diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40evf')
21 files changed, 1624 insertions, 292 deletions
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index a393f4a07f06..1e89c5487676 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ################################################################################ # # Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index d1aab6b8bfb1..6fd677efa9da 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index e0bfaa3d4a21..a7137c165256 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 815de8d9c3fb..439e71882049 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h index 8e6a6dd9212b..7e0fddd8af36 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 67bf5cebb76f..67140cdbcd7a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h index 0469e4bfd3ec..352dd3f3eb6a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h index 00ed24bfce13..7432596164f4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h index a5d79877354c..ddac0e4908d3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h index a90737786c34..8668ad6c1a65 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index 47c429931a57..72501bd0f1a9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h index 10febcfd7cd8..c9c935659758 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_register.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_register.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/i40evf/i40e_status.h index 5b222246e08b..0d7993ecb99a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_status.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_status.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/i40evf/i40e_trace.h index 9a5100b2b7c7..ece01dd12a3c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel(R) 40-10 Gigabit Ethernet Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 357d6051281f..12bd937861e7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -196,7 +197,7 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40evf_get_tx_pending(tx_ring, false) ? packets : -1; + i40evf_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -392,99 +393,241 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) val); } +static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) +{ + return &q_vector->rx == rc; +} + +static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +{ + unsigned int divisor; + + switch (q_vector->adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + break; + case I40E_LINK_SPEED_25GB: + case I40E_LINK_SPEED_20GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + break; + default: + case I40E_LINK_SPEED_10GB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + break; + case I40E_LINK_SPEED_1GB: + case I40E_LINK_SPEED_100MB: + divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + break; + } + + return divisor; +} + /** - * i40e_set_new_dynamic_itr - Find new ITR level + * i40e_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * - * Returns true if ITR changed, false if not - * - * Stores a new ITR value based on packets and byte counts during - * the last interrupt. The advantage of per interrupt computation - * is faster updates and more accurate ITR for the current traffic - * pattern. Constants in this function were computed based on - * theoretical maximum wire speed and thresholds were set based on - * testing data as well as attempting to minimize response time + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) +static void i40e_update_itr(struct i40e_q_vector *q_vector, + struct i40e_ring_container *rc) { - enum i40e_latency_range new_latency_range = rc->latency_range; - u32 new_itr = rc->itr; - int bytes_per_usec; - unsigned int usecs, estimated_usecs; + unsigned int avg_wire_size, packets, bytes, itr; + unsigned long next_update = jiffies; - if (rc->total_packets == 0 || !rc->itr) - return false; + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!rc->ring || !ITR_IS_DYNAMIC(rc->ring->itr_setting)) + return; + + /* For Rx we want to push the delay up and default to low latency. + * for Tx we want to pull the delay down and default to high latency. + */ + itr = i40e_container_is_rx(q_vector, rc) ? + I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : + I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, rc->next_update)) + goto clear_counts; + + /* If itr_countdown is set it means we programmed an ITR within + * the last 4 interrupt cycles. This has a side effect of us + * potentially firing an early interrupt. In order to work around + * this we need to throw out any data received for a few + * interrupts following the update. + */ + if (q_vector->itr_countdown) { + itr = rc->target_itr; + goto clear_counts; + } + + packets = rc->total_packets; + bytes = rc->total_bytes; - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_usec = rc->total_bytes / usecs; + if (i40e_container_is_rx(q_vector, rc)) { + /* If Rx there are 1 to 4 packets and bytes are less than + * 9000 assume insufficient data to use bulk rate limiting + * approach unless Tx is already in bulk rate limiting. We + * are likely latency driven. + */ + if (packets && packets < 4 && bytes < 9000 && + (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { + itr = I40E_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + } else if (packets < 4) { + /* If we have Tx and Rx ITR maxed and Tx ITR is running in + * bulk mode and we are receiving 4 or fewer packets just + * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so + * that the Rx can relax. + */ + if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & I40E_ITR_MASK) == + I40E_ITR_ADAPTIVE_MAX_USECS) + goto clear_counts; + } else if (packets > 32) { + /* If we have processed over 32 packets in a single interrupt + * for Tx assume we need to switch over to "bulk" mode. + */ + rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + } - /* The calculations in this algorithm depend on interrupts actually - * firing at the ITR rate. This may not happen if the packet rate is - * really low, or if we've been napi polling. Check to make sure - * that's not the case before we continue. + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * Between 4 and 56 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. */ - estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); - if (estimated_usecs > usecs) { - new_latency_range = I40E_LOW_LATENCY; - goto reset_latency; + if (packets < 56) { + itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; + } + goto clear_counts; + } + + if (packets <= 256) { + itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); + itr &= I40E_ITR_MASK; + + /* Between 56 and 112 is our "goldilocks" zone where we are + * working out "just right". Just report that our current + * ITR is good for us. + */ + if (packets <= 112) + goto clear_counts; + + /* If packet count is 128 or greater we are likely looking + * at a slight overrun of the delay we want. Try halving + * our delay to see if that will cut the number of packets + * in half per interrupt. + */ + itr /= 2; + itr &= I40E_ITR_MASK; + if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) + itr = I40E_ITR_ADAPTIVE_MIN_USECS; + + goto clear_counts; } - /* simple throttlerate management - * 0-10MB/s lowest (50000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (18000 ints/s) + /* The paths below assume we are dealing with a bulk ITR since + * number of packets is greater than 256. We are just going to have + * to compute a value and try to bring the count under control, + * though for smaller packet sizes there isn't much we can do as + * NAPI polling will likely be kicking in sooner rather than later. + */ + itr = I40E_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value * - * The math works out because the divisor is in 10^(-6) which - * turns the bytes/us input value into MB/s values, but - * make sure to use usecs, as the register values written - * are in 2 usec increments in the ITR registers, and make sure - * to use the smoothed values that the countdown timer gives us. + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. */ - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - if (bytes_per_usec > 10) - new_latency_range = I40E_LOW_LATENCY; - break; - case I40E_LOW_LATENCY: - if (bytes_per_usec > 20) - new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_usec <= 10) - new_latency_range = I40E_LOWEST_LATENCY; - break; - case I40E_BULK_LATENCY: - default: - if (bytes_per_usec <= 20) - new_latency_range = I40E_LOW_LATENCY; - break; + if (avg_wire_size <= 60) { + /* Start at 250k ints/sec */ + avg_wire_size = 4096; + } else if (avg_wire_size <= 380) { + /* 250K ints/sec to 60K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 1696; + } else if (avg_wire_size <= 1084) { + /* 60K ints/sec to 36K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 36K ints/sec to 30K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 30K ints/sec */ + avg_wire_size = 32256; } -reset_latency: - rc->latency_range = new_latency_range; + /* If we are in low latency mode halve our delay which doubles the + * rate to somewhere between 100K to 16K ints/sec + */ + if (itr & I40E_ITR_ADAPTIVE_LATENCY) + avg_wire_size /= 2; - switch (new_latency_range) { - case I40E_LOWEST_LATENCY: - new_itr = I40E_ITR_50K; - break; - case I40E_LOW_LATENCY: - new_itr = I40E_ITR_20K; - break; - case I40E_BULK_LATENCY: - new_itr = I40E_ITR_18K; - break; - default: - break; + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * + I40E_ITR_ADAPTIVE_MIN_INC; + + if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { + itr &= I40E_ITR_ADAPTIVE_LATENCY; + itr += I40E_ITR_ADAPTIVE_MAX_USECS; } +clear_counts: + /* write back value */ + rc->target_itr = itr; + + /* next update should occur within next jiffy */ + rc->next_update = next_update + 1; + rc->total_bytes = 0; rc->total_packets = 0; - rc->last_itr_update = jiffies; - - if (new_itr != rc->itr) { - rc->itr = new_itr; - return true; - } - return false; } /** @@ -1273,7 +1416,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will - * either recycle the bufer or unmap it and free the associated resources. + * either recycle the buffer or unmap it and free the associated resources. */ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer) @@ -1457,33 +1600,45 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static u32 i40e_buildreg_itr(const int type, const u16 itr) +static inline u32 i40e_buildreg_itr(const int type, u16 itr) { u32 val; + /* We don't bother with setting the CLEARPBA bit as the data sheet + * points out doing so is "meaningless since it was already + * auto-cleared". The auto-clearing happens when the interrupt is + * asserted. + * + * Hardware errata 28 for also indicates that writing to a + * xxINT_DYN_CTLx CSR with INTENA_MSK (bit 31) set to 0 will clear + * an event in the PBA anyway so we need to rely on the automask + * to hold pending events for us until the interrupt is re-enabled + * + * The itr value is reported in microseconds, and the register + * value is recorded in 2 microsecond units. For this reason we + * only need to shift by the interval shift - 1 instead of the + * full value. + */ + itr &= I40E_ITR_MASK; + val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); + (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ #define INTREG I40E_VFINT_DYN_CTLN1 -static inline int get_rx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - return adapter->rx_rings[idx].rx_itr_setting; -} - -static inline int get_tx_itr(struct i40e_vsi *vsi, int idx) -{ - struct i40evf_adapter *adapter = vsi->back; - - return adapter->tx_rings[idx].tx_itr_setting; -} +/* The act of updating the ITR will cause it to immediately trigger. In order + * to prevent this from throwing off adaptive update statistics we defer the + * update so that it can only happen so often. So after either Tx or Rx are + * updated we make the adaptive scheme wait until either the ITR completely + * expires via the next_update expiration or we have been through at least + * 3 interrupts. + */ +#define ITR_COUNTDOWN_START 3 /** * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt @@ -1495,70 +1650,51 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { struct i40e_hw *hw = &vsi->back->hw; - bool rx = false, tx = false; - u32 rxval, txval; - int idx = q_vector->v_idx; - int rx_itr_setting, tx_itr_setting; - - /* avoid dynamic calculation if in countdown mode OR if - * all dynamic is disabled - */ - rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0); - - rx_itr_setting = get_rx_itr(vsi, idx); - tx_itr_setting = get_tx_itr(vsi, idx); + u32 intval; - if (q_vector->itr_countdown > 0 || - (!ITR_IS_DYNAMIC(rx_itr_setting) && - !ITR_IS_DYNAMIC(tx_itr_setting))) { - goto enable_int; - } - - if (ITR_IS_DYNAMIC(rx_itr_setting)) { - rx = i40e_set_new_dynamic_itr(&q_vector->rx); - rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr); - } + /* These will do nothing if dynamic updates are not enabled */ + i40e_update_itr(q_vector, &q_vector->tx); + i40e_update_itr(q_vector, &q_vector->rx); - if (ITR_IS_DYNAMIC(tx_itr_setting)) { - tx = i40e_set_new_dynamic_itr(&q_vector->tx); - txval = i40e_buildreg_itr(I40E_TX_ITR, q_vector->tx.itr); - } - - if (rx || tx) { - /* get the higher of the two ITR adjustments and - * use the same value for both ITR registers - * when in adaptive mode (Rx and/or Tx) - */ - u16 itr = max(q_vector->tx.itr, q_vector->rx.itr); - - q_vector->tx.itr = q_vector->rx.itr = itr; - txval = i40e_buildreg_itr(I40E_TX_ITR, itr); - tx = true; - rxval = i40e_buildreg_itr(I40E_RX_ITR, itr); - rx = true; - } - - /* only need to enable the interrupt once, but need - * to possibly update both ITR values + /* This block of logic allows us to get away with only updating + * one ITR value with each interrupt. The idea is to perform a + * pseudo-lazy update with the following criteria. + * + * 1. Rx is given higher priority than Tx if both are in same state + * 2. If we must reduce an ITR that is given highest priority. + * 3. We then give priority to increasing ITR based on amount. */ - if (rx) { - /* set the INTENA_MSK_MASK so that this first write - * won't actually enable the interrupt, instead just - * updating the ITR (it's bit 31 PF and VF) + if (q_vector->rx.target_itr < q_vector->rx.current_itr) { + /* Rx ITR needs to be reduced, this is highest priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) || + ((q_vector->rx.target_itr - q_vector->rx.current_itr) < + (q_vector->tx.target_itr - q_vector->tx.current_itr))) { + /* Tx ITR needs to be reduced, this is second priority + * Tx ITR needs to be increased more than Rx, fourth priority */ - rxval |= BIT(31); - /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(q_vector->reg_idx), rxval); + intval = i40e_buildreg_itr(I40E_TX_ITR, + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { + /* Rx ITR needs to be increased, third priority */ + intval = i40e_buildreg_itr(I40E_RX_ITR, + q_vector->rx.target_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; + q_vector->itr_countdown = ITR_COUNTDOWN_START; + } else { + /* No ITR update, lowest priority */ + intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + if (q_vector->itr_countdown) + q_vector->itr_countdown--; } -enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(q_vector->reg_idx), txval); - - if (q_vector->itr_countdown) - q_vector->itr_countdown--; - else - q_vector->itr_countdown = ITR_COUNTDOWN_START; + wr32(hw, INTREG(q_vector->reg_idx), intval); } /** diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 7798a6645c3f..5790897eae2e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -28,31 +29,35 @@ #define _I40E_TXRX_H_ /* Interrupt Throttling and Rate Limiting Goodies */ - -#define I40E_MAX_ITR 0x0FF0 /* reg uses 2 usec resolution */ -#define I40E_MIN_ITR 0x0001 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 0x0005 -#define I40E_ITR_50K 0x000A -#define I40E_ITR_20K 0x0019 -#define I40E_ITR_18K 0x001B -#define I40E_ITR_8K 0x003E -#define I40E_ITR_4K 0x007A -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ - I40E_ITR_DYNAMIC) -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ -#define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ #define I40E_DEFAULT_IRQ_WORK 256 -#define ITR_TO_REG(setting) ((setting & ~I40E_ITR_DYNAMIC) >> 1) -#define ITR_IS_DYNAMIC(setting) (!!