[dpdk-dev] [PATCH RFC 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

[dpdk-dev] [PATCH RFC 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

[Huawei Xie]

The virtio_net device and vhost virt queue should be allocated on the same numa node as vring descriptors.
When we firstly allocate the virtio_net device and vhost virt queue, we don't know the numa node of vring descriptors.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptors, so we will try to reallocate virtio_net and vhost virt queue to the same numa node.

Huawei Xie (2):
  use rte_malloc/free for virtio_net and virt_queue memory data allocation/free
  When we get the address of vring descriptor table, will try to reallocate virtio_net device and virtqueue to the same numa node.

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   3 ++
 4 files changed, 111 insertions(+), 9 deletions(-)

-- 
1.8.1.4

[dpdk-dev] [PATCH RFC 1/2] vhost: malloc -> rte_malloc for virtio_net and virt queue allocation

[Huawei Xie]

use rte_malloc/free for virtio_net and virt queue allocation/free

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 lib/librte_vhost/virtio-net.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 4672e67..19b74d6 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -45,6 +45,7 @@
 #include <rte_log.h>
 #include <rte_string_fns.h>
 #include <rte_memory.h>
+#include <rte_malloc.h>
 #include <rte_virtio_net.h>
 
 #include "vhost-net.h"
@@ -202,9 +203,9 @@ static void
 free_device(struct virtio_net_config_ll *ll_dev)
 {
 	/* Free any malloc'd memory */
-	free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
-	free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
-	free(ll_dev);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
+	rte_free(ll_dev);
 }
 
 /*
@@ -278,7 +279,7 @@ new_device(struct vhost_device_ctx ctx)
 	struct vhost_virtqueue *virtqueue_rx, *virtqueue_tx;
 
 	/* Setup device and virtqueues. */
-	new_ll_dev = malloc(sizeof(struct virtio_net_config_ll));
+	new_ll_dev = rte_malloc(NULL, sizeof(struct virtio_net_config_ll), 0);
 	if (new_ll_dev == NULL) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for dev.\n",
@@ -286,19 +287,19 @@ new_device(struct vhost_device_ctx ctx)
 		return -1;
 	}
 
-	virtqueue_rx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_rx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_rx == NULL) {
-		free(new_ll_dev);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for rxq.\n",
 			ctx.fh);
 		return -1;
 	}
 
-	virtqueue_tx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_tx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_tx == NULL) {
-		free(virtqueue_rx);
-		free(new_ll_dev);
+		rte_free(virtqueue_rx);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for txq.\n",
 			ctx.fh);
-- 
1.8.1.4

[dpdk-dev] [PATCH RFC 2/2] vhost: realloc virtio_net and virtqueue to the same node of vring desc table

[Huawei Xie]

When we get the address of vring descriptor table in VHOST_SET_VRING_ADDR message,
will try to reallocate virtio_net device and virtqueue to the same numa node.

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 config/common_linuxapp        |  1 +
 lib/librte_vhost/Makefile     |  4 ++
 lib/librte_vhost/virtio-net.c | 93 +++++++++++++++++++++++++++++++++++++++++++
 mk/rte.app.mk                 |  3 ++
 4 files changed, 101 insertions(+)

diff --git a/config/common_linuxapp b/config/common_linuxapp
index 0078dc9..4ace24e 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -421,6 +421,7 @@ CONFIG_RTE_KNI_VHOST_DEBUG_TX=n
 #
 CONFIG_RTE_LIBRTE_VHOST=n
 CONFIG_RTE_LIBRTE_VHOST_USER=y
+CONFIG_RTE_LIBRTE_VHOST_NUMA=n
 CONFIG_RTE_LIBRTE_VHOST_DEBUG=n
 
 #
diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index a8645a6..6681f22 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -46,6 +46,10 @@ CFLAGS += -I vhost_cuse -lfuse
 LDFLAGS += -lfuse
 endif
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+LDFLAGS += -lnuma
+endif
+
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_rxtx.c
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),y)
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 19b74d6..8a80f5e 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -38,6 +38,9 @@
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#ifdef RTE_LIBRTE_VHOST_NUMA
+#include <numaif.h>
+#endif
 
 #include <sys/socket.h>
 
@@ -481,6 +484,93 @@ set_vring_num(struct vhost_device_ctx ctx, struct vhost_vring_state *state)
 }
 
