From 1e6d6f8c1b07a5874444c3a403eb24427e8b39d3 Mon Sep 17 00:00:00 2001 From: Kiran Patil Date: Thu, 24 Sep 2015 15:43:02 -0400 Subject: [PATCH 1/6] i40e: Move i40e_get_head into header file i40e_get_head needs to be called in multiple files in a further patch, prepare by moving the function into a header file. Signed-off-by: Kiran Patil Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 13 ------------- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 738aca68f665..9a800f99ec13 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -600,19 +600,6 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) } } -/** - * i40e_get_head - Retrieve head from head writeback - * @tx_ring: tx ring to fetch head of - * - * Returns value of Tx ring head based on value stored - * in head write-back location - **/ -static inline u32 i40e_get_head(struct i40e_ring *tx_ring) -{ - void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count; - - return le32_to_cpu(*(volatile __le32 *)head); -} /** * i40e_get_tx_pending - how many tx descriptors not processed diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f1385a1989fa..51487ef9eda3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -326,4 +326,18 @@ int i40e_xmit_descriptor_count(struct sk_buff *skb, struct i40e_ring *tx_ring); int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, struct i40e_ring *tx_ring, u32 *flags); #endif + +/** + * i40e_get_head - Retrieve head from head writeback + * @tx_ring: tx ring to fetch head of + * + * Returns value of Tx ring head based on value stored + * in head write-back location + **/ +static inline u32 i40e_get_head(struct i40e_ring *tx_ring) +{ + void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count; + + return le32_to_cpu(*(volatile __le32 *)head); +} #endif /* _I40E_TXRX_H_ */ From b03a8c1f4c0c6f95f5addaf4a13dd3aa118c3c1a Mon Sep 17 00:00:00 2001 From: Kiran Patil Date: Thu, 24 Sep 2015 18:13:15 -0400 Subject: [PATCH 2/6] i40e/i40evf: refactor tx timeout logic This patch modifies the driver timeout logic by issuing a writeback request via a software interrupt to the hardware the first time the driver detects a hang. The driver was too aggressive in resetting a hung queue, so back that off by removing logic to down the netdevice after too many hangs, and move the function to the service task. Change-ID: Ife100b9d124cd08cbdb81ab659008c1b9abbedea Signed-off-by: Kiran Patil Signed-off-by: Shannon Nelson Signed-off-by: Jesse Brandeburg Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 1 - drivers/net/ethernet/intel/i40e/i40e_main.c | 272 +++++++++++------- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 75 +---- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 10 +- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 94 +----- drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 8 - 6 files changed, 173 insertions(+), 287 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index e7462793d48d..4797269d1200 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -243,7 +243,6 @@ struct i40e_pf { struct pci_dev *pdev; struct i40e_hw hw; unsigned long state; - unsigned long link_check_timeout; struct msix_entry *msix_entries; bool fc_autoneg_status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 530d8b6739f9..c246dca5de71 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -299,25 +299,69 @@ static void i40e_tx_timeout(struct net_device *netdev) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + struct i40e_ring *tx_ring = NULL; + unsigned int i, hung_queue = 0; + u32 head, val; pf->tx_timeout_count++; + /* find the stopped queue the same way the stack does */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + unsigned long trans_start; + + q = netdev_get_tx_queue(netdev, i); + trans_start = q->trans_start ? : netdev->trans_start; + if (netif_xmit_stopped(q) && + time_after(jiffies, + (trans_start + netdev->watchdog_timeo))) { + hung_queue = i; + break; + } + } + + if (i == netdev->num_tx_queues) { + netdev_info(netdev, "tx_timeout: no netdev hung queue found\n"); + } else { + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_queue_pairs; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (hung_queue == + vsi->tx_rings[i]->queue_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + } + if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ*20))) - pf->tx_timeout_recovery_level = 1; + pf->tx_timeout_recovery_level = 1; /* reset after some time */ + else if (time_before(jiffies, + (pf->tx_timeout_last_recovery + netdev->watchdog_timeo))) + return; /* don't do