From: Si-Wei Liu <si-wei.liu@oracle.com>
To: eperezma@redhat.com, jasowang@redhat.com, mst@redhat.com,
dtatulea@nvidia.com, leiyang@redhat.com, yin31149@gmail.com,
boris.ostrovsky@oracle.com, jonah.palmer@oracle.com
Cc: qemu-devel@nongnu.org
Subject: [PATCH 33/40] vdpa: batch multiple dma_unmap to a single call for vm stop
Date: Thu, 7 Dec 2023 09:39:46 -0800 [thread overview]
Message-ID: <1701970793-6865-34-git-send-email-si-wei.liu@oracle.com> (raw)
In-Reply-To: <1701970793-6865-1-git-send-email-si-wei.liu@oracle.com>
Should help live migration downtime on source host. Below are the
coalesced dma_unmap time series on 2 queue pair config (no
dedicated descriptor group ASID for SVQ).
109531@1693367276.853503:vhost_vdpa_reset_device dev: 0x55c933926890
109531@1693367276.853513:vhost_vdpa_add_status dev: 0x55c933926890 status: 0x3
109531@1693367276.853520:vhost_vdpa_flush_map dev: 0x55c933926890 doit: 1 svq_flush: 0 persist: 1
109531@1693367276.853524:vhost_vdpa_set_config_call dev: 0x55c933926890 fd: -1
109531@1693367276.853579:vhost_vdpa_iotlb_begin_batch vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 type: 5
109531@1693367276.853586:vhost_vdpa_dma_unmap vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 asid: 0 iova: 0x1000 size: 0x2000 type: 3
109531@1693367276.853600:vhost_vdpa_dma_unmap vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 asid: 0 iova: 0x3000 size: 0x1000 type: 3
109531@1693367276.853618:vhost_vdpa_dma_unmap vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 asid: 0 iova: 0x4000 size: 0x2000 type: 3
109531@1693367276.853625:vhost_vdpa_dma_unmap vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 asid: 0 iova: 0x6000 size: 0x1000 type: 3
109531@1693367276.853630:vhost_vdpa_dma_unmap vdpa:0x7fa2aa84c190 fd: 16 msg_type: 2 asid: 0 iova: 0x7000 size: 0x2000 type: 3
109531@1693367276.853636:vhost_vdpa_dma_unmap vdpa:0x7fa2aa84c190 fd: 16 msg_type: 2 asid: 0 iova: 0x9000 size: 0x1000 type: 3
109531@1693367276.853642:vhost_vdpa_dma_unmap vdpa:0x7fa2aa84c190 fd: 16 msg_type: 2 asid: 0 iova: 0xa000 size: 0x2000 type: 3
109531@1693367276.853648:vhost_vdpa_dma_unmap vdpa:0x7fa2aa84c190 fd: 16 msg_type: 2 asid: 0 iova: 0xc000 size: 0x1000 type: 3
109531@1693367276.853654:vhost_vdpa_dma_unmap vdpa:0x7fa2aa6b6190 fd: 16 msg_type: 2 asid: 0 iova: 0xf000 size: 0x1000 type: 3
109531@1693367276.853660:vhost_vdpa_dma_unmap vdpa:0x7fa2aa6b6190 fd: 16 msg_type: 2 asid: 0 iova: 0x10000 size: 0x1000 type: 3
109531@1693367276.853666:vhost_vdpa_dma_unmap vdpa:0x7fa2aa6b6190 fd: 16 msg_type: 2 asid: 0 iova: 0xd000 size: 0x1000 type: 3
109531@1693367276.853670:vhost_vdpa_dma_unmap vdpa:0x7fa2aa6b6190 fd: 16 msg_type: 2 asid: 0 iova: 0xe000 size: 0x1000 type: 3
109531@1693367276.853675:vhost_vdpa_iotlb_end_batch vdpa:0x7fa2aa895190 fd: 16 msg_type: 2 type: 6
109531@1693367277.014697:vhost_vdpa_get_vq_index dev: 0x55c933925de0 idx: 0 vq idx: 0
109531@1693367277.014747:vhost_vdpa_get_vq_index dev: 0x55c933925de0 idx: 1 vq idx: 1
109531@1693367277.014753:vhost_vdpa_get_vq_index dev: 0x55c9339262e0 idx: 2 vq idx: 2
109531@1693367277.014756:vhost_vdpa_get_vq_index dev: 0x55c9339262e0 idx: 3 vq idx: 3