 /*
+ * Reallocate virtio_det and vhost_virtqueue data structure to make them on the
+ * same numa node as the memory of vring descriptor.
+ */
+#ifdef RTE_LIBRTE_VHOST_NUMA
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index)
+{
+	int oldnode, newnode;
+	struct virtio_net_config_ll *old_ll_dev, *new_ll_dev;
+	struct vhost_virtqueue *old_vq, *new_vq;
+	int ret;
+	int realloc_dev = 0, realloc_vq = 0;
+
+	old_ll_dev = (struct virtio_net_config_ll *)dev;
+	old_vq = dev->virtqueue[index];
+
+	ret  = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	ret = ret | get_mempolicy(&oldnode, NULL, 0, old_ll_dev,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vring desc or dev numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_dev = 1;
+
+	ret = get_mempolicy(&oldnode, NULL, 0, old_vq,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vq numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_vq = 1;
+
+	if (realloc_dev == 0 && realloc_vq == 0)
+		return dev;
+
+	if (realloc_dev)
+		new_ll_dev = rte_malloc_socket(NULL,
+			sizeof(struct virtio_net_config_ll), 0, newnode);
+	if (realloc_vq)
+		new_vq = rte_malloc_socket(NULL,
+			sizeof(struct vhost_virtqueue), 0, newnode);
+	if (!new_ll_dev || !new_vq) {
+		if (new_ll_dev)
+			rte_free(new_ll_dev);
+		if (new_vq)
+			rte_free(new_vq);
+		return dev;
+	}
+
+	if (realloc_vq)
+		memcpy(new_vq, old_vq, sizeof(*new_vq));
+	if (realloc_dev)
+		memcpy(new_ll_dev, old_ll_dev, sizeof(*new_ll_dev));
+	(new_ll_dev ? new_ll_dev : old_ll_dev)->dev.virtqueue[index] =
+		new_vq ? new_vq : old_vq;
+	if (realloc_vq)
+		rte_free(old_vq);
+	if (realloc_dev) {
+		if (ll_root == old_ll_dev)
+			ll_root = new_ll_dev;
+		else {
+			struct virtio_net_config_ll *prev = ll_root;
+			while (prev->next != old_ll_dev)
+				prev = prev->next;
+			prev->next = new_ll_dev;
+			new_ll_dev->next = old_ll_dev->next;
+		}
+		rte_free(old_ll_dev);
+	}
+
+	return &new_ll_dev->dev;
+}
+#else
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index __rte_unused)
+{
+	return dev;
+}
+#endif
+
+/*
  * Called from CUSE IOCTL: VHOST_SET_VRING_ADDR
  * The virtio device sends us the desc, used and avail ring addresses.
  * This function then converts these to our address space.
@@ -508,6 +598,9 @@ set_vring_addr(struct vhost_device_ctx ctx, struct vhost_vring_addr *addr)
 		return -1;
 	}
 
+	dev = numa_realloc(dev, addr->index);
+	vq = dev->virtqueue[addr->index];
+
 	vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
 			addr->avail_user_addr);
 	if (vq->avail == 0) {
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 1a2043a..5aba56a 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -92,6 +92,9 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
+
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
 endif
-- 
1.8.1.4

Re: [dpdk-dev] [PATCH RFC 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

[Long, Thomas]

Acked-by: Tommy Long <thomas.long@intel.com>

-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Huawei Xie
Sent: Thursday, May 28, 2015 3:04 AM
To: dev@dpdk.org
Subject: [dpdk-dev] [PATCH RFC 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

The virtio_net device and vhost virt queue should be allocated on the same numa node as vring descriptors.
When we firstly allocate the virtio_net device and vhost virt queue, we don't know the numa node of vring descriptors.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptors, so we will try to reallocate virtio_net and vhost virt queue to the same numa node.

Huawei Xie (2):
  use rte_malloc/free for virtio_net and virt_queue memory data allocation/free
  When we get the address of vring descriptor table, will try to reallocate virtio_net device and virtqueue to the same numa node.

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   3 ++
 4 files changed, 111 insertions(+), 9 deletions(-)

-- 
1.8.1.4

[dpdk-dev] [PATCH 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

[Huawei Xie]

The virtio_net device and vhost virt queue should be allocated on the same numa node as vring descriptors.
When we firstly allocate the virtio_net device and vhost virt queue, we don't know the numa node of vring descriptors.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptors, so we will try to reallocate virtio_net and vhost virt queue to the same numa node.

Huawei Xie (2):
  use rte_malloc/free for virtio_net and virt_queue memory data allocation/free
  When we get the address of vring descriptor table, will try to reallocate virtio_net device and virtqueue to the same numa node.