any new action before the next timeout */ + + if (tx_ring) { + head = i40e_get_head(tx_ring); + /* Read interrupt register */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + val = rd32(&pf->hw, + I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + else + val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); + + netdev_info(netdev, "tx_timeout: VSI_seid: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + vsi->seid, hung_queue, tx_ring->next_to_clean, + head, tx_ring->next_to_use, + readl(tx_ring->tail), val); + } + pf->tx_timeout_last_recovery = jiffies; - netdev_info(netdev, "tx_timeout recovery level %d\n", - pf->tx_timeout_recovery_level); + netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n", + pf->tx_timeout_recovery_level, hung_queue); switch (pf->tx_timeout_recovery_level) { - case 0: - /* disable and re-enable queues for the VSI */ - if (in_interrupt()) { - set_bit(__I40E_REINIT_REQUESTED, &pf->state); - set_bit(__I40E_REINIT_REQUESTED, &vsi->state); - } else { - i40e_vsi_reinit_locked(vsi); - } - break; case 1: set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); break; @@ -329,10 +373,9 @@ static void i40e_tx_timeout(struct net_device *netdev) break; default: netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); - set_bit(__I40E_DOWN_REQUESTED, &pf->state); - set_bit(__I40E_DOWN_REQUESTED, &vsi->state); break; } + i40e_service_event_schedule(pf); pf->tx_timeout_recovery_level++; } @@ -754,7 +797,6 @@ static void i40e_update_link_xoff_rx(struct i40e_pf *pf) struct i40e_hw_port_stats *nsd = &pf->stats; struct i40e_hw *hw = &pf->hw; u64 xoff = 0; - u16 i, v; if ((hw->fc.current_mode != I40E_FC_FULL) && (hw->fc.current_mode != I40E_FC_RX_PAUSE)) @@ -769,18 +811,6 @@ static void i40e_update_link_xoff_rx(struct i40e_pf *pf) if (!(nsd->link_xoff_rx - xoff)) return; - /* Clear the __I40E_HANG_CHECK_ARMED bit for all Tx rings */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - - if (!vsi || !vsi->tx_rings[0]) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *ring = vsi->tx_rings[i]; - clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state); - } - } } /** @@ -796,7 +826,7 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf) bool xoff[I40E_MAX_TRAFFIC_CLASS] = {false}; struct i40e_dcbx_config *dcb_cfg; struct i40e_hw *hw = &pf->hw; - u16 i, v; + u16 i; u8 tc; dcb_cfg = &hw->local_dcbx_config; @@ -821,23 +851,6 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf) tc = dcb_cfg->etscfg.prioritytable[i]; xoff[tc] = true; } - - /* Clear the __I40E_HANG_CHECK_ARMED bit for Tx rings */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - - if (!vsi || !vsi->tx_rings[0]) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *ring = vsi->tx_rings[i]; - - tc = ring->dcb_tc; - if (xoff[tc]) - clear_bit(__I40E_HANG_CHECK_ARMED, - &ring->state); - } - } } /** @@ -2609,8 +2622,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl); i40e_flush(hw); - clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state); - /* cache tail off for easier writes later */ ring->tail = hw->hw_addr + I40E_QTX_TAIL(pf_q); @@ -4145,6 +4156,108 @@ static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf) } #endif + +/** + * i40e_detect_recover_hung_queue - Function to detect and recover hung_queue + * @q_idx: TX queue number + * @vsi: Pointer to VSI struct + * + * This function checks specified queue for given VSI. Detects hung condition. + * Sets hung bit since it is two step process. Before next run of service task + * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not, + * hung condition remain unchanged and during subsequent run, this function + * issues SW interrupt to recover from hung condition. + **/ +static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) +{ + struct i40e_ring *tx_ring = NULL; + struct i40e_pf *pf; + u32 head, val, tx_pending; + int i; + + pf = vsi->back; + + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_queue_pairs; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (q_idx == vsi->tx_rings[i]->queue_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + + if (!tx_ring) + return; + + /* Read interrupt register */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + val = rd32(&pf->hw, + I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + else + val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); + + head = i40e_get_head(tx_ring); + + tx_pending = i40e_get_tx_pending(tx_ring); + + /* Interrupts are disabled and TX pending is non-zero, + * trigger the SW interrupt (don't wait). Worst case + * there will