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
---
hw/virtio/vhost-vdpa.c | 7 +--
include/hw/virtio/vhost-vdpa.h | 3 ++
net/vhost-vdpa.c | 112 +++++++++++++++++++++++++++--------------
3 files changed, 80 insertions(+), 42 deletions(-)
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index d98704a..4010fd9 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -1162,8 +1162,8 @@ static void vhost_vdpa_svq_unmap_ring(struct vhost_vdpa *v, hwaddr addr)
vhost_iova_tree_remove(v->shared->iova_tree, *result);
}
-static void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
- const VhostShadowVirtqueue *svq)
+void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
+ const VhostShadowVirtqueue *svq)
{
struct vhost_vdpa *v = dev->opaque;
struct vhost_vring_addr svq_addr;
@@ -1346,17 +1346,14 @@ static void vhost_vdpa_svqs_stop(struct vhost_dev *dev)
return;
}
- vhost_vdpa_dma_batch_begin_once(v->shared, v->address_space_id);
for (unsigned i = 0; i < v->shadow_vqs->len; ++i) {
VhostShadowVirtqueue *svq = g_ptr_array_index(v->shadow_vqs, i);
vhost_svq_stop(svq);
- vhost_vdpa_svq_unmap_rings(dev, svq);
event_notifier_cleanup(&svq->hdev_kick);
event_notifier_cleanup(&svq->hdev_call);
}
- vhost_vdpa_dma_batch_end_once(v->shared, v->address_space_id);
}
static void vhost_vdpa_suspend(struct vhost_dev *dev)
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index aa13679..f426e2c 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -112,6 +112,9 @@ int vhost_vdpa_dma_batch_end_once(VhostVDPAShared *s, uint32_t asid);
int vhost_vdpa_load_setup(VhostVDPAShared *s, AddressSpace *dma_as);
int vhost_vdpa_load_cleanup(VhostVDPAShared *s, bool vhost_will_start);
+void vhost_vdpa_svq_unmap_rings(struct vhost_dev *dev,
+ const VhostShadowVirtqueue *svq);
+
typedef struct vdpa_iommu {
VhostVDPAShared *dev_shared;
IOMMUMemoryRegion *iommu_mr;
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 683619f..41714d1 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -29,6 +29,7 @@
#include "migration/migration.h"
#include "migration/misc.h"
#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-vdpa.h"
/* Todo:need to add the multiqueue support here */
typedef struct VhostVDPAState {
@@ -467,15 +468,89 @@ static int vhost_vdpa_net_data_load(NetClientState *nc)
return 0;
}
+static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
+{
+ VhostIOVATree *tree = v->shared->iova_tree;
+ DMAMap needle = {
+ /*
+ * No need to specify size or to look for more translations since
+ * this contiguous chunk was allocated by us.
+ */
+ .translated_addr = (hwaddr)(uintptr_t)addr,
+ };
+ const DMAMap *map = vhost_iova_tree_find_iova(tree, &needle);
+ int r;
+
+ if (unlikely(!map)) {
+ error_report("Cannot locate expected map");
+ return;
+ }
+
+ r = vhost_vdpa_dma_unmap(v->shared, v->address_space_id, map->iova,
+ map->size + 1);
+ if (unlikely(r != 0)) {
+ error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
+ }
+
+ vhost_iova_tree_remove(tree, *map);
+}
+
static void vhost_vdpa_net_client_stop(NetClientState *nc)
{
VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
+ struct vhost_vdpa *v = &s->vhost_vdpa;