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   3 ++
 4 files changed, 111 insertions(+), 9 deletions(-)

-- 
1.8.1.4

[dpdk-dev] [PATCH 1/2] vhost: malloc -> rte_malloc for virtio_net and virt queue allocation

[Huawei Xie]

use rte_malloc/free for virtio_net and virt queue allocation/free

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 lib/librte_vhost/virtio-net.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 4672e67..19b74d6 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -45,6 +45,7 @@
 #include <rte_log.h>
 #include <rte_string_fns.h>
 #include <rte_memory.h>
+#include <rte_malloc.h>
 #include <rte_virtio_net.h>
 
 #include "vhost-net.h"
@@ -202,9 +203,9 @@ static void
 free_device(struct virtio_net_config_ll *ll_dev)
 {
 	/* Free any malloc'd memory */
-	free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
-	free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
-	free(ll_dev);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
+	rte_free(ll_dev);
 }
 
 /*
@@ -278,7 +279,7 @@ new_device(struct vhost_device_ctx ctx)
 	struct vhost_virtqueue *virtqueue_rx, *virtqueue_tx;
 
 	/* Setup device and virtqueues. */
-	new_ll_dev = malloc(sizeof(struct virtio_net_config_ll));
+	new_ll_dev = rte_malloc(NULL, sizeof(struct virtio_net_config_ll), 0);
 	if (new_ll_dev == NULL) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for dev.\n",
@@ -286,19 +287,19 @@ new_device(struct vhost_device_ctx ctx)
 		return -1;
 	}
 
-	virtqueue_rx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_rx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_rx == NULL) {
-		free(new_ll_dev);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for rxq.\n",
 			ctx.fh);
 		return -1;
 	}
 
-	virtqueue_tx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_tx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_tx == NULL) {
-		free(virtqueue_rx);
-		free(new_ll_dev);
+		rte_free(virtqueue_rx);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for txq.\n",
 			ctx.fh);
-- 
1.8.1.4

[dpdk-dev] [PATCH 2/2] vhost: realloc virtio_net and virtqueue to the same node of vring desc table

[Huawei Xie]

When we get the address of vring descriptor table in VHOST_SET_VRING_ADDR message,
will try to reallocate virtio_net device and virtqueue to the same numa node.

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 config/common_linuxapp        |  1 +
 lib/librte_vhost/Makefile     |  4 ++
 lib/librte_vhost/virtio-net.c | 93 +++++++++++++++++++++++++++++++++++++++++++
 mk/rte.app.mk                 |  3 ++
 4 files changed, 101 insertions(+)

diff --git a/config/common_linuxapp b/config/common_linuxapp
index 0078dc9..4ace24e 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -421,6 +421,7 @@ CONFIG_RTE_KNI_VHOST_DEBUG_TX=n
 #
 CONFIG_RTE_LIBRTE_VHOST=n
 CONFIG_RTE_LIBRTE_VHOST_USER=y
+CONFIG_RTE_LIBRTE_VHOST_NUMA=n
 CONFIG_RTE_LIBRTE_VHOST_DEBUG=n
 
 #
diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index a8645a6..6681f22 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -46,6 +46,10 @@ CFLAGS += -I vhost_cuse -lfuse
 LDFLAGS += -lfuse
 endif
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+LDFLAGS += -lnuma
+endif
+
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_rxtx.c
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),y)
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 19b74d6..8a80f5e 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -38,6 +38,9 @@
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#ifdef RTE_LIBRTE_VHOST_NUMA
+#include <numaif.h>
+#endif
 
 #include <sys/socket.h>
 
@@ -481,6 +484,93 @@ set_vring_num(struct vhost_device_ctx ctx, struct vhost_vring_state *state)
 }
 
