DPDK patches and discussions
 help / color / mirror / Atom feed
From: Vlad Zolotarov <vladz@cloudius-systems.com>
To: dev@dpdk.org
Subject: [dpdk-dev]  [PATCH v8 3/3] ixgbe: Add LRO support
Date: Wed, 18 Mar 2015 19:52:24 +0200	[thread overview]
Message-ID: <1426701144-21231-4-git-send-email-vladz@cloudius-systems.com> (raw)
In-Reply-To: <1426701144-21231-1-git-send-email-vladz@cloudius-systems.com>

    - Only x540 and 82599 devices support LRO.
    - Add the appropriate HW configuration.
    - Add RSC aware rx_pkt_burst() handlers:
       - Implemented bulk allocation and non-bulk allocation versions.
       - Add LRO-specific fields to rte_eth_rxmode, to rte_eth_dev_data
         and to ixgbe_rx_queue.
       - Use the appropriate handler when LRO is requested.

Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
---
New in v8:
   - Took the RSC configuration code from ixgbe_dev_rx_init() into a separate
     function - ixgbe_set_rsc().
   - Added some missing macros for HW configuration.
   - Styling adjustments:
      - Functions names.
      - Functions descriptions.
   - Reworked the ixgbe_free_rsc_cluster() code to make it more readable.
   - Kill the HEADER_SPLIT flow in ixgbe_set_rsc() since it's not supported by
     ixgbe PMD.

New in v7:
   - Free not-yet-completed RSC aggregations in rte_eth_dev_stop() flow.
   - Reset the sw_ring[].mbuf entry in a bulk allocation case.
     This is needed for ixgbe_rx_queue_release_mbufs().
   - _recv_pkts_lro(): added the missing memory barrier before RDT update in a
     non-bulk allocation case.
   - Don't allow RSC when device is configured in an SR-IOV mode.

New in v5:
   - Put the RTE_ETHDEV_HAS_LRO_SUPPORT definition at the beginning of rte_ethdev.h.
   - Removed the "TODO: Remove me" comment near RTE_ETHDEV_HAS_LRO_SUPPORT.

New in v4:
   - Define RTE_ETHDEV_HAS_LRO_SUPPORT in rte_ethdev.h instead of
     RTE_ETHDEV_LRO_SUPPORT defined in config/common_linuxapp.

New in v2:
   - Removed rte_eth_dev_data.lro_bulk_alloc.
   - Fixed a few styling and spelling issues.
---
 lib/librte_ether/rte_ethdev.h           |   9 +-
 lib/librte_net/rte_ip.h                 |   3 +
 lib/librte_pmd_ixgbe/ixgbe/ixgbe_type.h |   6 +
 lib/librte_pmd_ixgbe/ixgbe_ethdev.c     |  11 +
 lib/librte_pmd_ixgbe/ixgbe_ethdev.h     |   5 +
 lib/librte_pmd_ixgbe/ixgbe_rxtx.c       | 610 +++++++++++++++++++++++++++++++-
 lib/librte_pmd_ixgbe/ixgbe_rxtx.h       |   6 +
 7 files changed, 642 insertions(+), 8 deletions(-)

diff --git a/lib/librte_ether/rte_ethdev.h b/lib/librte_ether/rte_ethdev.h
index 21aa359..61dc49a 100644
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -172,6 +172,9 @@ extern "C" {
 
 #include <stdint.h>
 
+/* Use this macro to check if LRO API is supported */
+#define RTE_ETHDEV_HAS_LRO_SUPPORT
+
 #include <rte_log.h>
 #include <rte_interrupts.h>
 #include <rte_pci.h>
@@ -320,14 +323,15 @@ struct rte_eth_rxmode {
 	enum rte_eth_rx_mq_mode mq_mode;
 	uint32_t max_rx_pkt_len;  /**< Only used if jumbo_frame enabled. */
 	uint16_t split_hdr_size;  /**< hdr buf size (header_split enabled).*/
-	uint8_t header_split : 1, /**< Header Split enable. */
+	uint16_t header_split : 1, /**< Header Split enable. */
 		hw_ip_checksum   : 1, /**< IP/UDP/TCP checksum offload enable. */
 		hw_vlan_filter   : 1, /**< VLAN filter enable. */
 		hw_vlan_strip    : 1, /**< VLAN strip enable. */
 		hw_vlan_extend   : 1, /**< Extended VLAN enable. */
 		jumbo_frame      : 1, /**< Jumbo Frame Receipt enable. */
 		hw_strip_crc     : 1, /**< Enable CRC stripping by hardware. */
-		enable_scatter   : 1; /**< Enable scatter packets rx handler */
+		enable_scatter   : 1, /**< Enable scatter packets rx handler */
+		enable_lro       : 1; /**< Enable LRO */
 };
 
 /**
@@ -1515,6 +1519,7 @@ struct rte_eth_dev_data {
 	uint8_t port_id;           /**< Device [external] port identifier. */
 	uint8_t promiscuous   : 1, /**< RX promiscuous mode ON(1) / OFF(0). */
 		scattered_rx : 1,  /**< RX of scattered packets is ON(1) / OFF(0) */
+		lro          : 1,  /**< RX LRO is ON(1) / OFF(0) */
 		all_multicast : 1, /**< RX all multicast mode ON(1) / OFF(0). */
 		dev_started : 1;   /**< Device state: STARTED(1) / STOPPED(0). */
 };
diff --git a/lib/librte_net/rte_ip.h b/lib/librte_net/rte_ip.h
index 64935d9..74c9ced 100644
--- a/lib/librte_net/rte_ip.h
+++ b/lib/librte_net/rte_ip.h
@@ -110,6 +110,9 @@ struct ipv4_hdr {
 					   (((c) & 0xff) << 8)  | \
 					   ((d) & 0xff))
 
