From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: dev@dpdk.org, yliu@fridaylinux.org, jfreiman@redhat.com,
tiwei.bie@intel.com
Cc: mst@redhat.com, vkaplans@redhat.com, jasowang@redhat.com,
Maxime Coquelin <maxime.coquelin@redhat.com>
Subject: [dpdk-dev] [PATCH 21/21] vhost: iotlb: reduce iotlb read lock usage
Date: Thu, 31 Aug 2017 11:50:23 +0200 [thread overview]
Message-ID: <20170831095023.21037-22-maxime.coquelin@redhat.com> (raw)
In-Reply-To: <20170831095023.21037-1-maxime.coquelin@redhat.com>
Prior to this patch, iotlb cache's read/write lock was
read-locked at every guest IOVA to app VA translation,
i.e. at least once per packet with indirect off and twice
with indirect on.
The problem is that rte_rwlock_read_lock() makes use of atomic
operation, which is costly.
This patch introduces iotlb lock helpers, so that a full burst
can be protected with taking the lock once, which reduces the
number of atomic operations by up to 64 with indirect
descriptors.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/librte_vhost/iotlb.c | 22 +++++++++++-----------
lib/librte_vhost/iotlb.h | 14 ++++++++++++++
lib/librte_vhost/vhost.h | 1 +
lib/librte_vhost/virtio_net.c | 22 ++++++++++++++++++++++
4 files changed, 48 insertions(+), 11 deletions(-)
diff --git a/lib/librte_vhost/iotlb.c b/lib/librte_vhost/iotlb.c
index d014bfe98..7dca95281 100644
--- a/lib/librte_vhost/iotlb.c
+++ b/lib/librte_vhost/iotlb.c
@@ -55,14 +55,14 @@ static void vhost_user_iotlb_pending_remove_all(struct vhost_virtqueue *vq)
{
struct vhost_iotlb_entry *node, *temp_node;
- rte_rwlock_write_lock(&vq->iotlb_lock);
+ rte_rwlock_write_lock(&vq->iotlb_pending_lock);
TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next, temp_node) {
TAILQ_REMOVE(&vq->iotlb_pending_list, node, next);
rte_mempool_put(vq->iotlb_pool, node);
}
- rte_rwlock_write_unlock(&vq->iotlb_lock);
+ rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}
int vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
@@ -71,7 +71,7 @@ int vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
struct vhost_iotlb_entry *node;
int found = 0;
- rte_rwlock_read_lock(&vq->iotlb_lock);
+ rte_rwlock_read_lock(&vq->iotlb_pending_lock);
TAILQ_FOREACH(node, &vq->iotlb_pending_list, next) {
if ((node->iova == iova) && (node->perm == perm)) {
@@ -80,7 +80,7 @@ int vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
}
}
- rte_rwlock_read_unlock(&vq->iotlb_lock);
+ rte_rwlock_read_unlock(&vq->iotlb_pending_lock);
return found;
}
@@ -105,11 +105,11 @@ void vhost_user_iotlb_pending_insert(struct vhost_virtqueue *vq,
node->iova = iova;
node->perm = perm;
- rte_rwlock_write_lock(&vq->iotlb_lock);
+ rte_rwlock_write_lock(&vq->iotlb_pending_lock);
TAILQ_INSERT_TAIL(&vq->iotlb_pending_list, node, next);
- rte_rwlock_write_unlock(&vq->iotlb_lock);
+ rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}
static void vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
@@ -117,7 +117,8 @@ static void vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
{
struct vhost_iotlb_entry *node, *temp_node;
- /* .iotlb_lock already locked by the caller */
+ rte_rwlock_write_lock(&vq->iotlb_pending_lock);
+
TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next, temp_node) {
if (node->iova < iova)
continue;
@@ -128,6 +129,8 @@ static void vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
TAILQ_REMOVE(&vq->iotlb_pending_list, node, next);
rte_mempool_put(vq->iotlb_pool, node);
}
+
+ rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}
static void vhost_user_iotlb_cache_remove_all(struct vhost_virtqueue *vq)
@@ -226,8 +229,6 @@ uint64_t vhost_user_iotlb_cache_find(struct vhost_virtqueue *vq, uint64_t iova,
