dev/driver.c | 19 ++++++++----------- 2 files changed, 13 insertions(+), 20 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 331ce47f51a1..6574c145dc1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1680,6 +1680,8 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) struct devlink *devlink = priv_to_devlink(dev); int err; + devl_lock(devlink); + devl_register(devlink); dev->state = MLX5_DEVICE_STATE_UP; err = mlx5_function_enable(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); if (err) { @@ -1693,27 +1695,21 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) goto query_hca_caps_err; } - devl_lock(devlink); - devl_register(devlink); - err = mlx5_devlink_params_register(priv_to_devlink(dev)); if (err) { mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); - goto params_reg_err; + goto query_hca_caps_err; } devl_unlock(devlink); return 0; -params_reg_err: - devl_unregister(devlink); - devl_unlock(devlink); query_hca_caps_err: - devl_unregister(devlink); - devl_unlock(devlink); mlx5_function_disable(dev, true); out: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + devl_unregister(devlink); + devl_unlock(devlink); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 7ebe71280827..b2986175d9af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -60,6 +60,13 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto remap_err; } + /* Peer devlink logic expects to work on unregistered devlink instance. */ + err = mlx5_core_peer_devlink_set(sf_dev, devlink); + if (err) { + mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err); + goto peer_devlink_set_err; + } + if (MLX5_ESWITCH_MANAGER(sf_dev->parent_mdev)) err = mlx5_init_one_light(mdev); else @@ -69,20 +76,10 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } - err = mlx5_core_peer_devlink_set(sf_dev, devlink); - if (err) { - mlx5_core_warn(mdev, "mlx5_core_peer_devlink_set err=%d\n", err); - goto peer_devlink_set_err; - } - return 0; -peer_devlink_set_err: - if (mlx5_dev_is_lightweight(sf_dev->mdev)) - mlx5_uninit_one_light(sf_dev->mdev); - else - mlx5_uninit_one(sf_dev->mdev); init_one_err: +peer_devlink_set_err: iounmap(mdev->iseg); remap_err: mlx5_mdev_uninit(mdev); -- cgit v1.2.3 From 0f06228d4a2dcc1fca5b3ddb0eefa09c05b102c4 Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Thu, 9 May 2024 14:29:49 +0300 Subject: net/mlx5: Reload only IB representors upon lag disable/enable On lag disable, the bond IB device along with all of its representors are destroyed, and then the slaves' representors get reloaded. In case the slave IB representor load fails, the eswitch error flow unloads all representors, including ethernet representors, where the netdevs get detached and removed from lag bond. Such flow is inaccurate as the lag driver is not responsible for loading/unloading ethernet representors. Furthermore, the flow described above begins by holding lag lock to prevent bond changes during disable flow. However, when reaching the ethernet representors detachment from lag, the lag lock is required again, triggering the following deadlock: Call trace: __switch_to+0xf4/0x148 __schedule+0x2c8/0x7d0 schedule+0x50/0xe0 schedule_preempt_disabled+0x18/0x28 __mutex_lock.isra.13+0x2b8/0x570 __mutex_lock_slowpath+0x1c/0x28 mutex_lock+0x4c/0x68 mlx5_lag_remove_netdev+0x3c/0x1a0 [mlx5_core] mlx5e_uplink_rep_disable+0x70/0xa0 [mlx5_core] mlx5e_detach_netdev+0x6c/0xb0 [mlx5_core] mlx5e_netdev_change_profile+0x44/0x138 [mlx5_core] mlx5e_netdev_attach_nic_profile+0x28/0x38 [mlx5_core] mlx5e_vport_rep_unload+0x184/0x1b8 [mlx5_core] mlx5_esw_offloads_rep_load+0xd8/0xe0 [mlx5_core] mlx5_eswitch_reload_reps+0x74/0xd0 [mlx5_core] mlx5_disable_lag+0x130/0x138 [mlx5_core] mlx5_lag_disable_change+0x6c/0x70 [mlx5_core] // hold ldev->lock mlx5_devlink_eswitch_mode_set+0xc0/0x410 [mlx5_core] devlink_nl_cmd_eswitch_set_doit+0xdc/0x180 genl_family_rcv_msg_doit.isra.17+0xe8/0x138 genl_rcv_msg+0xe4/0x220 netlink_rcv_skb+0x44/0x108 genl_rcv+0x40/0x58 netlink_unicast+0x198/0x268 netlink_sendmsg+0x1d4/0x418 sock_sendmsg+0x54/0x60 __sys_sendto+0xf4/0x120 __arm64_sys_sendto+0x30/0x40 el0_svc_common+0x8c/0x120 do_el0_svc+0x30/0xa0 el0_svc+0x20/0x30 el0_sync_handler+0x90/0xb8 el0_sync+0x160/0x180 Thus, upon lag enable/disable, load and unload only the IB representors of the slaves preventing the deadlock mentioned above. While at it, refactor the mlx5_esw_offloads_rep_load() function to have a static helper method for its internal logic, in symmetry with the representor unload design. Fixes: 598fe77df855 ("net/mlx5: Lag, Create shared FDB when in switchdev mode") Co-developed-by: Mark Bloch Signed-off-by: Mark Bloch Signed-off-by: Maher Sanalla Signed-off-by: Tariq Toukan Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240509112951.590184-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ++-- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 28 ++++++++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 6 ++--- .../net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 4 ++-- 4 files changed, 25 insertions(+), 17 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 349e28a6dd8d..ef55674876cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -833,7 +833,7 @@ int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw, int max_slaves); void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); -int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw); +int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw); bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev); void mlx5_eswitch_unblock_encap(struct mlx5_core_dev *dev); @@ -925,7 +925,7 @@ mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) { return 0; } static inline int -mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 844d3e3a65dd..e8caf12f4c4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2502,6 +2502,16 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw) esw_offloads_cleanup_reps(esw); } +static int __esw_offloads_load_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + if (atomic_cmpxchg(&rep->rep_data[rep_type].state, + REP_REGISTERED, REP_LOADED) == REP_REGISTERED) + return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep); + + return 0; +} + static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u8 rep_type) { @@ -2526,13 +2536,11 @@ static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num) int err; rep = mlx5_eswitch_get_rep(esw, vport_num); - for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) - if (atomic_cmpxchg(&rep->rep_data[rep_type].state, - REP_REGISTERED, REP_LOADED) == REP_REGISTERED) { - err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep); - if (err) - goto err_reps; - } + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_reps; + } return 0; @@ -3277,7 +3285,7 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) esw_vport_destroy_offloads_acl_tables(esw, vport); } -int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) +int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw) { struct mlx5_eswitch_rep *rep; unsigned long i; @@ -3290,13 +3298,13 @@ int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) return 0; - ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK); + ret = __esw_offloads_load_rep(esw, rep, REP_IB); if (ret) return ret; mlx5_esw_for_each_rep(esw, i, rep) { if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED) - mlx5_esw_offloads_rep_load(esw, rep->vport); + __esw_offloads_load_rep(esw, rep, REP_IB); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 69d482f7c5a2..37598d116f3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -814,7 +814,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) if (shared_fdb) for (i = 0; i < ldev->ports; i++) if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); } static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) @@ -922,7 +922,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) mlx5_rescan_drivers_locked(dev0); for (i = 0; i < ldev->ports; i++) { - err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) break; } @@ -933,7 +933,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) mlx5_deactivate_lag(ldev); mlx5_lag_add_devices(ldev); for (i = 0; i < ldev->ports; i++) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_core_err(dev0, "Failed to enable lag\n"); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 82889f30506e..571ea26edd0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -99,7 +99,7 @@ static int enable_mpesw(struct mlx5_lag *ldev) dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); for (i = 0; i < ldev->ports; i++) { - err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + err = mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); if (err) goto err_rescan_drivers; } @@ -113,7 +113,7 @@ err_rescan_drivers: err_add_devices: mlx5_lag_add_devices(ldev); for (i = 0; i < ldev->ports; i++) - mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch); mlx5_mpesw_metadata_cleanup(ldev); return err; } -- cgit v1.2.3 From 485d65e1357123a697c591a5aeb773994b247ad7 Mon Sep 17 00:00:00 2001 From: Akiva Goldberger Date: Thu, 9 May 2024 14:29:50 +0300 Subject: net/mlx5: Add a timeout to acquire the command queue semaphore Prevent forced completion handling on an entry that has not yet been assigned an index, causing an out of bounds access on idx = -22. Instead of waiting indefinitely for the sem, blocking flow now waits for index to be allocated or a sem acquisition timeout before beginning the timer for FW completion. Kernel log example: mlx5_core 0000:06:00.0: wait_func_handle_exec_timeout:1128:(pid 185911): cmd[-22]: CREATE_UCTX(0xa04) No done completion Fixes: 8e715cd613a1 ("net/mlx5: Set command entry semaphore up once got index free") Signed-off-by: Akiva Goldberger Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Link: https://lore.kernel.org/r/20240509112951.590184-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 41 +++++++++++++++++++++------ include/linux/mlx5/driver.h | 1 + 2 files changed, 33 insertions(+), 9 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4957412ff1f6..511e7fee39ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -969,19 +969,32 @@ static void cmd_work_handler(struct work_struct *work) bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; struct mlx5_core_dev *dev; - unsigned long cb_timeout; - struct semaphore *sem; + unsigned long timeout; unsigned long flags; int alloc_ret; int cmd_mode; + complete(&ent->handling); + dev = container_of(cmd, struct mlx5_core_dev, cmd); - cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); - complete(&ent->handling); - sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; - down(sem); if (!ent->page_queue) { + if (down_timeout(&cmd->vars.sem, timeout)) { + mlx5_core_warn(dev, "%s(0x%x) timed out while waiting for a slot.\n", + mlx5_command_str(ent->op), ent->op); + if (ent->callback) { + ent->callback(-EBUSY, ent->context); + mlx5_free_cmd_msg(dev, ent->out); + free_msg(dev, ent->in); + cmd_ent_put(ent); + } else { + ent->ret = -EBUSY; + complete(&ent->done); + } + complete(&ent->slotted); + return; + } alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); @@ -994,10 +1007,11 @@ static void cmd_work_handler(struct work_struct *work) ent->ret = -EAGAIN; complete(&ent->done); } - up(sem); + up(&cmd->vars.sem); return; } } else { + down(&cmd->vars.pages_sem); ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->vars.bitmask); @@ -1005,6 +1019,8 @@ static void cmd_work_handler(struct work_struct *work) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } + complete(&ent->slotted); + lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -1023,7 +1039,7 @@ static void cmd_work_handler(struct work_struct *work) ent->ts1 = ktime_get_ns(); cmd_mode = cmd->mode; - if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout)) + if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, timeout)) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); @@ -1143,6 +1159,9 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) ent->ret = -ECANCELED; goto out_err; } + + wait_for_completion(&ent->slotted); + if (cmd->mode == CMD_MODE_POLLING || ent->polling) wait_for_completion(&ent->done); else if (!wait_for_completion_timeout(&ent->done, timeout)) @@ -1157,6 +1176,9 @@ out_err: } else if (err == -ECANCELED) { mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n", mlx5_command_str(ent->op), ent->op); + } else if (err == -EBUSY) { + mlx5_core_warn(dev, "%s(0x%x) timeout while waiting for command semaphore.