From 08771bce330036d473be6ce851cd00bcd351ebf6 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Feb 2021 13:19:22 -0800 Subject: ice: Continue probe on link/PHY errors An incorrect NVM update procedure can result in the driver failing probe. In this case, the recommended resolution method is to update the NVM using the right procedure. However, if the driver fails probe, the user will not be able to update the NVM. So do not fail probe on link/PHY errors. Fixes: 1a3571b5938c ("ice: restore PHY settings on media insertion") Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 2c23c8f468a5..53e053c997eb 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4192,28 +4192,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_send_version_unroll; } + /* not a fatal error if this fails */ err = ice_init_nvm_phy_type(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err); - goto err_send_version_unroll; - } + /* not a fatal error if this fails */ err = ice_update_link_info(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_update_link_info failed: %d\n", err); - goto err_send_version_unroll; - } ice_init_link_dflt_override(pf->hw.port_info); /* if media available, initialize PHY settings */ if (pf->hw.port_info->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + /* not a fatal error if this fails */ err = ice_init_phy_user_cfg(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err); - goto err_send_version_unroll; - } if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) { struct ice_vsi *vsi = ice_get_main_vsi(pf); -- cgit From e95fc8573e07c5e4825df4650fd8b8c93fad27a7 Mon Sep 17 00:00:00 2001 From: Krzysztof Goreczny Date: Fri, 26 Feb 2021 13:19:26 -0800 Subject: ice: prevent ice_open and ice_stop during reset There is a possibility of race between ice_open or ice_stop calls performed by OS and reset handling routine both trying to modify VSI resources. Observed scenarios: - reset handler deallocates memory in ice_vsi_free_arrays and ice_open tries to access it in ice_vsi_cfg_txq leading to driver crash - reset handler deallocates memory in ice_vsi_free_arrays and ice_close tries to access it in ice_down leading to driver crash - reset handler clears port scheduler topology and sets port state to ICE_SCHED_PORT_STATE_INIT leading to ice_ena_vsi_txq fail in ice_open To prevent this additional checks in ice_open and ice_stop are introduced to make sure that OS is not allowed to alter VSI config while reset is in progress. Fixes: cdedef59deb0 ("ice: Configure VSIs for Tx/Rx") Signed-off-by: Krzysztof Goreczny Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 53e053c997eb..255a07c1e33a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6632,6 +6632,28 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) * Returns 0 on success, negative value on failure */ int ice_open(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't open net device while reset is in progress"); + return -EBUSY; + } + + return ice_open_internal(netdev); +} + +/** + * ice_open_internal - Called when a network interface becomes active + * @netdev: network interface device structure + * + * Internal ice_open implementation. Should not be used directly except for ice_open and reset + * handling routine + * + * Returns 0 on success, negative value on failure + */ +int ice_open_internal(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; @@ -6712,6 +6734,12 @@ int ice_stop(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't stop net device while reset is in progress"); + return -EBUSY; + } ice_vsi_close(vsi); -- cgit From 3176551979b92b02756979c0f1e2d03d1fc82b1e Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Feb 2021 13:19:30 -0800 Subject: ice: Use port number instead of PF ID for WoL As per the spec, the WoL control word read from the NVM should be interpreted as port numbers, and not PF numbers. So when checking if WoL supported, use the port