[PATCH v3 5/6] tap: Convert packet pools to per-queue-pair arrays for multiqueue

[Laurent Vivier <lvivier@redhat.com>]

Convert the global pool_tap4 and pool_tap6 packet pools from single
pools to arrays of pools, one for each queue pair. This change is
necessary to support multiqueue operation in vhost-user mode, where
multiple queue pairs may be processing packets concurrently.

The pool storage structures (pool_tap4_storage and pool_tap6_storage)
are now arrays of VHOST_USER_MAX_VQS/2 elements, with corresponding
pointer arrays (pool_tap4 and pool_tap6) for accessing them.

Update tap_flush_pools() and tap_handler() to take a qpair parameter
that selects which pool to operate on. Add bounds checking assertions
to ensure qpair is within valid range.

In passt and pasta modes, all operations use queue pair 0 (hardcoded
in tap_passt_input and tap_pasta_input). In vhost-user mode, the queue
pair is derived from the virtqueue index (index / 2, as TX/RX queues
come in pairs).

All pools within the array share the same buffer pointer:
- In vhost-user mode: Points to the vhost-user memory structure, which
  is safe as packet data remains in guest memory and pools only track
  iovecs
- In passt/pasta mode: Points to pkt_buf, which is safe as only queue
  pair 0 is used

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
 tap.c       | 77 ++++++++++++++++++++++++++++++-----------------------
 tap.h       |  5 ++--
 vu_common.c |  6 ++---
 3 files changed, 50 insertions(+), 38 deletions(-)

diff --git a/tap.c b/tap.c
index 0d1f05865d60..c56afb73fd7e 100644
--- a/tap.c
+++ b/tap.c
@@ -94,9 +94,13 @@ CHECK_FRAME_LEN(L2_MAX_LEN_VU);
 	DIV_ROUND_UP(sizeof(pkt_buf),					\
 		     ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct udphdr))
 
-/* IPv4 (plus ARP) and IPv6 message batches from tap/guest to IP handlers */
-static PACKET_POOL_NOINIT(pool_tap4, TAP_MSGS_IP4);
-static PACKET_POOL_NOINIT(pool_tap6, TAP_MSGS_IP6);
+/* IPv4 (plus ARP) and IPv6 message batches from tap/guest to IP handlers
+ * One pool per queue pair for multiqueue support
+ */
+static PACKET_POOL_DECL(pool_tap4, TAP_MSGS_IP4) pool_tap4_storage[VHOST_USER_MAX_VQS / 2];
+static struct pool *pool_tap4[VHOST_USER_MAX_VQS / 2];
+static PACKET_POOL_DECL(pool_tap6, TAP_MSGS_IP6) pool_tap6_storage[VHOST_USER_MAX_VQS / 2];
+static struct pool *pool_tap6[VHOST_USER_MAX_VQS / 2];
 
 #define TAP_SEQS		128 /* Different L4 tuples in one batch */
 #define FRAGMENT_MSG_RATE	10  /* # seconds between fragment warnings */
@@ -714,12 +718,12 @@ static int tap4_handler(struct ctx *c, unsigned int qpair,
 	unsigned int i, j, seq_count;
 	struct tap4_l4_t *seq;
 
-	if (!c->ifi4 || !pool_tap4->count)
-		return pool_tap4->count;
+	if (!c->ifi4 || !pool_tap4[qpair]->count)
+		return pool_tap4[qpair]->count;
 
 	i = 0;
 resume:
-	for (seq_count = 0, seq = NULL; i < pool_tap4->count; i++) {
+	for (seq_count = 0, seq = NULL; i < pool_tap4[qpair]->count; i++) {
 		size_t l3len, hlen, l4len;
 		struct ethhdr eh_storage;
 		struct iphdr iph_storage;
@@ -729,7 +733,7 @@ resume:
 		struct iov_tail data;
 		struct iphdr *iph;
 
-		if (!packet_get(pool_tap4, i, &data))
+		if (!packet_get(pool_tap4[qpair], i, &data))
 			continue;
 
 		eh = IOV_PEEK_HEADER(&data, eh_storage);
@@ -796,7 +800,7 @@ resume:
 		if (iph->protocol == IPPROTO_UDP) {
 			struct iov_tail eh_data;
 