if (unlikely(!*size))
goto out;
- rte_rwlock_read_lock(&vq->iotlb_lock);
-
TAILQ_FOREACH(node, &vq->iotlb_list, next) {
/* List sorted by iova */
if (unlikely(iova < node->iova))
@@ -252,8 +253,6 @@ uint64_t vhost_user_iotlb_cache_find(struct vhost_virtqueue *vq, uint64_t iova,
break;
}
- rte_rwlock_read_unlock(&vq->iotlb_lock);
-
out:
/* Only part of the requested chunk is mapped */
if (unlikely(mapped < *size))
@@ -285,6 +284,7 @@ int vhost_user_iotlb_init(struct virtio_net *dev, int vq_index)
socket = 0;
rte_rwlock_init(&vq->iotlb_lock);
+ rte_rwlock_init(&vq->iotlb_pending_lock);
TAILQ_INIT(&vq->iotlb_list);
TAILQ_INIT(&vq->iotlb_pending_list);
diff --git a/lib/librte_vhost/iotlb.h b/lib/librte_vhost/iotlb.h
index 4be1f7e85..d70c05a70 100644
--- a/lib/librte_vhost/iotlb.h
+++ b/lib/librte_vhost/iotlb.h
@@ -34,6 +34,20 @@
#define _VHOST_IOTLB_H_
#include "vhost.h"
+
+
+static __rte_always_inline void
+vhost_user_iotlb_rd_lock(struct vhost_virtqueue *vq)
+{
+ rte_rwlock_read_lock(&vq->iotlb_lock);
+}
+
+static __rte_always_inline void
+vhost_user_iotlb_rd_unlock(struct vhost_virtqueue *vq)
+{
+ rte_rwlock_read_unlock(&vq->iotlb_lock);
+}
+
void vhost_user_iotlb_cache_insert(struct vhost_virtqueue *vq, uint64_t iova,
uint64_t uaddr, uint64_t size,
uint8_t perm);
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 52bbc9a1c..008fc2ada 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -119,6 +119,7 @@ struct vhost_virtqueue {
struct vhost_vring_addr ring_addrs;
rte_rwlock_t iotlb_lock;
+ rte_rwlock_t iotlb_pending_lock;
struct rte_mempool *iotlb_pool;
TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 1bd21330e..799e12d2c 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -45,6 +45,7 @@
#include <rte_sctp.h>
#include <rte_arp.h>
+#include "iotlb.h"
#include "vhost.h"
#define MAX_PKT_BURST 32
@@ -306,6 +307,10 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
}
rte_prefetch0(&vq->desc[desc_indexes[0]]);
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
for (i = 0; i < count; i++) {
uint16_t desc_idx = desc_indexes[i];
int err;
@@ -338,6 +343,9 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
rte_prefetch0(&vq->desc[desc_indexes[i+1]]);
}
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_unlock(vq);
+
rte_smp_wmb();
*(volatile uint16_t *)&vq->used->idx += count;
@@ -574,6 +582,10 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
vq->shadow_used_idx = 0;
avail_head = *((volatile uint16_t *)&vq->avail->idx);
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen;
@@ -600,6 +612,9 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
vq->last_avail_idx += num_buffers;
}
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_unlock(vq);
+
if (likely(vq->shadow_used_idx)) {
flush_shadow_used_ring(dev, vq);
@@ -1143,6 +1158,10 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
/* Prefetch descriptor index. */
rte_prefetch0(&vq->desc[desc_indexes[0]]);
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
for (i = 0; i < count; i++) {
struct vring_desc *desc;
uint16_t sz, idx;
@@ -1206,6 +1225,9 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next);
}
}
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_unlock(vq);
+
vq->last_avail_idx += i;
if (likely(dev->dequeue_zero_copy == 0)) {
--
2.13.3
next prev parent reply other threads:[~2017-08-31 9:52 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-31 9:50 [dpdk-dev] [PATCH 00/21] Vhost-user: Implement device IOTLB support Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 01/21] Revert "vhost: workaround MQ fails to startup" Maxime Coquelin
2017-09-07 11:54 ` Yuanhan Liu
2017-09-07 12:59 ` Maxime Coquelin