 /*
+ * Reallocate virtio_det and vhost_virtqueue data structure to make them on the
+ * same numa node as the memory of vring descriptor.
+ */
+#ifdef RTE_LIBRTE_VHOST_NUMA
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index)
+{
+	int oldnode, newnode;
+	struct virtio_net_config_ll *old_ll_dev, *new_ll_dev;
+	struct vhost_virtqueue *old_vq, *new_vq;
+	int ret;
+	int realloc_dev = 0, realloc_vq = 0;
+
+	old_ll_dev = (struct virtio_net_config_ll *)dev;
+	old_vq = dev->virtqueue[index];
+
+	ret  = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	ret = ret | get_mempolicy(&oldnode, NULL, 0, old_ll_dev,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vring desc or dev numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_dev = 1;
+
+	ret = get_mempolicy(&oldnode, NULL, 0, old_vq,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vq numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_vq = 1;
+
+	if (realloc_dev == 0 && realloc_vq == 0)
+		return dev;
+
+	if (realloc_dev)
+		new_ll_dev = rte_malloc_socket(NULL,
+			sizeof(struct virtio_net_config_ll), 0, newnode);
+	if (realloc_vq)
+		new_vq = rte_malloc_socket(NULL,
+			sizeof(struct vhost_virtqueue), 0, newnode);
+	if (!new_ll_dev || !new_vq) {
+		if (new_ll_dev)
+			rte_free(new_ll_dev);
+		if (new_vq)
+			rte_free(new_vq);
+		return dev;
+	}
+
+	if (realloc_vq)
+		memcpy(new_vq, old_vq, sizeof(*new_vq));
+	if (realloc_dev)
+		memcpy(new_ll_dev, old_ll_dev, sizeof(*new_ll_dev));
+	(new_ll_dev ? new_ll_dev : old_ll_dev)->dev.virtqueue[index] =
+		new_vq ? new_vq : old_vq;
+	if (realloc_vq)
+		rte_free(old_vq);
+	if (realloc_dev) {
+		if (ll_root == old_ll_dev)
+			ll_root = new_ll_dev;
+		else {
+			struct virtio_net_config_ll *prev = ll_root;
+			while (prev->next != old_ll_dev)
+				prev = prev->next;
+			prev->next = new_ll_dev;
+			new_ll_dev->next = old_ll_dev->next;
+		}
+		rte_free(old_ll_dev);
+	}
+
+	return &new_ll_dev->dev;
+}
+#else
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index __rte_unused)
+{
+	return dev;
+}
+#endif
+
+/*
  * Called from CUSE IOCTL: VHOST_SET_VRING_ADDR
  * The virtio device sends us the desc, used and avail ring addresses.
  * This function then converts these to our address space.
@@ -508,6 +598,9 @@ set_vring_addr(struct vhost_device_ctx ctx, struct vhost_vring_addr *addr)
 		return -1;
 	}
 
+	dev = numa_realloc(dev, addr->index);
+	vq = dev->virtqueue[addr->index];
+
 	vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
 			addr->avail_user_addr);
 	if (vq->avail == 0) {
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 1a2043a..5aba56a 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -92,6 +92,9 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
+
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
 endif
-- 
1.8.1.4

Re: [dpdk-dev] [PATCH 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

[Long, Thomas]

Acked-by: Tommy Long <thomas.long@intel.com>

-----Original Message-----
From: Xie, Huawei 
Sent: Friday, June 5, 2015 4:13 AM
To: dev@dpdk.org
Cc: Long, Thomas
Subject: [PATCH 0/2] vhost: numa aware allocation of virtio_net device and vhost virt queue

The virtio_net device and vhost virt queue should be allocated on the same numa node as vring descriptors.
When we firstly allocate the virtio_net device and vhost virt queue, we don't know the numa node of vring descriptors.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptors, so we will try to reallocate virtio_net and vhost virt queue to the same numa node.

Huawei Xie (2):
  use rte_malloc/free for virtio_net and virt_queue memory data allocation/free
  When we get the address of vring descriptor table, will try to reallocate virtio_net device and virtqueue to the same numa node.

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   3 ++
 4 files changed, 111 insertions(+), 9 deletions(-)

-- 
1.8.1.4

Re: [dpdk-dev] [PATCH 2/2] vhost: realloc virtio_net and virtqueue to the same node of vring desc table

[Thomas Monjalon]

2015-06-05 11:13, Huawei Xie:
> --- a/mk/rte.app.mk
> +++ b/mk/rte.app.mk
> @@ -92,6 +92,9 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
>  
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
>  
> +ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
> +_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
> +
>  ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
>  _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
>  endif

An endif is missing.

Re: [dpdk-dev] [PATCH 2/2] vhost: realloc virtio_net and virtqueue to the same node of vring desc table

[Thomas Monjalon]

2015-06-17 18:47, Thomas Monjalon:
> 2015-06-05 11:13, Huawei Xie:
> > --- a/mk/rte.app.mk
> > +++ b/mk/rte.app.mk
> > @@ -92,6 +92,9 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
> >  
> >  _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
> >  
> > +ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
> > +_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
> > +
> >  ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
> >  _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
> >  endif
> 
> An endif is missing.

After adding the endif and enabling the NUMA option, these errors appear:

lib/librte_vhost/virtio-net.c:535:21: error: ‘new_vq’ may be used uninitialized in this function
lib/librte_vhost/virtio-net.c:547:63: error: ‘new_ll_dev’ may be used uninitialized in this function

Tommy,
I won't review the code, but given it doesn't build, I can guess how it has
been reviewed.
Acked-by line is valuable only if the review is carefully done.