(setting & I40E_ITR_DYNAMIC)) -#define ITR_REG_TO_USEC(itr_reg) (itr_reg << 1) + +/* The datasheet for the X710 and XL710 indicate that the maximum value for + * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec + * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing + * the register value which is divided by 2 lets use the actual values and + * avoid an excessive amount of translation. + */ +#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define I40E_ITR_100K 10 /* all values below must be even */ +#define I40E_ITR_50K 20 +#define I40E_ITR_20K 50 +#define I40E_ITR_18K 60 +#define I40E_ITR_8K 122 +#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) + +#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) + /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) +#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) #define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) #define I40E_INTRL_8K 125 /* 8000 ints/sec */ @@ -362,8 +367,7 @@ struct i40e_ring { * these values always store the USER setting, and must be converted * before programming to a register. */ - u16 rx_itr_setting; - u16 tx_itr_setting; + u16 itr_setting; u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -425,21 +429,21 @@ static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; } -enum i40e_latency_range { - I40E_LOWEST_LATENCY = 0, - I40E_LOW_LATENCY = 1, - I40E_BULK_LATENCY = 2, -}; +#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 +#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e +#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 +#define I40E_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) struct i40e_ring_container { - /* array of pointers to rings */ - struct i40e_ring *ring; + struct i40e_ring *ring; /* pointer to linked list of ring(s) */ + unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ - unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; - enum i40e_latency_range latency_range; - u16 itr; + u16 target_itr; /* target ITR setting for ring(s) */ + u16 current_itr; /* current ITR setting for ring(s) */ }; /* iterator for handling rings in ring container */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 54951c84a481..449de4b0058e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 9690c1ea019e..3a7a1e77bf39 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -52,7 +53,10 @@ #include <linux/socket.h> #include <linux/jiffies.h> #include <net/ip6_checksum.h> +#include <net/pkt_cls.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> #include "i40e_type.h" #include <linux/avf/virtchnl.h> @@ -106,6 +110,7 @@ struct i40e_vsi { #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ /* MAX_MSIX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. @@ -117,9 +122,8 @@ struct i40e_q_vector { struct i40e_ring_container rx; struct i40e_ring_container tx; u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ u8 num_ringpairs; /* total number of ring pairs in vector */ -#define ITR_COUNTDOWN_START 100 - u8 itr_countdown; /* when 0 or 1 update ITR */ u16 v_idx; /* index in the vsi->q_vector array. */ u16 reg_idx; /* register index of the interrupt */ char name[IFNAMSIZ + 15]; @@ -169,6 +173,28 @@ struct i40evf_vlan_filter { bool add; /* filter needs to be added */ }; +#define I40EVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum i40evf_tc_state_t { + __I40EVF_TC_INVALID, /* no traffic class, default state */ + __I40EVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct i40evf_channel_config { + struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS]; + enum i40evf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum i40evf_cloud_filter_state_t { + __I40EVF_CF_INVALID, /* cloud filter not added */ + __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __I40EVF_CF_ACTIVE, /* cloud filter is active */ +}; + /* Driver state. The order of these is important! */ enum i40evf_state_t { __I40EVF_STARTUP, /* driver loaded, probe complete */ @@ -190,6 +216,36 @@ enum i40evf_critical_section_t { __I40EVF_IN_REMOVE_TASK, /* device being removed */ }; +#define I40EVF_CLOUD_FIELD_OMAC 0x01 +#define I40EVF_CLOUD_FIELD_IMAC 0x02 +#define I40EVF_CLOUD_FIELD_IVLAN 0x04 +#define I40EVF_CLOUD_FIELD_TEN_ID 0x08 +#define I40EVF_CLOUD_FIELD_IIP 0x10 + +#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC +#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC +#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN) +#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\ + I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ + I40EVF_CLOUD_FIELD_IVLAN |\ + I40EVF_CLOUD_FIELD_TEN_ID) +#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct i40evf_cloud_filter { + enum i40evf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + /* board specific private data structure */ struct i40evf_adapter { struct timer_list watchdog_timer; @@ -225,13 +281,10 @@ struct i40evf_adapter { u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IMIR_ENABLED BIT(1) -#define I40EVF_FLAG_MQ_CAPABLE BIT(2) #define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) #define I40EVF_FLAG_RESET_PENDING BIT(4) #define I40EVF_FLAG_RESET_NEEDED BIT(5) #define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(7) #define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) #define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) @@ -241,6 +294,7 @@ struct i40evf_adapter { #define I40EVF_FLAG_ALLMULTI_ON BIT(14) #define I40EVF_FLAG_LEGACY_RX BIT(15) #define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define I40EVF_FLAG_QUEUES_DISABLED BIT(17) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED @@ -269,6 +323,10 @@ struct i40evf_adapter { #define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) #define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) #define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) /* OS defined structs */ struct net_device *netdev; @@ -314,6 +372,13 @@ struct i40evf_adapter { u16 rss_lut_size; u8 *rss_key; u8 *rss_lut; + /* ADQ related members */ + struct i40evf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protest access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; }; @@ -380,4 +445,8 @@ void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); void i40evf_notify_client_open(struct i40e_vsi *vsi); void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); +void i40evf_enable_channels(struct i40evf_adapter *adapter); +void i40evf_disable_channels(struct i40evf_adapter *adapter); +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter); +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index e2d8aa19d205..dc4cde274fb8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -457,14 +458,14 @@ static int __i40evf_get_coalesce(struct net_device *netdev, rx_ring = &adapter->rx_rings[queue]; tx_ring = &adapter->tx_rings[queue]; - if (ITR_IS_DYNAMIC(rx_ring->rx_itr_setting)) + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) ec->use_adaptive_rx_coalesce = 1; - if (ITR_IS_DYNAMIC(tx_ring->tx_itr_setting)) + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) ec->use_adaptive_tx_coalesce = 1; - ec->rx_coalesce_usecs = rx_ring->rx_itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->tx_itr_setting & ~I40E_ITR_DYNAMIC; + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; return 0; } @@ -502,7 +503,7 @@ static int i40evf_get_per_queue_coalesce(struct net_device *netdev, /** * i40evf_set_itr_per_queue - set ITR values for specific queue - * @vsi: the VSI to set values for + * @adapter: the VF adapter struct to set values for * @ec: coalesce settings from ethtool * @queue: the queue to modify * @@ -514,33 +515,29 @@ static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, { struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; - struct i40e_vsi *vsi = &adapter->vsi; - struct i40e_hw *hw = &adapter->hw; struct i40e_q_vector *q_vector; - u16 vector; - rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; - tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_rx_coalesce) - rx_ring->rx_itr_setting ^= I40E_ITR_DYNAMIC; + rx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->itr_setting |= I40E_ITR_DYNAMIC; if (!ec->use_adaptive_tx_coalesce) - tx_ring->tx_itr_setting ^= I40E_ITR_DYNAMIC; + tx_ring->itr_setting ^= I40E_ITR_DYNAMIC; q_vector = rx_ring->q_vector; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, vector - 1), q_vector->rx.itr); + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector = tx_ring->q_vector; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - vector = vsi->base_vector + q_vector->v_idx; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, vector - 1), q_vector->tx.itr); + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - i40e_flush(hw); + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ } /** @@ -565,8 +562,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->rx_coalesce_usecs == 0) { if (ec->use_adaptive_rx_coalesce) netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) || + (ec->rx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; } @@ -575,8 +572,8 @@ static int __i40evf_set_coalesce(struct net_device *netdev, if (ec->tx_coalesce_usecs == 0) { if (ec->use_adaptive_tx_coalesce) netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1))) { + } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) || + (ec->tx_coalesce_usecs > I40E_MAX_ITR)) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } @@ -699,6 +696,12 @@ static int i40evf_set_channels(struct net_device *netdev, return -EINVAL; } + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 16989ad2ca90..5f71532be7f1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -353,11 +354,12 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) rx_ring->vsi = &adapter->vsi; q_vector->rx.ring = rx_ring; q_vector->rx.count++; - q_vector->rx.latency_range = I40E_LOW_LATENCY; - q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); + q_vector->rx.next_update = jiffies + 1; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); - q_vector->itr_countdown = ITR_COUNTDOWN_START; - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, v_idx - 1), q_vector->rx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx), + q_vector->rx.current_itr); + q_vector->rx.current_itr = q_vector->rx.target_itr; } /** @@ -378,11 +380,12 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) tx_ring->vsi = &adapter->vsi; q_vector->tx.ring = tx_ring; q_vector->tx.count++; - q_vector->tx.latency_range = I40E_LOW_LATENCY; - q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); - q_vector->itr_countdown = ITR_COUNTDOWN_START; + q_vector->tx.next_update = jiffies + 1; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, v_idx - 1), q_vector->tx.itr); + wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx), + q_vector->tx.target_itr); + q_vector->tx.current_itr = q_vector->tx.target_itr; } /** @@ -783,7 +786,7 @@ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, **/ static struct i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; @@ -806,20 +809,18 @@ i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, **/ static struct i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, - u8 *macaddr) + const u8 *macaddr) { struct i40evf_mac_filter *f; if (!macaddr) return NULL; - spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_filter(adapter, macaddr); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) - goto clearout; + return f; ether_addr_copy(f->macaddr, macaddr); @@ -830,8 +831,6 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, f->remove = false; } -clearout: - spin_unlock_bh(&adapter->mac_vlan_list_lock); return f; } @@ -866,9 +865,10 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; } + f = i40evf_add_filter(adapter, addr->sa_data); + spin_unlock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_add_filter(adapter, addr->sa_data); if (f) { ether_addr_copy(hw->mac.addr, addr->sa_data); ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); @@ -878,50 +878,64 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) } /** - * i40evf_set_rx_mode - NDO callback to set the netdev filters - * @netdev: network interface device structure - **/ -static void i40evf_set_rx_mode(struct net_device *netdev) + * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be added. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr) { struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_mac_filter *f, *ftmp; - struct netdev_hw_addr *uca; - struct netdev_hw_addr *mca; - struct netdev_hw_addr *ha; - - /* add addr if not already in the filter list */ - netdev_for_each_uc_addr(uca, netdev) { - i40evf_add_filter(adapter, uca->addr); - } - netdev_for_each_mc_addr(mca, netdev) { - i40evf_add_filter(adapter, mca->addr); - } - spin_lock_bh(&adapter->mac_vlan_list_lock); - - list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { - netdev_for_each_mc_addr(mca, netdev) - if (ether_addr_equal(mca->addr, f->macaddr)) - goto bottom_of_search_loop; - - netdev_for_each_uc_addr(uca, netdev) - if (ether_addr_equal(uca->addr, f->macaddr)) - goto bottom_of_search_loop; + if (i40evf_add_filter(adapter, addr)) + return 0; + else + return -ENOMEM; +} - for_each_dev_addr(netdev, ha) - if (ether_addr_equal(ha->addr, f->macaddr)) - goto bottom_of_search_loop; +/** + * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * @netdev: the netdevice + * @addr: address to add + * + * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call + * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. + */ +static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_mac_filter *f; - if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) - goto bottom_of_search_loop; + /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC/VLAN filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; - /* f->macaddr wasn't found in uc, mc, or ha list so delete it */ + f = i40evf_find_filter(adapter, addr); + if (f) { f->remove = true; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; - -bottom_of_search_loop: - continue; } + return 0; +} + +/** + * i40evf_set_rx_mode - NDO callback to set the netdev filters + * @netdev: network interface device structure + **/ +static void i40evf_set_rx_mode(struct net_device *netdev) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + spin_unlock_bh(&adapter->mac_vlan_list_lock); if (netdev->flags & IFF_PROMISC && !(adapter->flags & I40EVF_FLAG_PROMISC_ON)) @@ -936,8 +950,6 @@ bottom_of_search_loop: else if (!