Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2015-10-19

This series contains updates to i40e and i40evf only.

Kiran adds a spinlock around code accessing VSI MAC filter list to
ensure that we are synchronizing access to the filter list, otherwise
we can end up with multiple accesses at the same time which can cause
the VSI MAC filter list to get in an unstable or corrupted state.

Jesse fixes overlong BIT defines, where the RSS enabling call were
mistakenly missed.  Also fixes a bug where the enable function was
enabling the interrupt twice while trying to update the two interrupt
throttle rate thresholds for Rx and Tx, while refactoring the IRQ
enable function to simplify reading the flow.  Addressed the high
CPU utilization of some small streaming workloads that the driver should
reduce CPU in.

Anjali fixes two X722 issues with respect to EEPROM checksum verify and
reading NVM version info.  Fixed where a mask value was accidentally
replaced with a bit mask causing Flow Director sideband to be broken.

Alex Duyck fixes areas of the drivers which run from hard interrupt
context or with interrupts already disabled in netpoll, so use
napi_schedule_irqoff() instead of napi_schedule().

Mitch fixes the VF drivers to not easily give up when it is not able
to communicate with the PF driver.

Carolyn fixes a problem where our tools MAC loopback test, after driver
unbind would fail because the hardware was configured for multiqueue and
unbind operation did not clear this configuration.  Also fixed a issue
where the NVMUpdate tool gets bad data from the PHY when using the PHY
NVM feature because of contention on the MDIO interface from getting
PHY capability calls from the driver during regular operations.

Catherine fixed an issue where we were checking if autoneg was allowed
to change before checking if autoneg was changing, these checks need to
be in the reverse order.

Jean Sacren fixes up an function header comment to align the kernel-docs
with the actual code.

v2: Cleaned up the use of spin_is_locked() in patch 1 based on feedback
    from David Miller, since it always evaluates to zero on uni-processor
    builds
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 135 insertions, 73 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 7435fb396dcd..a4c5a49ddbcf 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -443,9 +443,6 @@ static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
 					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
 
-	cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)lut));
-	cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)lut));
-
 	status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL);
 
 	return status;
@@ -520,8 +517,6 @@ static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 					  I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
 					  I40E_AQC_SET_RSS_KEY_VSI_ID_MASK));
 	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID);
-	cmd_resp->addr_high = cpu_to_le32(high_16_bits((u64)key));
-	cmd_resp->addr_low = cpu_to_le32(lower_32_bits((u64)key));
 
 	status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL);
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 97493a4164eb..47e9a90d6b10 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -318,6 +318,8 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector
  * i40e_set_new_dynamic_itr - Find new ITR level
  * @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
@@ -326,21 +328,32 @@ static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector
  * testing data as well as attempting to minimize response time
  * while increasing bulk throughput.
  **/
-static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
+static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 {
 	enum i40e_latency_range new_latency_range = rc->latency_range;
+	struct i40e_q_vector *qv = rc->ring->q_vector;
 	u32 new_itr = rc->itr;
 	int bytes_per_int;
+	int usecs;
 
 	if (rc->total_packets == 0 || !rc->itr)
-		return;
+		return false;
 
 	/* simple throttlerate management
-	 *   0-10MB/s   lowest (100000 ints/s)
+	 *   0-10MB/s   lowest (50000 ints/s)
 	 *  10-20MB/s   low    (20000 ints/s)
-	 *  20-1249MB/s bulk   (8000 ints/s)
+	 *  20-1249MB/s bulk   (18000 ints/s)
+	 *  > 40000 Rx packets per second (8000 ints/s)
+	 *
+	 * 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.
 	 */
-	bytes_per_int = rc->total_bytes / rc->itr;
+	usecs = (rc->itr << 1) * ITR_COUNTDOWN_START;
+	bytes_per_int = rc->total_bytes / usecs;
+
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
 		if (bytes_per_int > 10)
@@ -353,35 +366,52 @@ static void i40e_set_new_dynamic_itr(struct i40e_ring_container *rc)
 			new_latency_range = I40E_LOWEST_LATENCY;
 		break;
 	case I40E_BULK_LATENCY:
-		if (bytes_per_int <= 20)
-			new_latency_range = I40E_LOW_LATENCY;
-		break;
+	case I40E_ULTRA_LATENCY:
 	default:
 		if (bytes_per_int <= 20)
 			new_latency_range = I40E_LOW_LATENCY;
 		break;
 	}
+
+	/* this is to adjust RX more aggressively when streaming small
+	 * packets.  The value of 40000 was picked as it is just beyond
+	 * what the hardware can receive per second if in low latency
+	 * mode.
+	 */
+#define RX_ULTRA_PACKET_RATE 40000
+
+	if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) &&
+	    (&qv->rx == rc))
+		new_latency_range = I40E_ULTRA_LATENCY;
+
 	rc->latency_range = new_latency_range;
 