This patch series go back to lowest merge priority.

Re: [dpdk-dev] [PATCH 1/2] vhost: malloc -> rte_malloc for virtio_net and virt queue allocation

[Thomas Monjalon]

2015-06-05 11:13, Huawei Xie:
> use rte_malloc/free for virtio_net and virt queue allocation/free
> 
> Signed-off-by: Huawei Xie <huawei.xie@intel.com>

I suggest this title:
vhost: use rte_malloc to allocate device and queues

[dpdk-dev] [PATCH v2 0/2] vhost: numa aware allocation of vhost device and queues

[Huawei Xie]

The vhost device and queues should be allocated on the same numa node as vring descriptor table.
When we firstly allocate the vhost device and queues, we don't know the numa node of vring descriptor table.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptor table, we will try to reallocate vhost device and queues to the same numa node.


Huawei Xie (2):
  use rte_malloc to allocate vhost device and queues
  reallocate vhost device and queues when we get the address of vring descriptor table

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 112 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   4 ++
 4 files changed, 112 insertions(+), 9 deletions(-)

-- 
1.8.1.4

[dpdk-dev] [PATCH v2 1/2] vhost: use rte_malloc to allocate device and queues

[Huawei Xie]

use rte_malloc to allocate vhost device and queues

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 lib/librte_vhost/virtio-net.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 4672e67..19b74d6 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -45,6 +45,7 @@
 #include <rte_log.h>
 #include <rte_string_fns.h>
 #include <rte_memory.h>
+#include <rte_malloc.h>
 #include <rte_virtio_net.h>
 
 #include "vhost-net.h"
@@ -202,9 +203,9 @@ static void
 free_device(struct virtio_net_config_ll *ll_dev)
 {
 	/* Free any malloc'd memory */
-	free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
-	free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
-	free(ll_dev);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
+	rte_free(ll_dev);
 }
 
 /*
@@ -278,7 +279,7 @@ new_device(struct vhost_device_ctx ctx)
 	struct vhost_virtqueue *virtqueue_rx, *virtqueue_tx;
 
 	/* Setup device and virtqueues. */
-	new_ll_dev = malloc(sizeof(struct virtio_net_config_ll));
+	new_ll_dev = rte_malloc(NULL, sizeof(struct virtio_net_config_ll), 0);
 	if (new_ll_dev == NULL) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for dev.\n",
@@ -286,19 +287,19 @@ new_device(struct vhost_device_ctx ctx)
 		return -1;
 	}
 
-	virtqueue_rx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_rx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_rx == NULL) {
-		free(new_ll_dev);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for rxq.\n",
 			ctx.fh);
 		return -1;
 	}
 
-	virtqueue_tx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_tx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_tx == NULL) {
-		free(virtqueue_rx);
-		free(new_ll_dev);
+		rte_free(virtqueue_rx);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for txq.\n",
 			ctx.fh);
-- 
1.8.1.4

[dpdk-dev] [PATCH v2 2/2] vhost: realloc vhost device and queues to the same numa node of vring desc table

[Huawei Xie]

When we get the address of vring descriptor table in VHOST_SET_VRING_ADDR message, will try to reallocate vhost device and queues to the same numa node.

v2 changes:
- fix uninitialised new_vq and new_ll_device
- fix missed endif in rte.app.mk
- fix new_ll_dev and new_vq allocation failure issue
- return old virtio device if new_ll_dev isn't allocated

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 config/common_linuxapp        |  1 +
 lib/librte_vhost/Makefile     |  4 ++
 lib/librte_vhost/virtio-net.c | 93 +++++++++++++++++++++++++++++++++++++++++++
 mk/rte.app.mk                 |  4 ++
 4 files changed, 102 insertions(+)

diff --git a/config/common_linuxapp b/config/common_linuxapp
index 0078dc9..4ace24e 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -421,6 +421,7 @@ CONFIG_RTE_KNI_VHOST_DEBUG_TX=n
 #
 CONFIG_RTE_LIBRTE_VHOST=n
 CONFIG_RTE_LIBRTE_VHOST_USER=y
+CONFIG_RTE_LIBRTE_VHOST_NUMA=n
 CONFIG_RTE_LIBRTE_VHOST_DEBUG=n
 
 #
diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index a8645a6..6681f22 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -46,6 +46,10 @@ CFLAGS += -I vhost_cuse -lfuse
 LDFLAGS += -lfuse
 endif
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+LDFLAGS += -lnuma
+endif
+
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_rxtx.c
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),y)
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 19b74d6..0a065af 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -38,6 +38,9 @@
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#ifdef RTE_LIBRTE_VHOST_NUMA
+#include <numaif.h>
+#endif
 