-			packet_get(pool_tap4, i, &eh_data);
+			packet_get(pool_tap4[qpair], i, &eh_data);
 			if (dhcp(c, qpair, &eh_data))
 				continue;
 		}
@@ -827,7 +831,7 @@ resume:
 			goto append;
 
 		if (seq_count == TAP_SEQS)
-			break;	/* Resume after flushing if i < pool_tap4->count */
+			break;	/* Resume after flushing if i < pool_tap4[qpair]->count */
 
 		for (seq = tap4_l4 + seq_count - 1; seq >= tap4_l4; seq--) {
 			if (L4_MATCH(iph, uh, seq)) {
@@ -873,10 +877,10 @@ append:
 		}
 	}
 
-	if (i < pool_tap4->count)
+	if (i < pool_tap4[qpair]->count)
 		goto resume;
 
-	return pool_tap4->count;
+	return pool_tap4[qpair]->count;
 }
 
 /**
@@ -892,12 +896,12 @@ static int tap6_handler(struct ctx *c, unsigned int qpair, const struct timespec
 	unsigned int i, j, seq_count = 0;
 	struct tap6_l4_t *seq;
 
-	if (!c->ifi6 || !pool_tap6->count)
-		return pool_tap6->count;
+	if (!c->ifi6 || !pool_tap6[qpair]->count)
+		return pool_tap6[qpair]->count;
 
 	i = 0;
 resume:
-	for (seq_count = 0, seq = NULL; i < pool_tap6->count; i++) {
+	for (seq_count = 0, seq = NULL; i < pool_tap6[qpair]->count; i++) {
 		size_t l4len, plen, check;
 		struct in6_addr *saddr, *daddr;
 		struct ipv6hdr ip6h_storage;
@@ -909,7 +913,7 @@ resume:
 		struct ipv6hdr *ip6h;
 		uint8_t proto;
 
-		if (!packet_get(pool_tap6, i, &data))
+		if (!packet_get(pool_tap6[qpair], i, &data))
 			return -1;
 
 		eh = IOV_REMOVE_HEADER(&data, eh_storage);
@@ -1017,7 +1021,7 @@ resume:
 			goto append;
 
 		if (seq_count == TAP_SEQS)
-			break;	/* Resume after flushing if i < pool_tap6->count */
+			break;	/* Resume after flushing if i < pool_tap6[qpair]->count */
 
 		for (seq = tap6_l4 + seq_count - 1; seq >= tap6_l4; seq--) {
 			if (L4_MATCH(ip6h, proto, uh, seq)) {
@@ -1064,19 +1068,19 @@ append:
 		}
 	}
 
-	if (i < pool_tap6->count)
+	if (i < pool_tap6[qpair]->count)
 		goto resume;
 
-	return pool_tap6->count;
+	return pool_tap6[qpair]->count;
 }
 
 /**
- * tap_flush_pools() - Flush both IPv4 and IPv6 packet pools
+ * tap_flush_pools() - Flush both IPv4 and IPv6 packet pools for a given qpair
  */
-void tap_flush_pools(void)
+void tap_flush_pools(unsigned int qpair)
 {
-	pool_flush(pool_tap4);
-	pool_flush(pool_tap6);
+	pool_flush(pool_tap4[qpair]);
+	pool_flush(pool_tap6[qpair]);
 }
 
 /**
@@ -1087,6 +1091,7 @@ void tap_flush_pools(void)
  */
 void tap_handler(struct ctx *c, unsigned int qpair, const struct timespec *now)
 {
+	ASSERT(qpair < VHOST_USER_MAX_VQS / 2);
 	tap4_handler(c, qpair, now);
 	tap6_handler(c, qpair, now);
 }
@@ -1119,21 +1124,23 @@ void tap_add_packet(struct ctx *c, unsigned int qpair, struct iov_tail *data,
 		proto_update_l2_buf(c->guest_mac);
 	}
 