 	switch (new_latency_range) {
 	case I40E_LOWEST_LATENCY:
-		new_itr = I40E_ITR_100K;
+		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;
+	case I40E_ULTRA_LATENCY:
 		new_itr = I40E_ITR_8K;
 		break;
 	default:
 		break;
 	}
 
-	if (new_itr != rc->itr)
-		rc->itr = new_itr;
-
 	rc->total_bytes = 0;
 	rc->total_packets = 0;
+
+	if (new_itr != rc->itr) {
+		rc->itr = new_itr;
+		return true;
+	}
+
+	return false;
 }
 
 /*
@@ -1187,6 +1217,21 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 	return total_rx_packets;
 }
 
+static u32 i40e_buildreg_itr(const int type, const u16 itr)
+{
+	u32 val;
+
+	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);
+
+	return val;
+}
+
+/* a small macro to shorten up some long lines */
+#define INTREG I40E_VFINT_DYN_CTLN1
+
 /**
  * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt
  * @vsi: the VSI we care about
@@ -1197,55 +1242,67 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 					  struct i40e_q_vector *q_vector)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	u16 old_itr;
+	bool rx = false, tx = false;
+	u32 rxval, txval;
 	int vector;
-	u32 val;
 
 	vector = (q_vector->v_idx + vsi->base_vector);
+
+	/* avoid dynamic calculation if in countdown mode OR if
+	 * all dynamic is disabled
+	 */
+	rxval = txval = i40e_buildreg_itr(I40E_ITR_NONE, 0);
+
+	if (q_vector->itr_countdown > 0 ||
+	    (!ITR_IS_DYNAMIC(vsi->rx_itr_setting) &&
+	     !ITR_IS_DYNAMIC(vsi->tx_itr_setting))) {
+		goto enable_int;
+	}
+
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting)) {
-		old_itr = q_vector->rx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->rx);
-		if (old_itr != q_vector->rx.itr) {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-			(I40E_RX_ITR <<
-				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
-			(q_vector->rx.itr <<
-				I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
-		} else {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-			I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-			(I40E_ITR_NONE <<
-				I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
-	} else {
-		i40evf_irq_enable_queues(vsi->back, 1
-			<< q_vector->v_idx);
+		rx = i40e_set_new_dynamic_itr(&q_vector->rx);
+		rxval = i40e_buildreg_itr(I40E_RX_ITR, q_vector->rx.itr);
 	}
 	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting)) {
-		old_itr = q_vector->tx.itr;
-		i40e_set_new_dynamic_itr(&q_vector->tx);
-		if (old_itr != q_vector->tx.itr) {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-				(I40E_TX_ITR <<
-				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) |
-				(q_vector->tx.itr <<
-				   I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT);
+		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);
 