 #include <sys/socket.h>
 
@@ -481,6 +484,93 @@ set_vring_num(struct vhost_device_ctx ctx, struct vhost_vring_state *state)
 }
 
 /*
+ * Reallocate virtio_det and vhost_virtqueue data structure to make them on the
+ * same numa node as the memory of vring descriptor.
+ */
+#ifdef RTE_LIBRTE_VHOST_NUMA
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index)
+{
+	int oldnode, newnode;
+	struct virtio_net_config_ll *old_ll_dev, *new_ll_dev = NULL;
+	struct vhost_virtqueue *old_vq, *new_vq = NULL;
+	int ret;
+	int realloc_dev = 0, realloc_vq = 0;
+
+	old_ll_dev = (struct virtio_net_config_ll *)dev;
+	old_vq = dev->virtqueue[index];
+
+	ret  = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	ret = ret | get_mempolicy(&oldnode, NULL, 0, old_ll_dev,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vring desc or dev numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_dev = 1;
+
+	ret = get_mempolicy(&oldnode, NULL, 0, old_vq,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vq numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_vq = 1;
+
+	if (realloc_dev == 0 && realloc_vq == 0)
+		return dev;
+
+	if (realloc_dev)
+		new_ll_dev = rte_malloc_socket(NULL,
+			sizeof(struct virtio_net_config_ll), 0, newnode);
+	if (realloc_vq)
+		new_vq = rte_malloc_socket(NULL,
+			sizeof(struct vhost_virtqueue), 0, newnode);
+	if (!new_ll_dev && !new_vq) {
+		if (new_ll_dev)
+			rte_free(new_ll_dev);
+		if (new_vq)
+			rte_free(new_vq);
+		return dev;
+	}
+
+	if (realloc_vq)
+		memcpy(new_vq, old_vq, sizeof(*new_vq));
+	if (realloc_dev)
+		memcpy(new_ll_dev, old_ll_dev, sizeof(*new_ll_dev));
+	(new_ll_dev ? new_ll_dev : old_ll_dev)->dev.virtqueue[index] =
+		new_vq ? new_vq : old_vq;
+	if (realloc_vq)
+		rte_free(old_vq);
+	if (realloc_dev) {
+		if (ll_root == old_ll_dev)
+			ll_root = new_ll_dev;
+		else {
+			struct virtio_net_config_ll *prev = ll_root;
+			while (prev->next != old_ll_dev)
+				prev = prev->next;
+			prev->next = new_ll_dev;
+			new_ll_dev->next = old_ll_dev->next;
+		}
+		rte_free(old_ll_dev);
+	}
+
+	return realloc_dev ? &new_ll_dev->dev : dev;
+}
+#else
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index __rte_unused)
+{
+	return dev;
+}
+#endif
+
+/*
  * Called from CUSE IOCTL: VHOST_SET_VRING_ADDR
  * The virtio device sends us the desc, used and avail ring addresses.
  * This function then converts these to our address space.
@@ -508,6 +598,9 @@ set_vring_addr(struct vhost_device_ctx ctx, struct vhost_vring_addr *addr)
 		return -1;
 	}
 
+	dev = numa_realloc(dev, addr->index);
+	vq = dev->virtqueue[addr->index];
+
 	vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
 			addr->avail_user_addr);
 	if (vq->avail == 0) {
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 1a2043a..0d6c14a 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -92,6 +92,10 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
+endif
+
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
 endif
-- 
1.8.1.4

[dpdk-dev] [PATCH v3 0/2] vhost: numa aware allocation of vhost device and queues

[Huawei Xie]

The vhost device and queues should be allocated on the same numa node as vring descriptor table.
When we firstly allocate the vhost device and queues, we don't know the numa node of vring descriptor table.
When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptor table, we will try to reallocate vhost device and queues to the same numa node.