+/** Maximal IPv4 packet length (including a header) */
+#define IPV4_MAX_PKT_LEN        65535
+
 /** Internet header length mask for version_ihl field */
 #define IPV4_HDR_IHL_MASK	(0x0f)
 /**
diff --git a/lib/librte_pmd_ixgbe/ixgbe/ixgbe_type.h b/lib/librte_pmd_ixgbe/ixgbe/ixgbe_type.h
index 9a66370..4998627 100644
--- a/lib/librte_pmd_ixgbe/ixgbe/ixgbe_type.h
+++ b/lib/librte_pmd_ixgbe/ixgbe/ixgbe_type.h
@@ -234,8 +234,14 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_EITR(_i)		(((_i) <= 23) ? (0x00820 + ((_i) * 4)) : \
 				 (0x012300 + (((_i) - 24) * 4)))
 #define IXGBE_EITR_ITR_INT_MASK	0x00000FF8
+#define IXGBE_EITR_ITR_INT_SHIFT 3
 #define IXGBE_EITR_LLI_MOD	0x00008000
 #define IXGBE_EITR_CNT_WDIS	0x80000000
+/* EITR Inteval is in 2048ns uinits for 1G and 10G link */
+#define IXGBE_EITR_INTERVAL_UNIT_NS	2048
+#define IXGBE_EITR_INTERVAL_US(us)	\
+   (((us) * 1000 / IXGBE_EITR_INTERVAL_UNIT_NS << IXGBE_EITR_ITR_INT_SHIFT) & \
+		IXGBE_EITR_ITR_INT_MASK)
 #define IXGBE_IVAR(_i)		(0x00900 + ((_i) * 4)) /* 24 at 0x900-0x960 */
 #define IXGBE_IVAR_MISC		0x00A00 /* misc MSI-X interrupt causes */
 #define IXGBE_EITRSEL		0x00894
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethdev.c b/lib/librte_pmd_ixgbe/ixgbe_ethdev.c
index 92d75db..923692e 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_ethdev.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_ethdev.c
@@ -1645,6 +1645,7 @@ ixgbe_dev_stop(struct rte_eth_dev *dev)
 
 	/* Clear stored conf */
 	dev->data->scattered_rx = 0;
+	dev->data->lro = 0;
 
 	/* Clear recorded link status */
 	memset(&link, 0, sizeof(link));
@@ -2013,6 +2014,16 @@ ixgbe_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 		DEV_RX_OFFLOAD_IPV4_CKSUM |
 		DEV_RX_OFFLOAD_UDP_CKSUM  |
 		DEV_RX_OFFLOAD_TCP_CKSUM;
+
+	/*
+	 * RSC is only supported by 82599 and x540 PF devices in a non-SR-IOV
+	 * mode.
+	 */
+	if ((hw->mac.type == ixgbe_mac_82599EB ||
+	     hw->mac.type == ixgbe_mac_X540) &&
+	    !RTE_ETH_DEV_SRIOV(dev).active)
+		dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO;
+
 	dev_info->tx_offload_capa =
 		DEV_TX_OFFLOAD_VLAN_INSERT |
 		DEV_TX_OFFLOAD_IPV4_CKSUM  |
diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethdev.h b/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
index ffe3471..7050340 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
+++ b/lib/librte_pmd_ixgbe/ixgbe_ethdev.h
@@ -344,6 +344,11 @@ uint16_t ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 uint16_t ixgbe_recv_scattered_pkts(void *rx_queue,
 		struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
 
+uint16_t ixgbe_recv_pkts_lro_single_alloc(void *rx_queue,
+		struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+uint16_t ixgbe_recv_pkts_lro_bulk_alloc(void *rx_queue,
+		struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+
 uint16_t ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 		uint16_t nb_pkts);
 
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
index a08ae6a..daa4c45 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c
@@ -70,6 +70,7 @@
 #include <rte_sctp.h>
 #include <rte_string_fns.h>
 #include <rte_errno.h>
+#include <rte_ip.h>
 
 #include "ixgbe_logs.h"
 #include "ixgbe/ixgbe_api.h"
@@ -1422,6 +1423,295 @@ ixgbe_fill_cluster_head_buf(
 	}
 }
 
