From a2c90d63b71223d69a813333c1abf4fdacddbbe5 Mon Sep 17 00:00:00 2001 From: Robert Malz Date: Tue, 20 May 2025 10:31:51 +0200 Subject: [PATCH 1/5] i40e: return false from i40e_reset_vf if reset is in progress The function i40e_vc_reset_vf attempts, up to 20 times, to handle a VF reset request, using the return value of i40e_reset_vf as an indicator of whether the reset was successfully triggered. Currently, i40e_reset_vf always returns true, which causes new reset requests to be ignored if a different VF reset is already in progress. This patch updates the return value of i40e_reset_vf to reflect when another VF reset is in progress, allowing the caller to properly use the retry mechanism. Fixes: 52424f974bc5 ("i40e: Fix VF hang when reset is triggered on another VF") Signed-off-by: Robert Malz Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 1120f8e4bb67..22d5b1ec2289 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * Returns true if the VF is in reset, resets successfully, or resets - * are disabled and false otherwise. + * Return: True if reset was performed successfully or if resets are disabled. + * False if reset is already in progress. **/ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { @@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) /* If VF is being reset already we don't need to continue. */ if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - return true; + return false; i40e_trigger_vf_reset(vf, flr); From fb4e9239e029954a37a00818b21e837cebf2aa10 Mon Sep 17 00:00:00 2001 From: Robert Malz Date: Tue, 20 May 2025 10:31:52 +0200 Subject: [PATCH 2/5] i40e: retry VFLR handling if there is ongoing VF reset When a VFLR interrupt is received during a VF reset initiated from a different source, the VFLR may be not fully handled. This can leave the VF in an undefined state. To address this, set the I40E_VFLR_EVENT_PENDING bit again during VFLR handling if the reset is not yet complete. This ensures the driver will properly complete the VF reset in such scenarios. Fixes: 52424f974bc5 ("i40e: Fix VF hang when reset is triggered on another VF") Signed-off-by: Robert Malz Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 22d5b1ec2289..88e6bef69342 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx)); if (reg & BIT(bit_idx)) /* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */ - i40e_reset_vf(vf, true); + if (!i40e_reset_vf(vf, true)) { + /* At least one VF did not finish resetting, retry next time */ + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + } } return 0; From 0c6f4631436ecea841f1583b98255aedd7495b18 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 24 Apr 2025 15:50:13 +0200 Subject: [PATCH 3/5] iavf: fix reset_task for early reset event If a reset event is received from the PF early in the init cycle, the state machine hangs for about 25 seconds. Reproducer: echo 1 > /sys/class/net/$PF0/device/sriov_numvfs ip link set dev $PF0 vf 0 mac $NEW_MAC The log shows: [792.620416] ice 0000:5e:00.0: Enabling 1 VFs [792.738812] iavf 0000:5e:01.0: enabling device (0000 -> 0002) [792.744182] ice 0000:5e:00.0: Enabling 1 VFs with 17 vectors and 16 queues per VF [792.839964] ice 0000:5e:00.0: Setting MAC 52:54:00:00:00:11 on VF 0. VF driver will be reinitialized [813.389684] iavf 0000:5e:01.0: Failed to communicate with PF; waiting before retry [818.635918] iavf 0000:5e:01.0: Hardware came out of reset. Attempting reinit. [818.766273] iavf 0000:5e:01.0: Multiqueue Enabled: Queue pair count = 16 Fix it by scheduling the reset task and making the reset task capable of resetting early in the init cycle. Fixes: ef8693eb90ae3 ("i40evf: refactor reset handling") Signed-off-by: Ahmed Zaki Tested-by: Przemek Kitszel Reviewed-by: Przemek Kitszel Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 11 +++++++++++ drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 17 +++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 2c0bb41809a4..81d7249d1149 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work) } continue_reset: + /* If we are still early in the state machine, just restart. */ + if (adapter->state <= __IAVF_INIT_FAILED) { + iavf_shutdown_adminq(hw); + iavf_change_state(adapter, __IAVF_STARTUP); + iavf_startup(adapter); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + netdev_unlock(netdev); + return; + } + /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index a6f0e5990be2..07f0d0a0f1e2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -79,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event, return iavf_status_to_errno(status); received_op = (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high); + + if (received_op == VIRTCHNL_OP_EVENT) { + struct iavf_adapter *adapter = hw->back; + struct virtchnl_pf_event *vpe = + (struct virtchnl_pf_event *)event->msg_buf; + + if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING) + continue; + + dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n"); + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) + iavf_schedule_reset(adapter, + IAVF_FLAG_RESET_PENDING); + + return -EIO; + } + if (op_to_poll == received_op) break; } From a5a441ae283d54ec329aadc7426991dc32786d52 Mon Sep 17 00:00:00 2001 From: Anton Nadezhdin Date: Tue, 20 May 2025 10:42:16 +0200 Subject: [PATCH 4/5] ice/ptp: fix crosstimestamp reporting Set use_nsecs=true as timestamp is reported in ns. Lack of this result in smaller timestamp error window which cause error during phc2sys execution on E825 NICs: phc2sys[1768.256]: ioctl PTP_SYS_OFFSET_PRECISE: Invalid argument This problem was introduced in the cited commit which omitted setting use_nsecs to true when converting the ice driver to use convert_base_to_cs(). Testing hints (ethX is PF netdev): phc2sys -s ethX -c CLOCK_REALTIME -O 37 -m phc2sys[1769.256]: CLOCK_REALTIME phc offset -5 s0 freq -0 delay 0 Fixes: d4bea547ebb57 ("ice/ptp: Remove convert_art_to_tsc()") Signed-off-by: Anton Nadezhdin Reviewed-by: Aleksandr Loktionov Reviewed-by: Arkadiusz Kubalewski Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index b79a148ed0f2..55cad824c5b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2299,6 +2299,7 @@ static int ice_capture_crosststamp(ktime_t *device, ts = ((u64)ts_hi << 32) | ts_lo; system->cycles = ts; system->cs_id = CSID_X86_ART; + system->use_nsecs = true; /* Read Device source clock time */ ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]); From b4a8085ceefb7bbb12c2b71c55e71fc946c6929f Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 3 Jun 2025 16:34:01 +0000 Subject: [PATCH 5/5] e1000: Move cancel_work_sync to avoid deadlock Previously, e1000_down called cancel_work_sync for the e1000 reset task (via e1000_down_and_stop), which takes RTNL. As reported by users and syzbot, a deadlock is possible in the following scenario: CPU 0: - RTNL is held - e1000_close - e1000_down - cancel_work_sync (cancel / wait for e1000_reset_task()) CPU 1: - process_one_work - e1000_reset_task - take RTNL To remedy this, avoid calling cancel_work_sync from e1000_down (e1000_reset_task does nothing if the device is down anyway). Instead, call cancel_work_sync for e1000_reset_task when the device is being removed. Fixes: e400c7444d84 ("e1000: Hold RTNL when e1000_down can be called") Reported-by: syzbot+846bb38dc67fe62cc733@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/683837bf.a00a0220.52848.0003.GAE@google.com/ Reported-by: John Closes: https://lore.kernel.org/netdev/CAP=Rh=OEsn4y_2LvkO3UtDWurKcGPnZ_NPSXK=FbgygNXL37Sw@mail.gmail.com/ Signed-off-by: Joe Damato Acked-by: Stanislav Fomichev Acked-by: Jacob Keller Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e1000/e1000_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3f089c3d47b2..d8595e84326d 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter) cancel_delayed_work_sync(&adapter->phy_info_task); cancel_delayed_work_sync(&adapter->fifo_stall_task); - - /* Only kill reset task if adapter is not resetting */ - if (!test_bit(__E1000_RESETTING, &adapter->flags)) - cancel_work_sync(&adapter->reset_task); } void e1000_down(struct e1000_adapter *adapter) @@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev) unregister_netdev(netdev); + /* Only kill reset task if adapter is not resetting */ + if (!test_bit(__E1000_RESETTING, &adapter->flags)) + cancel_work_sync(&adapter->reset_task); + e1000_phy_hw_reset(hw); kfree(adapter->tx_ring);