ixgbe: Move interrupt related values out of ring and into q_vector

This change moves work_limit, total_packets, and total_bytes into the ring
container struct of the q_vector.  The advantage of this is that it should
reduce the size of memory used in the event of multiple rings being
assigned to a single q_vector.  In addition it should help to reduce the
total workload for calculating itr since now total_packets and total_bytes
will be the total work done of the interrupt instead of for the ring.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index a5ed9fd69fdd3c67d0a29ad539bacfc92d38574d..fbae7352b0368616d712c29a673b545477b1dd89 100644 (file)
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -214,12 +214,10 @@ struct ixgbe_ring {
                struct ixgbe_rx_buffer *rx_buffer_info;
        };
        unsigned long state;
-       u8 atr_sample_rate;
-       u8 atr_count;
+       u8 __iomem *tail;
+
        u16 count;                      /* amount of descriptors */
        u16 rx_buf_len;
-       u16 next_to_use;
-       u16 next_to_clean;
 
        u8 queue_index; /* needed for multiqueue queue management */
        u8 reg_idx;                     /* holds the special value that gets
@@ -227,15 +225,13 @@ struct ixgbe_ring {
                                         * associated with this ring, which is
                                         * different for DCB and RSS modes
                                         */
-       u8 dcb_tc;
-
-       u16 work_limit;                 /* max work per interrupt */
-
-       u8 __iomem *tail;
+       u8 atr_sample_rate;
+       u8 atr_count;
 
-       unsigned int total_bytes;
-       unsigned int total_packets;
+       u16 next_to_use;
+       u16 next_to_clean;
 
+       u8 dcb_tc;
        struct ixgbe_queue_stats stats;
        struct u64_stats_sync syncp;
        union {
@@ -283,6 +279,9 @@ struct ixgbe_ring_container {
 #else
        DECLARE_BITMAP(idx, MAX_TX_QUEUES);
 #endif
+       unsigned int total_bytes;       /* total bytes processed this int */
+       unsigned int total_packets;     /* total packets processed this int */
+       u16 work_limit;                 /* total work allowed per interrupt */
        u8 count;                       /* total number of rings in vector */
        u8 itr;                         /* current ITR setting for ring */
 };
@@ -417,6 +416,9 @@ struct ixgbe_adapter {
        u16 eitr_low;
        u16 eitr_high;
 
+       /* Work limits */
+       u16 tx_work_limit;
+
        /* TX */
        struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp;
        int num_tx_queues;

diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index cd842f9dcae5fbaf26f56bddc43049a08332f910..6035cfa1b4c7f88f493564c12dca5376e863334f 100644 (file)
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -2103,7 +2103,7 @@ static int ixgbe_get_coalesce(struct net_device *netdev,
 {
        struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-       ec->tx_max_coalesced_frames_irq = adapter->tx_ring[0]->work_limit;
+       ec->tx_max_coalesced_frames_irq = adapter->tx_work_limit;
 
        /* only valid if in constant ITR mode */
        switch (adapter->rx_itr_setting) {
@@ -2192,7 +2192,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
                return -EINVAL;
 
        if (ec->tx_max_coalesced_frames_irq)
-               adapter->tx_ring[0]->work_limit = ec->tx_max_coalesced_frames_irq;
+               adapter->tx_work_limit = ec->tx_max_coalesced_frames_irq;
 
        if (ec->rx_coalesce_usecs > 1) {
                /* check the limits */
@@ -2267,12 +2267,14 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
                        else
                                /* rx only or mixed */
                                q_vector->eitr = adapter->rx_eitr_param;
+                       q_vector->tx.work_limit = adapter->tx_work_limit;
                        ixgbe_write_eitr(q_vector);
                }
        /* Legacy Interrupt Mode */
        } else {
                q_vector = adapter->q_vector[0];
                q_vector->eitr = adapter->rx_eitr_param;
+               q_vector->tx.work_limit = adapter->tx_work_limit;
                ixgbe_write_eitr(q_vector);
        }
 

diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index bd1fd8f422dc0e9cd5cc49a049a014039b962baf..298c95b1480fabc972456dfe16110277a50f9249 100644 (file)
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -805,7 +805,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
        eop_desc = IXGBE_TX_DESC_ADV(tx_ring, eop);
 
        while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
-              (count < tx_ring->work_limit)) {
+              (count < q_vector->tx.work_limit)) {
                bool cleaned = false;
                rmb(); /* read buffer_info after eop_desc */
                for ( ; !cleaned; count++) {
@@ -834,11 +834,11 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
        }
 
        tx_ring->next_to_clean = i;
-       tx_ring->total_bytes += total_bytes;
-       tx_ring->total_packets += total_packets;
-       u64_stats_update_begin(&tx_ring->syncp);
-       tx_ring->stats.packets += total_packets;
        tx_ring->stats.bytes += total_bytes;
+       tx_ring->stats.packets += total_packets;
+       u64_stats_update_begin(&tx_ring->syncp);
+       q_vector->tx.total_bytes += total_bytes;
+       q_vector->tx.total_packets += total_packets;
        u64_stats_update_end(&tx_ring->syncp);
 
        if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
@@ -886,7 +886,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
                }
        }
 