2017-09-24 10:41 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 02/21] vhost: make error handling consistent in rx path Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 03/21] vhost: protect virtio_net device struct Maxime Coquelin
2017-09-05 4:45 ` Tiwei Bie
2017-09-05 9:24 ` Maxime Coquelin
2017-09-05 10:07 ` Tiwei Bie
2017-09-05 11:00 ` Maxime Coquelin
2017-09-06 1:15 ` Tiwei Bie
2017-09-06 2:59 ` Stephen Hemminger
2017-09-06 7:50 ` Maxime Coquelin
2017-09-06 7:15 ` Maxime Coquelin
2017-09-06 7:30 ` Tiwei Bie
2017-09-06 20:02 ` Maxime Coquelin
2017-09-07 5:08 ` Tiwei Bie
2017-09-07 13:44 ` Yuanhan Liu
2017-09-07 14:01 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 04/21] vhost: prepare send_vhost_message() to slave requests Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 05/21] vhost: add support to slave requests channel Maxime Coquelin
2017-09-05 4:19 ` Tiwei Bie
2017-09-05 8:18 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 06/21] vhost: declare missing IOMMU-related definitions for old kernels Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 07/21] vhost: add iotlb helper functions Maxime Coquelin
2017-09-05 6:02 ` Tiwei Bie
2017-09-05 15:16 ` Maxime Coquelin
2017-09-08 8:08 ` Yuanhan Liu
2017-09-08 8:24 ` Maxime Coquelin
2017-09-08 8:36 ` Yuanhan Liu
2017-09-08 8:50 ` Maxime Coquelin
2017-09-08 9:21 ` Yuanhan Liu
2017-09-08 9:28 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 08/21] vhost: iotlb: add pending miss request list and helpers Maxime Coquelin
2017-09-05 7:11 ` Tiwei Bie
2017-09-05 15:18 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 09/21] vhost-user: add support to IOTLB miss slave requests Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 10/21] vhost: initialize vrings IOTLB caches Maxime Coquelin
2017-09-04 13:57 ` Remy Horton
2017-09-04 15:45 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 11/21] vhost-user: handle IOTLB update and invalidate requests Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 12/21] vhost: introduce guest IOVA to backend VA helper Maxime Coquelin
2017-09-05 4:14 ` Tiwei Bie
2017-09-05 7:05 ` Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 13/21] vhost: use the guest IOVA to host " Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 14/21] vhost: enable rings at the right time Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 15/21] vhost: don't dereference invalid dev pointer after its reallocation Maxime Coquelin
2017-09-04 13:58 ` Remy Horton
2017-08-31 9:50 ` [dpdk-dev] [PATCH 16/21] vhost: postpone rings addresses translation Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 17/21] vhost-user: translate ring addresses when IOMMU enabled Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 18/21] vhost-user: iommu: postpone device creation until ring are mapped Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 19/21] vhost: iommu: Invalidate vring in case of matching IOTLB invalidate Maxime Coquelin
2017-08-31 9:50 ` [dpdk-dev] [PATCH 20/21] vhost: enable IOMMU support Maxime Coquelin
2017-08-31 9:50 ` Maxime Coquelin [this message]
2017-09-11 4:18 ` [dpdk-dev] [PATCH 21/21] vhost: iotlb: reduce iotlb read lock usage Yuanhan Liu
2017-09-11 7:34 ` Maxime Coquelin
2017-09-11 9:39 ` Yuanhan Liu
2017-09-04 13:58 ` [dpdk-dev] [PATCH 00/21] Vhost-user: Implement device IOTLB support Remy Horton
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=20170831095023.21037-22-maxime.coquelin@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=dev@dpdk.org \
--cc=jasowang@redhat.com \
--cc=jfreiman@redhat.com \
--cc=mst@redhat.com \
--cc=tiwei.bie@intel.com \
--cc=vkaplans@redhat.com \
--cc=yliu@fridaylinux.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).