+/**
+ * ixgbe_recv_pkts_lro - receive handler for and LRO case.
+ *
+ * @rx_queue Rx queue handle
+ * @rx_pkts table of received packets
+ * @nb_pkts size of rx_pkts table
+ * @bulk_alloc if TRUE bulk allocation is used for a HW ring refilling
+ *
+ * Handles the Rx HW ring completions when RSC feature is configured. Uses an
+ * additional ring of ixgbe_rsc_entry's that will hold the relevant RSC info.
+ *
+ * We use the same logic as in Lunux and in FreeBSD ixgbe drivers:
+ * 1) When non-EOP RSC completion arrives:
+ *    a) Update the HEAD of the current RSC aggregation cluster with the new
+ *       segment's data length.
+ *    b) Set the "next" pointer of the current segment to point to the segment
+ *       at the NEXTP index.
+ *    c) Pass the HEAD of RSC aggregation cluster on to the next NEXTP entry
+ *       in the sw_rsc_ring.
+ * 2) When EOP arrives we just update the cluster's total length and offload
+ *    flags and deliver the cluster up to the upper layers. In our case - put it
+ *    in the rx_pkts table.
+ *
+ * Returns the number of received packets/clusters (according to the "bulk
+ * receive" interface).
+ */
+static inline uint16_t
+ixgbe_recv_pkts_lro(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts,
+		    bool bulk_alloc)
+{
+	struct ixgbe_rx_queue *rxq = rx_queue;
+	volatile union ixgbe_adv_rx_desc *rx_ring = rxq->rx_ring;
+	struct ixgbe_rx_entry *sw_ring = rxq->sw_ring;
+	struct ixgbe_rsc_entry *sw_rsc_ring = rxq->sw_rsc_ring;
+	uint16_t rx_id = rxq->rx_tail;
+	uint16_t nb_rx = 0;
+	uint16_t nb_hold = rxq->nb_rx_hold;
+	uint16_t prev_id = rxq->rx_tail;
+
+	while (nb_rx < nb_pkts) {
+		bool eop;
+		struct ixgbe_rx_entry *rxe;
+		struct ixgbe_rsc_entry *rsc_entry;
+		struct ixgbe_rsc_entry *next_rsc_entry;
+		struct ixgbe_rx_entry *next_rxe;
+		struct rte_mbuf *first_seg;
+		struct rte_mbuf *rxm;
+		struct rte_mbuf *nmb;
+		union ixgbe_adv_rx_desc rxd;
+		uint16_t data_len;
+		uint16_t next_id;
+		volatile union ixgbe_adv_rx_desc *rxdp;
+		uint32_t staterr;
+
+next_desc:
+		/*
+		 * The code in this whole file uses the volatile pointer to
+		 * ensure the read ordering of the status and the rest of the
+		 * descriptor fields (on the compiler level only!!!). This is so
+		 * UGLY - why not to just use the compiler barrier instead? DPDK
+		 * even has the rte_compiler_barrier() for that.
+		 *
+		 * But most importantly this is just wrong because this doesn't
+		 * ensure memory ordering in a general case at all. For
+		 * instance, DPDK is supposed to work on Power CPUs where
+		 * compiler barrier may just not be enough!
+		 *
+		 * I tried to write only this function properly to have a
+		 * starting point (as a part of an LRO/RSC series) but the
+		 * compiler cursed at me when I tried to cast away the
+		 * "volatile" from rx_ring (yes, it's volatile too!!!). So, I'm
+		 * keeping it the way it is for now.
+		 *
+		 * The code in this file is broken in so many other places and
+		 * will just not work on a big endian CPU anyway therefore the
+		 * lines below will have to be revisited together with the rest
+		 * of the ixgbe PMD.
+		 *
+		 * TODO:
+		 *    - Get rid of "volatile" crap and let the compiler do its
+		 *      job.
+		 *    - Use the proper memory barrier (rte_rmb()) to ensure the
+		 *      memory ordering below.
+		 */
+		rxdp = &rx_ring[rx_id];
+		staterr = rte_le_to_cpu_32(rxdp->wb.upper.status_error);
+
+		if (!(staterr & IXGBE_RXDADV_STAT_DD))
+			break;
+
+		rxd = *rxdp;
+
+		PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_id=%u "
+				  "staterr=0x%x data_len=%u",
+			   rxq->port_id, rxq->queue_id, rx_id, staterr,
+			   rte_le_to_cpu_16(rxd.wb.upper.length));
+
+		if (!bulk_alloc) {
+			nmb = rte_rxmbuf_alloc(rxq->mb_pool);
+			if (nmb == NULL) {
+				PMD_RX_LOG(DEBUG, "RX mbuf alloc failed "
+						  "port_id=%u queue_id=%u",
+					   rxq->port_id, rxq->queue_id);
+
+				rte_eth_devices[rxq->port_id].data->
+							rx_mbuf_alloc_failed++;
+				break;
+			}
+		} else if (nb_hold > rxq->rx_free_thresh) {
+			uint16_t next_rdt = rxq->rx_free_trigger;
+
+			if (!ixgbe_rx_alloc_bufs(rxq, false)) {
+				rte_wmb();
+				IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr,
+						    next_rdt);
+				nb_hold -= rxq->rx_free_thresh;
+			} else {
+				PMD_RX_LOG(DEBUG, "RX bulk alloc failed "
+						  "port_id=%u queue_id=%u",
+					   rxq->port_id, rxq->queue_id);
+
+				rte_eth_devices[rxq->port_id].data->
+							rx_mbuf_alloc_failed++;
+				break;
+			}
+		}
+
+		nb_hold++;
+		rxe = &sw_ring[rx_id];
+		eop = staterr & IXGBE_RXDADV_STAT_EOP;
+
+		next_id = rx_id + 1;
+		if (next_id == rxq->nb_rx_desc)
+			next_id = 0;
+
+		/* Prefetch next mbuf while processing current one. */
+		rte_ixgbe_prefetch(sw_ring[next_id].mbuf);
+
+		/*
+		 * When next RX descriptor is on a cache-line boundary,
+		 * prefetch the next 4 RX descriptors and the next 4 pointers
+		 * to mbufs.
+		 */
+		if ((next_id & 0x3) == 0) {
+			rte_ixgbe_prefetch(&rx_ring[next_id]);
+			rte_ixgbe_prefetch(&sw_ring[next_id]);
+		}
+
+		rxm = rxe->mbuf;
+
+		if (!bulk_alloc) {
+			__le64 dma =
+			  rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(nmb));
+			/*
+			 * Update RX descriptor with the physical address of the
+			 * new data buffer of the new allocated mbuf.
+			 */
+			rxe->mbuf = nmb;
+
+			rxm->data_off = RTE_PKTMBUF_HEADROOM;
+			rxdp->read.hdr_addr = dma;
+			rxdp->read.pkt_addr = dma;
+		} else
+			rxe->mbuf = NULL;
+
+		/*
+		 * Set data length & data buffer address of mbuf.
+		 */
+		data_len = rte_le_to_cpu_16(rxd.wb.upper.length);
+		rxm->data_len = data_len;
+
+		if (!eop) {
+			uint16_t nextp_id;
+			/*
+			 * Get next descriptor index:
+			 *  - For RSC it's in the NEXTP field.
+			 *  - For a scattered packet - it's just a following
+			 *    descriptor.
+			 */
+			if (ixgbe_rsc_count(&rxd))
+				nextp_id =
+					(staterr & IXGBE_RXDADV_NEXTP_MASK) >>
+						       IXGBE_RXDADV_NEXTP_SHIFT;
+			else
+				nextp_id = next_id;
+
+			next_rsc_entry = &sw_rsc_ring[nextp_id];
+			next_rxe = &sw_ring[nextp_id];
+			rte_ixgbe_prefetch(next_rxe);
+		}
+
+		rsc_entry = &sw_rsc_ring[rx_id];
+		first_seg = rsc_entry->fbuf;
+		rsc_entry->fbuf = NULL;
+
+		/*
+		 * If this is the first buffer of the received packet,
+		 * set the pointer to the first mbuf of the packet and
+		 * initialize its context.
+		 * Otherwise, update the total length and the number of segments
+		 * of the current scattered packet, and update the pointer to
+		 * the last mbuf of the current packet.
+		 */
+		if (first_seg == NULL) {
+			first_seg = rxm;
+			first_seg->pkt_len = data_len;
+			first_seg->nb_segs = 1;
+		} else {
+			first_seg->pkt_len += data_len;
+			first_seg->nb_segs++;
+		}
+
+		prev_id = rx_id;
+		rx_id = next_id;
+
+		/*
+		 * If this is not the last buffer of the received packet, update
+		 * the pointer to the first mbuf at the NEXTP entry in the
+		 * sw_rsc_ring and continue to parse the RX ring.
+		 */
+		if (!eop) {
+			rxm->next = next_rxe->mbuf;
+			next_rsc_entry->fbuf = first_seg;
+			goto next_desc;
+		}
+
+		/*
+		 * This is the last buffer of the received packet - return
+		 * the current cluster to the user.
+		 */
+		rxm->next = NULL;
+
+		/* Initialize the first mbuf of the returned packet */
+		ixgbe_fill_cluster_head_buf(first_seg, &rxd, rxq->port_id,
+					    staterr);
+
+		/* Prefetch data of first segment, if configured to do so. */
+		rte_packet_prefetch((char *)first_seg->buf_addr +
+			first_seg->data_off);
+
+		/*
+		 * Store the mbuf address into the next entry of the array
+		 * of returned packets.
+		 */
+		rx_pkts[nb_rx++] = first_seg;
+	}
+
+	/*
+	 * Record index of the next RX descriptor to probe.
+	 */
+	rxq->rx_tail = rx_id;
+
+	/*
+	 * If the number of free RX descriptors is greater than the RX free
+	 * threshold of the queue, advance the Receive Descriptor Tail (RDT)
+	 * register.
+	 * Update the RDT with the value of the last processed RX descriptor
+	 * minus 1, to guarantee that the RDT register is never equal to the
+	 * RDH register, which creates a "full" ring situtation from the
+	 * hardware point of view...
+	 */
+	if (!bulk_alloc && nb_hold > rxq->rx_free_thresh) {
+		PMD_RX_LOG(DEBUG, "port_id=%u queue_id=%u rx_tail=%u "
+			   "nb_hold=%u nb_rx=%u",
+			   rxq->port_id, rxq->queue_id, rx_id, nb_hold, nb_rx);
+
+		rte_wmb();
+		IXGBE_PCI_REG_WRITE(rxq->rdt_reg_addr, prev_id);
+		nb_hold = 0;
+	}
+
+	rxq->nb_rx_hold = nb_hold;
+	return nb_rx;
+}
+
+uint16_t
+ixgbe_recv_pkts_lro_single_alloc(void *rx_queue, struct rte_mbuf **rx_pkts,
+				 uint16_t nb_pkts)
+{
+	return ixgbe_recv_pkts_lro(rx_queue, rx_pkts, nb_pkts, false);
+}
+
+uint16_t
+ixgbe_recv_pkts_lro_bulk_alloc(void *rx_queue, struct rte_mbuf **rx_pkts,
+			       uint16_t nb_pkts)
+{
+	return ixgbe_recv_pkts_lro(rx_queue, rx_pkts, nb_pkts, true);
+}
+
 uint16_t
 ixgbe_recv_scattered_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
 			  uint16_t nb_pkts)
@@ -2005,6 +2295,31 @@ ixgbe_dev_tx_queue_setup(struct rte_eth_dev *dev,
 	return (0);
 }
 
