From eef33aa44935d001747ca97703c08dd6f9031162 Mon Sep 17 00:00:00 2001 From: Larysa Zaremba Date: Wed, 3 Dec 2025 14:29:48 +0100 Subject: [PATCH 1/8] ice: fix adding AQ LLDP filter for VF The referenced commit came from a misunderstanding of the FW LLDP filter AQ (Admin Queue) command due to the error in the internal documentation. Contrary to the assumptions in the original commit, VFs can be added and deleted from this filter without any problems. Introduced dev_info message proved to be useful, so reverting the whole commit does not make sense. Without this fix, trusted VFs do not receive LLDP traffic, if there is an AQ LLDP filter on PF. When trusted VF attempts to add an LLDP multicast MAC address, the following message can be seen in dmesg on host: ice 0000:33:00.0: Failed to add Rx LLDP rule on VSI 20 error: -95 Revert checking VSI type when adding LLDP filter through AQ. Fixes: 4d5a1c4e6d49 ("ice: do not add LLDP-specific filter if not necessary") Reviewed-by: Aleksandr Loktionov Signed-off-by: Larysa Zaremba Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 6cd63190f55d..74fe74225277 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -6391,7 +6391,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) struct ice_aqc_lldp_filter_ctrl *cmd; struct libie_aq_desc desc; - if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + if (!ice_fw_supports_lldp_fltr_ctrl(hw)) return -EOPNOTSUPP; cmd = libie_aq_raw(&desc); From 326256c0a72d4877cec1d4df85357da106233128 Mon Sep 17 00:00:00 2001 From: Jakub Staniszewski Date: Tue, 13 Jan 2026 20:38:16 +0100 Subject: [PATCH 2/8] ice: reintroduce retry mechanism for indirect AQ Add retry mechanism for indirect Admin Queue (AQ) commands. To do so we need to keep the command buffer. This technically reverts commit 43a630e37e25 ("ice: remove unused buffer copy code in ice_sq_send_cmd_retry()"), but combines it with a fix in the logic by using a kmemdup() call, making it more robust and less likely to break in the future due to programmer error. Cc: Michal Schmidt Cc: stable@vger.kernel.org Fixes: 3056df93f7a8 ("ice: Re-send some AQ commands, as result of EBUSY AQ error") Signed-off-by: Jakub Staniszewski Co-developed-by: Dawid Osuchowski Signed-off-by: Dawid Osuchowski Reviewed-by: Aleksandr Loktionov Reviewed-by: Przemek Kitszel Reviewed-by: Paul Menzel Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 74fe74225277..fd32c318d3f5 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1841,6 +1841,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, { struct libie_aq_desc desc_cpy; bool is_cmd_for_retry; + u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; int status; @@ -1850,8 +1851,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, memset(&desc_cpy, 0, sizeof(desc_cpy)); if (is_cmd_for_retry) { - /* All retryable cmds are direct, without buf. */ - WARN_ON(buf); + if (buf) { + buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + } memcpy(&desc_cpy, desc, sizeof(desc_cpy)); } @@ -1863,12 +1867,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) break; + if (buf_cpy) + memcpy(buf, buf_cpy, buf_size); memcpy(desc, &desc_cpy, sizeof(desc_cpy)); - msleep(ICE_SQ_SEND_DELAY_TIME_MS); } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); + kfree(buf_cpy); return status; } From fb4903b3354aed4a2301180cf991226f896c87ed Mon Sep 17 00:00:00 2001 From: Jakub Staniszewski Date: Tue, 13 Jan 2026 20:38:17 +0100 Subject: [PATCH 3/8] ice: fix retry for AQ command 0x06EE Executing ethtool -m can fail reporting a netlink I/O error while firmware link management holds the i2c bus used to communicate with the module. According to Intel(R) Ethernet Controller E810 Datasheet Rev 2.8 [1] Section 3.3.10.4 Read/Write