\n", + mlx5_command_str(ent->op), ent->op); } mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n", err, deliv_status_to_str(ent->status), ent->status); @@ -1208,6 +1230,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, ent->polling = force_polling; init_completion(&ent->handling); + init_completion(&ent->slotted); if (!callback) init_completion(&ent->done); @@ -1225,7 +1248,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, return 0; /* mlx5_cmd_comp_handler() will put(ent) */ err = wait_func(dev, ent); - if (err == -ETIMEDOUT || err == -ECANCELED) + if (err == -ETIMEDOUT || err == -ECANCELED || err == -EBUSY) goto out_free; ds = ent->ts2 - ent->ts1; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..80452bd98253 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -862,6 +862,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; -- cgit v1.2.3 From db9b31aa9bc56ff0d15b78f7e827d61c4a096e40 Mon Sep 17 00:00:00 2001 From: Akiva Goldberger Date: Thu, 9 May 2024 14:29:51 +0300 Subject: net/mlx5: Discard command completions in internal error Fix use after free when FW completion arrives while device is in internal error state. Avoid calling completion handler in this case, since the device will flush the command interface and trigger all completions manually. Kernel log: ------------[ cut here ]------------ refcount_t: underflow; use-after-free. ... RIP: 0010:refcount_warn_saturate+0xd8/0xe0 ... Call Trace: ? __warn+0x79/0x120 ? refcount_warn_saturate+0xd8/0xe0 ? report_bug+0x17c/0x190 ? handle_bug+0x3c/0x60 ? exc_invalid_op+0x14/0x70 ? asm_exc_invalid_op+0x16/0x20 ? refcount_warn_saturate+0xd8/0xe0 cmd_ent_put+0x13b/0x160 [mlx5_core] mlx5_cmd_comp_handler+0x5f9/0x670 [mlx5_core] cmd_comp_notifier+0x1f/0x30 [mlx5_core] notifier_call_chain+0x35/0xb0 atomic_notifier_call_chain+0x16/0x20 mlx5_eq_async_int+0xf6/0x290 [mlx5_core] notifier_call_chain+0x35/0xb0 atomic_notifier_call_chain+0x16/0x20 irq_int_handler+0x19/0x30 [mlx5_core] __handle_irq_event_percpu+0x4b/0x160 handle_irq_event+0x2e/0x80 handle_edge_irq+0x98/0x230 __common_interrupt+0x3b/0xa0 common_interrupt+0x7b/0xa0 asm_common_interrupt+0x22/0x40 Fixes: 51d138c2610a ("net/mlx5: Fix health error state handling") Signed-off-by: Akiva Goldberger Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Link: https://lore.kernel.org/r/20240509112951.590184-6-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 511e7fee39ac..20768ef2e9d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1634,6 +1634,9 @@ static int cmd_comp_notifier(struct notifier_block *nb, dev = container_of(cmd, struct mlx5_core_dev, cmd); eqe = data; + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + return NOTIFY_DONE; + mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false); return NOTIFY_OK; -- cgit v1.2.3 From 5eefb477d21a26183bc3499aeefa991198315a2d Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Fri, 10 May 2024 13:30:55 +0200 Subject: net: smc91x: Fix m68k kernel compilation for ColdFire CPU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Compiling the m68k kernel with support for the ColdFire CPU family fails with the following error: In file included from drivers/net/ethernet/smsc/smc91x.c:80: drivers/net/ethernet/smsc/smc91x.c: In function ‘smc_reset’: drivers/net/ethernet/smsc/smc91x.h:160:40: error: implicit declaration of function ‘_swapw’; did you mean ‘swap’? [-Werror=implicit-function-declaration] 160 | #define SMC_outw(lp, v, a, r) writew(_swapw(v), (a) + (r)) | ^~~~~~ drivers/net/ethernet/smsc/smc91x.h:904:25: note: in expansion of macro ‘SMC_outw’ 904 | SMC_outw(lp, x, ioaddr, BANK_SELECT); \ | ^~~~~~~~ drivers/net/ethernet/smsc/smc91x.c:250:9: note: in expansion of macro ‘SMC_SELECT_BANK’ 250 | SMC_SELECT_BANK(lp, 2); | ^~~~~~~~~~~~~~~ cc1: some warnings being treated as errors The function _swapw() was removed in commit d97cf70af097 ("m68k: use asm-generic/io.h for non-MMU io access functions"), but is still used in drivers/net/ethernet/smsc/smc91x.h. Use ioread16be() and iowrite16be() to resolve the error. Cc: stable@vger.kernel.org Fixes: d97cf70af097 ("m68k: use asm-generic/io.h for non-MMU io access functions") Signed-off-by: Thorsten Blum Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20240510113054.186648-2-thorsten.blum@toblux.