-       return count < tx_ring->work_limit;
+       return count < q_vector->tx.work_limit;
 }
 
 #ifdef CONFIG_IXGBE_DCA
@@ -1486,12 +1486,12 @@ next_desc:
        }
 #endif /* IXGBE_FCOE */
 
-       rx_ring->total_packets += total_rx_packets;
-       rx_ring->total_bytes += total_rx_bytes;
        u64_stats_update_begin(&rx_ring->syncp);
        rx_ring->stats.packets += total_rx_packets;
        rx_ring->stats.bytes += total_rx_bytes;
        u64_stats_update_end(&rx_ring->syncp);
+       q_vector->rx.total_packets += total_rx_packets;
+       q_vector->rx.total_bytes += total_rx_bytes;
 }
 
 static int ixgbe_clean_rxonly(struct napi_struct *, int);
@@ -1597,11 +1597,8 @@ enum latency_range {
 
 /**
  * ixgbe_update_itr - update the dynamic ITR value based on statistics
- * @adapter: pointer to adapter
- * @eitr: eitr setting (ints per sec) to give last timeslice
- * @itr_setting: current throttle rate in ints/second
- * @packets: the number of packets during this measurement interval
- * @bytes: the number of bytes during this measurement interval
+ * @q_vector: structure containing interrupt and ring information
+ * @ring_container: structure containing ring performance data
  *
  *      Stores a new ITR value based on packets and byte
  *      counts during the last interrupt.  The advantage of per interrupt
@@ -1613,17 +1610,18 @@ enum latency_range {
  *      this functionality is controlled by the InterruptThrottleRate module
  *      parameter (see ixgbe_param.c)
  **/
-static u8 ixgbe_update_itr(struct ixgbe_adapter *adapter,
-                          u32 eitr, u8 itr_setting,
-                          int packets, int bytes)
+static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector,
+                            struct ixgbe_ring_container *ring_container)
 {
-       unsigned int retval = itr_setting;
-       u32 timepassed_us;
        u64 bytes_perint;
+       struct ixgbe_adapter *adapter = q_vector->adapter;
+       int bytes = ring_container->total_bytes;
+       int packets = ring_container->total_packets;
+       u32 timepassed_us;
+       u8 itr_setting = ring_container->itr;
 
        if (packets == 0)
-               goto update_itr_done;
-
+               return;
 
        /* simple throttlerate management
         *    0-20MB/s lowest (100000 ints/s)
@@ -1631,28 +1629,32 @@ static u8 ixgbe_update_itr(struct ixgbe_adapter *adapter,
         *  100-1249MB/s bulk (8000 ints/s)
         */
        /* what was last interrupt timeslice? */
-       timepassed_us = 1000000/eitr;
+       timepassed_us = 1000000/q_vector->eitr;
        bytes_perint = bytes / timepassed_us; /* bytes/usec */
 
        switch (itr_setting) {
        case lowest_latency:
                if (bytes_perint > adapter->eitr_low)
-                       retval = low_latency;
+                       itr_setting = low_latency;
                break;
        case low_latency:
                if (bytes_perint > adapter->eitr_high)
-                       retval = bulk_latency;
+                       itr_setting = bulk_latency;
                else if (bytes_perint <= adapter->eitr_low)
-                       retval = lowest_latency;
+                       itr_setting = lowest_latency;
                break;
        case bulk_latency:
                if (bytes_perint <= adapter->eitr_high)
-                       retval = low_latency;
+                       itr_setting = low_latency;
                break;
        }
 
-update_itr_done:
-       return retval;
+       /* clear work counters since we have the values we need */
+       ring_container->total_bytes = 0;
+       ring_container->total_packets = 0;
+
+       /* write updated itr to ring container */
+       ring_container->itr = itr_setting;
 }
 
 /**
@@ -1698,42 +1700,13 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector)
        IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg);
 }
 