be one extra interrupt which may result + * into not cleaning any queues because queues are cleaned. + */ + if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) + i40e_force_wb(vsi, tx_ring->q_vector); +} + +/** + * i40e_detect_recover_hung - Function to detect and recover hung_queues + * @pf: pointer to PF struct + * + * LAN VSI has netdev and netdev has TX queues. This function is to check + * each of those TX queues if they are hung, trigger recovery by issuing + * SW interrupt. + **/ +static void i40e_detect_recover_hung(struct i40e_pf *pf) +{ + struct net_device *netdev; + struct i40e_vsi *vsi; + int i; + + /* Only for LAN VSI */ + vsi = pf->vsi[pf->lan_vsi]; + + if (!vsi) + return; + + /* Make sure, VSI state is not DOWN/RECOVERY_PENDING */ + if (test_bit(__I40E_DOWN, &vsi->back->state) || + test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) + return; + + /* Make sure type is MAIN VSI */ + if (vsi->type != I40E_VSI_MAIN) + return; + + netdev = vsi->netdev; + if (!netdev) + return; + + /* Bail out if netif_carrier is not OK */ + if (!netif_carrier_ok(netdev)) + return; + + /* Go thru' TX queues for netdev */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + + q = netdev_get_tx_queue(netdev, i); + if (q) + i40e_detect_recover_hung_queue(i, vsi); + } +} + /** * i40e_get_iscsi_tc_map - Return TC map for iSCSI APP * @pf: pointer to PF @@ -5758,68 +5871,6 @@ static void i40e_link_event(struct i40e_pf *pf) i40e_ptp_set_increment(pf); } -/** - * i40e_check_hang_subtask - Check for hung queues and dropped interrupts - * @pf: board private structure - * - * Set the per-queue flags to request a check for stuck queues in the irq - * clean functions, then force interrupts to be sure the irq clean is called. - **/ -static void i40e_check_hang_subtask(struct i40e_pf *pf) -{ - int i, v; - - /* If we're down or resetting, just bail */ - if (test_bit(__I40E_DOWN, &pf->state) || - test_bit(__I40E_CONFIG_BUSY, &pf->state)) - return; - - /* for each VSI/netdev - * for each Tx queue - * set the check flag - * for each q_vector - * force an interrupt - */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - int armed = 0; - - if (!pf->vsi[v] || - test_bit(__I40E_DOWN, &vsi->state) || - (vsi->netdev && !netif_carrier_ok(vsi->netdev))) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - set_check_for_tx_hang(vsi->tx_rings[i]); - if (test_bit(__I40E_HANG_CHECK_ARMED, - &vsi->tx_rings[i]->state)) - armed++; - } - - if (armed) { - if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) { - wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0, - (I40E_PFINT_DYN_CTL0_INTENA_MASK | - I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK | - I40E_PFINT_DYN_CTL0_ITR_INDX_MASK | - I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK | - I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK)); - } else { - u16 vec = vsi->base_vector - 1; - u32 val = (I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | - I40E_PFINT_DYN_CTLN_ITR_INDX_MASK | - I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | - I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK); - for (i = 0; i < vsi->num_q_vectors; i++, vec++) - wr32(&vsi->back->hw, - I40E_PFINT_DYN_CTLN(vec), val); - } - i40e_flush(&vsi->back->hw); - } - } -} - /** * i40e_watchdog_subtask - periodic checks not using event driven response * @pf: board private structure @@ -5839,7 +5890,6 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf) return; pf->service_timer_previous = jiffies; - i40e_check_hang_subtask(pf); i40e_link_event(pf); /* Update the stats for active netdevs so the network stack @@ -6807,6 +6857,7 @@ static void i40e_service_task(struct work_struct *work) return; } + i40e_detect_recover_hung(pf); i40e_reset_subtask(pf); i40e_handle_mdd_event(pf); i40e_vc_process_vflr_event(pf); @@ -10101,7 +10152,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&pf->service_task, i40e_service_task); clear_bit(__I40E_SERVICE_SCHED, &pf->state); pf->flags |= I40E_FLAG_NEED_LINK_UPDATE; - pf->link_check_timeout = jiffies; /* WoL defaults to disabled */ pf->wol_en = false; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 9a800f99ec13..4f9ff894d7c5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -600,7 +600,6 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) } } - /** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors @@ -608,7 +607,7 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -static u32 i40e_get_tx_pending(struct i40e_ring *ring) +u32 i40e_get_tx_pending(struct i40e_ring *ring) { u32 head, tail; @@ -622,50 +621,6 @@ static u32 i40e_get_tx_pending(struct i40e_ring *ring) return 0; } -/** - * i40e_check_tx_hang - Is there a hang in the Tx queue - * @tx_ring: the ring of descriptors - **/ -static bool i40e_check_tx_hang(struct i40e_ring *tx_ring) -{ - u32 tx_done = tx_ring->stats.packets; - u32 tx_done_old = tx_ring->tx_stats.tx_done_old; - u32 tx_pending = i40e_get_tx_pending(tx_ring); - struct i40e_pf *pf = tx_ring->vsi->back; - bool ret = false; - - clear_check_for_tx_hang(tx_ring); - - /* Check for a hung queue, but be thorough. This verifies - * that a transmit has been completed since the previous - * check AND there is at least one packet pending. The - * ARMED bit is set to indicate a potential hang. The - * bit is cleared if a pause frame is received to remove - * false hang detection due to PFC or 802.3x frames. By - * requiring this to fail twice we avoid races with - * PFC clearing the ARMED bit and conditions where we - * run the check_tx_hang logic with a transmit completion - * pending but without time to complete it yet. - */ - if ((tx_done_old == tx_done) && tx_pending) { - /* make sure it is true for two checks in a row */ - ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED, - &tx_ring->state); - } else if (tx_done_old == tx_done && - (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) { - if (I40E_DEBUG_FLOW & pf->hw.debug_mask) - dev_info(tx_ring->dev, "HW needs some more descs to do a cacheline flush. tx_pending %d, queue %d", - tx_pending, tx_ring->queue_index); - pf->tx_sluggish_count++; - } else { - /* update completed stats and disarm the hang check */ - tx_ring->tx_stats.tx_done_old = tx_done; - clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state); - } - - return ret; -} - #define WB_STRIDE 0x3 /** @@ -783,32 +738,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) else tx_ring->arm_wb = false; - if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) { - /* schedule immediate reset if we believe we hung */ - dev_info(tx_ring->dev, "Detected Tx Unit Hang\n" - " VSI <%d>\n" - " Tx Queue <%d>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n", - tx_ring->vsi->seid, - tx_ring->queue_index, - tx_ring->next_to_use, i); - - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - - dev_info(tx_ring->dev, - "tx hang detected on queue %d, reset requested\n", - tx_ring->queue_index); - - /* do not fire the reset immediately, wait for the stack to - * decide we are truly stuck, also prevents every queue from - * simultaneously requesting a reset - */ - - /* the adapter is about to reset, no point in enabling polling */ - budget = 1; - } - netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), total_packets, total_bytes); @@ -838,7 +767,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) * @q_vector: the vector on which to force writeback * **/ -static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 51487ef9eda3..977cb5b46115 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -199,8 +199,6 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, - __I40E_TX_DETECT_HANG, - __I40E_HANG_CHECK_ARMED, __I40E_RX_PS_ENABLED, __I40E_RX_16BYTE_DESC_ENABLED, }; @@ -211,12 +209,6 @@ enum i40e_ring_state_t { set_bit(__I40E_RX_PS_ENABLED, &(ring)->state) #define clear_ring_ps_enabled(ring) \ clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state) -#define check_for_tx_hang(ring) \ - test_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state) #define ring_is_16byte_desc_enabled(ring) \ test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state) #define set_ring_16byte_desc_enabled(ring) \ @@ -326,6 +318,8 @@ int i40e_xmit_descriptor_count(struct sk_buff *skb, struct i40e_ring *tx_ring); int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, struct i40e_ring *tx_ring, u32 *flags); #endif +void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); +u32 i40e_get_tx_pending(struct i40e_ring *ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 7e91d825c760..830979380466 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -140,65 +140,6 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) return le32_to_cpu(*(volatile __le32 *)head); } -/** - * i40e_get_tx_pending - how many tx descriptors not processed - * @tx_ring: the ring of descriptors - * - * Since there is no access to the ring head register - * in XL710, we need to use our local copies - **/ -static u32 i40e_get_tx_pending(struct i40e_ring *ring) -{ - u32 head, tail; - - head = i40e_get_head(ring); - tail = readl(ring->tail); - - if (head != tail) - return (head < tail) ? - tail - head : (tail + ring->count - head); - - return 0; -} - -/** - * i40e_check_tx_hang - Is there a hang in the Tx queue - * @tx_ring: the ring of descriptors - **/ -static bool i40e_check_tx_hang(struct i40e_ring *tx_ring) -{ - u32 tx_done = tx_ring->stats.packets; - u32 tx_done_old = tx_ring->tx_stats.tx_done_old; - u32 tx_pending = i40e_get_tx_pending(tx_ring); - bool ret = false; - - clear_check_for_tx_hang(tx_ring); - - /* Check for a hung queue, but be thorough. This verifies - * that a transmit has been completed since the previous - * check AND there is at least one packet pending. The - * ARMED bit is set to indicate a potential hang. The - * bit is cleared if a pause frame is received to remove - * false hang detection due to PFC or 802.3x frames. By - * requiring this to fail twice we avoid races with - * PFC clearing the ARMED bit and conditions where we - * run the check_tx_hang logic with a transmit completion - * pending but without time to complete it yet. - */ - if ((tx_done_old == tx_done) && tx_pending) { - /* make sure it is true for two checks in a row */ - ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED, - &tx_ring->state); - } else if (tx_done_old == tx_done && - (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) { - /* update completed stats and disarm the hang check */ - tx_ring->tx_stats.tx_done_old = tx_done; - clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state); - } - - return ret; -} - #define WB_STRIDE 0x3 /** @@ -304,6 +245,10 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; + /* check to see if there are any non-cache aligned descriptors + * waiting to be written back, and kick the hardware to force + * them to be written back in case of napi polling + */ if (budget && !((i & WB_STRIDE) == WB_STRIDE) && !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && @@ -312,29 +257,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) else tx_ring->arm_wb = false; - if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) { - /* schedule immediate reset if we believe we hung */ - dev_info(tx_ring->dev, "Detected Tx Unit Hang\n" - " VSI <%d>\n" - " Tx Queue <%d>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n", - tx_ring->vsi->seid, - tx_ring->queue_index, - tx_ring->next_to_use, i); - - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - - dev_info(tx_ring->dev, - "tx hang detected on queue %d, resetting adapter\n", - tx_ring->queue_index); - - tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev); - - /* the adapter is about to reset, no point in enabling stuff */ - return true; - } - netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), total_packets, total_bytes); @@ -355,16 +277,16 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) } } - return budget > 0; + return !!budget; } /** - * i40e_force_wb -Arm hardware to do a wb on noncache aligned descriptors + * i40evf_force_wb -Arm hardware to do a wb on noncache aligned descriptors * @vsi: the VSI we care about * @q_vector: the vector on which to force writeback * **/ -static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; @@ -1385,7 +1307,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { if (arm_wb) - i40e_force_wb(vsi, q_vector); + i40evf_force_wb(vsi, q_vector); return budget; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 9a30f5d8c089..d5cb7aca87b4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -198,8 +198,6 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, - __I40E_TX_DETECT_HANG, - __I40E_HANG_CHECK_ARMED, __I40E_RX_PS_ENABLED, __I40E_RX_16BYTE_DESC_ENABLED, }; @@ -210,12 +208,6 @@ enum i40e_ring_state_t { set_bit(__I40E_RX_PS_ENABLED, &(ring)->state) #define clear_ring_ps_enabled(ring) \ clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state) -#define check_for_tx_hang(ring) \ - test_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state) #define ring_is_16byte_desc_enabled(ring) \ test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state) #define set_ring_16byte_desc_enabled(ring) \ From c1d1791dc8b2a13c316a4e163552804361a786a4 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Fri, 25 Sep 2015 19:26:04 +0000 Subject: [PATCH 3/6] i40e: add GRE tunnel type to csum encoding Make sure the Tx checksum encoder knows about GRE protocol and sets the descriptor flag appropriately. Signed-off-by: Shannon Nelson Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 4f9ff894d7c5..d699fc941a77 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2240,6 +2240,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; break; + case