From 5aac9108a180fc06e28d4e7fb00247ce603b72ee Mon Sep 17 00:00:00 2001 From: Shyam Sundar S K Date: Thu, 27 Jan 2022 14:50:03 +0530 Subject: net: amd-xgbe: Fix skb data length underflow There will be BUG_ON() triggered in include/linux/skbuff.h leading to intermittent kernel panic, when the skb length underflow is detected. Fix this by dropping the packet if such length underflows are seen because of inconsistencies in the hardware descriptors. Fixes: 622c36f143fc ("amd-xgbe: Fix jumbo MTU processing on newer hardware") Suggested-by: Tom Lendacky Signed-off-by: Shyam Sundar S K Acked-by: Tom Lendacky Link: https://lore.kernel.org/r/20220127092003.2812745-1-Shyam-sundar.S-k@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 492ac383f16d..ec3b287e3a71 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -2550,6 +2550,14 @@ read_again: buf2_len = xgbe_rx_buf2_len(rdata, packet, len); len += buf2_len; + if (buf2_len > rdata->rx.buf.dma_len) { + /* Hardware inconsistency within the descriptors + * that has resulted in a length underflow. + */ + error = 1; + goto skip_data; + } + if (!skb) { skb = xgbe_create_skb(pdata, napi, rdata, buf1_len); @@ -2579,8 +2587,10 @@ skip_data: if (!last || context_next) goto read_again; - if (!skb) + if (!skb || error) { + dev_kfree_skb(skb); goto next_packet; + } /* Be sure we don't exceed the configured MTU */ max_len = netdev->mtu + ETH_HLEN; -- cgit v1.2.3 From 7674b7b559b683478c3832527c59bceb169e701d Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Thu, 27 Jan 2022 11:32:22 +0530 Subject: net: amd-xgbe: ensure to reset the tx_timer_active flag Ensure to reset the tx_timer_active flag in xgbe_stop(), otherwise a port restart may result in tx timeout due to uncleared flag. Fixes: c635eaacbf77 ("amd-xgbe: Remove Tx coalescing") Co-developed-by: Sudheesh Mavila Signed-off-by: Sudheesh Mavila Signed-off-by: Raju Rangoju Acked-by: Tom Lendacky Link: https://lore.kernel.org/r/20220127060222.453371-1-Raju.Rangoju@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index ec3b287e3a71..a3593290886f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -721,7 +721,9 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata) if (!channel->tx_ring) break; + /* Deactivate the Tx timer */ del_timer_sync(&channel->tx_timer); + channel->tx_timer_active = 0; } } -- cgit v1.2.3 From 928d6fe996f69330ded6b887baf4534c5fac7988 Mon Sep 17 00:00:00 2001 From: Yuji Ishikawa Date: Thu, 27 Jan 2022 21:17:14 +0900 Subject: net: stmmac: dwmac-visconti: No change to ETHER_CLOCK_SEL for unexpected speed request. Variable clk_sel_val is not initialized in the default case of the first switch statement. In that case, the function should return immediately without any changes to the hardware. Reported-by: kernel test robot Reported-by: Dan Carpenter Fixes: b38dd98ff8d0 ("net: stmmac: Add Toshiba Visconti SoCs glue driver") Signed-off-by: Yuji Ishikawa Reviewed-by: Nobuhiro Iwamatsu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index dde5b772a5af..c3f10a92b62b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -49,13 +49,15 @@ struct visconti_eth { void __iomem *reg; u32 phy_intf_sel; struct clk *phy_ref_clk; + struct device *dev; spinlock_t lock; /* lock to protect register update */ }; static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) { struct visconti_eth *dwmac = priv; - unsigned int val, clk_sel_val; + struct net_device *netdev = dev_get_drvdata(dwmac->dev); + unsigned int val, clk_sel_val = 0; unsigned long flags; spin_lock_irqsave(&dwmac->lock, flags); @@ -85,7 +87,9 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) break; default: /* No bit control */ - break; + netdev_err(netdev, "Unsupported speed request (%d)", speed); + spin_unlock_irqrestore(&dwmac->lock, flags); + return; } writel(val, dwmac->reg + MAC_CTRL_REG); @@ -229,6 +233,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) spin_lock_init(&dwmac->lock); dwmac->reg = stmmac_res.addr; + dwmac->dev = &pdev->dev; plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed; -- cgit v1.2.3 From 1f84a9450d75e08af70d9e2f2d5e1c0ac0c881d2 Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Fri, 28 Jan 2022 18:47:14 +0800 Subject: gve: fix the wrong AdminQ buffer queue index check The 'tail' and 'head' are 'unsigned int' type free-running count, when 'head' is overflow, the 'int i (= tail) < u32 head' will be false: Only '- loop 0: idx = 63' result is shown, so it needs to use 'int' type to compare, it can handle the overflow correctly. typedef uint32_t u32; int main() { u32 tail, head; int stail, shead; int i, loop; tail = 0xffffffff; head = 0x00000000; for (i = tail, loop = 0; i < head; i++) { unsigned int idx = i & 63; printf("+ loop %d: idx = %u\n", loop++, idx); } stail = tail; shead = head; for (i = stail, loop = 0; i < shead; i++) { unsigned int idx = i & 63; printf("- loop %d: idx = %u\n", loop++, idx); } return 0; } Fixes: 5cdad90de62c ("gve: Batch AQ commands for creating and destroying queues.") Signed-off-by: Haiyue Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_adminq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 2ad7f57f7e5b..f7621ab672b9 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -301,7 +301,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) */ static int gve_adminq_kick_and_wait(struct gve_priv *priv) { - u32 tail, head; + int tail, head; int i; tail = ioread32be(&priv->reg_bar0->adminq_event_counter); -- cgit v1.2.3 From 6449520391dfc3d2cef134f11a91251a054ff7d0 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 28 Jan 2022 22:15:50 +0800 Subject: net: stmmac: properly handle with runtime pm in stmmac_dvr_remove() There are two issues with runtime pm handling in stmmac_dvr_remove(): 1. the mac is runtime suspended before stopping dma and rx/tx. We need to ensure the device is properly resumed back. 2. the stmmaceth clk enable/disable isn't balanced in both exit and error handling code path. Take the exit code path for example, when we unbind the driver or rmmod the driver module, the mac is runtime suspended as said above, so the stmmaceth clk is disabled, but stmmac_dvr_remove() stmmac_remove_config_dt() clk_disable_unprepare() CCF will complain this time. The error handling code path suffers from the similar situtaion. Here are kernel warnings in error handling code path on Allwinner D1 platform: [ 1.604695] ------------[ cut here ]------------ [ 1.609328] bus-emac already disabled [ 1.613015] WARNING: CPU: 0 PID: 38 at drivers/clk/clk.c:952 clk_core_disable+0xcc/0xec [ 1.621039] CPU: 0 PID: 38 Comm: kworker/u2:1 Not tainted 5.14.0-rc4#1 [ 1.627653] Hardware name: Allwinner D1 NeZha (DT) [ 1.632443] Workqueue: events_unbound deferred_probe_work_func [ 1.638286] epc : clk_core_disable+0xcc/0xec [ 1.642561] ra : clk_core_disable+0xcc/0xec [ 1.646835] epc : ffffffff8023c2ec ra : ffffffff8023c2ec sp : ffffffd00411bb10 [ 1.654054] gp : ffffffff80ec9988 tp : ffffffe00143a800 t0 : ffffffff80ed6a6f [ 1.661272] t1 : ffffffff80ed6a60 t2 : 0000000000000000 s0 : ffffffe001509e00 [ 1.668489] s1 : 