-static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
+static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector)
 {
-       struct ixgbe_adapter *adapter = q_vector->adapter;
-       int i, r_idx;
-       u32 new_itr;
-       u8 current_itr, ret_itr;
-
-       r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
-       for (i = 0; i < q_vector->tx.count; i++) {
-               struct ixgbe_ring *tx_ring = adapter->tx_ring[r_idx];
-               ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
-                                          q_vector->tx.itr,
-                                          tx_ring->total_packets,
-                                          tx_ring->total_bytes);
-               /* if the result for this queue would decrease interrupt
-                * rate for this vector then use that result */
-               q_vector->tx.itr = ((q_vector->tx.itr > ret_itr) ?
-                                   q_vector->tx.itr - 1 : ret_itr);
-               r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
-                                     r_idx + 1);
-       }
+       u32 new_itr = q_vector->eitr;
+       u8 current_itr;
 
-       r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
-       for (i = 0; i < q_vector->rx.count; i++) {
-               struct ixgbe_ring *rx_ring = adapter->rx_ring[r_idx];
-               ret_itr = ixgbe_update_itr(adapter, q_vector->eitr,
-                                          q_vector->rx.itr,
-                                          rx_ring->total_packets,
-                                          rx_ring->total_bytes);
-               /* if the result for this queue would decrease interrupt
-                * rate for this vector then use that result */
-               q_vector->rx.itr = ((q_vector->rx.itr > ret_itr) ?
-                                   q_vector->rx.itr - 1 : ret_itr);
-               r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
-                                     r_idx + 1);
-       }
+       ixgbe_update_itr(q_vector, &q_vector->tx);
+       ixgbe_update_itr(q_vector, &q_vector->rx);
 
        current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
 
@@ -1746,16 +1719,17 @@ static void ixgbe_set_itr_msix(struct ixgbe_q_vector *q_vector)
                new_itr = 20000; /* aka hwitr = ~200 */
                break;
        case bulk_latency:
-       default:
                new_itr = 8000;
                break;
+       default:
+               break;
        }
 
        if (new_itr != q_vector->eitr) {
                /* do an exponential smoothing */
                new_itr = ((q_vector->eitr * 9) + new_itr)/10;
 
-               /* save the algorithm value here, not the smoothed one */
+               /* save the algorithm value here */
                q_vector->eitr = new_itr;
 
                ixgbe_write_eitr(q_vector);
@@ -2001,8 +1975,6 @@ static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data)
        r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
        for (i = 0; i < q_vector->tx.count; i++) {
                tx_ring = adapter->tx_ring[r_idx];
-               tx_ring->total_bytes = 0;
-               tx_ring->total_packets = 0;
                r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
                                      r_idx + 1);
        }
@@ -2034,8 +2006,6 @@ static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data)
        r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
        for (i = 0; i < q_vector->rx.count; i++) {
                rx_ring = adapter->rx_ring[r_idx];
-               rx_ring->total_bytes = 0;
-               rx_ring->total_packets = 0;
                r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
                                      r_idx + 1);
        }
@@ -2063,8 +2033,6 @@ static irqreturn_t ixgbe_msix_clean_many(int irq, void *data)
        r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues);
        for (i = 0; i < q_vector->tx.count; i++) {
                ring = adapter->tx_ring[r_idx];
-               ring->total_bytes = 0;
-               ring->total_packets = 0;
                r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues,
                                      r_idx + 1);
        }
@@ -2072,8 +2040,6 @@ static irqreturn_t ixgbe_msix_clean_many(int irq, void *data)
        r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues);
        for (i = 0; i < q_vector->rx.count; i++) {
                ring = adapter->rx_ring[r_idx];
-               ring->total_bytes = 0;
-               ring->total_packets = 0;
                r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues,
                                      r_idx + 1);
        }
@@ -2115,7 +2081,7 @@ static int ixgbe_clean_rxonly(struct napi_struct *napi, int budget)
        if (work_done < budget) {
                napi_complete(napi);
                if (adapter->rx_itr_setting & 1)
-                       ixgbe_set_itr_msix(q_vector);
+                       ixgbe_set_itr(q_vector);
                if (!test_bit(__IXGBE_DOWN, &adapter->state))
                        ixgbe_irq_enable_queues(adapter,
                                                ((u64)1 << q_vector->v_idx));
@@ -2173,7 +2139,7 @@ static int ixgbe_clean_rxtx_many(struct napi_struct *napi, int budget)
        if (work_done < budget) {
                napi_complete(napi);
                if (adapter->rx_itr_setting & 1)
-                       ixgbe_set_itr_msix(q_vector);
+                       ixgbe_set_itr(q_vector);
                if (!test_bit(__IXGBE_DOWN, &adapter->state))
                        ixgbe_irq_enable_queues(adapter,
                                                ((u64)1 << q_vector->v_idx));
@@ -2215,7 +2181,7 @@ static int ixgbe_clean_txonly(struct napi_struct *napi, int budget)
        if (work_done < budget) {
                napi_complete(napi);
                if (adapter->tx_itr_setting & 1)
-                       ixgbe_set_itr_msix(q_vector);
+                       ixgbe_set_itr(q_vector);
                if (!test_bit(__IXGBE_DOWN, &adapter->state))
                        ixgbe_irq_enable_queues(adapter,
                                                ((u64)1 << q_vector->v_idx));
@@ -2244,6 +2210,7 @@ static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx,
        set_bit(t_idx, q_vector->tx.idx);
        q_vector->tx.count++;
        tx_ring->q_vector = q_vector;
+       q_vector->tx.work_limit = a->tx_work_limit;
 }
 
