be2net: fix adaptive interrupt coalescing

The current EQ delay calculation for AIC is based only on RX packet rate.
This fails to be effective when there's only TX and no RX.
This patch inclues:
- Calculating EQ-delay based on both RX and TX pps.
- Modifying EQ-delay of all EQs via one cmd, instead of issuing a separate
  cmd for each EQ.
- A new structure to store interrupt coalescing parameters, in a separate
  cache-line from the EQ-obj.

Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 68 insertions, 42 deletions

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 961e9f0500c5..6691d75b6cca 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1261,53 +1261,79 @@ static int be_set_vf_tx_rate(struct net_device *netdev,
         return status;
 }
 
-static void be_eqd_update(struct be_adapter *adapter, struct be_eq_obj *eqo)
+static void be_aic_update(struct be_aic_obj *aic, u64 rx_pkts, u64 tx_pkts,
+                          ulong now)
 {
-        struct be_rx_stats *stats = rx_stats(&adapter->rx_obj[eqo->idx]);
-        ulong now = jiffies;
-        ulong delta = now - stats->rx_jiffies;
-        u64 pkts;
-        unsigned int start, eqd;
+        aic->rx_pkts_prev = rx_pkts;
+        aic->tx_reqs_prev = tx_pkts;
+        aic->jiffies = now;
+}
 
-        if (!eqo->enable_aic) {
-                eqd = eqo->eqd;
-                goto modify_eqd;
-        }
+static void be_eqd_update(struct be_adapter *adapter)
+{
+        struct be_set_eqd set_eqd[MAX_EVT_QS];
+        int eqd, i, num = 0, start;
+        struct be_aic_obj *aic;
+        struct be_eq_obj *eqo;
+        struct be_rx_obj *rxo;
+        struct be_tx_obj *txo;
+        u64 rx_pkts, tx_pkts;
+        ulong now;
+        u32 pps, delta;
 
-        if (eqo->idx >= adapter->num_rx_qs)
-                return;
+        for_all_evt_queues(adapter, eqo, i) {
+                aic = &adapter->aic_obj[eqo->idx];
+                if (!aic->enable) {
+                        if (aic->jiffies)
+                                aic->jiffies = 0;
+                        eqd = aic->et_eqd;
+                        goto modify_eqd;
+                }
 
-        stats = rx_stats(&adapter->rx_obj[eqo->idx]);
+                rxo = &adapter->rx_obj[eqo->idx];
+                do {
+                        start = u64_stats_fetch_begin_bh(&rxo->stats.sync);
+                        rx_pkts = rxo->stats.rx_pkts;
+                } while (u64_stats_fetch_retry_bh(&rxo->stats.sync, start));
 
-        /* Wrapped around */
-        if (time_before(now, stats->rx_jiffies)) {
-                stats->rx_jiffies = now;
-                return;
-        }
+                txo = &adapter->tx_obj[eqo->idx];
+                do {
+                        start = u64_stats_fetch_begin_bh(&txo->stats.sync);
+                        tx_pkts = txo->stats.tx_reqs;
+                } while (u64_stats_fetch_retry_bh(&txo->stats.sync, start));
 
-        /* Update once a second */
-        if (delta < HZ)
-                return;
 
-        do {
-                start = u64_stats_fetch_begin_bh(&stats->sync);
-                pkts = stats->rx_pkts;
-        } while (u64_stats_fetch_retry_bh(&stats->sync, start));
-
-        stats->rx_pps = (unsigned long)(pkts - stats->rx_pkts_prev) / (delta / HZ);
-        stats->rx_pkts_prev = pkts;
-        stats->rx_jiffies = now;
-        eqd = (stats->rx_pps / 110000) << 3;
-        eqd = min(eqd, eqo->max_eqd);
-        eqd = max(eqd, eqo->min_eqd);
-        if (eqd < 10)
-                eqd = 0;
+                /* Skip, if wrapped around or first calculation */
+                now = jiffies;
+                if (!aic->jiffies || time_before(now, aic->jiffies) ||
+                    rx_pkts < aic->rx_pkts_prev ||
+                    tx_pkts < aic->tx_reqs_prev) {
+                        be_aic_update(aic, rx_pkts, tx_pkts, now);
+                        continue;
+                }
+
+                delta = jiffies_to_msecs(now - aic->jiffies);
+                pps = (((u32)(rx_pkts - aic->rx_pkts_prev) * 1000) / delta) +
+                        (((u32)(tx_pkts - aic->tx_reqs_prev) * 1000) / delta);
+                eqd = (pps / 15000) << 2;
 
+                if (eqd < 8)
+                        eqd = 0;
+                eqd = min_t(u32, eqd, aic->max_eqd);
+                eqd = max_t(u32, eqd, aic->min_eqd);
+
+                be_aic_update(aic, rx_pkts, tx_pkts, now);
 modify_eqd:
-        if (eqd != eqo->cur_eqd) {
-                be_cmd_modify_eqd(adapter, eqo->q.id, eqd);
-                eqo->cur_eqd = eqd;
+                if (eqd != aic->prev_eqd) {
+                        set_eqd[num].delay_multiplier = (eqd * 65)/100;
+                        set_eqd[num].eq_id = eqo->q.id;
+                        aic->prev_eqd = eqd;
+                        num++;
+                }
         }
+
+        if (num)
+                be_cmd_modify_eqd(adapter, set_eqd, num);
 }
 
 static void be_rx_stats_update(struct be_rx_obj *rxo,
@@ -1924,6 +1950,7 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 {
         struct be_queue_info *eq;
         struct be_eq_obj *eqo;
+        struct be_aic_obj *aic;
         int i, rc;
 
         adapter->num_evt_qs = min_t(u16, num_irqs(adapter),
@@ -1932,11 +1959,12 @@ static int be_evt_queues_create(struct be_adapter *adapter)
         for_all_evt_queues(adapter, eqo, i) {
                 netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
                                BE_NAPI_WEIGHT);
+                aic = &adapter->aic_obj[i];
                 eqo->adapter = adapter;
                 eqo->tx_budget = BE_TX_BUDGET;
                 eqo->idx = i;
-                eqo->max_eqd = BE_MAX_EQD;
-                eqo->enable_aic = true;
+                aic->max_eqd = BE_MAX_EQD;
+                aic->enable = true;
 
                 eq = &eqo->q;
                 rc = be_queue_alloc(adapter, eq, EVNT_Q_LEN,
@@ -4240,7 +4268,6 @@ static void be_worker(struct work_struct *work)
         struct be_adapter *adapter =
                 container_of(work, struct be_adapter, work.work);
         struct be_rx_obj *rxo;
-        struct be_eq_obj *eqo;
         int i;
 
         /* when interrupts are not yet enabled, just reap any pending
@@ -4271,8 +4298,7 @@ static void be_worker(struct work_struct *work)
                 }
         }
 
-        for_all_evt_queues(adapter, eqo, i)
-                be_eqd_update(adapter, eqo);
+        be_eqd_update(adapter);
 
 reschedule:
         adapter->work_counter++;