SFF EEPROM (0x06EE) request should to be retried upon receiving EBUSY from firmware. Commit e9c9692c8a81 ("ice: Reimplement module reads used by ethtool") implemented it only for part of ice_get_module_eeprom(), leaving all other calls to ice_aq_sff_eeprom() vulnerable to returning early on getting EBUSY without retrying. Remove the retry loop from ice_get_module_eeprom() and add Admin Queue (AQ) command with opcode 0x06EE to the list of commands that should be retried on receiving EBUSY from firmware. Cc: stable@vger.kernel.org Fixes: e9c9692c8a81 ("ice: Reimplement module reads used by ethtool") Signed-off-by: Jakub Staniszewski Co-developed-by: Dawid Osuchowski Signed-off-by: Dawid Osuchowski Reviewed-by: Aleksandr Loktionov Reviewed-by: Przemek Kitszel Link: https://www.intel.com/content/www/us/en/content-details/613875/intel-ethernet-controller-e810-datasheet.html [1] Reviewed-by: Paul Menzel Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 1 + drivers/net/ethernet/intel/ice/ice_ethtool.c | 35 ++++++++------------ 2 files changed, 15 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index fd32c318d3f5..ce11fea122d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode) case ice_aqc_opc_lldp_stop: case ice_aqc_opc_lldp_start: case ice_aqc_opc_lldp_filter_ctrl: + case ice_aqc_opc_sff_eeprom: return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 3c1a084c2a4b..29e341251754 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4509,7 +4509,7 @@ ice_get_module_eeprom(struct net_device *netdev, u8 addr = ICE_I2C_EEPROM_DEV_ADDR; struct ice_hw *hw = &pf->hw; bool is_sfp = false; - unsigned int i, j; + unsigned int i; u16 offset = 0; u8 page = 0; int status; @@ -4551,26 +4551,19 @@ ice_get_module_eeprom(struct net_device *netdev, if (page == 0 || !(data[0x2] & 0x4)) { u32 copy_len; - /* If i2c bus is busy due to slow page change or - * link management access, call can fail. This is normal. - * So we retry this a few times. - */ - for (j = 0; j < 4; j++) { - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, - !is_sfp, value, - SFF_READ_BLOCK_SIZE, - 0, NULL); - netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n", - addr, offset, page, is_sfp, - value[0], value[1], value[2], value[3], - value[4], value[5], value[6], value[7], - status); - if (status) { - usleep_range(1500, 2500); - memset(value, 0, SFF_READ_BLOCK_SIZE); - continue; - } - break; + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, + !is_sfp, value, + SFF_READ_BLOCK_SIZE, + 0, NULL); + netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n", + addr, offset, page, is_sfp, + value[0], value[1], value[2], value[3], + value[4], value[5], value[6], value[7], + ERR_PTR(status)); + if (status) { + netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n", + __func__, ERR_PTR(status)); + return status; } /* Make sure we have enough room for the new block */ From fe868b499d16f55bbeea89992edb98043c9de416 Mon Sep 17 00:00:00 2001 From: Zilin Guan Date: Thu, 22 Jan 2026 03:26:44 +0000 Subject: [PATCH 4/8] ice: Fix memory leak in ice_set_ringparam() In ice_set_ringparam, tx_rings and xdp_rings are allocated before rx_rings. If the allocation of rx_rings fails, the code jumps to the done label leaking both tx_rings and xdp_rings. Furthermore, if the setup of an individual Rx ring fails during the loop, the code jumps to the free_tx label which releases tx_rings but leaks xdp_rings. Fix this by introducing a free_xdp label and updating the error paths to ensure both xdp_rings and tx_rings are properly freed if rx_rings allocation or setup fails. Compile tested only. Issue found using a prototype static analysis tool and code review. Fixes: fcea6f3da546 ("ice: Add stats and ethtool