Huawei Xie (2):
  use rte_malloc to allocate vhost device and queues
  reallocate vhost device and queues when we get the address of vring descriptor table

 config/common_linuxapp        |   1 +
 lib/librte_vhost/Makefile     |   4 ++
 lib/librte_vhost/virtio-net.c | 107 ++++++++++++++++++++++++++++++++++++++----
 mk/rte.app.mk                 |   4 ++
 4 files changed, 107 insertions(+), 9 deletions(-)

-- 
1.8.1.4

[dpdk-dev] [PATCH v3 1/2] vhost: use rte_malloc to allocate device and queues

[Huawei Xie]

use rte_malloc to allocate vhost device and queues


Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 lib/librte_vhost/virtio-net.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 4672e67..19b74d6 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -45,6 +45,7 @@
 #include <rte_log.h>
 #include <rte_string_fns.h>
 #include <rte_memory.h>
+#include <rte_malloc.h>
 #include <rte_virtio_net.h>
 
 #include "vhost-net.h"
@@ -202,9 +203,9 @@ static void
 free_device(struct virtio_net_config_ll *ll_dev)
 {
 	/* Free any malloc'd memory */
-	free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
-	free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
-	free(ll_dev);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_RXQ]);
+	rte_free(ll_dev->dev.virtqueue[VIRTIO_TXQ]);
+	rte_free(ll_dev);
 }
 
 /*
@@ -278,7 +279,7 @@ new_device(struct vhost_device_ctx ctx)
 	struct vhost_virtqueue *virtqueue_rx, *virtqueue_tx;
 
 	/* Setup device and virtqueues. */
-	new_ll_dev = malloc(sizeof(struct virtio_net_config_ll));
+	new_ll_dev = rte_malloc(NULL, sizeof(struct virtio_net_config_ll), 0);
 	if (new_ll_dev == NULL) {
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for dev.\n",
@@ -286,19 +287,19 @@ new_device(struct vhost_device_ctx ctx)
 		return -1;
 	}
 
-	virtqueue_rx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_rx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_rx == NULL) {
-		free(new_ll_dev);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for rxq.\n",
 			ctx.fh);
 		return -1;
 	}
 
-	virtqueue_tx = malloc(sizeof(struct vhost_virtqueue));
+	virtqueue_tx = rte_malloc(NULL, sizeof(struct vhost_virtqueue), 0);
 	if (virtqueue_tx == NULL) {
-		free(virtqueue_rx);
-		free(new_ll_dev);
+		rte_free(virtqueue_rx);
+		rte_free(new_ll_dev);
 		RTE_LOG(ERR, VHOST_CONFIG,
 			"(%"PRIu64") Failed to allocate memory for txq.\n",
 			ctx.fh);
-- 
1.8.1.4

[dpdk-dev] [PATCH v3 2/2] vhost: realloc vhost device and queues to the same numa node of vring desc table

[Huawei Xie]

When we get the address of vring descriptor table in VHOST_SET_VRING_ADDR message, will try to reallocate vhost device and virt queue to the same numa node.

v3 changes:
- remove unnecessary rte_free of new_vq and new_ll_dev

v2 changes:
- fix uninitialised new_vq and new_ll_device
- fix missed endif in rte.app.mk
- fix new_ll_dev and new_vq allocation failure issue
- return old virtio device if new_ll_dev isn't allocated

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---
 config/common_linuxapp        |  1 +
 lib/librte_vhost/Makefile     |  4 ++
 lib/librte_vhost/virtio-net.c | 88 +++++++++++++++++++++++++++++++++++++++++++
 mk/rte.app.mk                 |  4 ++
 4 files changed, 97 insertions(+)

diff --git a/config/common_linuxapp b/config/common_linuxapp
index 0078dc9..4ace24e 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -421,6 +421,7 @@ CONFIG_RTE_KNI_VHOST_DEBUG_TX=n
 #
 CONFIG_RTE_LIBRTE_VHOST=n
 CONFIG_RTE_LIBRTE_VHOST_USER=y
+CONFIG_RTE_LIBRTE_VHOST_NUMA=n
 CONFIG_RTE_LIBRTE_VHOST_DEBUG=n
 
 #
diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index a8645a6..6681f22 100644
--- a/lib/librte_vhost/Makefile
+++ b/lib/librte_vhost/Makefile
@@ -46,6 +46,10 @@ CFLAGS += -I vhost_cuse -lfuse
 LDFLAGS += -lfuse
 endif
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+LDFLAGS += -lnuma
+endif
+
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_VHOST) := virtio-net.c vhost_rxtx.c
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),y)
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 19b74d6..fcaefd6 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -38,6 +38,9 @@
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <unistd.h>
+#ifdef RTE_LIBRTE_VHOST_NUMA
+#include <numaif.h>
+#endif
 
 #include <sys/socket.h>
 
@@ -481,6 +484,88 @@ set_vring_num(struct vhost_device_ctx ctx, struct vhost_vring_state *state)
 }
 