(netdev->flags & IFF_ALLMULTI) && adapter->flags & I40EVF_FLAG_ALLMULTI_ON) adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI; - - spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** @@ -1025,7 +1037,9 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter) void i40evf_down(struct i40evf_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct i40evf_vlan_filter *vlf; struct i40evf_mac_filter *f; + struct i40evf_cloud_filter *cf; if (adapter->state <= __I40EVF_DOWN_PENDING) return; @@ -1038,17 +1052,29 @@ void i40evf_down(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); + /* clear the sync flag on all filters */ + __dev_uc_unsync(adapter->netdev, NULL); + __dev_mc_unsync(adapter->netdev, NULL); + /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->remove = true; } + /* remove all VLAN filters */ - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - f->remove = true; + list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { + vlf->remove = true; } spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* remove all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->del = true; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && adapter->state != __I40EVF_RESETTING) { /* cancel any current operation */ @@ -1059,6 +1085,7 @@ void i40evf_down(struct i40evf_adapter *adapter) */ adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; } @@ -1144,6 +1171,9 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) */ if (adapter->num_req_queues) num_active_queues = adapter->num_req_queues; + else if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + num_active_queues = adapter->ch_config.total_qps; else num_active_queues = min_t(int, adapter->vsi_res->num_queue_pairs, @@ -1169,7 +1199,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; + tx_ring->itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1178,7 +1208,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; + rx_ring->itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1471,6 +1501,16 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_alloc_q_vectors; } + /* If we've made it so far while ADq flag being ON, then we haven't + * bailed out anywhere in middle. And ADq isn't just enabled but actual + * resources have been allocated in the reset path. + * Now we can truly claim that ADq is enabled. + */ + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) + dev_info(&adapter->pdev->dev, "ADq Enabled, %u TCs created", + adapter->num_tc); + dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u", (adapter->num_active_queues > 1) ? "Enabled" : "Disabled", adapter->num_active_queues); @@ -1712,6 +1752,27 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) { + i40evf_enable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) { + i40evf_disable_channels(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) { + i40evf_add_cloud_filter(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) { + i40evf_del_cloud_filter(adapter); + goto watchdog_done; + } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) @@ -1735,6 +1796,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) { struct i40evf_mac_filter *f, *ftmp; struct i40evf_vlan_filter *fv, *fvtmp; + struct i40evf_cloud_filter *cf, *cftmp; adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; @@ -1756,7 +1818,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - /* Delete all of the filters, both MAC and VLAN. */ + /* Delete all of the filters */ list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { list_del(&f->list); kfree(f); @@ -1769,6 +1831,14 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + i40evf_free_misc_irq(adapter); i40evf_reset_interrupt_capability(adapter); i40evf_free_queues(adapter); @@ -1798,9 +1868,11 @@ static void i40evf_reset_task(struct work_struct *work) struct i40evf_adapter *adapter = container_of(work, struct i40evf_adapter, reset_task); + struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct i40e_hw *hw = &adapter->hw; struct i40evf_vlan_filter *vlf; + struct i40evf_cloud_filter *cf; struct i40evf_mac_filter *f; u32 reg_val; int i = 0, err; @@ -1893,6 +1965,7 @@ continue_reset: i40evf_free_all_rx_resources(adapter); i40evf_free_all_tx_resources(adapter); + adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED; /* kill and reinit the admin queue */ i40evf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; @@ -1924,8 +1997,19 @@ continue_reset: spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* check if TCs are running and re-add all cloud filters */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + if ((vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + cf->add = true; + } + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -2191,6 +2275,712 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) } /** + * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth + * @adapter: board private structure + * @max_tx_rate: max Tx bw for a tc + **/ +static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, + u64 max_tx_rate) +{ + int speed = 0, ret = 0; + + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + speed = 40000; + break; + case I40E_LINK_SPEED_25GB: + speed = 25000; + break; + case I40E_LINK_SPEED_20GB: + speed = 20000; + break; + case I40E_LINK_SPEED_10GB: + speed = 10000; + break; + case I40E_LINK_SPEED_1GB: + speed = 1000; + break; + case I40E_LINK_SPEED_100MB: + speed = 100; + break; + default: + break; + } + + if (max_tx_rate > speed) { + dev_err(&adapter->pdev->dev, + "Invalid tx rate specified\n"); + ret = -EINVAL; + } + + return ret; +} + +/** + * i40evf_validate_channel_config - validate queue mapping info + * @adapter: board private structure + * @mqprio_qopt: queue parameters + * + * This function validates if the config provided by the user to + * configure queue channels is valid or not. Returns 0 on a valid + * config. + **/ +static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + u64 total_max_rate = 0; + int i, num_qps = 0; + u64 tx_rate = 0; + int ret = 0; + + if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS || + mqprio_qopt->qopt.num_tc < 1) + return -EINVAL; + + for (i = 0; i <= mqprio_qopt->qopt.num_tc - 1; i++) { + if (!mqprio_qopt->qopt.count[i] || + mqprio_qopt->qopt.offset[i] != num_qps) + return -EINVAL; + if (mqprio_qopt->min_rate[i]) { + dev_err(&adapter->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); + return -EINVAL; + } + /*convert to Mbps */ + tx_rate = div_u64(mqprio_qopt->max_rate[i], + I40EVF_MBPS_DIVISOR); + total_max_rate += tx_rate; + num_qps += mqprio_qopt->qopt.count[i]; + } + if (num_qps > MAX_QUEUES) + return -EINVAL; + + ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate); + return ret; +} + +/** + * i40evf_del_all_cloud_filters - delete all cloud filters + * on the traffic classes + **/ +static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); +} + +/** + * __i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type_date: tc offload data + * + * This function processes the config information provided by the + * user to configure traffic classes/queue channels and packages the + * information to request the PF to setup traffic classes. + * + * Returns 0 on success. + **/ +static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; + struct i40evf_adapter *adapter = netdev_priv(netdev); + struct virtchnl_vf_resource *vfres = adapter->vf_res; + u8 num_tc = 0, total_qps = 0; + int ret = 0, netdev_tc = 0; + u64 max_tx_rate; + u16 mode; + int i; + + num_tc = mqprio_qopt->qopt.num_tc; + mode = mqprio_qopt->mode; + + /* delete queue_channel */ + if (!mqprio_qopt->qopt.hw) { + if (adapter->ch_config.state == __I40EVF_TC_RUNNING) { + /* reset the tc configuration */ + netdev_reset_tc(netdev); + adapter->num_tc = 0; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + i40evf_del_all_cloud_filters(adapter); + adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS; + goto exit; + } else { + return -EINVAL; + } + } + + /* add queue channel */ + if (mode == TC_MQPRIO_MODE_CHANNEL) { + if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)) { + dev_err(&adapter->pdev->dev, "ADq not supported\n"); + return -EOPNOTSUPP; + } + if (adapter->ch_config.state != __I40EVF_TC_INVALID) { + dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); + return -EINVAL; + } + + ret = i40evf_validate_ch_config(adapter, mqprio_qopt); + if (ret) + return ret; + /* Return if same TC config is requested */ + if (adapter->num_tc == num_tc) + return 0; + adapter->num_tc = num_tc; + + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + if (i < num_tc) { + adapter->ch_config.ch_info[i].count = + mqprio_qopt->qopt.count[i]; + adapter->ch_config.ch_info[i].offset = + mqprio_qopt->qopt.offset[i]; + total_qps += mqprio_qopt->qopt.count[i]; + max_tx_rate = mqprio_qopt->max_rate[i]; + /* convert to Mbps */ + max_tx_rate = div_u64(max_tx_rate, + I40EVF_MBPS_DIVISOR); + adapter->ch_config.ch_info[i].max_tx_rate = + max_tx_rate; + } else { + adapter->ch_config.ch_info[i].count = 1; + adapter->ch_config.ch_info[i].offset = 0; + } + } + adapter->ch_config.total_qps = total_qps; + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS; + netdev_reset_tc(netdev); + /* Report the tc mapping up the stack */ + netdev_set_num_tc(adapter->netdev, num_tc); + for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + u16 qcount = mqprio_qopt->qopt.count[i]; + u16 qoffset = mqprio_qopt->qopt.offset[i]; + + if (i < num_tc) + netdev_set_tc_queue(netdev, netdev_tc++, qcount, + qoffset); + } + } +exit: + return ret; +} + +/** + * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel + * @adapter: board private structure + * @cls_flower: pointer to struct tc_cls_flower_offload + * @filter: pointer to cloud filter structure + */ +static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct i40evf_cloud_filter *filter) +{ + u16 n_proto_mask = 0; + u16 n_proto_key = 0; + u8 field_flags = 0; + u16 addr_type = 0; + u16 n_proto = 0; + int i = 0; + struct virtchnl_filter *vf = &filter->f; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + + if (mask->keyid != 0) + field_flags |= I40EVF_CLOUD_FIELD_TEN_ID; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + n_proto = n_proto_key & n_proto_mask; + if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) + return -EINVAL; + if (n_proto == ETH_P_IPV6) { + /* specify flow type as TCP IPv6 */ + vf->flow_type = VIRTCHNL_TCP_V6_FLOW; + } + + if (key->ip_proto != IPPROTO_TCP) { + dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); + return -EINVAL; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + /* use is_broadcast and is_zero to check for all 0xf or 0 */ + if (!is_zero_ether_addr(mask->dst)) { + if (is_broadcast_ether_addr(mask->dst)) { + field_flags |= I40EVF_CLOUD_FIELD_OMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", + mask->dst); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(mask->src)) { + if (is_broadcast_ether_addr(mask->src)) { + field_flags |= I40EVF_CLOUD_FIELD_IMAC; + } else { + dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", + mask->src); + return I40E_ERR_CONFIG; + } + } + + if (!is_zero_ether_addr(key->dst)) + if (is_valid_ether_addr(key->dst) || + is_multicast_ether_addr(key->dst)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.dst_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.dst_mac, + key->dst); + } + + if (!is_zero_ether_addr(key->src)) + if (is_valid_ether_addr(key->src) || + is_multicast_ether_addr(key->src)) { + /* set the mask if a valid dst_mac address */ + for (i = 0; i < ETH_ALEN; i++) + vf->mask.tcp_spec.src_mac[i] |= 0xff; + ether_addr_copy(vf->data.tcp_spec.src_mac, + key->src); + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + struct flow_dissector_key_vlan *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_id) { + if (mask->vlan_id == VLAN_VID_MASK) { + field_flags |= I40EVF_CLOUD_FIELD_IVLAN; + } else { + dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", + mask->vlan_id); + return I40E_ERR_CONFIG; + } + } + vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); + vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + addr_type = key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + if (mask->dst) { + if (mask->dst == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (mask->src) { + if (mask->src == cpu_to_be32(0xffffffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", + be32_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + + if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) { + dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); + return I40E_ERR_CONFIG; + } + if (key->dst) { + vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.dst_ip[0] = key->dst; + } + if (key->src) { + vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); + vf->data.tcp_spec.src_ip[0] = key->src; + } + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + /* validate mask, make sure it is not IPV6_ADDR_ANY */ + if (ipv6_addr_any(&mask->dst)) { + dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", + IPV6_ADDR_ANY); + return I40E_ERR_CONFIG; + } + + /* src and dest IPv6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1) which can be represented as ::1 + */ + if (ipv6_addr_loopback(&key->dst) || + ipv6_addr_loopback(&key->src)) { + dev_err(&adapter->pdev->dev, + "ipv6 addr should not be loopback\n"); + return I40E_ERR_CONFIG; + } + if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + field_flags |= I40EVF_CLOUD_FIELD_IIP; + + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + sizeof(vf->data.tcp_spec.dst_ip)); + for (i = 0; i < 4; i++) + vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); + memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + sizeof(vf->data.tcp_spec.src_ip)); + } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + + if (mask->src) { + if (mask->src == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", + be16_to_cpu(mask->src)); + return I40E_ERR_CONFIG; + } + } + + if (mask->dst) { + if (mask->dst == cpu_to_be16(0xffff)) { + field_flags |= I40EVF_CLOUD_FIELD_IIP; + } else { + dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", + be16_to_cpu(mask->dst)); + return I40E_ERR_CONFIG; + } + } + if (key->dst) { + vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.dst_port = key->dst; + } + + if (key->src) { + vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); + vf->data.tcp_spec.src_port = key->src; + } + } + vf->field_flags = field_flags; + + return 0; +} + +/** + * i40evf_handle_tclass - Forward to a traffic class on the device + * @adapter: board private structure + * @tc: traffic class index on the device + * @filter: pointer to cloud filter structure + */ +static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, + struct i40evf_cloud_filter *filter) +{ + if (tc == 0) + return 0; + if (tc < adapter->num_tc) { + if (!filter->f.data.tcp_spec.dst_port) { + dev_err(&adapter->pdev->dev, + "Specify destination port to redirect to traffic class other than TC0\n"); + return -EINVAL; + } + } + /* redirect to a traffic class on the same device */ + filter->f.action = VIRTCHNL_ACTION_TC_REDIRECT; + filter->f.action_meta = tc; + return 0; +} + +/** + * i40evf_configure_clsflower - Add tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + struct i40evf_cloud_filter *filter = NULL; + int err = -EINVAL, count = 50; + + if (tc < 0) { + dev_err(&adapter->pdev->dev, "Invalid traffic