number instead of the PF ID. Also, ice_is_wol_supported doesn't really need a pointer to the pf struct, but just needs a pointer to the hw instance. Fixes: 769c500dcc1e ("ice: Add advanced power mgmt for WoL") Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 255a07c1e33a..9f1adff85be7 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3537,15 +3537,14 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** - * ice_is_wol_supported - get NVM state of WoL - * @pf: board private structure + * ice_is_wol_supported - check if WoL is supported + * @hw: pointer to hardware info * * Check if WoL is supported based on the HW configuration. * Returns true if NVM supports and enables WoL for this port, false otherwise */ -bool ice_is_wol_supported(struct ice_pf *pf) +bool ice_is_wol_supported(struct ice_hw *hw) { - struct ice_hw *hw = &pf->hw; u16 wol_ctrl; /* A bit set to 1 in the NVM Software Reserved Word 2 (WoL control @@ -3554,7 +3553,7 @@ bool ice_is_wol_supported(struct ice_pf *pf) if (ice_read_sr_word(hw, ICE_SR_NVM_WOL_CFG, &wol_ctrl)) return false; - return !(BIT(hw->pf_id) & wol_ctrl); + return !(BIT(hw->port_info->lport) & wol_ctrl); } /** -- cgit From 1831da7ea5bdf5531d78bcf81f526faa4c4375fa Mon Sep 17 00:00:00 2001 From: Yongxin Liu Date: Thu, 1 Apr 2021 11:59:15 -0700 Subject: ice: fix memory leak of aRFS after resuming from suspend In ice_suspend(), ice_clear_interrupt_scheme() is called, and then irq_free_descs() will be eventually called to free irq and its descriptor. In ice_resume(), ice_init_interrupt_scheme() is called to allocate new irqs. However, in ice_rebuild_arfs(), struct irq_glue and struct cpu_rmap maybe cannot be freed, if the irqs that released in ice_suspend() were reassigned to other devices, which makes irq descriptor's affinity_notify lost. So call ice_free_cpu_rx_rmap() before ice_clear_interrupt_scheme(), which can make sure all irq_glue and cpu_rmap can be correctly released before corresponding irq and descriptor are released. Fix the following memory leak. unreferenced object 0xffff95bd951afc00 (size 512): comm "kworker/0:1", pid 134, jiffies 4294684283 (age 13051.958s) hex dump (first 32 bytes): 18 00 00 00 18 00 18 00 70 fc 1a 95 bd 95 ff ff ........p....... 00 00 ff ff 01 00 ff ff 02 00 ff ff 03 00 ff ff ................ backtrace: [<0000000072e4b914>] __kmalloc+0x336/0x540 [<0000000054642a87>] alloc_cpu_rmap+0x3b/0xb0 [<00000000f220deec>] ice_set_cpu_rx_rmap+0x6a/0x110 [ice] [<000000002370a632>] ice_probe+0x941/0x1180 [ice] [<00000000d692edba>] local_pci_probe+0x47/0xa0 [<00000000503934f0>] work_for_cpu_fn+0x1a/0x30 [<00000000555a9e4a>] process_one_work+0x1dd/0x410 [<000000002c4b414a>] worker_thread+0x221/0x3f0 [<00000000bb2b556b>] kthread+0x14c/0x170 [<00000000ad2cf1cd>] ret_from_fork+0x1f/0x30 unreferenced object 0xffff95bd81b0a2a0 (size 96): comm "kworker/0:1", pid 134, jiffies 4294684283 (age 13051.958s) hex dump (first 32 bytes): 38 00 00 00 01 00 00 00 e0 ff ff ff 0f 00 00 00 8............... b0 a2 b0 81 bd 95 ff ff b0 a2 b0 81 bd 95 ff ff ................ backtrace: [<00000000582dd5c5>] kmem_cache_alloc_trace+0x31f/0x4c0 [<000000002659850d>] irq_cpu_rmap_add+0x25/0xe0 [<00000000495a3055>] ice_set_cpu_rx_rmap+0xb4/0x110 [ice] [<000000002370a632>] ice_probe+0x941/0x1180 [ice] [<00000000d692edba>] local_pci_probe+0x47/0xa0 [<00000000503934f0>] work_for_cpu_fn+0x1a/0x30 [<00000000555a9e4a>] process_one_work+0x1dd/0x410 [<000000002c4b414a>] worker_thread+0x221/0x3f0 [<00000000bb2b556b>] kthread+0x14c/0x170 [<00000000ad2cf1cd>] ret_from_fork+0x1f/0x30 Fixes: 769c500dcc1e ("ice: Add advanced power mgmt for WoL") Signed-off-by: Yongxin Liu Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 9f1adff85be7..d821c687f239 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4564,6 +4564,7 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } + ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); -- cgit