support") Fixes: efc2214b6047 ("ice: Add support for XDP") Signed-off-by: Zilin Guan Reviewed-by: Paul Menzel Reviewed-by: Aleksandr Loktionov Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 29e341251754..b9be10b58856 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3332,7 +3332,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq); if (!rx_rings) { err = -ENOMEM; - goto done; + goto free_xdp; } ice_for_each_rxq(vsi, i) { @@ -3359,7 +3359,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, } kfree(rx_rings); err = -ENOMEM; - goto free_tx; + goto free_xdp; } } @@ -3411,6 +3411,13 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, } goto done; +free_xdp: + if (xdp_rings) { + ice_for_each_xdp_txq(vsi, i) + ice_free_tx_ring(&xdp_rings[i]); + kfree(xdp_rings); + } + free_tx: /* error cleanup if the Rx allocations failed after getting Tx */ if (tx_rings) { From 636cc3bd12f499c74eaf5dc9a7d5b832f1bb24ed Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Wed, 11 Feb 2026 10:11:40 +0100 Subject: [PATCH 5/8] libie: don't unroll if fwlog isn't supported The libie_fwlog_deinit() function can be called during driver unload even when firmware logging was never properly initialized. This led to call trace: [ 148.576156] Oops: Oops: 0000 [#1] SMP NOPTI [ 148.576167] CPU: 80 UID: 0 PID: 12843 Comm: rmmod Kdump: loaded Not tainted 6.17.0-rc7next-queue-3oct-01915-g06d79d51cf51 #1 PREEMPT(full) [ 148.576177] Hardware name: HPE ProLiant DL385 Gen10 Plus/ProLiant DL385 Gen10 Plus, BIOS A42 07/18/2020 [ 148.576182] RIP: 0010:__dev_printk+0x16/0x70 [ 148.576196] Code: 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 55 41 54 49 89 d4 55 48 89 fd 53 48 85 f6 74 3c <4c> 8b 6e 50 48 89 f3 4d 85 ed 75 03 4c 8b 2e 48 89 df e8 f3 27 98 [ 148.576204] RSP: 0018:ffffd2fd7ea17a48 EFLAGS: 00010202 [ 148.576211] RAX: ffffd2fd7ea17aa0 RBX: ffff8eb288ae2000 RCX: 0000000000000000 [ 148.576217] RDX: ffffd2fd7ea17a70 RSI: 00000000000000c8 RDI: ffffffffb68d3d88 [ 148.576222] RBP: ffffffffb68d3d88 R08: 0000000000000000 R09: 0000000000000000 [ 148.576227] R10: 00000000000000c8 R11: ffff8eb2b1a49400 R12: ffffd2fd7ea17a70 [ 148.576231] R13: ffff8eb3141fb000 R14: ffffffffc1215b48 R15: ffffffffc1215bd8 [ 148.576236] FS: 00007f5666ba6740(0000) GS:ffff8eb2472b9000(0000) knlGS:0000000000000000 [ 148.576242] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 148.576247] CR2: 0000000000000118 CR3: 000000011ad17000 CR4: 0000000000350ef0 [ 148.576252] Call Trace: [ 148.576258] [ 148.576269] _dev_warn+0x7c/0x96 [ 148.576290] libie_fwlog_deinit+0x112/0x117 [libie_fwlog] [ 148.576303] ixgbe_remove+0x63/0x290 [ixgbe] [ 148.576342] pci_device_remove+0x42/0xb0 [ 148.576354] device_release_driver_internal+0x19c/0x200 [ 148.576365] driver_detach+0x48/0x90 [ 148.576372] bus_remove_driver+0x6d/0xf0 [ 148.576383] pci_unregister_driver+0x2e/0xb0 [ 148.576393] ixgbe_exit_module+0x1c/0xd50 [ixgbe] [ 148.576430] __do_sys_delete_module.isra.0+0x1bc/0x2e0 [ 148.576446] do_syscall_64+0x7f/0x980 It can be reproduced by trying to unload ixgbe driver in recovery mode. Fix that by checking if fwlog is supported before doing unroll. Fixes: 641585bc978e ("ixgbe: fwlog support for e610") Reviewed-by: Aleksandr Loktionov Signed-off-by: Michal Swiatkowski Reviewed-by: Simon Horman Tested-by: Rinitha S (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/libie/fwlog.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c index 79020d990859..4d0c8370386b 100644 --- a/drivers/net/ethernet/intel/libie/fwlog.c +++ b/drivers/net/ethernet/intel/libie/fwlog.c @@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog) { int status; + /* if FW logging isn't supported it means no configuration was done */ + if (!libie_fwlog_supported(fwlog)) + return; + /* make sure FW logging is disabled to not put the FW in a weird state * for the next driver load */ From b84852170153671bb0fa6737a6e48370addd8e1a Mon Sep 17 00:00:00 2001 From: Kohei Enju Date: Tue, 10 Feb 2026 15:57:14 +0000 Subject: [PATCH 6/8] iavf: fix netdev->max_mtu to respect actual hardware limit iavf sets LIBIE_MAX_MTU as netdev->max_mtu, ignoring vf_res->max_mtu from PF [1]. This allows setting an MTU beyond the actual hardware limit, causing TX queue timeouts [2]. Set correct netdev->max_mtu using vf_res->max_mtu from the PF. Note that currently PF drivers such as ice/i40e set the frame size in vf_res->max_mtu, not MTU. Convert vf_res->max_mtu to MTU before setting netdev->max_mtu. [1] # ip -j -d link show $DEV | jq '.[0].max_mtu' 16356 [2] iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 1: transmit queue 0 timed out 5692 ms iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 6: transmit queue 3 timed out 5312 ms iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex ... Fixes: 5fa4caff59f2 ("iavf: switch to Page Pool") Signed-off-by: Kohei Enju Reviewed-by: Alexander Lobakin Reviewed-by: Simon Horman Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index bceaf4b1b85d..86c1964f42e1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netdev->watchdog_timeo = 5 * HZ; netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = LIBIE_MAX_MTU; + + /* PF/VF API: vf_res->max_mtu is max frame size (not MTU). + * Convert to MTU. + */ + if (!adapter->vf_res->max_mtu) { + netdev->max_mtu = LIBIE_MAX_MTU; + } else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU || + adapter->vf_res->max_mtu > + LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) { + netdev_warn_once(adapter->netdev, + "invalid max frame size %d from PF, using default MTU %d", + adapter->vf_res->max_mtu, LIBIE_MAX_MTU); + netdev->max_mtu = LIBIE_MAX_MTU; + } else { + netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN; + } if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", From d4c13ab36273a8c318ba06799793cc1f5d9c6fa1 Mon Sep 17 00:00:00 2001 From: Vivek Behera Date: Thu, 22 Jan 2026 15:16:52 +0100 Subject: [PATCH 7/8] igb: Fix trigger of incorrect irq in igb_xsk_wakeup The current implementation in the igb_xsk_wakeup expects the Rx and Tx queues to share the same irq. This would lead to triggering of incorrect irq in split irq configuration. This patch addresses this issue which could impact environments with 2 active cpu cores or when the number of queues is reduced to 2 or less cat /proc/interrupts | grep eno2 167: 0 0 0 0 IR-PCI-MSIX-0000:08:00.0 0-edge eno2 168: 0 0 0 0 IR-PCI-MSIX-0000:08:00.0 1-edge eno2-rx-0 169: 0 0 0 0 IR-PCI-MSIX-0000:08:00.0 2-edge eno2-rx-1 170: 0 0 0 0 IR-PCI-MSIX-0000:08:00.0 3-edge eno2-tx-0 171: 0 0 0 0 IR-PCI-MSIX-0000:08:00.0 4-edge eno2-tx-1 Furthermore it uses the flags input argument to trigger either rx, tx or both rx and tx irqs as specified in the ndo_xsk_wakeup api documentation Fixes: 80f6ccf9f116 ("igb: Introduce XSK data structures and helpers") Signed-off-by: Vivek Behera Reviewed-by: Aleksandr Loktionov Suggested-by: Maciej Fijalkowski Acked-by: Maciej Fijalkowski Tested-by: Saritha Sanigani (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_xsk.c | 38 +++++++++++++++++++----- 1 file changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 30ce5fbb5b77..ce4a7b58cad2 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) return nb_pkts < budget; } +static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector) +{ + u32 eics = 0; + + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); @@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) ring = adapter->tx_ring[qid]; - if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) - return -ENETDOWN; - if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; - if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + if (flags & XDP_WAKEUP_TX) { + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (flags & XDP_WAKEUP_RX) { + /* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the TX path, making this RX call a NOP + */ + ring = adapter->rx_ring[qid]; + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (eics) { /* Cause software interrupt */ - if (adapter->flags & IGB_FLAG_HAS_MSIX) { - eics |= ring->q_vector->eims_value; + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EICS, eics); - } else { + else wr32(E1000_ICS, E1000_ICS_RXDMT0); - } } return 0; From 554a1c34c11a057d01819ce9bb04653a8ffc8071 Mon Sep 17 00:00:00 2001 From: Vivek Behera Date: Tue, 20 Jan 2026 08:52:16 +0100 Subject: [PATCH 8/8] igc: Fix trigger of incorrect irq in igc_xsk_wakeup function This patch addresses the issue where the igc_xsk_wakeup function was triggering an incorrect IRQ for tx-0 when the i226 is configured with only 2 combined queues or in an environment with 2 active CPU cores. This prevented XDP Zero-copy send functionality in such split IRQ configurations. The fix implements the correct logic for extracting q_vectors saved during rx and tx ring allocation and utilizes flags provided by the ndo_xsk_wakeup API to trigger the appropriate IRQ. Fixes: fc9df2a0b520 ("igc: Enable RX via AF_XDP zero-copy") Fixes: 15fd021bc427 ("igc: Add Tx hardware timestamp request for AF_XDP zero-copy packet") Signed-off-by: Vivek Behera Reviewed-by: Jacob Keller Reviewed-by: Aleksandr loktinov Reviewed-by: Piotr Kwapulinski Reviewed-by: Song Yoong Siang Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_main.c | 34 ++++++++++++++++------- drivers/net/ethernet/intel/igc/igc_ptp.c | 3 +- 2 files changed, 26 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27e5c2109138..b2e8d0c0f827 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return nxmit; } -static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, - struct igc_q_vector *q_vector) +static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector) { - struct igc_hw *hw = &adapter->hw; u32 eics = 0; - eics |= q_vector->eims_value; - wr32(IGC_EICS, eics); + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; } int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct igc_adapter *adapter = netdev_priv(dev); - struct igc_q_vector *q_vector; + struct igc_hw *hw = &adapter->hw; struct igc_ring *ring; + u32 eics = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return -ENETDOWN; if (!igc_xdp_is_enabled(adapter)) return -ENXIO; - + /* Check if queue_id is valid. Tx and Rx queue numbers are always same */ if (queue_id >= adapter->num_rx_queues) return -EINVAL; @@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (!ring->xsk_pool) return -ENXIO; - q_vector = adapter->q_vector[queue_id]; - if (!napi_if_scheduled_mark_missed(&q_vector->napi)) - igc_trigger_rxtxq_interrupt(adapter, q_vector); + if (flags & XDP_WAKEUP_RX) + eics |= igc_sw_irq_prep(ring->q_vector); + + if (flags & XDP_WAKEUP_TX) { + /* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the RX path, making this TX call a NOP + */ + ring = adapter->tx_ring[queue_id]; + eics |= igc_sw_irq_prep(ring->q_vector); + } + + if (eics) + /* Cause software interrupt */ + wr32(IGC_EICS, eics); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 7aae83c108fd..44ee19386766 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, tstamp->buffer_type = 0; /* Trigger txrx interrupt for transmit completion */ - igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, + XDP_WAKEUP_TX); return; }