From: Huawei Xie <huawei.xie@intel.com>
Date: Thu, 25 Jun 2015 05:47:37 +0000 (+0800)
Subject: vhost: realloc device and queues to same numa node as vring desc
X-Git-Tag: spdx-start~8921
X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=af295ad4698c81913965f1354d9d3ad054e988f6;p=dpdk.git

vhost: realloc device and queues to same numa node as vring desc

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.

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
---

diff --git a/config/common_linuxapp b/config/common_linuxapp
index aae22f4b27..f0bfce50b5 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -429,6 +429,7 @@ 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 a8645a664a..6681f22227 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 8b59c02ab2..b520ec5ee2 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)
 	return 0;
 }
 
+/*
+ * 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.
@@ -509,6 +594,9 @@ 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 1a2043ac41..0d6c14a776 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