+/**
+ * ixgbe_free_rsc_cluster - free the not-yet-completed RSC cluster
+ *
+ * The "next" pointer of the last segment of (not-yet-completed) RSC clusters
+ * in the sw_rsc_ring is not set to NULL but rather points to the next
+ * mbuf of this RSC aggregation (that has not been completed yet and still
+ * resides on the HW ring). So, instead of calling for rte_pktmbuf_free() we
+ * will just free first "nb_segs" segments of the cluster explicitly by calling
+ * an rte_pktmbuf_free_seg().
+ *
+ * @m RSC cluster head
+ */
+static void
+ixgbe_free_rsc_cluster(struct rte_mbuf *m)
+{
+	uint8_t i, nb_segs = m->nb_segs;
+	struct rte_mbuf *next_seg;
+
+	for (i = 0; i < nb_segs; i++) {
+		next_seg = m->next;
+		rte_pktmbuf_free_seg(m);
+		m = next_seg;
+	}
+}
+
 static void
 ixgbe_rx_queue_release_mbufs(struct ixgbe_rx_queue *rxq)
 {
@@ -2028,6 +2343,13 @@ ixgbe_rx_queue_release_mbufs(struct ixgbe_rx_queue *rxq)
 		}
 #endif
 	}
+
+	if (rxq->sw_rsc_ring)
+		for (i = 0; i < rxq->nb_rx_desc; i++)
+			if (rxq->sw_rsc_ring[i].fbuf) {
+				ixgbe_free_rsc_cluster(rxq->sw_rsc_ring[i].fbuf);
+				rxq->sw_rsc_ring[i].fbuf = NULL;
+			}
 }
 