0000000000000001 a0 : 0000000000000019 a1 : ffffffff80e80bd8 [ 1.675707] a2 : 00000000ffffefff a3 : 00000000000000f4 a4 : 0000000000000002 [ 1.682924] a5 : 0000000000000001 a6 : 0000000000000030 a7 : 00000000028f5c29 [ 1.690141] s2 : 0000000000000800 s3 : ffffffe001375000 s4 : ffffffe01fdf7a80 [ 1.697358] s5 : ffffffe001375010 s6 : ffffffff8001fc10 s7 : ffffffffffffffff [ 1.704577] s8 : 0000000000000001 s9 : ffffffff80ecb248 s10: ffffffe001b80000 [ 1.711794] s11: ffffffe001b80760 t3 : 0000000000000062 t4 : ffffffffffffffff [ 1.719012] t5 : ffffffff80e0f6d8 t6 : ffffffd00411b8f0 [ 1.724321] status: 8000000201800100 badaddr: 0000000000000000 cause: 0000000000000003 [ 1.732233] [] clk_core_disable+0xcc/0xec [ 1.737810] [] clk_disable+0x38/0x78 [ 1.742956] [] worker_thread+0x1a8/0x4d8 [ 1.748451] [] stmmac_remove_config_dt+0x1c/0x4c [ 1.754646] [] sun8i_dwmac_probe+0x378/0x82c [ 1.760484] [] worker_thread+0x1a8/0x4d8 [ 1.765975] [] platform_probe+0x64/0xf0 [ 1.771382] [] really_probe.part.0+0x8c/0x30c [ 1.777305] [] __driver_probe_device+0xa0/0x148 [ 1.783402] [] driver_probe_device+0x38/0x138 [ 1.789324] [] __device_attach_driver+0xd0/0x170 [ 1.795508] [] __driver_attach_async_helper+0xbc/0xc0 [ 1.802125] [] bus_for_each_drv+0x68/0xb4 [ 1.807701] [] __device_attach+0xd8/0x184 [ 1.813277] [] bus_probe_device+0x98/0xbc [ 1.818852] [] deferred_probe_work_func+0x90/0xd4 [ 1.825122] [] process_one_work+0x1e4/0x390 [ 1.830872] [] worker_thread+0x31c/0x4d8 [ 1.836362] [] kthreadd+0x94/0x188 [ 1.841335] [] kthreadd+0x94/0x188 [ 1.846304] [] process_one_work+0x38c/0x390 [ 1.852054] [] kthread+0x124/0x160 [ 1.857021] [] set_kthread_struct+0x5c/0x60 [ 1.862770] [] ret_from_syscall_rejected+0x8/0xc [ 1.868956] ---[ end trace 8d5c6046255f84a0 ]--- [ 1.873675] ------------[ cut here ]------------ [ 1.878366] bus-emac already unprepared [ 1.882378] WARNING: CPU: 0 PID: 38 at drivers/clk/clk.c:810 clk_core_unprepare+0xe4/0x168 [ 1.890673] CPU: 0 PID: 38 Comm: kworker/u2:1 Tainted: G W 5.14.0-rc4 #1 [ 1.898674] Hardware name: Allwinner D1 NeZha (DT) [ 1.903464] Workqueue: events_unbound deferred_probe_work_func [ 1.909305] epc : clk_core_unprepare+0xe4/0x168 [ 1.913840] ra : clk_core_unprepare+0xe4/0x168 [ 1.918375] epc : ffffffff8023d6cc ra : ffffffff8023d6cc sp : ffffffd00411bb10 [ 1.925593] gp : ffffffff80ec9988 tp : ffffffe00143a800 t0 : 0000000000000002 [ 1.932811] t1 : ffffffe01f743be0 t2 : 0000000000000040 s0 : ffffffe001509e00 [ 1.940029] s1 : 0000000000000001 a0 : 000000000000001b a1 : ffffffe00143a800 [ 1.947246] a2 : 0000000000000000 a3 : 00000000000000f4 a4 : 0000000000000001 [ 1.954463] a5 : 0000000000000000 a6 : 0000000005fce2a5 a7 : 0000000000000001 [ 1.961680] s2 : 0000000000000800 s3 : ffffffff80afeb90 s4 : ffffffe01fdf7a80 [ 1.968898] s5 : ffffffe001375010 s6 : ffffffff8001fc10 s7 : ffffffffffffffff [ 1.976115] s8 : 0000000000000001 s9 : ffffffff80ecb248 s10: ffffffe001b80000 [ 1.983333] s11: ffffffe001b80760 t3 : ffffffff80b39120 t4 : 0000000000000001 [ 1.990550] t5 : 0000000000000000 t6 : ffffffe001600002 [ 1.995859] status: 8000000201800120 badaddr: 0000000000000000 cause: 0000000000000003 [ 2.003771] [] clk_core_unprepare+0xe4/0x168 [ 2.009609] [] clk_unprepare+0x24/0x3c [ 2.014929] [] stmmac_remove_config_dt+0x24/0x4c [ 2.021125] [] sun8i_dwmac_probe+0x378/0x82c [ 2.026965] [] worker_thread+0x1a8/0x4d8 [ 2.032463] [] platform_probe+0x64/0xf0 [ 2.037871] [] really_probe.part.0+0x8c/0x30c [ 2.043795] [] __driver_probe_device+0xa0/0x148 [ 2.049892] [] driver_probe_device+0x38/0x138 [ 2.055815] [] __device_attach_driver+0xd0/0x170 [ 2.061999] [] __driver_attach_async_helper+0xbc/0xc0 [ 2.068616] [] bus_for_each_drv+0x68/0xb4 [ 2.074193] [] __device_attach+0xd8/0x184 [ 2.079769] [] bus_probe_device+0x98/0xbc [ 2.085345] [] deferred_probe_work_func+0x90/0xd4 [ 2.091616] [] process_one_work+0x1e4/0x390 [ 2.097367] [] worker_thread+0x31c/0x4d8 [ 2.102858] [] kthreadd+0x94/0x188 [ 2.107830] [] kthreadd+0x94/0x188 [ 2.112800] [] process_one_work+0x38c/0x390 [ 2.118551] [] kthread+0x124/0x160 [ 2.123520] [] set_kthread_struct+0x5c/0x60 [ 2.129268] [] ret_from_syscall_rejected+0x8/0xc [ 2.135455] ---[ end trace 8d5c6046255f84a1 ]--- Fixes: 5ec55823438e ("net: stmmac: add clocks management for gmac driver") Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 639a753266e6..bde76ea2deec 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7252,6 +7252,10 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); + pm_runtime_get_sync(dev); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); + stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); @@ -7270,8 +7274,6 @@ int stmmac_dvr_remove(struct device *dev) if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); reset_control_assert(priv->plat->stmmac_ahb_rst); - pm_runtime_put(dev); - pm_runtime_disable(dev); if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); -- cgit v1.2.3 From 3d2504663c41104b4359a15f35670cfa82de1bbf Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Tue, 14 Dec 2021 10:08:22 +0000 Subject: i40e: Fix reset bw limit when DCB enabled with 1 TC There was an AQ error I40E_AQ_RC_EINVAL when trying to reset bw limit as part of bw allocation setup. This was caused by trying to reset bw limit with DCB enabled. Bw limit should not be reset when DCB is enabled. The code was relying on the pf->flags to check if DCB is enabled but if only 1 TC is available this flag will not be set even though DCB is enabled. Add a check for number of TC and if it is 1 don't try to reset bw limit even if pf->flags shows DCB as disabled. Fixes: fa38e30ac73f ("i40e: Fix for Tx timeouts when interface is brought up if DCB is enabled") Suggested-by: Alexander Lobakin # Flatten the condition Signed-off-by: Sylwester Dziedziuch Signed-off-by: Jedrzej Jagielski Reviewed-by: Alexander Lobakin Tested-by: Imam Hassan Reza Biswas Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f70c478dafdb..5cb4dc69fe87 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5372,7 +5372,15 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { + + if (!vsi->mqprio_qopt.qopt.hw) { + if (pf->flags & I40E_FLAG_DCB_ENABLED) + goto skip_reset; + + if (IS_ENABLED(CONFIG_I40E_DCB) && + i40e_dcb_hw_get_num_tc(&pf->hw) == 1) + goto skip_reset; + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5380,6 +5388,8 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } + +skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) -- cgit v1.2.3 From 6533e558c6505e94c3e0ed4281ed5e31ec985f4d Mon Sep 17 00:00:00 2001 From: Karen Sornek Date: Wed, 12 Jan 2022 10:19:47 +0100 Subject: i40e: Fix reset path while removing the driver Fix the crash in kernel while dereferencing the NULL pointer, when the driver is unloaded and simultaneously the VSI rings are being stopped. The hardware requires 50msec in order to finish RX queues disable. For this purpose the driver spins in mdelay function for the operation to be completed. For example changing number of queues which requires reset would fail in the following call stack: 