 /**
@@ -2386,51 +2353,6 @@ free_queue_irqs:
        return err;
 }
 
-static void ixgbe_set_itr(struct ixgbe_adapter *adapter)
-{
-       struct ixgbe_q_vector *q_vector = adapter->q_vector[0];
-       struct ixgbe_ring *rx_ring = adapter->rx_ring[0];
-       struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
-       u32 new_itr = q_vector->eitr;
-       u8 current_itr;
-
-       q_vector->tx.itr = ixgbe_update_itr(adapter, new_itr,
-                                           q_vector->tx.itr,
-                                           tx_ring->total_packets,
-                                           tx_ring->total_bytes);
-       q_vector->rx.itr = ixgbe_update_itr(adapter, new_itr,
-                                           q_vector->rx.itr,
-                                           rx_ring->total_packets,
-                                           rx_ring->total_bytes);
-
-       current_itr = max(q_vector->rx.itr, q_vector->tx.itr);
-
-       switch (current_itr) {
-       /* counts and packets in update_itr are dependent on these numbers */
-       case lowest_latency:
-               new_itr = 100000;
-               break;
-       case low_latency:
-               new_itr = 20000; /* aka hwitr = ~200 */
-               break;
-       case bulk_latency:
-               new_itr = 8000;
-               break;
-       default:
-               break;
-       }
-
-       if (new_itr != q_vector->eitr) {
-               /* do an exponential smoothing */
-               new_itr = ((q_vector->eitr * 9) + new_itr)/10;
-
-               /* save the algorithm value here */
-               q_vector->eitr = new_itr;
-
-               ixgbe_write_eitr(q_vector);
-       }
-}
-
 /**
  * ixgbe_irq_enable - Enable default interrupt generation settings
  * @adapter: board private structure
@@ -2528,10 +2450,6 @@ static irqreturn_t ixgbe_intr(int irq, void *data)
        ixgbe_check_fan_failure(adapter, eicr);
 
        if (napi_schedule_prep(&(q_vector->napi))) {
-               adapter->tx_ring[0]->total_packets = 0;
-               adapter->tx_ring[0]->total_bytes = 0;
-               adapter->rx_ring[0]->total_packets = 0;
-               adapter->rx_ring[0]->total_bytes = 0;
                /* would disable interrupts here but EIAM disabled it */
                __napi_schedule(&(q_vector->napi));
        }
@@ -4299,7 +4217,7 @@ static int ixgbe_poll(struct napi_struct *napi, int budget)
        if (work_done < budget) {
                napi_complete(napi);
                if (adapter->rx_itr_setting & 1)
-                       ixgbe_set_itr(adapter);
+                       ixgbe_set_itr(q_vector);
                if (!test_bit(__IXGBE_DOWN, &adapter->state))
                        ixgbe_irq_enable_queues(adapter, IXGBE_EIMS_RTX_QUEUE);
        }
@@ -5224,6 +5142,9 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
        adapter->tx_ring_count = IXGBE_DEFAULT_TXD;
        adapter->rx_ring_count = IXGBE_DEFAULT_RXD;
 
+       /* set default work limits */
+       adapter->tx_work_limit = adapter->tx_ring_count;
+
        /* initialize eeprom parameters */
        if (ixgbe_init_eeprom_params_generic(hw)) {
                e_dev_err("EEPROM initialization failed\n");
@@ -5270,7 +5191,6 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 
        tx_ring->next_to_use = 0;
        tx_ring->next_to_clean = 0;
-       tx_ring->work_limit = tx_ring->count;
        return 0;
 
 err: