From 2c0069f3f91f125b1b2ce66cc6bea8eb134723c3 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 31 Mar 2022 09:20:07 -0700 Subject: ice: Fix MAC address setting Commit 2ccc1c1ccc671b ("ice: Remove excess error variables") merged the usage of 'status' and 'err' variables into single one in function ice_set_mac_address(). Unfortunately this causes a regression when call of ice_fltr_add_mac() returns -EEXIST because this return value does not indicate an error in this case but value of 'err' remains to be -EEXIST till the end of the function and is returned to caller. Prior mentioned commit this does not happen because return value of ice_fltr_add_mac() was stored to 'status' variable first and if it was -EEXIST then 'err' remains to be zero. Fix the problem by reset 'err' to zero when ice_fltr_add_mac() returns -EEXIST. Fixes: 2ccc1c1ccc671b ("ice: Remove excess error variables") Signed-off-by: Ivan Vecera Reviewed-by: Jacob Keller Acked-by: Alexander Lobakin Signed-off-by: Alice Michael Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 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 b588d7995631..d755ce07869f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5475,16 +5475,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { -- cgit From 1273f89578f268ea705ddbad60c4bd2dcff80611 Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 31 Mar 2022 09:20:08 -0700 Subject: ice: Fix broken IFF_ALLMULTI handling Handling of all-multicast flag and associated multicast promiscuous mode is broken in ice driver. When an user switches allmulticast flag on or off the driver checks whether any VLANs are configured over the interface (except default VLAN 0). If any extra VLANs are registered it enables multicast promiscuous mode for all these VLANs (including default VLAN 0) using ICE_SW_LKUP_PROMISC_VLAN look-up type. In this situation all multicast packets tagged with known VLAN ID or untagged are received and multicast packets tagged with unknown VLAN ID ignored. If no extra VLANs are registered (so only VLAN 0 exists) it enables multicast promiscuous mode for VLAN 0 and uses ICE_SW_LKUP_PROMISC look-up type. In this situation any multicast packets including tagged ones are received. The driver handles IFF_ALLMULTI in ice_vsi_sync_fltr() this way: ice_vsi_sync_fltr() { ... if (changed_flags & IFF_ALLMULTI) { if (netdev->flags & IFF_ALLMULTI) { if (vsi->num_vlans > 1) ice_set_promisc(..., ICE_MCAST_VLAN_PROMISC_BITS); else ice_set_promisc(..., ICE_MCAST_PROMISC_BITS); } else { if (vsi->num_vlans > 1) ice_clear_promisc(..., ICE_MCAST_VLAN_PROMISC_BITS); else ice_clear_promisc(..., ICE_MCAST_PROMISC_BITS); } } ... } The code above depends on value vsi->num_vlan that specifies number of VLANs configured over the interface (including VLAN 0) and this is problem because that value is modified in NDO callbacks ice_vlan_rx_add_vid() and ice_vlan_rx_kill_vid(). Scenario 1: 1. ip link set ens7f0 allmulticast on 2. ip link add vlan10 link ens7f0 type vlan id 10 3. ip link set ens7f0 allmulticast off 4. ip link set ens7f0 allmulticast on [1] In this scenario IFF_ALLMULTI is enabled and the driver calls ice_set_promisc(..., ICE_MCAST_PROMISC_BITS) that installs multicast promisc rule with non-VLAN look-up type. [2] Then VLAN with ID 10 is added and vsi->num_vlan incremented to 2 [3] Command switches IFF_ALLMULTI off and the driver calls ice_clear_promisc(..., ICE_MCAST_VLAN_PROMISC_BITS) but this call is effectively NOP because it looks for multicast promisc rules for VLAN 0 and VLAN 10 with VLAN look-up type but no such rules exist. So the all-multicast remains enabled silently in hardware. [4] Command tries to switch IFF_ALLMULTI on and the driver calls ice_clear_promisc(..., ICE_MCAST_PROMISC_BITS) but this call fails (-EEXIST) because non-VLAN multicast promisc rule already exists. Scenario 2: 1. ip link add vlan10 link ens7f0 type vlan id 10 2. ip link set ens7f0 allmulticast on 3. ip link add vlan20 link ens7f0 type vlan id 20 4. ip link del vlan10 ; ip link del vlan20 5. ip link set ens7f0 allmulticast off [1] VLAN with ID 10 is added and vsi->num_vlan==2 [2] Command switches IFF_ALLMULTI on and driver installs multicast promisc rules with VLAN look-up type for VLAN 0 and 10 [3] VLAN with ID 20 is added and vsi->num_vlan==3 but no multicast promisc rules is added for this new VLAN so the interface does not receive MC packets from VLAN 20 [4] Both VLANs are removed but multicast rule for VLAN 10 remains installed so interface receives multicast packets from VLAN 10 [5] Command switches IFF_ALLMULTI off and because vsi->num_vlan is 1 the driver tries to remove multicast promisc rule for VLAN 0 with non-VLAN look-up that does not exist. All-multicast looks disabled from user point of view but it is partially enabled in HW (interface receives all multicast packets either untagged or tagged with VLAN ID 10) To resolve these issues the patch introduces these changes: 1. Adds handling for IFF_ALLMULTI to ice_vlan_rx_add_vid() and ice_vlan_rx_kill_vid() callbacks. So when VLAN is added/removed and IFF_ALLMULTI is enabled an appropriate multicast promisc rule for that VLAN ID is added/removed. 2. In ice_vlan_rx_add_vid() when first VLAN besides VLAN 0 is added so (vsi->num_vlan == 2) and IFF_ALLMULTI is enabled then look-up type for existing multicast promisc rule for VLAN 0 is updated to ICE_MCAST_VLAN_PROMISC_BITS. 3. In ice_vlan_rx_kill_vid() when last VLAN besides VLAN 0 is removed so (vsi->num_vlan == 1) and IFF_ALLMULTI is enabled then look-up type for existing multicast promisc rule for VLAN 0 is updated to ICE_MCAST_PROMISC_BITS. 4. Both ice_vlan_rx_{add,kill}_vid() have to run under ICE_CFG_BUSY bit protection to avoid races with ice_vsi_sync_fltr() that runs in ice_service_task() context. 5. Bit ICE_VSI_VLAN_FLTR_CHANGED is use-less and can be removed. 6. Error messages added to ice_fltr_*_vsi_promisc() helper functions to avoid them in their callers 7. Small improvements to increase readability Fixes: 5eda8afd6bcc ("ice: Add support for PF/VF promiscuous mode") Signed-off-by: Ivan Vecera Reviewed-by: Jacob Keller Signed-off-by: Alice Michael Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice.h | 1 - drivers/net/ethernet/intel/ice/ice_fltr.c | 44 ++++++++++-- drivers/net/ethernet/intel/ice/ice_main.c | 114 +++++++++++++++++++++--------- 3 files changed, 121 insertions(+), 38 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d4f1874df7d0..26eaee0b6503 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index af57eb114966..85a94483c2ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d755ce07869f..1d2ca39add95 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -3488,6 +3481,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); + if (ret) + goto finish; + } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged @@ -3495,8 +3502,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) */ vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->add_vlan(vsi, &vlan); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3522,6 +3544,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Make sure VLAN delete is successful before updating VLAN @@ -3530,10 +3555,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return 0; + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); + + return ret; } /** -- cgit From f9124c68f05ffdb87a47e3ea6d5fae9dad7cb6eb Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Thu, 17 Mar 2022 19:36:27 +0100 Subject: ice: synchronize_rcu() when terminating rings Unfortunately, the ice driver doesn't respect the RCU critical section that XSK wakeup is surrounded with. To fix this, add synchronize_rcu() calls to paths that destroy resources that might be in use. This was addressed in other AF_XDP ZC enabled drivers, for reference see for example commit b3873a5be757 ("net/i40e: Fix concurrency issues between config flow and XSK") Fixes: efc2214b6047 ("ice: Add support for XDP") Fixes: 2d4238f55697 ("ice: Add support for AF_XDP") Signed-off-by: Maciej Fijalkowski Tested-by: Shwetha Nagaraju Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 2 +- drivers/net/ethernet/intel/ice/ice_main.c | 4 +++- drivers/net/ethernet/intel/ice/ice_xsk.c | 4 +++- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 26eaee0b6503..8ed3c9ab7ff7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -671,7 +671,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1d2ca39add95..d2039a9306b8 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2758,8 +2758,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dfbcaf08520e..33b28a72ffcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } -- cgit From e19778e6c911691856447c3bf9617f00b3e1347f Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Thu, 17 Mar 2022 19:36:29 +0100 Subject: ice: clear cmd_type_offset_bsz for TX rings Currently when XDP rings are created, each descriptor gets its DD bit set, which turns out to be the wrong approach as it can lead to a situation where more descriptors get cleaned than it was supposed to, e.g. when AF_XDP busy poll is run with a large batch size. In this situation, the driver would request for more buffers than it is able to handle. Fix this by not setting the DD bits in ice_xdp_alloc_setup_rings(). They should be initialized to zero instead. Fixes: 9610bd988df9 ("ice: optimize XDP_TX workloads") Signed-off-by: Maciej Fijalkowski Tested-by: Shwetha Nagaraju Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (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 d2039a9306b8..d768925785ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2562,7 +2562,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } -- cgit From d7442f512b71fc63a99c8a801422dde4fbbf9f93 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 4 Apr 2022 18:15:09 +0200 Subject: ice: arfs: fix use-after-free when freeing @rx_cpu_rmap The CI testing bots triggered the following splat: [ 718.203054] BUG: KASAN: use-after-free in free_irq_cpu_rmap+0x53/0x80 [ 718.206349] Read of size 4 at addr ffff8881bd127e00 by task sh/20834 [ 718.212852] CPU: 28 PID: 20834 Comm: sh Kdump: loaded Tainted: G S W IOE 5.17.0-rc8_nextqueue-devqueue-02643-g23f3121aca93 #1 [ 718.219695] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0012.070720200218 07/07/2020 [ 718.223418] Call Trace: [ 718.227139] [ 718.230783] dump_stack_lvl+0x33/0x42 [ 718.234431] print_address_description.constprop.9+0x21/0x170 [ 718.238177] ? free_irq_cpu_rmap+0x53/0x80 [ 718.241885] ? free_irq_cpu_rmap+0x53/0x80 [ 718.245539] kasan_report.cold.18+0x7f/0x11b [ 718.249197] ? free_irq_cpu_rmap+0x53/0x80 [ 718.252852] free_irq_cpu_rmap+0x53/0x80 [ 718.256471] ice_free_cpu_rx_rmap.part.11+0x37/0x50 [ice] [ 718.260174] ice_remove_arfs+0x5f/0x70 [ice] [ 718.263810] ice_rebuild_arfs+0x3b/0x70 [ice] [ 718.267419] ice_rebuild+0x39c/0xb60 [ice] [ 718.270974] ? asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 718.274472] ? ice_init_phy_user_cfg+0x360/0x360 [ice] [ 718.278033] ? delay_tsc+0x4a/0xb0 [ 718.281513] ? preempt_count_sub+0x14/0xc0 [ 718.284984] ? delay_tsc+0x8f/0xb0 [ 718.288463] ice_do_reset+0x92/0xf0 [ice] [ 718.292014] ice_pci_err_resume+0x91/0xf0 [ice] [ 718.295561] pci_reset_function+0x53/0x80 <...> [ 718.393035] Allocated by task 690: [ 718.433497] Freed by task 20834: [ 718.495688] Last potentially related work creation: [ 718.568966] The buggy address belongs to the object at ffff8881bd127e00 which belongs to the cache kmalloc-96 of size 96 [ 718.574085] The buggy address is located 0 bytes inside of 96-byte region [ffff8881bd127e00, ffff8881bd127e60) [ 718.579265] The buggy address belongs to the page: [ 718.598905] Memory state around the buggy address: [ 718.601809] ffff8881bd127d00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 718.604796] ffff8881bd127d80: 00 00 00 00 00 00 00 00 00 00 fc fc fc fc fc fc [ 718.607794] >ffff8881bd127e00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 718.610811] ^ [ 718.613819] ffff8881bd127e80: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc [ 718.617107] ffff8881bd127f00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc This is due to that free_irq_cpu_rmap() is always being called *after* (devm_)free_irq() and thus it tries to work with IRQ descs already freed. For example, on device reset the driver frees the rmap right before allocating a new one (the splat above). Make rmap creation and freeing function symmetrical with {request,free}_irq() calls i.e. do that on ifup/ifdown instead of device probe/remove/resume. These operations can be performed independently from the actual device aRFS configuration. Also, make sure ice_vsi_free_irq() clears IRQ affinity notifiers only when aRFS is disabled -- otherwise, CPU rmap sets and clears its own and they must not be touched manually. Fixes: 28bf26724fdb0 ("ice: Implement aRFS") Co-developed-by: Ivan Vecera Signed-off-by: Ivan Vecera Signed-off-by: Alexander Lobakin Tested-by: Ivan Vecera Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_arfs.c | 9 ++------- drivers/net/ethernet/intel/ice/ice_lib.c | 5 ++++- drivers/net/ethernet/intel/ice/ice_main.c | 18 ++++++++---------- 3 files changed, 14 insertions(+), 18 deletions(-) (limited to 'drivers/net/ethernet/intel/ice/ice_main.c') diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 5daade32ea62..fba178e07600 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -599,7 +599,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -636,7 +636,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -653,9 +652,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 2774cbd5b12a..6d19c58ccacd 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2689,6 +2689,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2702,7 +2704,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index d768925785ca..5b1198859da7 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2510,6 +2510,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -3692,20 +3699,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return 0; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: @@ -5167,7 +5166,6 @@ 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