+ struct vhost_vdpa *last_vi = NULL;
+ bool has_cvq = v->dev->vq_index_end % 2;
+ int nvqp;
assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
if (s->vhost_vdpa.index == 0) {
migration_remove_notifier(&s->migration_state);
}
+
+ if (v->dev->vq_index + v->dev->nvqs != v->dev->vq_index_end) {
+ return;
+ }
+
+ nvqp = (v->dev->vq_index_end + 1) / 2;
+ for (int i = 0; i < nvqp; ++i) {
+ VhostVDPAState *s_i = vhost_vdpa_net_get_nc_vdpa(s, i);
+ struct vhost_vdpa *v_i = &s_i->vhost_vdpa;
+
+ if (!v_i->shadow_vqs_enabled) {
+ continue;
+ }
+ if (!last_vi) {
+ vhost_vdpa_dma_batch_begin_once(v_i->shared,
+ v_i->address_space_id);
+ last_vi = v_i;
+ } else if (last_vi->address_space_id != v_i->address_space_id) {
+ vhost_vdpa_dma_batch_end_once(last_vi->shared,
+ last_vi->address_space_id);
+ vhost_vdpa_dma_batch_begin_once(v_i->shared,
+ v_i->address_space_id);
+ last_vi = v_i;
+ }
+
+ for (unsigned j = 0; j < v_i->shadow_vqs->len; ++j) {
+ VhostShadowVirtqueue *svq = g_ptr_array_index(v_i->shadow_vqs, j);
+
+ vhost_vdpa_svq_unmap_rings(v_i->dev, svq);
+ }
+ }
+ if (has_cvq) {
+ if (last_vi) {
+ assert(last_vi->address_space_id == v->address_space_id);
+ }
+ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
+ vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
+ }
+ if (last_vi) {
+ vhost_vdpa_dma_batch_end_once(last_vi->shared,
+ last_vi->address_space_id);
+ last_vi = NULL;
+ }
}
static int vhost_vdpa_net_load_setup(NetClientState *nc, NICState *nic)
@@ -585,33 +660,6 @@ static int64_t vhost_vdpa_get_vring_desc_group(int device_fd,
return state.num;
}
-static void vhost_vdpa_cvq_unmap_buf(struct vhost_vdpa *v, void *addr)
-{
- VhostIOVATree *tree = v->shared->iova_tree;
- DMAMap needle = {
- /*
- * No need to specify size or to look for more translations since
- * this contiguous chunk was allocated by us.
- */
- .translated_addr = (hwaddr)(uintptr_t)addr,
- };
- const DMAMap *map = vhost_iova_tree_find_iova(tree, &needle);
- int r;
-
- if (unlikely(!map)) {
- error_report("Cannot locate expected map");
- return;
- }
-
- r = vhost_vdpa_dma_unmap(v->shared, v->address_space_id, map->iova,
- map->size + 1);
- if (unlikely(r != 0)) {
- error_report("Device cannot unmap: %s(%d)", g_strerror(r), r);
- }
-
- vhost_iova_tree_remove(tree, *map);
-}
-
/** Map CVQ buffer. */
static int vhost_vdpa_cvq_map_buf(struct vhost_vdpa *v, void *buf, size_t size,
bool write)
@@ -740,18 +788,8 @@ err:
static void vhost_vdpa_net_cvq_stop(NetClientState *nc)
{
- VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
- struct vhost_vdpa *v = &s->vhost_vdpa;
-
assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
- if (s->vhost_vdpa.shadow_vqs_enabled) {
- vhost_vdpa_dma_batch_begin_once(v->shared, v->address_space_id);
- vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->cvq_cmd_out_buffer);
- vhost_vdpa_cvq_unmap_buf(&s->vhost_vdpa, s->status);
- vhost_vdpa_dma_batch_end_once(v->shared, v->address_space_id);
- }
-
vhost_vdpa_net_client_stop(nc);
}
--
1.8.3.1
next prev parent reply other threads:[~2023-12-07 18:55 UTC|newest]