 /*
+ * Reallocate virtio_det and vhost_virtqueue data structure to make them on the
+ * same numa node as the memory of vring descriptor.
+ */
+#ifdef RTE_LIBRTE_VHOST_NUMA
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index)
+{
+	int oldnode, newnode;
+	struct virtio_net_config_ll *old_ll_dev, *new_ll_dev = NULL;
+	struct vhost_virtqueue *old_vq, *new_vq = NULL;
+	int ret;
+	int realloc_dev = 0, realloc_vq = 0;
+
+	old_ll_dev = (struct virtio_net_config_ll *)dev;
+	old_vq = dev->virtqueue[index];
+
+	ret  = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	ret = ret | get_mempolicy(&oldnode, NULL, 0, old_ll_dev,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vring desc or dev numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_dev = 1;
+
+	ret = get_mempolicy(&oldnode, NULL, 0, old_vq,
+			MPOL_F_NODE | MPOL_F_ADDR);
+	if (ret) {
+		RTE_LOG(ERR, VHOST_CONFIG,
+			"Unable to get vq numa information.\n");
+		return dev;
+	}
+	if (oldnode != newnode)
+		realloc_vq = 1;
+
+	if (realloc_dev == 0 && realloc_vq == 0)
+		return dev;
+
+	if (realloc_dev)
+		new_ll_dev = rte_malloc_socket(NULL,
+			sizeof(struct virtio_net_config_ll), 0, newnode);
+	if (realloc_vq)
+		new_vq = rte_malloc_socket(NULL,
+			sizeof(struct vhost_virtqueue), 0, newnode);
+	if (!new_ll_dev && !new_vq)
+		return dev;
+
+	if (realloc_vq)
+		memcpy(new_vq, old_vq, sizeof(*new_vq));
+	if (realloc_dev)
+		memcpy(new_ll_dev, old_ll_dev, sizeof(*new_ll_dev));
+	(new_ll_dev ? new_ll_dev : old_ll_dev)->dev.virtqueue[index] =
+		new_vq ? new_vq : old_vq;
+	if (realloc_vq)
+		rte_free(old_vq);
+	if (realloc_dev) {
+		if (ll_root == old_ll_dev)
+			ll_root = new_ll_dev;
+		else {
+			struct virtio_net_config_ll *prev = ll_root;
+			while (prev->next != old_ll_dev)
+				prev = prev->next;
+			prev->next = new_ll_dev;
+			new_ll_dev->next = old_ll_dev->next;
+		}
+		rte_free(old_ll_dev);
+	}
+
+	return realloc_dev ? &new_ll_dev->dev : dev;
+}
+#else
+static struct virtio_net*
+numa_realloc(struct virtio_net *dev, int index __rte_unused)
+{
+	return dev;
+}
+#endif
+
+/*
  * Called from CUSE IOCTL: VHOST_SET_VRING_ADDR
  * The virtio device sends us the desc, used and avail ring addresses.
  * This function then converts these to our address space.
@@ -508,6 +593,9 @@ set_vring_addr(struct vhost_device_ctx ctx, struct vhost_vring_addr *addr)
 		return -1;
 	}
 
+	dev = numa_realloc(dev, addr->index);
+	vq = dev->virtqueue[addr->index];
+
 	vq->avail = (struct vring_avail *)(uintptr_t)qva_to_vva(dev,
 			addr->avail_user_addr);
 	if (vq->avail == 0) {
diff --git a/mk/rte.app.mk b/mk/rte.app.mk
index 1a2043a..0d6c14a 100644
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -92,6 +92,10 @@ endif # ! CONFIG_RTE_BUILD_COMBINE_LIBS
 
 _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_PCAP)       += -lpcap
 
+ifeq ($(CONFIG_RTE_LIBRTE_VHOST_NUMA),y)
+_LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lnuma
+endif
+
 ifeq ($(CONFIG_RTE_LIBRTE_VHOST_USER),n)
 _LDLIBS-$(CONFIG_RTE_LIBRTE_VHOST)          += -lfuse
 endif
-- 
1.8.1.4

Re: [dpdk-dev] [PATCH v3 0/2] vhost: numa aware allocation of vhost device and queues

[Thomas Monjalon]

2015-06-25 13:47, Huawei Xie:
> The vhost device and queues should be allocated on the same numa node as vring descriptor table.
> When we firstly allocate the vhost device and queues, we don't know the numa node of vring descriptor table.
> When we receive the VHOST_SET_VRING_ADDR message, we get the numa node of vring descriptor table, we will try to reallocate vhost device and queues to the same numa node.

Commit messages must be wrapped.

> Huawei Xie (2):
>   use rte_malloc to allocate vhost device and queues
>   reallocate vhost device and queues when we get the address of vring descriptor table

Applied, thanks