+	ASSERT(qpair < VHOST_USER_MAX_VQS / 2);
+
 	switch (ntohs(eh->h_proto)) {
 	case ETH_P_ARP:
 	case ETH_P_IP:
-		if (!pool_can_fit(pool_tap4, data)) {
+		if (!pool_can_fit(pool_tap4[qpair], data)) {
 			tap4_handler(c, qpair, now);
-			pool_flush(pool_tap4);
+			pool_flush(pool_tap4[qpair]);
 		}
-		packet_add(pool_tap4, data);
+		packet_add(pool_tap4[qpair], data);
 		break;
 	case ETH_P_IPV6:
-		if (!pool_can_fit(pool_tap6, data)) {
+		if (!pool_can_fit(pool_tap6[qpair], data)) {
 			tap6_handler(c, qpair, now);
-			pool_flush(pool_tap6);
+			pool_flush(pool_tap6[qpair]);
 		}
-		packet_add(pool_tap6, data);
+		packet_add(pool_tap6[qpair], data);
 		break;
 	default:
 		break;
@@ -1173,7 +1180,7 @@ static void tap_passt_input(struct ctx *c, const struct timespec *now)
 	ssize_t n;
 	char *p;
 
-	tap_flush_pools();
+	tap_flush_pools(0);
 
 	if (partial_len) {
 		/* We have a partial frame from an earlier pass.  Move it to the
@@ -1256,7 +1263,7 @@ static void tap_pasta_input(struct ctx *c, const struct timespec *now)
 {
 	ssize_t n, len;
 
-	tap_flush_pools();
+	tap_flush_pools(0);
 
 	for (n = 0;
 	     n <= (ssize_t)(sizeof(pkt_buf) - L2_MAX_LEN_PASTA);
@@ -1512,10 +1519,14 @@ static void tap_sock_tun_init(struct ctx *c)
  */
 static void tap_sock_update_pool(void *base, size_t size)
 {
-	int i;
+	unsigned int i;
 
-	pool_tap4_storage = PACKET_INIT(pool_tap4, TAP_MSGS_IP4, base, size);
-	pool_tap6_storage = PACKET_INIT(pool_tap6, TAP_MSGS_IP6, base, size);
+	for (i = 0; i < VHOST_USER_MAX_VQS / 2; i++) {
+		pool_tap4_storage[i] = PACKET_INIT(pool_tap4, TAP_MSGS_IP4, base, size);
+		pool_tap4[i] = (struct pool *)&pool_tap4_storage[i];
+		pool_tap6_storage[i] = PACKET_INIT(pool_tap6, TAP_MSGS_IP6, base, size);
+		pool_tap6[i] = (struct pool *)&pool_tap6_storage[i];
+	}
 
 	for (i = 0; i < TAP_SEQS; i++) {
 		tap4_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, base, size);
diff --git a/tap.h b/tap.h
index d3ac0cb6a233..6d4f8bd156fb 100644
--- a/tap.h
+++ b/tap.h
@@ -119,8 +119,9 @@ void tap_handler_passt(struct ctx *c, uint32_t events,
 int tap_sock_unix_open(char *sock_path);
 void tap_sock_reset(struct ctx *c);
 void tap_backend_init(struct ctx *c);
-void tap_flush_pools(void);
-void tap_handler(struct ctx *c, unsigned int qpair, const struct timespec *now);
+void tap_flush_pools(unsigned int qpair);
+void tap_handler(struct ctx *c, unsigned int qpair,
+		 const struct timespec *now);
 void tap_add_packet(struct ctx *c, unsigned int qpair, struct iov_tail *data,
 		    const struct timespec *now);
 #endif /* TAP_H */
diff --git a/vu_common.c b/vu_common.c
index 80d9a30f6f71..8f0fa1180c78 100644
--- a/vu_common.c
+++ b/vu_common.c
@@ -170,7 +170,7 @@ static void vu_handle_tx(struct vu_dev *vdev, int index,
 
 	ASSERT(VHOST_USER_IS_QUEUE_TX(index));
 
-	tap_flush_pools();
+	tap_flush_pools(index / 2);
 
 	count = 0;
 	out_sg_count = 0;
@@ -196,11 +196,11 @@ static void vu_handle_tx(struct vu_dev *vdev, int index,
 
 		data = IOV_TAIL(elem[count].out_sg, elem[count].out_num, 0);
 		if (IOV_DROP_HEADER(&data, struct virtio_net_hdr_mrg_rxbuf))
-			tap_add_packet(vdev->context, 0, &data, now);
+			tap_add_packet(vdev->context, index / 2, &data, now);
 
 		count++;
 	}
-	tap_handler(vdev->context, 0, now);
+	tap_handler(vdev->context, index / 2, now);
 
 	if (count) {
 		int i;
-- 
2.51.1