Thread overview: 102+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-07 17:39 [PATCH 00/40] vdpa-net: improve migration downtime through descriptor ASID and persistent IOTLB Si-Wei Liu
2023-12-07 17:39 ` [PATCH 01/40] linux-headers: add vhost_types.h and vhost.h Si-Wei Liu
2023-12-11 7:47 ` Eugenio Perez Martin
2024-01-11 3:32 ` Jason Wang
2023-12-07 17:39 ` [PATCH 02/40] vdpa: add vhost_vdpa_get_vring_desc_group Si-Wei Liu
2024-01-11 3:51 ` Jason Wang
2023-12-07 17:39 ` [PATCH 03/40] vdpa: probe descriptor group index for data vqs Si-Wei Liu
2023-12-11 18:49 ` Eugenio Perez Martin
2024-01-11 4:02 ` Jason Wang
2023-12-07 17:39 ` [PATCH 04/40] vdpa: piggyback desc_group index when probing isolated cvq Si-Wei Liu
2024-01-11 7:06 ` Jason Wang
2023-12-07 17:39 ` [PATCH 05/40] vdpa: populate desc_group from net_vhost_vdpa_init Si-Wei Liu
2023-12-11 10:46 ` Eugenio Perez Martin
2023-12-11 11:01 ` Eugenio Perez Martin
2024-01-11 7:09 ` Jason Wang
2023-12-07 17:39 ` [PATCH 06/40] vhost: make svq work with gpa without iova translation Si-Wei Liu
2023-12-11 11:17 ` Eugenio Perez Martin
2024-01-11 7:31 ` Jason Wang
2023-12-07 17:39 ` [PATCH 07/40] vdpa: move around vhost_vdpa_set_address_space_id Si-Wei Liu
2023-12-11 11:18 ` Eugenio Perez Martin
2024-01-11 7:33 ` Jason Wang
2023-12-07 17:39 ` [PATCH 08/40] vdpa: add back vhost_vdpa_net_first_nc_vdpa Si-Wei Liu
2023-12-11 11:19 ` Eugenio Perez Martin
2024-01-11 7:37 ` Jason Wang
2023-12-07 17:39 ` [PATCH 09/40] vdpa: no repeat setting shadow_data Si-Wei Liu
2023-12-11 11:21 ` Eugenio Perez Martin
2024-01-11 7:34 ` Jason Wang
2023-12-07 17:39 ` [PATCH 10/40] vdpa: assign svq descriptors a separate ASID when possible Si-Wei Liu
2023-12-11 13:35 ` Eugenio Perez Martin
2024-01-11 8:02 ` Jason Wang
2023-12-07 17:39 ` [PATCH 11/40] vdpa: factor out vhost_vdpa_last_dev Si-Wei Liu
2023-12-11 13:36 ` Eugenio Perez Martin
2024-01-11 8:03 ` Jason Wang
2023-12-07 17:39 ` [PATCH 12/40] vdpa: check map_thread_enabled before join maps thread Si-Wei Liu
2023-12-07 17:39 ` [PATCH 13/40] vdpa: ref counting VhostVDPAShared Si-Wei Liu
2024-01-11 8:12 ` Jason Wang
2023-12-07 17:39 ` [PATCH 14/40] vdpa: convert iova_tree to ref count based Si-Wei Liu
2023-12-11 17:21 ` Eugenio Perez Martin
2024-01-11 8:15 ` Jason Wang
2023-12-07 17:39 ` [PATCH 15/40] vdpa: add svq_switching and flush_map to header Si-Wei Liu
2024-01-11 8:16 ` Jason Wang
2023-12-07 17:39 ` [PATCH 16/40] vdpa: indicate SVQ switching via flag Si-Wei Liu
2024-01-11 8:17 ` Jason Wang
2023-12-07 17:39 ` [PATCH 17/40] vdpa: judge if map can be kept across reset Si-Wei Liu
2023-12-13 9:51 ` Eugenio Perez Martin
2024-01-11 8:24 ` Jason Wang
2023-12-07 17:39 ` [PATCH 18/40] vdpa: unregister listener on last dev cleanup Si-Wei Liu
2023-12-11 17:37 ` Eugenio Perez Martin
2024-01-11 8:26 ` Jason Wang
2023-12-07 17:39 ` [PATCH 19/40] vdpa: should avoid map flushing with persistent iotlb Si-Wei Liu
2024-01-11 8:28 ` Jason Wang
2023-12-07 17:39 ` [PATCH 20/40] vdpa: avoid mapping flush across reset Si-Wei Liu
2024-01-11 8:30 ` Jason Wang
2023-12-07 17:39 ` [PATCH 21/40] vdpa: vhost_vdpa_dma_batch_end_once rename Si-Wei Liu
2024-01-15 2:40 ` Jason Wang
2024-01-15 2:52 ` Jason Wang