1) i40e_prep_for_reset 2) i40e_pf_quiesce_all_vsi 3) i40e_quiesce_vsi 4) i40e_vsi_close 5) i40e_down 6) i40e_vsi_stop_rings 7) i40e_vsi_control_rx -> disable requires the delay of 50msecs 8) continue back in i40e_down function where i40e_clean_tx_ring(vsi->tx_rings[i]) is going to crash When the driver was spinning vsi_release called i40e_vsi_free_arrays where the vsi->tx_rings resources were freed and the pointer was set to NULL. Fixes: 5b6d4a7f20b0 ("i40e: Fix crash during removing i40e driver") Signed-off-by: Slawomir Laba Signed-off-by: Sylwester Dziedziuch Signed-off-by: Karen Sornek Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 19 ++++++++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2e02cc68cd3f..80c5cecaf2b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -144,6 +144,7 @@ enum i40e_state_t { __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ + __I40E_IN_REMOVE, __I40E_VFS_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5cb4dc69fe87..0c4b7dfb3b35 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10863,6 +10863,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { int ret; + + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; /* Now we wait for GRST to settle out. * We don't have to delete the VEBs or VSIs from the hw switch * because the reset will make them disappear. @@ -12222,6 +12225,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) vsi->req_queue_pairs = queue_count; i40e_prep_for_reset(pf); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return pf->alloc_rss_size; pf->alloc_rss_size = new_rss_size; @@ -13048,6 +13053,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, if (need_reset) i40e_prep_for_reset(pf); + /* VSI shall be deleted in a moment, just return EINVAL */ + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; + old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { @@ -15938,8 +15947,13 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); - while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE + * flags, once they are set, i40e_rebuild should not be called as + * i40e_prep_for_reset always returns early. + */ + while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) usleep_range(1000, 2000); + set_bit(__I40E_IN_REMOVE, pf->state); if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { set_bit(__I40E_VF_RESETS_DISABLED, pf->state); @@ -16138,6 +16152,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; + i40e_reset_and_rebuild(pf, false, false); } -- cgit v1.2.3 From 7af037c39b600bac2c716dd1228e8ddbe149573f Mon Sep 17 00:00:00 2001 From: Camel Guo Date: Mon, 31 Jan 2022 09:38:40 +0100 Subject: net: stmmac: dump gmac4 DMA registers correctly Unlike gmac100, gmac1000, gmac4 has 27 DMA registers and they are located at DMA_CHAN_BASE_ADDR (0x1100). In order for ethtool to dump gmac4 DMA registers correctly, this commit checks if a net_device has gmac4 and uses different logic to dump its DMA registers. This fixes the following KASAN warning, which can normally be triggered by a command similar like "ethtool -d eth0": BUG: KASAN: vmalloc-out-of-bounds in dwmac4_dump_dma_regs+0x6d4/0xb30 Write of size 4 at addr ffffffc010177100 by task ethtool/1839 kasan_report+0x200/0x21c __asan_report_store4_noabort+0x34/0x60 dwmac4_dump_dma_regs+0x6d4/0xb30 stmmac_ethtool_gregs+0x110/0x204 ethtool_get_regs+0x200/0x4b0 dev_ethtool+0x1dac/0x3800 dev_ioctl+0x7c0/0xb50 sock_ioctl+0x298/0x6c4 ... Fixes: fbf68229ffe7 ("net: stmmac: unify registers dumps methods") Signed-off-by: Camel Guo Link: https://lore.kernel.org/r/20220131083841.3346801-1-camel.guo@axis.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 1914ad698cab..acd70b9a3173 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -150,6 +150,7 @@ #define NUM_DWMAC100_DMA_REGS 9 #define NUM_DWMAC1000_DMA_REGS 23 +#define NUM_DWMAC4_DMA_REGS 27 void dwmac_enable_dma_transmission(void __iomem *ioaddr); void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan, bool rx, bool tx); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 164dff5ec32e..abfb3cd5958d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -21,10 +21,18 @@ #include "dwxgmac2.h" #define REG_SPACE_SIZE 0x1060 +#define GMAC4_REG_SPACE_SIZE 0x116C #define MAC100_ETHTOOL_NAME "st_mac100" #define GMAC_ETHTOOL_NAME "st_gmac" #define XGMAC_ETHTOOL_NAME "st_xgmac" +/* Same as DMA_CHAN_BASE_ADDR defined in dwmac4_dma.h + * + * It is here because dwmac_dma.h and dwmac4_dam.h can not be included at the + * same time due to the conflicting macro names. + */ +#define GMAC4_DMA_CHAN_BASE_ADDR 0x00001100 + #define ETHTOOL_DMA_OFFSET 55 struct stmmac_stats { @@ -434,6 +442,8 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev) if (priv->plat->has_xgmac) return XGMAC_REGSIZE * 4; + else if (priv->plat->has_gmac4) + return GMAC4_REG_SPACE_SIZE; return REG_SPACE_SIZE; } @@ -446,8 +456,13 @@ static void stmmac_ethtool_gregs(struct net_device *dev, stmmac_dump_mac_regs(priv, priv->hw, reg_space); stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); - if (!priv->plat->has_xgmac) { - /* Copy DMA registers to where ethtool expects them */ + /* Copy DMA registers to where ethtool expects them */ + if (priv->plat->has_gmac4) { + /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */ + memcpy(®_space[ETHTOOL_DMA_OFFSET], + ®_space[GMAC4_DMA_CHAN_BASE_ADDR / 4], + NUM_DWMAC4_DMA_REGS * 4); + } else if (!priv->plat->has_xgmac) { memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); -- cgit v1.2.3 From 68defd528f94ed1cf11f49a75cc1875dccd781fa Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Tue, 7 Dec 2021 13:23:06 +0200 Subject: e1000e: Separate ADP board type from TGP We have the same LAN controller on different PCH's. Separate ADP board type from a TGP which will allow for specific fixes to be applied for ADP platforms. Suggested-by: Kai-Heng Feng Suggested-by: Dima Ruinskiy Signed-off-by: Sasha Neftin Tested-by: Nechama Kraus Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/e1000.h | 4 +++- drivers/net/ethernet/intel/e1000e/ich8lan.c | 20 +++++++++++++++++ drivers/net/ethernet/intel/e1000e/netdev.c | 33 +++++++++++++++-------------- 3 files changed, 40 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index c3def0ee7788..8d06c9d8ff8b 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -115,7 +115,8 @@ enum e1000_boards { board_pch_lpt, board_pch_spt, board_pch_cnp, - board_pch_tgp + board_pch_tgp, + board_pch_adp }; struct e1000_ps_page { @@ -502,6 +503,7 @@ extern const struct e1000_info e1000_pch_lpt_info; extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; +extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 5e4fc9b4e2ad..c908c84b86d2 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -6021,3 +6021,23 @@ const struct e1000_info e1000_pch_tgp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_adp_info = { + .mac = e1000_pch_adp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 635a95927e93..d2de8bc4c3b7 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -52,6 +52,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_spt] = &e1000_pch_spt_info, [board_pch_cnp] = &e1000_pch_cnp_info, [board_pch_tgp] = &e1000_pch_tgp_info, + [board_pch_adp] = &e1000_pch_adp_info, }; struct e1000_reg_info { @@ -7898,22 +7899,22 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; -- cgit v1.2.3 From cad014b7b5a6897d8c4fad13e2888978bfb7a53f Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Tue, 7 Dec 2021 13:23:42 +0200 Subject: e1000e: Handshake with CSME starts from ADL platforms Handshake with CSME/AMT on none provisioned platforms during S0ix flow is not supported on TGL platform and can cause to HW unit hang. Update the handshake with CSME flow to start from the ADL platform. Fixes: 3e55d231716e ("e1000e: Add handshake with the CSME to support S0ix") Signed-off-by: Sasha Neftin Tested-by: Nechama Kraus Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000e/netdev.