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/smsc/smc91x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 46eee747c699..45ef5ac0788a 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -156,8 +156,8 @@ static inline void mcf_outsw(void *a, unsigned char *p, int l) writew(*wp++, a); } -#define SMC_inw(a, r) _swapw(readw((a) + (r))) -#define SMC_outw(lp, v, a, r) writew(_swapw(v), (a) + (r)) +#define SMC_inw(a, r) ioread16be((a) + (r)) +#define SMC_outw(lp, v, a, r) iowrite16be(v, (a) + (r)) #define SMC_insw(a, r, p, l) mcf_insw(a + r, p, l) #define SMC_outsw(a, r, p, l) mcf_outsw(a + r, p, l) -- cgit v1.2.3 From ecf848eb934b03959918f5269f64c0e52bc23998 Mon Sep 17 00:00:00 2001 From: Jose Ignacio Tornos Martinez Date: Fri, 10 May 2024 11:08:28 +0200 Subject: net: usb: ax88179_178a: fix link status when link is set to down/up The idea was to keep only one reset at initialization stage in order to reduce the total delay, or the reset from usbnet_probe or the reset from usbnet_open. I have seen that restarting from usbnet_probe is necessary to avoid doing too complex things. But when the link is set to down/up (for example to configure a different mac address) the link is not correctly recovered unless a reset is commanded from usbnet_open. So, detect the initialization stage (first call) to not reset from usbnet_open after the reset from usbnet_probe and after this stage, always reset from usbnet_open too (when the link needs to be rechecked). Apply to all the possible devices, the behavior now is going to be the same. cc: stable@vger.kernel.org # 6.6+ Fixes: 56f78615bcb1 ("net: usb: ax88179_178a: avoid writing the mac address before first reading") Reported-by: Isaac Ganoung Reported-by: Yongqin Liu Signed-off-by: Jose Ignacio Tornos Martinez Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240510090846.328201-1-jtornosm@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/ax88179_178a.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index df9d767cb524..56ede5fa0261 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -174,6 +174,7 @@ struct ax88179_data { u32 wol_supported; u32 wolopts; u8 disconnecting; + u8 initialized; }; struct ax88179_int_data { @@ -1673,6 +1674,18 @@ static int ax88179_reset(struct usbnet *dev) return 0; } +static int ax88179_net_reset(struct usbnet *dev) +{ + struct ax88179_data *ax179_data = dev->driver_priv; + + if (ax179_data->initialized) + ax88179_reset(dev); + else + ax179_data->initialized = 1; + + return 0; +} + static int ax88179_stop(struct usbnet *dev) { u16 tmp16; @@ -1692,6 +1705,7 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1704,6 +1718,7 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1716,7 +1731,7 @@ static const struct driver_info cypress_GX3_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1729,7 +1744,7 @@ static const struct driver_info dlink_dub1312_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1742,7 +1757,7 @@ static const struct driver_info sitecom_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1755,7 +1770,7 @@ static const struct driver_info samsung_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1768,7 +1783,7 @@ static const struct driver_info lenovo_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1781,7 +1796,7 @@ static const struct driver_info belkin_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1794,7 +1809,7 @@ static const struct driver_info toshiba_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1807,7 +1822,7 @@ static const struct driver_info mct_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1820,7 +1835,7 @@ static const struct driver_info at_umc2000_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1833,7 +1848,7 @@ static const struct driver_info at_umc200_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1846,7 +1861,7 @@ static const struct driver_info at_umc2000sp_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, + .