2023-12-07 17:39 ` [PATCH 22/40] vdpa: factor out vhost_vdpa_map_batch_begin Si-Wei Liu
2024-01-15 3:02 ` Jason Wang
2023-12-07 17:39 ` [PATCH 23/40] vdpa: vhost_vdpa_dma_batch_begin_once rename Si-Wei Liu
2024-01-15 3:03 ` Jason Wang
2023-12-07 17:39 ` [PATCH 24/40] vdpa: factor out vhost_vdpa_dma_batch_end Si-Wei Liu
2024-01-15 3:05 ` Jason Wang
2023-12-07 17:39 ` [PATCH 25/40] vdpa: add asid to dma_batch_once API Si-Wei Liu
2023-12-13 15:42 ` Eugenio Perez Martin
2024-01-15 3:07 ` Jason Wang
2023-12-07 17:39 ` [PATCH 26/40] vdpa: return int for " Si-Wei Liu
2023-12-07 17:39 ` [PATCH 27/40] vdpa: add asid to all dma_batch call sites Si-Wei Liu
2023-12-07 17:39 ` [PATCH 28/40] vdpa: support iotlb_batch_asid Si-Wei Liu
2023-12-13 15:42 ` Eugenio Perez Martin
2024-01-15 3:19 ` Jason Wang
2023-12-07 17:39 ` [PATCH 29/40] vdpa: expose API vhost_vdpa_dma_batch_once Si-Wei Liu
2023-12-13 15:42 ` Eugenio Perez Martin
2024-01-15 3:32 ` Jason Wang
2023-12-07 17:39 ` [PATCH 30/40] vdpa: batch map/unmap op per svq pair basis Si-Wei Liu
2024-01-15 3:33 ` Jason Wang
2023-12-07 17:39 ` [PATCH 31/40] vdpa: batch map and unmap around cvq svq start/stop Si-Wei Liu
2024-01-15 3:34 ` Jason Wang
2023-12-07 17:39 ` [PATCH 32/40] vdpa: factor out vhost_vdpa_net_get_nc_vdpa Si-Wei Liu
2024-01-15 3:35 ` Jason Wang
2023-12-07 17:39 ` Si-Wei Liu [this message]
2023-12-13 16:46 ` [PATCH 33/40] vdpa: batch multiple dma_unmap to a single call for vm stop Eugenio Perez Martin
2024-01-15 3:47 ` Jason Wang
2023-12-07 17:39 ` [PATCH 34/40] vdpa: fix network breakage after cancelling migration Si-Wei Liu
2024-01-15 3:48 ` Jason Wang
2023-12-07 17:39 ` [PATCH 35/40] vdpa: add vhost_vdpa_set_address_space_id trace Si-Wei Liu
2023-12-11 18:13 ` Eugenio Perez Martin
2024-01-15 3:50 ` Jason Wang
2023-12-07 17:39 ` [PATCH 36/40] vdpa: add vhost_vdpa_get_vring_base trace for svq mode Si-Wei Liu
2023-12-11 18:14 ` Eugenio Perez Martin
2024-01-15 3:52 ` Jason Wang
2023-12-07 17:39 ` [PATCH 37/40] vdpa: add vhost_vdpa_set_dev_vring_base " Si-Wei Liu
2023-12-11 18:14 ` Eugenio Perez Martin
2024-01-15 3:53 ` Jason Wang
2023-12-07 17:39 ` [PATCH 38/40] vdpa: add trace events for eval_flush Si-Wei Liu
2024-01-15 3:57 ` Jason Wang
2023-12-07 17:39 ` [PATCH 39/40] vdpa: add trace events for vhost_vdpa_net_load_cmd Si-Wei Liu
2023-12-11 18:14 ` Eugenio Perez Martin
2023-12-07 17:39 ` [PATCH 40/40] vdpa: add trace event for vhost_vdpa_net_load_mq Si-Wei Liu
2023-12-11 18:15 ` Eugenio Perez Martin
2024-01-15 3:58 ` Jason Wang
2023-12-11 18:39 ` [PATCH 00/40] vdpa-net: improve migration downtime through descriptor ASID and persistent IOTLB Eugenio Perez Martin
2024-01-11 8:21 ` Jason Wang
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=1701970793-6865-34-git-send-email-si-wei.liu@oracle.com \
--to=si-wei.liu@oracle.com \
--cc=boris.ostrovsky@oracle.com \
--cc=dtatulea@nvidia.com \
--cc=eperezma@redhat.com \
--cc=jasowang@redhat.com \
--cc=jonah.palmer@oracle.com \
--cc=leiyang@redhat.com \
--cc=mst@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=yin31149@gmail.com \
/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).