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index d2de8bc4c3b7..a42aeb555f34 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6342,7 +6342,8 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) u32 mac_data; u16 phy_data; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME configure the device for S0ix */ mac_data = er32(H2ME); mac_data |= E1000_H2ME_START_DPG; @@ -6491,7 +6492,8 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) u16 phy_data; u32 i = 0; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME unconfigure the device from S0ix */ mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; -- cgit v1.2.3 From 6dde7acdb3dc2e0b3bcb090aac0b3699396d309f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 31 Jan 2022 13:17:30 -0800 Subject: ethernet: smc911x: fix indentation in get/set EEPROM Build bot produced a smatch indentation warning, the code looks correct but it mixes spaces and tabs. Reported-by: kernel test robot Link: https://lore.kernel.org/r/20220131211730.3940875-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/smsc/smc911x.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index dd6f69ced4ee..fc9cef9dcefc 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1648,7 +1648,7 @@ static int smc911x_ethtool_geteeprom(struct net_device *dev, return ret; if ((ret=smc911x_ethtool_read_eeprom_byte(dev, &eebuf[i]))!=0) return ret; - } + } memcpy(data, eebuf+eeprom->offset, eeprom->len); return 0; } @@ -1667,11 +1667,11 @@ static int smc911x_ethtool_seteeprom(struct net_device *dev, return ret; /* write byte */ if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0) - return ret; + return ret; if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0) return ret; - } - return 0; + } + return 0; } static int smc911x_ethtool_geteeprom_len(struct net_device *dev) -- cgit v1.2.3 From 04f8c12f031fcd0ffa0c72822eb665ceb2c872e7 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 6 Jan 2022 16:40:18 +0200 Subject: net/mlx5: Bridge, take rtnl lock in init error handler The mlx5_esw_bridge_cleanup() is expected to be called with rtnl lock taken, which is true for mlx5e_rep_bridge_cleanup() function but not for error handling code in mlx5e_rep_bridge_init(). Add missing rtnl lock/unlock calls and extend both mlx5_esw_bridge_cleanup() and its dual function mlx5_esw_bridge_init() with ASSERT_RTNL() to verify the invariant from now on. Fixes: 7cd6a54a8285 ("net/mlx5: Bridge, handle FDB events") Fixes: 19e9bfa044f3 ("net/mlx5: Bridge, add offload infrastructure") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index c6d2f8c78db7..d5cb27667005 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -509,7 +509,9 @@ err_register_swdev_blk: err_register_swdev: destroy_workqueue(br_offloads->wq); err_alloc_wq: + rtnl_lock(); mlx5_esw_bridge_cleanup(esw); + rtnl_unlock(); } void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index f690f430f40f..05e08cec5a8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1574,6 +1574,8 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads; + ASSERT_RTNL(); + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); if (!br_offloads) return ERR_PTR(-ENOMEM); @@ -1590,6 +1592,8 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + ASSERT_RTNL(); + if (!br_offloads) return; -- cgit v1.2.3 From 350d9a823734b5a7e767cddc3bdde5f0bcbb7ff4 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 6 Jan 2022 18:45:26 +0200 Subject: net/mlx5: Bridge, ensure dev_name is null-terminated Even though net_device->name is guaranteed to be null-terminated string of size<=IFNAMSIZ, the test robot complains that return value of netdev_name() can be larger: In file included from include/trace/define_trace.h:102, from drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h:113, from drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c:12: drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h: In function 'trace_event_raw_event_mlx5_esw_bridge_fdb_template': >> drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h:24:29: warning: 'strncpy' output may be truncated copying 16 bytes from a string of length 20 [-Wstringop-truncation] 24 | strncpy(__entry->dev_name, | ^~~~~~~~~~~~~~~~~~~~~~~~~~ 25 | netdev_name(fdb->dev), | ~~~~~~~~~~~~~~~~~~~~~~ 26 | IFNAMSIZ); | ~~~~~~~~~ This is caused by the fact that default value of IFNAMSIZ is 16, while placeholder value that is returned by netdev_name() for unnamed net devices is larger than that. The offending code is in a tracing function that is only called for mlx5 representors, so there is no straightforward way to reproduce the issue but let's fix it for correctness sake by replacing strncpy() with strscpy() to ensure that resulting string is always null-terminated. Fixes: 9724fd5d9c2a ("net/mlx5: Bridge, add tracepoints") Reported-by: kernel test robot Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h index 3401188e0a60..51ac24e6ec3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template, __field(unsigned int, used) ), TP_fast_assign( - strncpy(__entry->dev_name, + strscpy(__entry->dev_name, netdev_name(fdb->dev), IFNAMSIZ); memcpy(__entry->addr, fdb->key.addr, ETH_ALEN); -- cgit v1.2.3 From a2446bc77a16cefd27de712d28af2396d6287593 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 4 Jan 2022 10:38:02 +0200 Subject: net/mlx5e: TC, Reject rules with drop and modify hdr action This kind of action is not supported by firmware and generates a syndrome. kernel: mlx5_core 0000:08:00.0: mlx5_cmd_check:777:(pid 102063): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x8708c3) Fixes: d7e75a325cb2 ("net/mlx5e: Add offloading of E-Switch TC pedit (header re-write) actions") Signed-off-by: Roi Dayan Reviewed-by: Oz Shlomo Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3d908a7e1406..671f76c350db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3191,6 +3191,12 @@ actions_match_supported(struct mlx5e_priv *priv, return false; } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); + return false; + } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, ct_flow, ct_clear, extack)) -- cgit v1.2.3 From 4a08a131351e375a2969b98e46df260ed04dcba7 