IPPROTO_GRE: + l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING; + break; default: return; } From 5804474311912c1b80601a1afee052e8df962cd4 Mon Sep 17 00:00:00 2001 From: Anjali Singhai Date: Fri, 25 Sep 2015 18:26:13 -0700 Subject: [PATCH 4/6] i40e: Fix RS bit update in Tx path and disable force WB workaround This patch fixes the issue of forcing WB too often causing us to not benefit from NAPI. Without this patch we were forcing WB/arming interrupt too often taking away the benefits of NAPI and causing a performance impact. With this patch we disable force WB in the clean routine for X710 and XL710 adapters. X722 adapters do not enable interrupt to force a WB and benefit from WB_ON_ITR and hence force WB is left enabled for those adapters. For XL710 and X710 adapters if we have less than 4 packets pending a software Interrupt triggered from service task will force a WB. This patch also changes the conditions for setting RS bit as described in code comments. This optimizes when the HW does a tail bump and when it does a WB. It also optimizes when we do a wmb. Signed-off-by: Anjali Singhai Jain Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 129 +++++++++++++------- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 + 2 files changed, 87 insertions(+), 44 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d699fc941a77..3ce4900c0c43 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -726,17 +726,22 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; - /* check to see if there are any non-cache aligned descriptors - * waiting to be written back, and kick the hardware to force - * them to be written back in case of napi polling - */ - if (budget && - !((i & WB_STRIDE) == WB_STRIDE) && - !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; - else - tx_ring->arm_wb = false; + if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + unsigned int j = 0; + + /* check to see if there are < 4 descriptors + * waiting to be written back, then kick the hardware to force + * them to be written back in case we stay in NAPI. + * In this mode on X722 we do not enable Interrupt. + */ + j = i40e_get_tx_pending(tx_ring); + + if (budget && + ((j / (WB_STRIDE + 1)) == 0) && (j != 0) && + !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + } netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), @@ -2500,6 +2505,9 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, u32 td_tag = 0; dma_addr_t dma; u16 gso_segs; + u16 desc_count = 0; + bool tail_bump = true; + bool do_rs = false; if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; @@ -2540,6 +2548,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; + desc_count++; + if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); i = 0; @@ -2559,6 +2569,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; + desc_count++; + if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); i = 0; @@ -2573,34 +2585,6 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = &tx_ring->tx_bi[i]; } - /* Place RS bit on last descriptor of any packet that spans across the - * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline. - */ - if (((i & WB_STRIDE) != WB_STRIDE) && - (first <= &tx_ring->tx_bi[i]) && - (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) { - tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP << - I40E_TXD_QW1_CMD_SHIFT); - } else { - tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)I40E_TXD_CMD << - I40E_TXD_QW1_CMD_SHIFT); - } - - netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->queue_index), - first->bytecount); - - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - /* set next_to_watch value indicating a packet is present */ first->next_to_watch = tx_desc; @@ -2610,15 +2594,72 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; + netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index), + first->bytecount); i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + + /* Algorithm to optimize tail and RS bit setting: + * if xmit_more is supported + * if xmit_more is true + * do not update tail and do not mark RS bit. + * if xmit_more is false and last xmit_more was false + * if every packet spanned less than 4 desc + * then set RS bit on 4th packet and update tail + * on every packet + * else + * update tail and set RS bit on every packet. + * if xmit_more is false and last_xmit_more was true + * update tail and set RS bit. + * + * Optimization: wmb to be issued only in case of tail update. + * Also optimize the Descriptor WB path for RS bit with the same + * algorithm. + * + * Note: If there are less than 4 packets + * pending and interrupts were disabled the service task will + * trigger a force WB. + */ + if (skb->xmit_more && + !