 static void
@@ -2036,6 +2358,7 @@ ixgbe_rx_queue_release(struct ixgbe_rx_queue *rxq)
 	if (rxq != NULL) {
 		ixgbe_rx_queue_release_mbufs(rxq);
 		rte_free(rxq->sw_ring);
+		rte_free(rxq->sw_rsc_ring);
 		rte_free(rxq);
 	}
 }
@@ -2158,6 +2481,7 @@ ixgbe_reset_rx_queue(struct ixgbe_hw *hw, struct ixgbe_rx_queue *rxq)
 	rxq->nb_rx_hold = 0;
 	rxq->pkt_first_seg = NULL;
 	rxq->pkt_last_seg = NULL;
+	rxq->rsc_en = 0;
 }
 
 int
@@ -2172,6 +2496,14 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	struct ixgbe_rx_queue *rxq;
 	struct ixgbe_hw     *hw;
 	uint16_t len;
+	struct rte_eth_dev_info dev_info = { 0 };
+	struct rte_eth_rxmode *dev_rx_mode = &dev->data->dev_conf.rxmode;
+	bool rsc_requested = false;
+
+	dev->dev_ops->dev_infos_get(dev, &dev_info);
+	if ((dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TCP_LRO) &&
+	    dev_rx_mode->enable_lro)
+		rsc_requested = true;
 
 	PMD_INIT_FUNC_TRACE();
 	hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
@@ -2277,12 +2609,27 @@ ixgbe_dev_rx_queue_setup(struct rte_eth_dev *dev,
 	rxq->sw_ring = rte_zmalloc_socket("rxq->sw_ring",
 					  sizeof(struct ixgbe_rx_entry) * len,
 					  RTE_CACHE_LINE_SIZE, socket_id);
-	if (rxq->sw_ring == NULL) {
+	if (!rxq->sw_ring) {
 		ixgbe_rx_queue_release(rxq);
 		return (-ENOMEM);
 	}
-	PMD_INIT_LOG(DEBUG, "sw_ring=%p hw_ring=%p dma_addr=0x%"PRIx64,
-		     rxq->sw_ring, rxq->rx_ring, rxq->rx_ring_phys_addr);
+
+	if (rsc_requested) {
+		rxq->sw_rsc_ring =
+			rte_zmalloc_socket("rxq->sw_rsc_ring",
+					   sizeof(struct ixgbe_rsc_entry) * len,
+					   RTE_CACHE_LINE_SIZE, socket_id);
+		if (!rxq->sw_rsc_ring) {
+			ixgbe_rx_queue_release(rxq);
+			return (-ENOMEM);
+		}
+	} else
+		rxq->sw_rsc_ring = NULL;
+
+	PMD_INIT_LOG(DEBUG, "sw_ring=%p sw_rsc_ring=%p hw_ring=%p "
+			    "dma_addr=0x%"PRIx64,
+		     rxq->sw_ring, rxq->sw_rsc_ring, rxq->rx_ring,
+		     rxq->rx_ring_phys_addr);
 
 	if (!rte_is_power_of_2(nb_desc)) {
 		PMD_INIT_LOG(DEBUG, "queue[%d] doesn't meet Vector Rx "
@@ -3527,6 +3874,91 @@ ixgbe_dev_mq_tx_configure(struct rte_eth_dev *dev)
 	return 0;
 }
 