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 16 Jan 2022 09:07:22 +0200 Subject: net/mlx5e: Fix module EEPROM query When querying the module EEPROM, there was a misusage of the 'offset' variable vs the 'query.offset' field. Fix that by always using 'offset' and assigning its value to 'query.offset' right before the mcia register read call. While at it, the cross-pages read size adjustment was changed to be more intuitive. Fixes: e19b0a3474ab ("net/mlx5: Refactor module EEPROM query") Reported-by: Wang Yugui Signed-off-by: Gal Pressman Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1ef2b6a848c1..7b16a1188aab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -406,23 +406,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, switch (module_id) { case MLX5_MODULE_ID_SFP: - mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; case MLX5_MODULE_ID_QSFP: case MLX5_MODULE_ID_QSFP_PLUS: case MLX5_MODULE_ID_QSFP28: - mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; default: mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); return -EINVAL; } - if (query.offset + size > MLX5_EEPROM_PAGE_LENGTH) + if (offset + size > MLX5_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ - size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; + size = MLX5_EEPROM_PAGE_LENGTH - offset; query.size = size; + query.offset = offset; return mlx5_query_mcia(dev, &query, data); } -- cgit v1.2.3 From 3c5193a87b0fea090aa3f769d020337662d87b5e Mon Sep 17 00:00:00 2001 From: Maher Sanalla Date: Thu, 13 Jan 2022 15:48:48 +0200 Subject: net/mlx5: Use del_timer_sync in fw reset flow of halting poll Substitute del_timer() with del_timer_sync() in fw reset polling deactivation flow, in order to prevent a race condition which occurs when del_timer() is called and timer is deactivated while another process is handling the timer interrupt. A situation that led to the following call trace: RIP: 0010:run_timer_softirq+0x137/0x420 recalibrate_cpu_khz+0x10/0x10 ktime_get+0x3e/0xa0 ? sched_clock_cpu+0xb/0xc0 __do_softirq+0xf5/0x2ea irq_exit_rcu+0xc1/0xf0 sysvec_apic_timer_interrupt+0x9e/0xc0 asm_sysvec_apic_timer_interrupt+0x12/0x20 Fixes: 38b9f903f22b ("net/mlx5: Handle sync reset request event") Signed-off-by: Maher Sanalla Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 0b0234f9d694..84dbe46d5ede 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -132,7 +132,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; - del_timer(&fw_reset->timer); + del_timer_sync(&fw_reset->timer); } static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) -- cgit v1.2.3 From 5623ef8a118838aae65363750dfafcba734dc8cb Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Mon, 17 Jan 2022 15:00:30 +0200 Subject: net/mlx5e: TC, Reject rules with forward and drop actions Such rules are redundant but allowed and passed to the driver. The driver does not support offloading such rules so return an error. Fixes: 03a9d11e6eeb ("net/mlx5e: Add TC drop and mirred/redirect action parsing for SRIOV offloads") Signed-off-by: Roi Dayan Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 671f76c350db..4c6e3c26c1ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3191,6 +3191,12 @@ actions_match_supported(struct mlx5e_priv *priv, return false; } + if (!(~actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); + return false; + } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); -- cgit v1.2.3 From 55b2ca702cfa744a9eb108915996a2294da47e71 Mon Sep 17 00:00:00 2001 From: Dima Chumak Date: Mon, 17 Jan 2022 15:32:16 +0200 Subject: net/mlx5: Fix offloading with ESWITCH_IPV4_TTL_MODIFY_ENABLE Only prio 1 is supported for nic mode when there is no ignore flow level support in firmware. But for switchdev mode, which supports fixed number of statically pre-allocated prios, this restriction is not relevant so it can be relaxed. Fixes: d671e109bd85 ("net/mlx5: Fix tc max supported prio for nic mode") Signed-off-by: Dima Chumak Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index d5e47630e284..e94233a12a32 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -121,12 +121,13 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains) u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains) { - if (!mlx5_chains_prios_supported(chains)) - return 1; - if (mlx5_chains_ignore_flow_level_supported(chains)) return UINT_MAX; + if (!chains->dev->priv.eswitch || + chains->dev->priv.eswitch->mode != MLX5_ESWITCH_OFFLOADS) + return 1; + /* We should get here only for eswitch case */ return FDB_TC_MAX_PRIO; } -- cgit v1.2.3 From 880b517691908fb753019b9b27cd082e7617debd Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Mon, 24 Jan 2022 13:56:26 +0200 Subject: net/mlx5: Bridge, Fix devlink deadlock on net namespace deletion When changing mode to switchdev, rep bridge init registered to netdevice notifier holds the devlink lock and then takes pernet_ops_rwsem. At that time deleting a netns holds pernet_ops_rwsem and then takes the devlink lock. Example sequence is: $ ip netns add foo $ devlink dev eswitch set pci/0000:00:08.0 mode switchdev & $ ip netns del foo deleting netns trace: [ 1185.365555] ? devlink_pernet_pre_exit+0x74/0x1c0 [ 1185.368331] ? mutex_lock_io_nested+0x13f0/0x13f0 [ 1185.370984] ? xt_find_table+0x40/0x100 [ 1185.373244] ? __mutex_lock+0x24a/0x15a0 [ 1185.375494] ? net_generic+0xa0/0x1c0 [ 1185.376844] ? wait_for_completion_io+0x280/0x280 [ 1185.377767] ? devlink_pernet_pre_exit+0x74/0x1c0 [ 1185.378686] devlink_pernet_pre_exit+0x74/0x1c0 [ 1185.379579] ? devlink_nl_cmd_get_dumpit+0x3a0/0x3a0 [ 1185.380557] ? xt_find_table+0xda/0x100 [ 1185.381367] cleanup_net+0x372/0x8e0 changing mode to switchdev trace: [ 1185.411267] down_write+0x13a/0x150 [ 1185.412029] ? down_write_killable+0x180/0x180 [ 1185.413005] register_netdevice_notifier+0x1e/0x210 [ 1185.414000] mlx5e_rep_bridge_init+0x181/0x360 [mlx5_core] [ 1185.415243] mlx5e_uplink_rep_enable+0x269/0x480 [mlx5_core] [ 1185.416464] ? mlx5e_uplink_rep_disable+0x210/0x210 [mlx5_core] [ 1185.417749] mlx5e_attach_netdev+0x232/0x400 [mlx5_core] [ 1185.418906] mlx5e_netdev_attach_profile+0x15b/0x1e0 [mlx5_core] [ 1185.420172] mlx5e_netdev_change_profile+0x15a/0x1d0 [mlx5_core] [ 1185.421459] mlx5e_vport_rep_load+0x557/0x780 [mlx5_core] [ 1185.422624] ? mlx5e_stats_grp_vport_rep_num_stats+0x10/0x10 [mlx5_core] [ 1185.424006] mlx5_esw_offloads_rep_load+0xdb/0x190 [mlx5_core] [ 1185.425277] esw_offloads_enable+0xd74/0x14a0 [mlx5_core] Fix this by registering rep bridges for per net netdev notifier instead of global one, which operats on the net namespace without holding the pernet_ops_rwsem. Fixes: 19e9bfa044f3 ("net/mlx5: Bridge, add offload infrastructure") Signed-off-by: Roi Dayan Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index d5cb27667005..48dc121b2cb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -491,7 +491,7 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) } br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event; - err = register_netdevice_notifier(&br_offloads->netdev_nb); + err = register_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); if (err) { esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n", err); @@ -526,7 +526,7 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) return; cancel_delayed_work_sync(&br_offloads->update_work); - unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); destroy_workqueue(br_offloads->wq); -- cgit v1.2.3 From b8d91145ed7cfa046cc07bcfb277465b9d45da73 Mon Sep 17 00:00:00 2001 From: Khalid Manaa Date: Wed, 26 Jan 2022 14:14:58 +0200 Subject: net/mlx5e: Fix wrong calculation of header index in HW_GRO The HW doesn't wrap the CQE.shampo.header_index field according to the headers buffer size, instead it always increases it until reaching overflow of u16 size. Thus the mlx5e_handle_rx_cqe_mpwrq_shampo handler should mask the CQE header_index field to find the actual header index in the headers buffer. Fixes: f97d5c2a453e ("net/mlx5e: Add handle SHAMPO cqe support") Signed-off-by: Khalid Manaa Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 4cdf8e5b24c2..b789af07829c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1); +} + struct mlx5e_shampo_umr { u16 len; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index e86ccc22fb82..3a79ecd38003 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct tcphdr *skb_tcp_hd) { - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); struct tcphdr *last_tcp_hd; void *last_hd_addr; @@ -1973,7 +1973,7 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size; - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset); u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); u32 data_offset = wqe_offset & (PAGE_SIZE - 1); -- cgit v1.2.3 From 7957837b816f11eecb9146235bb0715478f4c81f Mon Sep 17 00:00:00 2001 From: Khalid Manaa Date: Wed, 26 Jan 2022 14:25:55 +0200 Subject: net/mlx5e: Fix broken SKB allocation in HW-GRO In case the HW doesn't perform header-data split, it will write the whole packet into the data buffer in the WQ, in this case the SHAMPO CQE handler couldn't use the header entry to build the SKB, instead it should allocate a new memory to build the SKB using the function: mlx5e_skb_from_cqe_mpwrq_nonlinear. Fixes: f97d5c2a453e ("net/mlx5e: Add handle SHAMPO cqe support") Signed-off-by: Khalid Manaa Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 26 ++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3a79ecd38003..ee0a8f5206e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1871,7 +1871,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } -static void +static struct sk_buff * mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { @@ -1895,7 +1895,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); if (unlikely(!skb)) - return; + return NULL; /* queue up for recycling/reuse */ page_ref_inc(head->page); @@ -1907,7 +1907,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, ALIGN(head_size, sizeof(long))); if (unlikely(!skb)) { rq->stats->buff_alloc_err++; - return; + return NULL; } prefetchw(skb->data); @@ -1918,9 +1918,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb->tail += head_size; skb->len += head_size; } - rq->hw_gro_data->skb = skb; - NAPI_GRO_CB(skb)->count = 1; - skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size; + return skb; } static void @@ -1980,6 +1978,7 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe); u16 wqe_id = be16_to_cpu(cqe->wqe_id); u32 page_idx = wqe_offset >> PAGE_SHIFT; + u16 head_size = cqe->shampo.header_size; struct sk_buff **skb = &rq->hw_gro_data->skb; bool flush = cqe->shampo.flush; bool match = cqe->shampo.match; @@ -2011,9 +2010,16 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } if (!*skb) { - mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + if (likely(head_size)) + *skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + else + *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset, + page_idx); if (unlikely(!*skb)) goto free_hd_entry; + + NAPI_GRO_CB(*skb)->count = 1; + skb_shinfo(*skb)->gso_size = cqe_bcnt - head_size; } else { NAPI_GRO_CB(*skb)->count++; if (NAPI_GRO_CB(*skb)->count == 2 && @@ -2027,8 +2033,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } } - di = &wi->umr.dma_info[page_idx]; - mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + if (likely(head_size)) { + di = &wi->umr.dma_info[page_idx]; + mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + } mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb); if (flush) -- cgit v1.2.3 From ec41332e02bd0acf1f24206867bb6a02f5877a62 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Thu, 13 Jan 2022 15:11:42 +0200 Subject: net/mlx5e: Fix handling of wrong devices during bond netevent Current implementation of bond netevent handler only check if the handled netdev is VF representor and it missing a check if the VF representor is on the same phys device of the bond handling the netevent. Fix by adding the missing check and optimizing the check if the netdev is VF representor so it will not access uninitialized private data and crashes. BUG: kernel NULL pointer dereference, address: 000000000000036c PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI Workqueue: eth3bond0 bond_mii_monitor [bonding] RIP: 0010:mlx5e_is_uplink_rep+0xc/0x50 [mlx5_core] RSP: 0018:ffff88812d69fd60 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8881cf800000 RCX: 0000000000000000 RDX: ffff88812d69fe10 RSI: 000000000000001b RDI: ffff8881cf800880 RBP: ffff8881cf800000 R08: 00000445cabccf2b R09: 0000000000000008 R10: 0000000000000004 R11: 0000000000000008 R12: ffff88812d69fe10 R13: 00000000fffffffe R14: ffff88820c0f9000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88846fb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000000036c CR3: 0000000103d80006 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5e_eswitch_uplink_rep+0x31/0x40 [mlx5_core] mlx5e_rep_is_lag_netdev+0x94/0xc0 [mlx5_core] mlx5e_rep_esw_bond_netevent+0xeb/0x3d0 [mlx5_core] raw_notifier_call_chain+0x41/0x60 call_netdevice_notifiers_info+0x34/0x80 netdev_lower_state_changed+0x4e/0xa0 bond_mii_monitor+0x56b/0x640 [bonding] process_one_work+0x1b9/0x390 worker_thread+0x4d/0x3d0 ? rescuer_thread+0x350/0x350 kthread+0x124/0x150 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x1f/0x30 Fixes: 7e51891a237f ("net/mlx5e: Use netdev events to set/del egress acl forward-to-vport rule") Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/rep/bond.c | 32 ++++++++++------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 9c076aa20306..b6f5c1bcdbcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,18 +183,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *priv; - - /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) - return false; - - priv = netdev_priv(netdev); - rpriv = priv->ppriv; - - /* Egress acl forward to vport is supported only non-uplink representor */ - return rpriv->rep->vport != MLX5_VPORT_UPLINK; + return netif_is_lag_port(netdev) && mlx5e_eswitch_vf_rep(netdev); } static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr) @@ -210,9 +199,6 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt u16 fwd_vport_num; int err; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - info = ptr; lag_info = info->lower_state_info; /* This is not an event of a representor becoming active slave */ @@ -266,9 +252,6 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr) struct net_device *lag_dev; struct mlx5e_priv *priv; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - priv = netdev_priv(netdev); rpriv = priv->ppriv; lag_dev = info->upper_dev; @@ -293,6 +276,19 @@ static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_bond *bond; + struct mlx5e_priv *priv; + + if (!mlx5e_rep_is_lag_netdev(netdev)) + return NOTIFY_DONE; + + bond = container_of(nb, struct mlx5e_rep_bond, nb); + priv = netdev_priv(netdev); + rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH); + /* Verify VF representor is on the same device of the bond handling the netevent. */ + if (rpriv->uplink_priv.bond != bond) + return NOTIFY_DONE; switch (event) { case NETDEV_CHANGELOWERSTATE: -- cgit v1.2.3 From d8e5883d694bb053b19c4142a2d1f43a34f6fe2c Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Sun, 30 Jan 2022 16:00:41 +0200 Subject: net/mlx5: E-Switch, Fix uninitialized variable modact The variable modact is not initialized before used in command modify header allocation which can cause command to fail. Fix by initializing modact with zeros. Addresses-Coverity: ("Uninitialized scalar variable") Fixes: 8f1e0b97cc70 ("net/mlx5: E-Switch, Mark miss packets with new chain id mapping") Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index e94233a12a32..df58cba37930 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -212,7 +212,7 @@ static int create_chain_restore(struct fs_chain *chain) { struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch; - char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)]; + u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_fs_chains *chains = chain->chains; enum mlx5e_tc_attr_to_reg chain_to_reg; struct mlx5_modify_hdr *mod_hdr; -- cgit v1.2.3 From 736dfe4e68b868829a1e89dfef4a44c1580d4478 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 18 Jan 2022 13:31:54 +0200 Subject: net/mlx5e: Don't treat small ceil values as unlimited in HTB offload The hardware spec defines max_average_bw == 0 as "unlimited bandwidth". max_average_bw is calculated as `ceil / BYTES_IN_MBIT`, which can become 0 when ceil is small, leading to an undesired effect of having no bandwidth limit. This commit fixes it by rounding up small values of ceil to 1 Mbit/s. Fixes: 214baf22870c ("net/mlx5e: Support HTB offload") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/qos.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 00449df98a5e..c1e07496c89c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -570,7 +570,8 @@ static int mlx5e_htb_convert_rate(struct mlx5e_priv *priv, u64 rate, static void mlx5e_htb_convert_ceil(struct mlx5e_priv *priv, u64 ceil, u32 *max_average_bw) { - *max_average_bw = div_u64(ceil, BYTES_IN_MBIT); + /* Hardware treats 0 as "unlimited", set at least 1. */ + *max_average_bw = max_t(u32, div_u64(ceil, BYTES_IN_MBIT), 1); qos_dbg(priv->mdev, "Convert: ceil %llu -> max_average_bw %u\n", ceil, *max_average_bw); -- cgit v1.2.3 From 5352859b3bfa0ca188b2f1d2c1436fddc781e3b6 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Thu, 2 Dec 2021 17:43:50 +0200 Subject: net/mlx5e: IPsec: Fix crypto offload for non TCP/UDP encapsulated traffic IPsec crypto offload always set the ethernet segment checksum flags with the inner L4 header checksum flag enabled for encapsulated IPsec offloaded packet regardless of the encapsulated L4 header type, and even if it doesn't exists in the first place, this breaks non TCP/UDP traffic as such. Set the inner L4 checksum flag only when the encapsulated L4 header protocol is TCP/UDP using software parser swp_inner_l4_offset field as indication. Fixes: 5cfb540ef27b ("net/mlx5e: Set IPsec WAs only in IP's non checksum partial case.") Signed-off-by: Raed Salem Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index b98db50c3418..428881e0adcb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -131,14 +131,17 @@ static inline bool mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - struct xfrm_offload *xo = xfrm_offload(skb); + u8 inner_ipproto; if (!mlx5e_ipsec_eseg_meta(eseg)) return false; eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (xo->inner_ipproto) { - eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM; + inner_ipproto = xfrm_offload(skb)->inner_ipproto; + if (inner_ipproto) { + eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; + if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP) + eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM; } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial_inner++; -- cgit v1.2.3 From de47db0cf7f4a9c555ad204e06baa70b50a70d08 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Thu, 2 Dec 2021 17:49:01 +0200 Subject: net/mlx5e: IPsec: Fix tunnel mode crypto offload for non TCP/UDP traffic IPsec Tunnel mode crypto offload software parser (SWP) setting in data path currently always set the inner L4 offset regardless of the encapsulated L4 header type and whether it exists in the first place, this breaks non TCP/UDP traffic as such. Set the SWP inner L4 offset only when the IPsec tunnel encapsulated L4 header protocol is TCP/UDP. While at it fix inner ip protocol read for setting MLX5_ETH_WQE_SWP_INNER_L4_UDP flag to address the case where the ip header protocol is IPv6. Fixes: f1267798c980 ("net/mlx5: Fix checksum issue of VXLAN and IPsec crypto offload") Signed-off-by: Raed Salem Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 2db9573a3fe6..b56fea142c24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -157,11 +157,20 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, /* Tunnel mode */ if (mode == XFRM_MODE_TUNNEL) { eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; if (xo->proto == IPPROTO_IPV6) eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP) + + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | IP | [TCP | UDP] */ + eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } return; } -- cgit v1.2.3 From 5b209d1a22afabfb7d644abb10510c5713a3e569 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Tue, 1 Feb 2022 15:27:48 +0200 Subject: net/mlx5e: Avoid implicit modify hdr for decap drop rule Currently the driver adds implicit modify hdr action for decap rules on tunnel devices if the port is an ovs port. This is also done if the action is drop and makes the modify hdr redundant and also the FW doesn't support it and will generate a syndrome. kernel: mlx5_core 0000:08:00.0: mlx5_cmd_check:777:(pid 102063): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x8708c3) Fix it by adding the implicit modify hdr only for fwd actions. Fixes: b16eb3c81fe2 ("net/mlx5: Support internal port as decap route device") Fixes: 077cdda764c7 ("net/mlx5e: TC, Fix memory leak with rules with internal port") Signed-off-by: Roi Dayan Reviewed-by: Ariel