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index))) { + tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; + tail_bump = false; + } else if (!skb->xmit_more && + !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index)) && + (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) && + (tx_ring->packet_stride < WB_STRIDE) && + (desc_count < WB_STRIDE)) { + tx_ring->packet_stride++; + } else { + tx_ring->packet_stride = 0; + tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; + do_rs = true; + } + if (do_rs) + tx_ring->packet_stride = 0; + + tx_desc->cmd_type_offset_bsz = + build_ctob(td_cmd, td_offset, size, td_tag) | + cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD : + I40E_TX_DESC_CMD_EOP) << + I40E_TXD_QW1_CMD_SHIFT); + /* notify HW of packet */ - if (!skb->xmit_more || - netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->queue_index))) - writel(i, tx_ring->tail); - else + if (!tail_bump) prefetchw(tx_desc + 1); + if (tail_bump) { + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, tx_ring->tail); + } + return; dma_error: diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 977cb5b46115..a3978c2b5fc9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -256,10 +256,12 @@ struct i40e_ring { bool ring_active; /* is ring online or not */ bool arm_wb; /* do something to arm write back */ + u8 packet_stride; u16 flags; #define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) #define I40E_TXR_FLAGS_OUTER_UDP_CSUM BIT(1) +#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2) /* stats structs */ struct i40e_queue_stats stats; From 30e2561b95295258890b4e0366ce867e04d34a97 Mon Sep 17 00:00:00 2001 From: Anjali Singhai Date: Mon, 28 Sep 2015 13:37:12 -0700 Subject: [PATCH 5/6] i40e: Fix for recursive RTNL lock during PROMISC change The sync_vsi_filters function can be called directly under RTNL or through the timer subtask without one. This was causing a deadlock. If sync_vsi_filters is called from a thread which held the lock, and in another thread the PROMISC setting got changed we would be executing the PROMISC change in the thread which already held the lock alongside the other filter update. The PROMISC change requires a reset if we are on a VEB, which requires it to be called under RTNL. Earlier the driver would call reset for PROMISC change without checking if we were already under RTNL and would try to grab it causing a deadlock. This patch changes the flow to see if we are already under RTNL before trying to grab it. Signed-off-by: Anjali Singhai Jain Signed-off-by: Kiran Patil Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 2 +- .../net/ethernet/intel/i40e/i40e_debugfs.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 19 ++++++++++++------- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 8 ++++---- 4 files changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4797269d1200..c64d18d4cb2d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -666,7 +666,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, bool is_vf, bool is_netdev); void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, bool is_vf, bool is_netdev); -int i40e_sync_vsi_filters(struct i40e_vsi *vsi); +int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); int i40e_vsi_release(struct i40e_vsi *vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d7c15d17faa6..508efb034e87 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1146,7 +1146,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, } f = i40e_add_filter(vsi, ma, vlan, false, false); - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, true); if (f && !ret) dev_info(&pf->pdev->dev, "add macaddr: %pM vlan=%d added to VSI %d\n", @@ -1183,7 +1183,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, } i40e_del_filter(vsi, ma, vlan, false, false); - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, true); if (!ret) dev_info(&pf->pdev->dev, "del macaddr: %pM vlan=%d removed from VSI %d\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c246dca5de71..52e58f304b21 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1527,7 +1527,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) f->is_laa = true; } - i40e_sync_vsi_filters(vsi); + i40e_sync_vsi_filters(vsi, false); ether_addr_copy(netdev->dev_addr, addr->sa_data); return 0; @@ -1764,12 +1764,13 @@ static void i40e_set_rx_mode(struct