+/**
+ * ixgbe_get_rscctl_maxdesc - Calculate the RSCCTL[n].MAXDESC for PF
+ *
+ * Return the RSCCTL[n].MAXDESC for 82599 and x540 PF devices according to the
+ * spec rev. 3.0 chapter 8.2.3.8.13.
+ *
+ * @pool Memory pool of the Rx queue
+ */
+static inline uint32_t
+ixgbe_get_rscctl_maxdesc(struct rte_mempool *pool)
+{
+	struct rte_pktmbuf_pool_private *mp_priv = rte_mempool_get_priv(pool);
+
+	/* MAXDESC * SRRCTL.BSIZEPKT must not exceed 64 KB minus one */
+	uint16_t maxdesc =
+		IPV4_MAX_PKT_LEN /
+			(mp_priv->mbuf_data_room_size - RTE_PKTMBUF_HEADROOM);
+
+	if (maxdesc >= 16)
+		return IXGBE_RSCCTL_MAXDESC_16;
+	else if (maxdesc >= 8)
+		return IXGBE_RSCCTL_MAXDESC_8;
+	else if (maxdesc >= 4)
+		return IXGBE_RSCCTL_MAXDESC_4;
+	else
+		return IXGBE_RSCCTL_MAXDESC_1;
+}
+
+/**
+ * ixgbe_set_ivar - Setup the correct IVAR register for a particular MSIX
+ * interrupt
+ *
+ * (Taken from FreeBSD tree)
+ * (yes this is all very magic and confusing :)
+ *
+ * @dev port handle
+ * @entry the register array entry
+ * @vector the MSIX vector for this queue
+ * @type RX/TX/MISC
+ */
+static void
+ixgbe_set_ivar(struct rte_eth_dev *dev, u8 entry, u8 vector, s8 type)
+{
+	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	u32 ivar, index;
+
+	vector |= IXGBE_IVAR_ALLOC_VAL;
+
+	switch (hw->mac.type) {
+
+	case ixgbe_mac_82598EB:
+		if (type == -1)
+			entry = IXGBE_IVAR_OTHER_CAUSES_INDEX;
+		else
+			entry += (type * 64);
+		index = (entry >> 2) & 0x1F;
+		ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index));
+		ivar &= ~(0xFF << (8 * (entry & 0x3)));
+		ivar |= (vector << (8 * (entry & 0x3)));
+		IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar);
+		break;
+
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+		if (type == -1) { /* MISC IVAR */
+			index = (entry & 1) * 8;
+			ivar = IXGBE_READ_REG(hw, IXGBE_IVAR_MISC);
+			ivar &= ~(0xFF << index);
+			ivar |= (vector << index);
+			IXGBE_WRITE_REG(hw, IXGBE_IVAR_MISC, ivar);
+		} else {	/* RX/TX IVARS */
+			index = (16 * (entry & 1)) + (8 * type);
+			ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(entry >> 1));
+			ivar &= ~(0xFF << index);
+			ivar |= (vector << index);
+			IXGBE_WRITE_REG(hw, IXGBE_IVAR(entry >> 1), ivar);
+		}
+
+		break;
+
+	default:
+		break;
+	}
+}
+
 void ixgbe_set_rx_function(struct rte_eth_dev *dev)
 {
 	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
@@ -3545,7 +3977,24 @@ void ixgbe_set_rx_function(struct rte_eth_dev *dev)
 		hw->rx_vec_allowed = false;
 	}
 
-	if (dev->data->scattered_rx) {
+	/*
+	 * Initialize the appropriate LRO callback.
+	 *
+	 * If all queues satisfy the bulk allocation preconditions
+	 * (hw->rx_bulk_alloc_allowed is TRUE) then we may use bulk allocation.
+	 * Otherwise use a single allocation version.
+	 */
+	if (dev->data->lro) {
+		if (hw->rx_bulk_alloc_allowed) {
+			PMD_INIT_LOG(INFO, "LRO is requested. Using a bulk "
+					   "allocation version");
+			dev->rx_pkt_burst = ixgbe_recv_pkts_lro_bulk_alloc;
+		} else {
+			PMD_INIT_LOG(INFO, "LRO is requested. Using a single "
+					   "allocation version");
+			dev->rx_pkt_burst = ixgbe_recv_pkts_lro_single_alloc;
+		}
+	} else if (dev->data->scattered_rx) {
 		/*
 		 * Set the non-LRO scattered callback: there are Vector and
 		 * single allocation versions.
@@ -3595,6 +4044,149 @@ void ixgbe_set_rx_function(struct rte_eth_dev *dev)
 	}
 }
 