-		} else {
-			val = I40E_VFINT_DYN_CTLN1_INTENA_MASK |
-				I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK |
-				(I40E_ITR_NONE <<
-				   I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT);
-		}
-		if (!test_bit(__I40E_DOWN, &vsi->state))
-			wr32(hw, I40E_VFINT_DYN_CTLN1(vector - 1), val);
-	} else {
-		i40evf_irq_enable_queues(vsi->back, BIT(q_vector->v_idx));
+		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
+	 */
+	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)
+		 */
+		rxval |= BIT(31);
+		/* don't check _DOWN because interrupt isn't being enabled */
+		wr32(hw, INTREG(vector - 1), rxval);
+	}
+
+enable_int:
+	if (!test_bit(__I40E_DOWN, &vsi->state))
+		wr32(hw, INTREG(vector - 1), txval);
+
+	if (q_vector->itr_countdown)
+		q_vector->itr_countdown--;
+	else
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index c4f5a4eb2907..ebc1bf77f036 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -32,12 +32,14 @@
 #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            I40E_ITR_8K
-#define I40E_ITR_TX_DEF            I40E_ITR_4K
+#define I40E_ITR_RX_DEF            I40E_ITR_20K
+#define I40E_ITR_TX_DEF            I40E_ITR_20K
 #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) */
@@ -89,16 +91,16 @@ enum i40e_dyn_idx_t {
 	BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
 
 #define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \
-		BIT(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-		BIT(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 #define i40e_pf_get_default_rss_hena(pf) \
 	(((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \
-		I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
+	  I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
 
 /* Supported Rx Buffer Sizes */
 #define I40E_RXBUFFER_512   512    /* Used for packet split */
@@ -291,6 +293,7 @@ enum i40e_latency_range {
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
 	I40E_BULK_LATENCY = 2,
+	I40E_ULTRA_LATENCY = 3,
 };
 
 struct i40e_ring_container {
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 85af3b48effc..301fe2b6dd03 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -1055,8 +1055,8 @@ enum i40e_filter_program_desc_fd_status {
 };
 
 #define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT	23
-#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK \
-				       BIT_ULL(I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
+#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK	(0x1FFUL << \
+					 I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT)
 
 #define I40E_TXD_FLTR_QW1_CMD_SHIFT	4
 #define I40E_TXD_FLTR_QW1_CMD_MASK	(0xFFFFULL << \
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 22841c619f37..22fc3d49c4b9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -112,6 +112,8 @@ struct i40e_q_vector {
 	struct i40e_ring_container tx;
 	u32 ring_mask;
 	u8 num_ringpairs;	/* total number of ring pairs in vector */
+#define ITR_COUNTDOWN_START 100
+	u8 itr_countdown;	/* when 0 or 1 update ITR */
 	int v_idx;	  /* vector index in list */
 	char name[IFNAMSIZ + 9];
 	bool arm_wb_state;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 4c4340cc4f45..10b2a4a33c68 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf";
 static const char i40evf_driver_string[] =
 	"Intel(R) XL710/X710 Virtual Function Network Driver";
 
-#define DRV_VERSION "1.3.21"
+#define DRV_VERSION "1.3.25"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2015 Intel Corporation.";
@@ -334,7 +334,7 @@ static irqreturn_t i40evf_msix_clean_rings(int irq, void *data)
 	if (!q_vector->tx.ring && !q_vector->rx.ring)
 		return IRQ_HANDLED;
 
-	napi_schedule(&q_vector->napi);
+	napi_schedule_irqoff(&q_vector->napi);
 
 	return IRQ_HANDLED;
 }
@@ -357,6 +357,7 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx)
 	q_vector->rx.ring = rx_ring;
 	q_vector->rx.count++;
 	q_vector->rx.latency_range = I40E_LOW_LATENCY;
+	q_vector->itr_countdown = ITR_COUNTDOWN_START;
 }
 
 /**
@@ -377,6 +378,7 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx)
 	q_vector->tx.ring = tx_ring;
 	q_vector->tx.count++;
 	q_vector->tx.latency_range = I40E_LOW_LATENCY;
+	q_vector->itr_countdown = ITR_COUNTDOWN_START;
 	q_vector->num_ringpairs++;
 	q_vector->ring_mask |= BIT(t_idx);
 }
@@ -2357,9 +2359,12 @@ err_alloc:
 err:
 	/* Things went into the weeds, so try again later */
 	if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) {
-		dev_err(&pdev->dev, "Failed to communicate with PF; giving up\n");
+		dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n");
 		adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
-		return; /* do not reschedule */
+		i40evf_shutdown_adminq(hw);
+		adapter->state = __I40EVF_STARTUP;
+		schedule_delayed_work(&adapter->init_task, HZ * 5);
+		return;
 	}
 	schedule_delayed_work(&adapter->init_task, HZ);
 }