net_device *netdev) /** * i40e_sync_vsi_filters - Update the VSI filter list to the HW * @vsi: ptr to the VSI + * @grab_rtnl: whether RTNL needs to be grabbed * * Push any outstanding VSI filter changes through the AdminQ. * * Returns 0 or error value **/ -int i40e_sync_vsi_filters(struct i40e_vsi *vsi) +int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) { struct i40e_mac_filter *f, *ftmp; bool promisc_forced_on = false; @@ -1958,7 +1959,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) */ if (pf->cur_promisc != cur_promisc) { pf->cur_promisc = cur_promisc; - i40e_do_reset_safe(pf, + if (grab_rtnl) + i40e_do_reset_safe(pf, + BIT(__I40E_PF_RESET_REQUESTED)); + else + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); } } else { @@ -2009,7 +2014,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) - i40e_sync_vsi_filters(pf->vsi[v]); + i40e_sync_vsi_filters(pf->vsi[v], true); } } @@ -2216,7 +2221,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; - return i40e_sync_vsi_filters(vsi); + return i40e_sync_vsi_filters(vsi, false); } /** @@ -2288,7 +2293,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; - return i40e_sync_vsi_filters(vsi); + return i40e_sync_vsi_filters(vsi, false); } /** @@ -8821,7 +8826,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) i40e_del_filter(vsi, f->macaddr, f->vlan, f->is_vf, f->is_netdev); - i40e_sync_vsi_filters(vsi); + i40e_sync_vsi_filters(vsi, false); i40e_vsi_delete(vsi); i40e_vsi_free_q_vectors(vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index d99c116032f3..eacce9389962 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -561,7 +561,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) } /* program mac filter */ - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, false); if (ret) dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); @@ -1605,7 +1605,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } /* program the updated filter list */ - if (i40e_sync_vsi_filters(vsi)) + if (i40e_sync_vsi_filters(vsi, false)) dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n"); error_param: @@ -1656,7 +1656,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) I40E_VLAN_ANY, true, false); /* program the updated filter list */ - if (i40e_sync_vsi_filters(vsi)) + if (i40e_sync_vsi_filters(vsi, false)) dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n"); error_param: @@ -2062,7 +2062,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id); /* program mac filter */ - if (i40e_sync_vsi_filters(vsi)) { + if (i40e_sync_vsi_filters(vsi, false)) { dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); ret = -EIO; goto error_param; From cbfe360a1541a32e9e28f8f8ac925d2b7979d767 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Thu, 17 Sep 2015 14:46:10 +0200 Subject: [PATCH 6/6] igb: assume MSI-X interrupts during initialization In igb_sw_init() the sequence of calls was changed from igb_init_queue_configuration() igb_init_interrupt_scheme() igb_probe_vfs() to igb_probe_vfs() igb_init_queue_configuration() igb_init_interrupt_scheme() This results in adapter->flags not having the IGB_FLAG_HAS_MSIX bit set during igb_probe_vfs()->igb_enable_sriov(). Therefore SR-IOV does not get enabled properly and we run into a NULL pointer if the max_vfs module parameter is specified (adapter->vf_data does not get allocated, crash on accessing the structure). [ 7.419348] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 [ 7.419367] IP: [] igb_reset+0xe6/0x5d0 [igb] [ 7.419370] PGD 0 [ 7.419373] Oops: 0002 [#1] SMP [ 7.419381] Modules linked in: ahci(+) libahci igb(+) i40e(+) vxlan ip6_udp_tunnel udp_tunnel megaraid_sas(+) ixgbe(+) mdio [ 7.419385] CPU: 0 PID: 4 Comm: kworker/0:0 Not tainted 4.2.0+ #153 [ 7.419387] Hardware name: Dell Inc. PowerEdge R720/0C4Y3R, BIOS 1.6.0 03/07/2013 [...] [ 7.419431] Call Trace: [ 7.419442] [] igb_probe+0x8b6/0x1340 [igb] [ 7.419447] [] local_pci_probe+0x45/0xa0 Prevent this by setting the IGB_FLAG_HAS_MSIX bit before calling igb_probe_vfs(). The real interrupt capabilities will be checked during igb_init_interrupt_scheme() so this is safe to do. Signed-off-by: Stefan Assmann Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index e174fbbdba40..ba019fc87fd1 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2986,6 +2986,9 @@ static int igb_sw_init(struct igb_adapter *adapter) } #endif /* CONFIG_PCI_IOV */ + /* Assume MSI-X interrupts, will be checked during IRQ allocation */ + adapter->flags |= IGB_FLAG_HAS_MSIX; + igb_probe_vfs(adapter); igb_init_queue_configuration(adapter);