+/**
+ * ixgbe_set_rsc - configure RSC related port HW registers
+ *
+ * Configures the port's RSC related registers according to the 4.6.7.2 chapter
+ * of 82599 Spec (x540 configuration is virtually the same).
+ *
+ * @dev port handle
+ *
+ * Returns 0 in case of success or a non-zero error code
+ */
+static int
+ixgbe_set_rsc(struct rte_eth_dev *dev)
+{
+	struct rte_eth_rxmode *rx_conf = &dev->data->dev_conf.rxmode;
+	struct ixgbe_hw *hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
+	struct rte_eth_dev_info dev_info = { 0 };
+	bool rsc_capable = false;
+	uint16_t i;
+	uint32_t rdrxctl;
+
+	/* Sanity check */
+	dev->dev_ops->dev_infos_get(dev, &dev_info);
+	if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TCP_LRO)
+		rsc_capable = true;
+
+	if (!rsc_capable && rx_conf->enable_lro) {
+		PMD_INIT_LOG(CRIT, "LRO is requested on HW that doesn't "
+				   "support it");
+		return -EINVAL;
+	}
+
+	/* RSC global configuration (chapter 4.6.7.2.1 of 82599 Spec) */
+
+	if (!rx_conf->hw_strip_crc && rx_conf->enable_lro) {
+		/*
+		 * According to chapter of 4.6.7.2.1 of the Spec Rev.
+		 * 3.0 RSC configuration requires HW CRC stripping being
+		 * enabled. If user requested both HW CRC stripping off
+		 * and RSC on - return an error.
+		 */
+		PMD_INIT_LOG(CRIT, "LRO can't be enabled when HW CRC "
+				    "is disabled");
+		return -EINVAL;
+	}
+
+	/* RFCTL configuration  */
+	if (rsc_capable) {
+		uint32_t rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL);
+		if (rx_conf->enable_lro)
+			/*
+			 * Since NFS packets coalescing is not supported - clear
+			 * RFCTL.NFSW_DIS and RFCTL.NFSR_DIS when RSC is
+			 * enabled.
+			 */
+			rfctl &= ~(IXGBE_RFCTL_RSC_DIS | IXGBE_RFCTL_NFSW_DIS |
+				   IXGBE_RFCTL_NFSR_DIS);
+		else
+			rfctl |= IXGBE_RFCTL_RSC_DIS;
+
+		IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl);
+	}
+
+	/* If LRO hasn't been requested - we are done here. */
+	if (!rx_conf->enable_lro)
+		return 0;
+
+	/* Set RDRXCTL.RSCACKC bit */
+	rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL);
+	rdrxctl |= IXGBE_RDRXCTL_RSCACKC;
+	IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
+
+	/* Per-queue RSC configuration (chapter 4.6.7.2.2 of 82599 Spec) */
+	for (i = 0; i < dev->data->nb_rx_queues; i++) {
+		struct ixgbe_rx_queue *rxq = dev->data->rx_queues[i];
+		uint32_t srrctl =
+			IXGBE_READ_REG(hw, IXGBE_SRRCTL(rxq->reg_idx));
+		uint32_t rscctl =
+			IXGBE_READ_REG(hw, IXGBE_RSCCTL(rxq->reg_idx));
+		uint32_t psrtype =
+			IXGBE_READ_REG(hw, IXGBE_PSRTYPE(rxq->reg_idx));
+		uint32_t eitr =
+			IXGBE_READ_REG(hw, IXGBE_EITR(rxq->reg_idx));
+
+		/*
+		 * ixgbe PMD doesn't support header-split at the moment.
+		 *
+		 * Following the 4.6.7.2.1 chapter of the 82599/x540
+		 * Spec if RSC is enabled the SRRCTL[n].BSIZEHEADER
+		 * should be configured even if header split is not
+		 * enabled. We will configure it 128 bytes following the
+		 * recommendation in the spec.
+		 */
+		srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK;
+		srrctl |= (128 << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) &
+					    IXGBE_SRRCTL_BSIZEHDR_MASK;
+
+		/*
+		 * TODO: Consider setting the Receive Descriptor Minimum
+		 * Threshold Size for an RSC case. This is not an obviously
+		 * beneficiary option but the one worth considering...
+		 */
+
+		rscctl |= IXGBE_RSCCTL_RSCEN;
+		rscctl |= ixgbe_get_rscctl_maxdesc(rxq->mb_pool);
+		psrtype |= IXGBE_PSRTYPE_TCPHDR;
+
+		/*
+		 * RSC: Set ITR interval corresponding to 2K ints/s.
+		 *
+		 * Full-sized RSC aggregations for a 10Gb/s link will
+		 * arrive at about 20K aggregation/s rate.
+		 *
+		 * 2K inst/s rate will make only 10% of the
+		 * aggregations to be closed due to the interrupt timer
+		 * expiration for a streaming at wire-speed case.
+		 *
+		 * For a sparse streaming case this setting will yield
+		 * at most 500us latency for a single RSC aggregation.
+		 */
+		eitr &= ~IXGBE_EITR_ITR_INT_MASK;
+		eitr |= IXGBE_EITR_INTERVAL_US(500) | IXGBE_EITR_CNT_WDIS;
+
+		IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(rxq->reg_idx), srrctl);
+		IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(rxq->reg_idx), rscctl);
+		IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(rxq->reg_idx), psrtype);
+		IXGBE_WRITE_REG(hw, IXGBE_EITR(rxq->reg_idx), eitr);
+
+		/*
+		 * RSC requires the mapping of the queue to the
+		 * interrupt vector.
+		 */
+		ixgbe_set_ivar(dev, rxq->reg_idx, i, 0);
+
+		rxq->rsc_en = 1;
+	}
+
+	dev->data->lro = 1;
+
+	PMD_INIT_LOG(INFO, "enabling LRO mode");
+
+	return 0;
+}
+
 /*
  * Initializes Receive Unit.
  */
@@ -3615,6 +4207,7 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev)
 	uint16_t buf_size;
 	uint16_t i;
 	struct rte_eth_rxmode *rx_conf = &dev->data->dev_conf.rxmode;
+	int rc;
 