Levkovich Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 4c6e3c26c1ab..2022fa4a9598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1414,7 +1414,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_out; - if (!attr->chain && esw_attr->int_port) { + if (!attr->chain && esw_attr->int_port && + attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { /* If decap route device is internal port, change the * source vport value in reg_c0 back to uplink just in * case the rule performs goto chain > 0. If we have a miss -- cgit v1.2.3 From 6d5c900eb64107001e91e1f46bddc254dded8a59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 Jan 2022 09:22:41 -0800 Subject: net/mlx5e: Use struct_group() for memcpy() region In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use struct_group() in struct vlan_ethhdr around members h_dest and h_source, so they can be referenced together. This will allow memcpy() and sizeof() to more easily reason about sizes, improve readability, and avoid future warnings about writing beyond the end of h_dest. "pahole" shows no size nor member offset changes to struct vlan_ethhdr. "objdump -d" shows no object code changes. Fixes: 34802a42b352 ("net/mlx5e: Do not modify the TX SKB") Signed-off-by: Kees Cook Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- include/linux/if_vlan.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 7fd33b356cc8..ee7ecb88adc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - memcpy(vhdr, skb->data, cpy1_sz); + memcpy(&vhdr->addrs, skb->data, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8420fe504927..2be4dd7e90a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; -- cgit v1.2.3 From ad5185735f7dab342fdd0dd41044da4c9ccfef67 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 Jan 2022 09:20:28 -0800 Subject: net/mlx5e: Avoid field-overflowing memcpy() In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use flexible arrays instead of zero-element arrays (which look like they are always overflowing) and split the cross-field memcpy() into two halves that can be appropriately bounds-checked by the compiler. We were doing: #define ETH_HLEN 14 #define VLAN_HLEN 4 ... #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) ... struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); ... struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; ... memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); target is wqe->eth.inline_hdr.start (which the compiler sees as being 2 bytes in size), but copying 18, intending to write across start (really vlan_tci, 2 bytes). The remaining 16 bytes get written into wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr (8 bytes). struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; /* 0 16 */ struct mlx5_wqe_eth_seg eth; /* 16 16 */ struct mlx5_wqe_data_seg data[]; /* 32 0 */ /* size: 32, cachelines: 1, members: 3 */ /* last cacheline: 32 bytes */ }; struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; /* 0 1 */ u8 swp_outer_l3_offset; /* 1 1 */ u8 swp_inner_l4_offset; /* 2 1 */ u8 swp_inner_l3_offset; /* 3 1 */ u8 cs_flags; /* 4 1 */ u8 swp_flags; /* 5 1 */ __be16 mss; /* 6 2 */ __be32 flow_table_metadata; /* 8 4 */ union { struct { __be16 sz; /* 12 2 */ u8 start[2]; /* 14 2 */ } inline_hdr; /* 12 4 */ struct { __be16 type; /* 12 2 */ __be16 vlan_tci; /* 14 2 */ } insert; /* 12 4 */ __be32 trailer; /* 12 4 */ }; /* 12 4 */ /* size: 16, cachelines: 1, members: 9 */ /* last cacheline: 16 bytes */ }; struct mlx5_wqe_data_seg { __be32 byte_count; /* 0 4 */ __be32 lkey; /* 4 4 */ __be64 addr; /* 8 8 */ /* size: 16, cachelines: 1, members: 3 */ /* last cacheline: 16 bytes */ }; So, split the memcpy() so the compiler can reason about the buffer sizes. "pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations). Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Kees Cook Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +++- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 812e6810cb3b..c14e06ca64d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -224,7 +224,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -241,8 +241,8 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; union { - struct mlx5_mtt inline_mtts[0]; - struct mlx5_klm inline_klms[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); + DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms); }; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 338d65e2c9ce..56e10c84a706 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; -- cgit v1.2.3 From 81eb8b0b18789e647e65579303529fd52d861cc2 Mon Sep 17 00:00:00 2001 From: Steen Hegelund Date: Wed, 2 Feb 2022 09:30:39 +0100 Subject: net: sparx5: do not refer to skb after passing it on Do not try to use any SKB fields after the packet has been passed up in the receive stack. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Steen Hegelund Link: https://lore.kernel.org/r/20220202083039.3774851-1-steen.hegelund@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/sparx5/sparx5_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index dc7e5ea6ec15..148d431fcde4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -145,9 +145,9 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) skb_put(skb, byte_cnt - ETH_FCS_LEN); eth_skb_pad(skb); skb->protocol = eth_type_trans(skb, netdev); - netif_rx(skb); netdev->stats.rx_bytes += skb->len; netdev->stats.rx_packets++; + netif_rx(skb); } static int sparx5_inject(struct sparx5 *sparx5, -- cgit v1.2.3 From 80d4609008e6d696a279e39ae7458c916fcd44c1 Mon Sep 17 00:00:00 2001 From: Yannick Vignon Date: Thu, 3 Feb 2022 17:00:25 +0100 Subject: net: stmmac: ensure PTP time register reads are consistent Even if protected from preemption and interrupts, a small time window remains when the 2 register reads could return inconsistent values, each time the "seconds" register changes. This could lead to an about 1-second error in the reported time. Add logic to ensure the "seconds" and "nanoseconds" values are consistent. Fixes: 92ba6888510c ("stmmac: add the support for PTP hw clock driver") Signed-off-by: Yannick Vignon Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20220203160025.750632-1-yannick.vignon@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 074e2cdfb0fa..a7ec9f4d46ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -145,15 +145,20 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, static void get_systime(void __iomem *ioaddr, u64 *systime) { - u64 ns; - - /* Get the TSSS value */ - ns = readl(ioaddr + PTP_STNSR); - /* Get the TSS and convert sec time value to nanosecond */ - ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; + u64 ns, sec0, sec1; + + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + do { + sec0 = sec1; + /* Get the TSSS value */ + ns = readl_relaxed(ioaddr + PTP_STNSR); + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + } while (sec0 != sec1); if (systime) - *systime = ns; + *systime = ns + (sec1 * 1000000000ULL); } static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) -- cgit v1.2.3