diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c96e581..7aea143 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -828,6 +828,7 @@
 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;
@@ -836,9 +837,10 @@
 		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
@@ -859,24 +861,37 @@
 			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:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 7c0ed84..0fe7eb77 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -32,7 +32,9 @@
 #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 */
@@ -296,6 +298,7 @@
 	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_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 7d98042..d76fe4a 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -331,6 +331,7 @@
 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;
@@ -339,9 +340,10 @@
 		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
@@ -362,24 +364,37 @@
 			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:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 03275eb..e2352b8 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -32,7 +32,9 @@
 #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 */
@@ -291,6 +293,7 @@
 	I40E_LOWEST_LATENCY = 0,
 	I40E_LOW_LATENCY = 1,
 	I40E_BULK_LATENCY = 2,
+	I40E_ULTRA_LATENCY = 3,
 };
 
 struct i40e_ring_container {