 	PMD_INIT_FUNC_TRACE();
 	hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
@@ -3724,6 +4317,7 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev)
 				       RTE_PKTMBUF_HEADROOM);
 		srrctl |= ((buf_size >> IXGBE_SRRCTL_BSIZEPKT_SHIFT) &
 			   IXGBE_SRRCTL_BSIZEPKT_MASK);
+
 		IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(rxq->reg_idx), srrctl);
 
 		buf_size = (uint16_t) ((srrctl & IXGBE_SRRCTL_BSIZEPKT_MASK) <<
@@ -3738,8 +4332,6 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev)
 	if (rx_conf->enable_scatter)
 		dev->data->scattered_rx = 1;
 
-	ixgbe_set_rx_function(dev);
-
 	/*
 	 * Device configured with multiple RX queues.
 	 */
@@ -3770,6 +4362,12 @@ ixgbe_dev_rx_init(struct rte_eth_dev *dev)
 		IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl);
 	}
 
+	rc = ixgbe_set_rsc(dev);
+	if (rc)
+		return rc;
+
+	ixgbe_set_rx_function(dev);
+
 	return 0;
 }
 
diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.h b/lib/librte_pmd_ixgbe/ixgbe_rxtx.h
index 3937cf6..120bbbd 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.h
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.h
@@ -79,6 +79,10 @@ struct ixgbe_rx_entry {
 	struct rte_mbuf *mbuf; /**< mbuf associated with RX descriptor. */
 };
 
+struct ixgbe_rsc_entry {
+	struct rte_mbuf *fbuf; /**< First segment of the fragmented packet. */
+};
+
 /**
  * Structure associated with each descriptor of the TX ring of a TX queue.
  */
@@ -105,6 +109,7 @@ struct ixgbe_rx_queue {
 	volatile uint32_t   *rdt_reg_addr; /**< RDT register address. */
 	volatile uint32_t   *rdh_reg_addr; /**< RDH register address. */
 	struct ixgbe_rx_entry *sw_ring; /**< address of RX software ring. */
+	struct ixgbe_rsc_entry *sw_rsc_ring; /**< address of RSC software ring. */
 	struct rte_mbuf *pkt_first_seg; /**< First segment of current packet. */
 	struct rte_mbuf *pkt_last_seg; /**< Last segment of current packet. */
 	uint64_t            mbuf_initializer; /**< value to init mbufs */
@@ -126,6 +131,7 @@ struct ixgbe_rx_queue {
 	uint8_t             port_id;  /**< Device port identifier. */
 	uint8_t             crc_len;  /**< 0 if CRC stripped, 4 otherwise. */
 	uint8_t             drop_en;  /**< If not 0, set SRRCTL.Drop_En. */
+	uint8_t             rsc_en;   /**< If not 0, RSC is enabled. */
 	uint8_t             rx_deferred_start; /**< not in global dev start. */
 #ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC
 	/** need to alloc dummy mbuf, for wraparound when scanning hw ring */
-- 
2.1.0

  parent reply	other threads:[~2015-03-18 17:52 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-18 17:52 [dpdk-dev] [PATCH v8 0/3]: Add LRO support to ixgbe PMD Vlad Zolotarov
2015-03-18 17:52 ` [dpdk-dev] [PATCH v8 1/3] ixgbe: Cleanups Vlad Zolotarov
2015-03-18 17:52 ` [dpdk-dev] [PATCH v8 2/3] ixgbe: Code refactoring Vlad Zolotarov
2015-03-18 17:52 ` Vlad Zolotarov [this message]
2015-03-30 14:18   ` [dpdk-dev] [PATCH v8 3/3] ixgbe: Add LRO support Ananyev, Konstantin
2015-03-30 15:37     ` Vlad Zolotarov
2015-03-30 15:57       ` Vlad Zolotarov
2015-03-29  8:57 ` [dpdk-dev] [PATCH v8 0/3]: Add LRO support to ixgbe PMD Vlad Zolotarov
2015-04-22  1:23 ` Zhang, Helin
2015-04-22  1:45   ` Stephen Hemminger
2015-04-22  2:01     ` Zhang, Helin
2015-04-22  2:22       ` Stephen Hemminger
2015-04-22  2:23       ` Stephen Hemminger
2015-04-22  4:58   ` Vlad Zolotarov
2015-04-22  5:28     ` Zhang, Helin
2015-04-22  9:19       ` Vlad Zolotarov
2015-04-23  0:28         ` Zhang, Helin
2015-04-23  9:20           ` Ananyev, Konstantin
2015-04-23 11:01             ` Vladislav Zolotarov
     [not found]               ` <2601191342CEEE43887BDE71AB9772582142100A@irsmsx105.ger.corp.intel.com>
2015-04-23 11:16                 ` Ananyev, Konstantin
2015-03-31 10:25 [dpdk-dev] [PATCH v8 3/3] ixgbe: Add LRO support Ananyev, Konstantin
2015-03-31 11:40 ` Vlad Zolotarov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1426701144-21231-4-git-send-email-vladz@cloudius-systems.com \
    --to=vladz@cloudius-systems.com \
    --cc=dev@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).