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, -- cgit v1.2.3 From c2e0c58b25a0a0c37ec643255558c5af4450c9f5 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Sat, 11 May 2024 14:20:09 +0800 Subject: net: fec: remove .ndo_poll_controller to avoid deadlocks There is a deadlock issue found in sungem driver, please refer to the commit ac0a230f719b ("eth: sungem: remove .ndo_poll_controller to avoid deadlocks"). The root cause of the issue is that netpoll is in atomic context and disable_irq() is called by .ndo_poll_controller interface of sungem driver, however, disable_irq() might sleep. After analyzing the implementation of fec_poll_controller(), the fec driver should have the same issue. Due to the fec driver uses NAPI for TX completions, the .ndo_poll_controller is unnecessary to be implemented in the fec driver, so fec_poll_controller() can be safely removed. Fixes: 7f5c6addcdc0 ("net/fec: add poll controller function for fec nic") Signed-off-by: Wei Fang Link: https://lore.kernel.org/r/20240511062009.652918-1-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 8bd213da8fb6..a72d8a2eb0b3 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3674,29 +3674,6 @@ fec_set_mac_address(struct net_device *ndev, void *p) return 0; } -#ifdef CONFIG_NET_POLL_CONTROLLER -/** - * fec_poll_controller - FEC Poll controller function - * @dev: The FEC network adapter - * - * Polled functionality used by netconsole and others in non interrupt mode - * - */ -static void fec_poll_controller(struct net_device *dev) -{ - int i; - struct fec_enet_private *fep = netdev_priv(dev); - - for (i = 0; i < FEC_IRQ_NUM; i++) { - if (fep->irq[i] > 0) { - disable_irq(fep->irq[i]); - fec_enet_interrupt(fep->irq[i], dev); - enable_irq(fep->irq[i]); - } - } -} -#endif - static inline void fec_enet_set_netdev_features(struct net_device *netdev, netdev_features_t features) { @@ -4003,9 +3980,6 @@ static const struct net_device_ops fec_netdev_ops = { .ndo_tx_timeout = fec_timeout, .ndo_set_mac_address = fec_set_mac_address, .ndo_eth_ioctl = phy_do_ioctl_running, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = fec_poll_controller, -#endif .ndo_set_features = fec_set_features, .ndo_bpf = fec_enet_bpf, .ndo_xdp_xmit = fec_enet_xdp_xmit, -- cgit v1.2.3 From aea27a92a41dae14843f92c79e9e42d8f570105c Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Mon, 13 May 2024 21:21:57 +0200 Subject: net: micrel: Fix receiving the timestamp in the frame for lan8841 The blamed commit started to use the ptp workqueue to get the second part of the timestamp. And when the port was set down, then this workqueue is stopped. But if the config option NETWORK_PHY_TIMESTAMPING is not enabled, then the ptp_clock is not initialized so then it would crash when it would try to access the delayed work. So then basically by setting up and then down the port, it would crash. The fix consists in checking if the ptp_clock is initialized and only then cancel the delayed work. Fixes: cc7554954848 ("net: micrel: Change to receive timestamp in the frame for lan8841") Signed-off-by: Horatiu Vultur Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index ddb50a0e2bc8..87780465cd0d 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -4676,7 +4676,8 @@ static int lan8841_suspend(struct phy_device *phydev) struct kszphy_priv *priv = phydev->priv; struct kszphy_ptp_priv *ptp_priv = &priv->ptp_priv; - ptp_cancel_worker_sync(ptp_priv->ptp_clock); + if (ptp_priv->ptp_clock) + ptp_cancel_worker_sync(ptp_priv->ptp_clock); return genphy_suspend(phydev); } -- cgit v1.2.3