class\n"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + &adapter->crit_section)) { + if (--count == 0) + goto err; + udelay(1); + } + + filter->cookie = cls_flower->cookie; + + /* set the mask to all zeroes to begin with */ + memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); + /* start out with flow type and eth type IPv4 to begin with */ + filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; + err = i40evf_parse_cls_flower(adapter, cls_flower, filter); + if (err < 0) + goto err; + + err = i40evf_handle_tclass(adapter, tc, filter); + if (err < 0) + goto err; + + /* add filter to the list */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_add_tail(&filter->list, &adapter->cloud_filter_list); + adapter->num_cloud_filters++; + filter->add = true; + adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + spin_unlock_bh(&adapter->cloud_filter_list_lock); +err: + if (err) + kfree(filter); + + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + return err; +} + +/* i40evf_find_cf - Find the cloud filter in the list + * @adapter: Board private structure + * @cookie: filter specific cookie + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * cloud_filter_list_lock. + */ +static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter, + unsigned long *cookie) +{ + struct i40evf_cloud_filter *filter = NULL; + + if (!cookie) + return NULL; + + list_for_each_entry(filter, &adapter->cloud_filter_list, list) { + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + } + return NULL; +} + +/** + * i40evf_delete_clsflower - Remove tc flower filters + * @adapter: board private structure + * @cls_flower: Pointer to struct tc_cls_flower_offload + */ +static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct i40evf_cloud_filter *filter = NULL; + int err = 0; + + spin_lock_bh(&adapter->cloud_filter_list_lock); + filter = i40evf_find_cf(adapter, &cls_flower->cookie); + if (filter) { + filter->del = true; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + } else { + err = -EINVAL; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + + return err; +} + +/** + * i40evf_setup_tc_cls_flower - flower classifier offloads + * @netdev: net device to configure + * @type_data: offload data + */ +static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return i40evf_configure_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_DESTROY: + return i40evf_delete_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +/** + * i40evf_setup_tc_block_cb - block callback for tc + * @type: type of offload + * @type_data: offload data + * @cb_priv: + * + * This function is the block callback for traffic classes + **/ +static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + switch (type) { + case TC_SETUP_CLSFLOWER: + return i40evf_setup_tc_cls_flower(cb_priv, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc_block - register callbacks for tc + * @netdev: network interface device structure + * @f: tc offload data + * + * This function registers block callbacks for tc + * offloads + **/ +static int i40evf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + struct i40evf_adapter *adapter = netdev_priv(dev); + + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, + adapter, adapter); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + +/** + * i40evf_setup_tc - configure multiple traffic classes + * @netdev: network interface device structure + * @type: type of offload + * @type_date: tc offload data + * + * This function is the callback to ndo_setup_tc in the + * netdev_ops. + * + * Returns 0 on success + **/ +static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return __i40evf_setup_tc(netdev, type_data); + case TC_SETUP_BLOCK: + return i40evf_setup_tc_block(netdev, type_data); + default: + return -EOPNOTSUPP; + } +} + +/** * i40evf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -2236,7 +3026,12 @@ static int i40evf_open(struct net_device *netdev) if (err) goto err_req_irq; + spin_lock_bh(&adapter->mac_vlan_list_lock); + i40evf_add_filter(adapter, adapter->hw.mac.addr); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + i40evf_configure(adapter); i40evf_up_complete(adapter); @@ -2457,6 +3252,7 @@ static const struct net_device_ops i40evf_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40evf_netpoll, #endif + .ndo_setup_tc = i40evf_setup_tc, }; /** @@ -2571,6 +3367,9 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); + /* Enable cloud filter if ADQ is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + hw_features |= NETIF_F_HW_TC; netdev->hw_features |= hw_features; @@ -2938,9 +3737,11 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&hw->aq.arq_mutex); spin_lock_init(&adapter->mac_vlan_list_lock); + spin_lock_init(&adapter->cloud_filter_list_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); + INIT_LIST_HEAD(&adapter->cloud_filter_list); INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); @@ -3065,7 +3866,9 @@ static void i40evf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct i40evf_adapter *adapter = netdev_priv(netdev); + struct i40evf_vlan_filter *vlf, *vlftmp; struct i40evf_mac_filter *f, *ftmp; + struct i40evf_cloud_filter *cf, *cftmp; struct i40e_hw *hw = &adapter->hw; int err; /* Indicate we are in remove and not to run reset_task */ @@ -3087,6 +3890,7 @@ static void i40evf_remove(struct pci_dev *pdev) /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; adapter->aq_required = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; i40evf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -3127,13 +3931,21 @@ static void i40evf_remove(struct pci_dev *pdev) list_del(&f->list); kfree(f); } - list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - list_del(&f->list); - kfree(f); + list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, + list) { + list_del(&vlf->list); + kfree(vlf); } spin_unlock_bh(&adapter->mac_vlan_list_lock); + spin_lock_bh(&adapter->cloud_filter_list_lock); + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + list_del(&cf->list); + kfree(cf); + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); + free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 50ce0d6c09ef..26a59890532f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver @@ -161,7 +162,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | - VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_OFFLOAD_ADQ; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -344,6 +346,7 @@ void i40evf_disable_queues(struct i40evf_adapter *adapter) void i40evf_map_queues(struct i40evf_adapter *adapter) { struct virtchnl_irq_map_info *vimi; + struct virtchnl_vector_map *vecmap; int v_idx, q_vectors, len; struct i40e_q_vector *q_vector; @@ -367,17 +370,22 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vimi->num_vectors = adapter->num_msix_vectors; /* Queue vectors first */ for (v_idx = 0; v_idx < q_vectors; v_idx++) { - q_vector = adapter->q_vectors + v_idx; - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = v_idx + NONQ_VECS; - vimi->vecmap[v_idx].txq_map = q_vector->ring_mask; - vimi->vecmap[v_idx].rxq_map = q_vector->ring_mask; + q_vector = &adapter->q_vectors[v_idx]; + vecmap = &vimi->vecmap[v_idx]; + + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = v_idx + NONQ_VECS; + vecmap->txq_map = q_vector->ring_mask; + vecmap->rxq_map = q_vector->ring_mask; + vecmap->rxitr_idx = I40E_RX_ITR; + vecmap->txitr_idx = I40E_TX_ITR; } /* Misc vector last - this is only for AdminQ messages */ - vimi->vecmap[v_idx].vsi_id = adapter->vsi_res->vsi_id; - vimi->vecmap[v_idx].vector_id = 0; - vimi->vecmap[v_idx].txq_map = 0; - vimi->vecmap[v_idx].rxq_map = 0; + vecmap = &vimi->vecmap[v_idx]; + vecmap->vsi_id = adapter->vsi_res->vsi_id; + vecmap->vector_id = 0; + vecmap->txq_map = 0; + vecmap->rxq_map = 0; adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS; i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, @@ -459,7 +467,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -532,7 +540,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) (count * sizeof(struct virtchnl_ether_addr)); more = true; } - veal = kzalloc(len, GFP_KERNEL); + veal = kzalloc(len, GFP_ATOMIC); if (!veal) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -606,7 +614,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -678,7 +686,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) (count * sizeof(u16)); more = true; } - vvfl = kzalloc(len, GFP_KERNEL); + vvfl = kzalloc(len, GFP_ATOMIC); if (!vvfl) { spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -967,6 +975,205 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) } /** + * i40evf_enable_channel + * @adapter: adapter structure + * + * Request that the PF enable channels as specified by + * the user via tc tool. + **/ +void i40evf_enable_channels(struct i40evf_adapter *adapter) +{ + struct virtchnl_tc_info *vti = NULL; + u16 len; + int i; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) + + sizeof(struct virtchnl_tc_info); + + vti = kzalloc(len, GFP_KERNEL); + if (!vti) + return; + vti->num_tc = adapter->num_tc; + for (i = 0; i < vti->num_tc; i++) { + vti->list[i].count = adapter->ch_config.ch_info[i].count; + vti->list[i].offset = adapter->ch_config.ch_info[i].offset; + vti->list[i].pad = 0; + vti->list[i].max_tx_rate = + adapter->ch_config.ch_info[i].max_tx_rate; + } + + adapter->ch_config.state = __I40EVF_TC_RUNNING; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, + (u8 *)vti, len); + kfree(vti); +} + +/** + * i40evf_disable_channel + * @adapter: adapter structure + * + * Request that the PF disable channels that are configured + **/ +void i40evf_disable_channels(struct i40evf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot configure mqprio, command %d pending\n", + adapter->current_op); + return; + } + + adapter->ch_config.state = __I40EVF_TC_INVALID; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; + adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, + NULL, 0); +} + +/** + * i40evf_print_cloud_filter + * @adapter: adapter structure + * @f: cloud filter to print + * + * Print the cloud filter + **/ +static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, + struct virtchnl_filter *f) +{ + switch (f->flow_type) { + case VIRTCHNL_TCP_V4_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI4 src_ip %pI4 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip[0], + &f->data.tcp_spec.src_ip[0], + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + case VIRTCHNL_TCP_V6_FLOW: + dev_info(&adapter->pdev->dev, "dst_mac: %pM src_mac: %pM vlan_id: %hu dst_ip: %pI6 src_ip %pI6 dst_port %hu src_port %hu\n", + &f->data.tcp_spec.dst_mac, + &f->data.tcp_spec.src_mac, + ntohs(f->data.tcp_spec.vlan_id), + &f->data.tcp_spec.dst_ip, + &f->data.tcp_spec.src_ip, + ntohs(f->data.tcp_spec.dst_port), + ntohs(f->data.tcp_spec.src_port)); + break; + } +} + +/** + * i40evf_add_cloud_filter + * @adapter: adapter structure + * + * Request that the PF add cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot add cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->add) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->add = false; + cf->state = __I40EVF_CF_ADD_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** + * i40evf_del_cloud_filter + * @adapter: adapter structure + * + * Request that the PF delete cloud filters as specified + * by the user via tc tool. + **/ +void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) +{ + struct i40evf_cloud_filter *cf, *cftmp; + struct virtchnl_filter *f; + int len = 0, count = 0; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot remove cloud filter, command %d pending\n", + adapter->current_op); + return; + } + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->del) { + count++; + break; + } + } + if (!count) { + adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + return; + } + adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; + + len = sizeof(struct virtchnl_filter); + f = kzalloc(len, GFP_KERNEL); + if (!f) + return; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { + if (cf->del) { + memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); + cf->del = false; + cf->state = __I40EVF_CF_DEL_PENDING; + i40evf_send_pf_msg(adapter, + VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); + } + } + kfree(f); +} + +/** * i40evf_request_reset * @adapter: adapter structure * @@ -1011,14 +1218,25 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (adapter->link_up == link_up) break; - /* If we get link up message and start queues before - * our queues are configured it will trigger a TX hang. - * In that case, just ignore the link status message, - * we'll get another one after we enable queues and - * actually prepared to send traffic. - */ - if (link_up && adapter->state != __I40EVF_RUNNING) - break; + if (link_up) { + /* If we get link up message and start queues + * before our queues are configured it will + * trigger a TX hang. In that case, just ignore + * the link status message,we'll get another one + * after we enable queues and actually prepared + * to send traffic. + */ + if (adapter->state != __I40EVF_RUNNING) + break; + + /* For ADq enabled VF, we reconfigure VSIs and + * re-allocate queues. Hence wait till all + * queues are enabled. + */ + if (adapter->flags & + I40EVF_FLAG_QUEUES_DISABLED) + break; + } adapter->link_up = link_up; if (link_up) { @@ -1031,7 +1249,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, i40evf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: - dev_info(&adapter->pdev->dev, "PF reset warning received\n"); + dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { adapter->flags |= I40EVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); @@ -1063,6 +1281,57 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", i40evf_stat_str(&adapter->hw, v_retval)); break; + case VIRTCHNL_OP_ENABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_INVALID; + netdev_reset_tc(netdev); + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_DISABLE_CHANNELS: + dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", + i40evf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __I40EVF_TC_RUNNING; + netif_tx_start_all_queues(netdev); + break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, + &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) { + cf->state = __I40EVF_CF_INVALID; + dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", + i40evf_stat_str(&adapter->hw, + v_retval)); + i40evf_print_cloud_filter(adapter, + &cf->f); + } + } + } + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, @@ -1102,6 +1371,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ i40evf_irq_enable(adapter, true); + adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: i40evf_free_all_tx_resources(adapter); @@ -1156,6 +1426,29 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } } break; + case VIRTCHNL_OP_ADD_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf; + + list_for_each_entry(cf, &adapter->cloud_filter_list, list) { + if (cf->state == __I40EVF_CF_ADD_PENDING) + cf->state = __I40EVF_CF_ACTIVE; + } + } + break; + case VIRTCHNL_OP_DEL_CLOUD_FILTER: { + struct i40evf_cloud_filter *cf, *cftmp; + + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + if (cf->state == __I40EVF_CF_DEL_PENDING) { + cf->state = __I40EVF_CF_INVALID; + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } + } + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", |